System

Abstract

A system is provided.SOLUTION: A system, comprising: means for inputting genetic information and clinical data of a patient; means for normalizing and preprocessing the genetic information and clinical data into a standard format; means for training a machine learning model based on historical treatment data; means for generating an optimal treatment plan for each patient using the machine learning model; means for transmitting the treatment plan to a terminal and providing the treatment plan to a user; means for collecting data during treatment of the patient in real time and adjusting the treatment plan; and means for feeding back the collected new data to the machine learning model to retrain the model.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In current medical care, standard treatments are often adopted, but because each patient responds differently, a uniform treatment may not be effective enough or may cause severe side effects. In particular, for patients with different genetic backgrounds and lifestyles, personalized treatment is required rather than a one-size-fits-all approach. However, it takes a great deal of time and effort for doctors and medical institutions to organize vast amounts of data and create optimal treatment plans. The purpose of this invention is to use AI to automatically generate optimal treatment plans based on each patient's individual data and provide them efficiently and effectively. [Means for solving the problem]

[0005] The present invention provides a system that automatically provides individually optimized treatments, including a means for inputting a patient's genetic information and clinical data, a means for normalizing and preprocessing the genetic information and clinical data into a standard format, a means for training a machine learning model based on past treatment data, a means for generating an optimal treatment plan for each patient using the machine learning model, a means for transmitting the treatment plan to a terminal and providing it to a user, a means for collecting data during the patient's treatment in real time and adjusting the treatment plan, and a means for feeding back the collected new data to the machine learning model and relearning the model. Furthermore, by including a means for monitoring a patient's vital signs and drug response data in real time and optimizing a predictive model based on the data, and a means for selecting a targeted therapeutic drug corresponding to a specific gene mutation through genetic information analysis, the provision of even more sophisticated treatment plans becomes possible.

[0006] "Genetic information" refers to data that indicates biological characteristics based on an individual's DNA sequence, including mutation information related to specific diseases or drug responses.

[0007] "Clinical data" refers to various health information obtained during the course of a patient's medical treatment, including medical history, diagnosis results, treatment progress, and test results.

[0008] A "standard format" is a format for uniformly organizing data obtained from different types and sources and making it analyzable.

[0009] "Preprocessing" refers to a series of steps taken to convert raw data into an analyzable format, including data cleansing and normalization.

[0010] A "machine learning model" is a collection of algorithms that learn from past data, identify patterns and trends, and make predictions and judgments about new data.

[0011] A "treatment plan" is an individual treatment policy that is formulated based on the patient's specific symptoms and condition, and includes the drugs and treatment methods to be used, administration schedules, etc.

[0012] A "terminal" is a device for inputting and outputting data, and includes personal computers, tablets, smartphones, etc.

[0013] "Vital signs" are indicators that show the state of basic bodily functions related to maintaining a patient's life, and include blood pressure, heart rate, body temperature, respiratory rate, etc.

[0014] "Real-time" refers to the temporal characteristics of data being processed and analyzed almost simultaneously as it is generated.

[0015] "Feedback" is the process by which the system reflects the data and results it receives in its next processing or decision. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention relates to a system for analyzing genetic information and clinical data of a patient and generating an optimal treatment plan using machine learning. The embodiments for carrying out the present invention will be described in the following means.

[0038] System Overview

[0039] In this system, the user (doctor or patient) enters genetic information and clinical data via a terminal and sends it to a server, which then generates an optimal treatment plan based on that data. The generated treatment plan is then sent to the terminal and used by the user for treatment. During treatment, data is collected in real time, and the treatment plan is adjusted and re-learned.

[0040] Program processing

[0041] Data collection

[0042] The user uses the terminal to input basic patient information (age, sex, medical history, etc.) into the electronic medical record system.

[0043] The user runs a sample taken from the patient through a genetic analyzer, and the genetic information output from the analyzer is sent to a server via the terminal.

[0044] Data Analysis and Learning

[0045] The server normalizes the received genetic and clinical data into a standard format and performs data preprocessing, imputing or cleaning incomplete or inappropriate data.

[0046] The server trains a machine learning model based on past treatment data, which is capable of detecting patterns in patient data and generating optimal treatment plans.

[0047] Treatment plan generation and presentation

[0048] The server uses machine learning models to generate optimal treatment plans for each patient. Specifically, in the case of cancer treatment, it selects targeted therapeutic drugs that correspond to the patient's genetic mutations and sets the administration schedule.

[0049] The server sends the generated treatment plan to the terminal and provides it to the user, who then begins treatment based on this plan.

[0050] Specific examples

[0051] In the case of cancer treatment

[0052] 1. Data Collection

[0053] - Users take blood samples from cancer patients and perform genetic analysis.

[0054] - The device sends the analysis data to the server.

[0055] 2. Data analysis and learning

[0056] - The server analyzes the genetic data of cancer patients and identifies specific genetic mutations.

[0057] - The server updates the machine learning model using data from similar past cases.

[0058] 3. Treatment plan generation

[0059] - The server uses machine learning models to generate targeted therapeutic drugs and their administration schedules that correspond to specific gene mutations.

[0060] - The server sends the generated treatment plan to the terminal and presents the treatment policy to the user.

[0061] 4. Data collection and prediction during treatment

[0062] - The device transmits the patient's vital signs and drug response data to a server in real time during treatment.

[0063] - The server analyzes the collected data, predicts treatment effectiveness, and adjusts the treatment plan as needed.

[0064] 5. Feedback and Retraining

[0065] - The user enters the progress of treatment and new data into the terminal and sends it to the server.

[0066] - The server retrains the machine learning model with new data to improve the accuracy of the next treatment plan.

[0067] In this way, the present invention can provide effective and safe treatment for patients by automatically generating individually optimized treatment plans and adjusting them in real time during treatment.

[0068] The processing flow will be explained below.

[0069] Step 1:

[0070] Data collection

[0071] The user (doctor or patient) inputs basic information about the patient (age, gender, medical history, etc.) into the terminal, which then organizes this information and sends it to the server.

[0072] The user takes blood or tissue samples from the patient and subjects them to a genetic analysis device, which then sends the genetic data output from the device to a server via a terminal.

[0073] Step 2:

[0074] Data Preprocessing

[0075] The server normalizes the received genetic and clinical data into a standard format, harmonizing different data formats.

[0076] The server performs a cleansing process, removing incomplete data and noise, and also complements the data as needed.

[0077] Step 3:

[0078] Training a machine learning model

[0079] The server trains the machine learning model using data from past treatments and similar cases, improving its pattern recognition capabilities.

[0080] The server uses normalized patient data as input to build predictive models for specific diseases and treatment responses.

[0081] Step 4:

[0082] Treatment plan generation

[0083] The server uses the trained machine learning model to generate an optimal treatment plan for each patient, such as selecting targeted drugs for specific gene mutations in cancer treatment.

[0084] The server creates a treatment plan that includes the treatment method, drugs to be used, and administration schedule.

[0085] Step 5:

[0086] Presentation of treatment plan

[0087] The server sends the generated treatment plan to the terminal.

[0088] The terminal displays the treatment plan to the user (doctor) in an easy-to-understand format and provides it as a treatment guideline.

[0089] Step 6:

[0090] Treatment initiation and monitoring

[0091] The user (doctor) starts treatment for the patient based on the treatment plan received from the server.

[0092] The device transmits real-time vital signs and drug response data of patients undergoing treatment to a server, including physiological data such as blood pressure, heart rate, and blood drug concentrations.

[0093] Step 7:

[0094] Real-time treatment prediction and adjustment

[0095] The server uses machine learning models to analyze real-time treatment data and predict treatment outcomes.

[0096] The server adjusts dosage and treatment schedule accordingly based on the predicted results.

[0097] Step 8:

[0098] Feedback and Retraining

[0099] The user (doctor) inputs the progress of treatment and new data into the terminal as needed and sends it to the server.

[0100] The server retrains the machine learning model using newly collected data, thereby improving the accuracy of future treatment plans.

[0101] This allows the system to continuously learn and provide optimal treatment plans for each patient.

[0102] Example 1

[0103] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0104] With conventional medical systems, it has been difficult to quickly generate optimal treatment plans that effectively utilize a patient's individual genetic information and clinical data. It has also been difficult to collect data during treatment in real time and immediately adjust the treatment plan based on that data. This has led to issues such as not being able to maximize the effectiveness and safety of the treatment provided to patients.

[0105] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0106] In this invention, the server includes means for inputting a patient's genetic information and clinical data, means for normalizing and preprocessing the genetic information and clinical data into a standard format, means for training a machine learning model based on past treatment data, means for generating an optimal treatment plan for each patient using the machine learning model, means for transmitting the treatment plan to a terminal and providing it to a user, means for collecting data during the patient's treatment in real time and adjusting the treatment plan, means for feeding back the collected new data to the machine learning model and retraining the model, means for acquiring and analyzing vital signs and drug response data in real time, means for transmitting data to the server via Wi-Fi or Bluetooth, means for updating the machine learning model based on case data, and means for automatically generating an individualized treatment plan for the patient and notifying the terminal. This makes it possible to quickly and effectively provide an optimized treatment plan for each patient and adjust the plan in real time based on treatment data.

[0107] "Patient genetic information" refers to the sequence data of a patient's DNA or RNA, and is biological information used to diagnose disease and develop treatment plans.

[0108] "Clinical data" refers to all information related to the provision of medical services, such as a patient's treatment history, diagnosis results, medication history, and vital signs.

[0109] "Normalizing to a standard format" refers to the process of converting data entered in different formats into a uniform format to make it consistent.

[0110] "Preprocessing" refers to the process of organizing and processing raw data into an analyzable form, including, for example, imputing missing values ​​and cleaning the data.

[0111] "Training a machine learning model" refers to the process of using existing data to teach an algorithm patterns that give it the ability to make predictions or classifications on new data.

[0112] "Generating optimal treatment plans" refers to using machine learning models to develop individualized treatment methods and drug administration schedules for each patient.

[0113] "Real-time collection" refers to the immediate acquisition and recording of data during treatment without delay.

[0114] "Retraining" refers to adding new data to update the learning model and improve its accuracy and effectiveness.

[0115] "Vital signs" are data that indicate the basic vital signs of a patient's body, and generally include heart rate, respiratory rate, body temperature, blood pressure, etc.

[0116] "Drug response data" refers to data that shows how a patient's body reacts to a drug after taking it, including, for example, the drug's effects and side effects.

[0117] "Transmitting data using Wi-Fi or Bluetooth" refers to transferring data between devices using wireless communication technologies.

[0118] "Case data" refers to data that includes past patient treatment history and diagnostic information, and is used to create treatment plans for new patients.

[0119] An "individualized treatment plan" refers to formulating the optimal treatment method and administration schedule for a specific patient based on each patient's genetic information and clinical data.

[0120] The present invention relates to a system for analyzing genetic information and clinical data of a patient and generating an optimal treatment plan using machine learning. An embodiment of the present invention will be described in detail below.

[0121] System configuration

[0122] This system sends genetic information and clinical data entered by the user via a terminal to a server, which then generates an optimal treatment plan based on that data.The system consists of the following main components.

[0123] 1. Terminal

[0124] Hardware: Personal computers, tablets, smartphones, etc.

[0125] Software: Electronic medical record systems (e.g., EPIC, Cerner), data entry interfaces, and data submission applications.

[0126] 2. Server

[0127] Hardware: High performance computers (e.g. server racks).

[0128] Software: Database management systems, data preprocessing programs (e.g., Python scripts, Pandas library), machine learning platforms (e.g., TensorFlow, PyTorch), web frameworks (e.g., Flask, Django).

[0129] 3. Genetic analysis equipment

[0130] Hardware: Genetic analysis equipment (e.g., Illumina).

[0131] Software: Genetic data analysis program.

[0132] System Operation

[0133] 1. Data Collection

[0134] Using a terminal, the user inputs basic patient information (age, gender, medical history, etc.) into the electronic medical record system. In addition, a sample taken from the patient is put through a genetic analyzer, and the obtained genetic information is sent to a server via the terminal.

[0135] 2. Data analysis and learning

[0136] The server normalizes the received genetic and clinical data into a standard format and performs data preprocessing. Incomplete or inappropriate data is cleaned and imputed. Using historical treatment data, the server trains a machine learning model. This model detects patterns in the patient data and generates an optimal treatment plan.

[0137] 3. Treatment plan generation and presentation

[0138] The server uses machine learning models to generate optimal treatment plans for each patient. For example, in the case of cancer treatment, it selects targeted therapeutic drugs that correspond to the patient's genetic mutations and sets an administration schedule. The generated treatment plan is then sent to the device and provided to the user, who then begins treatment based on this plan.

[0139] 4. Data collection and prediction during treatment

[0140] During treatment, the device transmits the patient's vital signs and drug response data in real time to a server, which analyzes the collected data, predicts treatment effectiveness, and adjusts the treatment plan as needed.

[0141] 5. Feedback and Retraining

[0142] The user inputs treatment progress and new data into the device and sends it to the server, which then uses the new data to retrain the machine learning model and improve the accuracy of the next treatment plan.

[0143] Specific examples

[0144] In the case of cancer treatment

[0145] 1. Data Collection

[0146] Users take blood samples from cancer patients and perform genetic analysis.

[0147] The terminal transmits the analysis data to the server.

[0148] 2. Data analysis and learning

[0149] The server analyzes the genetic data of cancer patients and identifies specific genetic mutations.

[0150] The server uses data from similar past cases to update the machine learning model.

[0151] 3. Treatment plan generation

[0152] The server uses machine learning models to generate targeted therapeutic drugs and their administration schedules that correspond to specific gene mutations.

[0153] The server sends the generated treatment plan to the terminal and presents the treatment policy to the user.

[0154] 4. Data collection and prediction during treatment

[0155] The device transmits the patient's vital signs and drug response data to a server in real time during treatment.

[0156] The server analyzes the collected data, predicts treatment effectiveness, and adjusts the treatment plan as needed.

[0157] 5. Feedback and Retraining

[0158] The user enters the progress of treatment and new data into the terminal and sends it to the server.

[0159] The server retrains the machine learning model using new data to improve the accuracy of the next treatment plan.

[0160] Prompt Sentence Examples

[0161] "Please explain the system that analyzes genetic information and clinical data of cancer patients and generates individually optimized treatment plans using machine learning. Please describe the specific data collection methods, analysis and processing, generation of treatment plans, and real-time data collection and re-learning during treatment."

[0162] In this way, the present invention can provide effective and safe treatment for patients by automatically generating individually optimized treatment plans and adjusting them in real time during treatment.

[0163] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0164] Step 1: Data collection

[0165] The user uses a terminal to input basic patient information (age, gender, medical history, etc.) into the electronic medical record system. The input basic information is saved in the database, allowing the system to obtain basic patient information to be used in subsequent processing.

[0166] The user runs a sample taken from a patient through a genetic analyzer and transfers the resulting genetic information to a terminal. The terminal then sends this genetic information to a server, where it is stored in a database.

[0167] Step 2: Data Preprocessing

[0168] The server normalizes the received genetic and clinical data into a standard format, such as JSON, to maintain consistency in the data format.

[0169] The server preprocesses the normalized data, including imputing missing data and cleaning outliers. For example, the server cleans the data using the Pandas library and imputes missing values ​​with the mean using a Python script. The processed data is used as a clean dataset.

[0170] Step 3: Train the machine learning model

[0171] The server uses the cleaned data to train a machine learning model, which trains the algorithm based on past treatment data. For example, a deep learning model is built using TensorFlow or PyTorch and fitted to the dataset.

[0172] Using the cleaned data as input, we obtain an optimal predictive model as output, which is used to generate a treatment plan for each patient.

[0173] Step 4: Generate a treatment plan

[0174] The server uses the trained machine learning model to generate a treatment plan for each patient. For example, in the case of cancer treatment, it calculates the appropriate treatment, medication, and administration schedule based on the patient's genetic information.

[0175] Based on the input data of each patient's genetic information and clinical data, an optimized treatment plan is obtained as output, including specific treatment procedures and schedules.

[0176] Step 5: Provide a treatment plan

[0177] The server sends the generated treatment plan to the terminal, which receives the plan and presents it to the user, who can then review the plan and begin optimal treatment for the patient.

[0178] Based on the treatment plan as input data, presentation data as output is generated and sent to the terminal. This presentation data includes specific treatment implementation procedures.

[0179] Step 6: Real-time data collection and prediction

[0180] The device transmits the patient's vital signs and drug response data to a server in real time via Bluetooth or Wi-Fi during treatment, for example, through a smartwatch or medical monitoring device.

[0181] The server analyzes the collected data and predicts the effectiveness of treatment, for example, by using Apache Kafka or Flink for real-time analysis to determine whether treatment is progressing appropriately.

[0182] Real-time data is used as input data, and analytical results are output, which are used to adjust the treatment plan.

[0183] Step 7: Feedback and Retraining

[0184] The user inputs treatment progress and new data into the terminal and sends it to the server, for example, entering details of regular checkups or new test results.

[0185] The server retrains the machine learning model using new data, improving the accuracy of the next treatment plan. For example, it combines past and new data to update the model and make more accurate predictions.

[0186] New clinical data and treatment effects are used as inputs to obtain updated prediction models as outputs, which can be reused for subsequent treatment plan generation.

[0187] This series of processing steps enables the system to provide individually optimized treatment plans and monitor and adjust treatment progress in real time.

[0188] (Application example 1)

[0189] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0190] In the current healthcare system, providing optimal treatment plans for individual patients requires the collection and analysis of large amounts of data, a process that is time-consuming and inefficient. Furthermore, there is a lack of adequate management of patients' daily health data and early detection of abnormalities. Furthermore, there is a lack of a mechanism for responding quickly when abnormalities are detected, which could result in a decline in the quality of patient healthcare.

[0191] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0192] In this invention, the server includes means for inputting a patient's genetic information and clinical data, means for normalizing and preprocessing the genetic information and clinical data into a standard format, means for training a machine learning model based on past treatment data, means for generating an optimal treatment plan for each patient using the machine learning model, means for transmitting the treatment plan to a terminal and providing it to a user, means for collecting data during the patient's treatment in real time and adjusting the treatment plan, means for feeding back the collected new data to the machine learning model and retraining the model, means for collecting daily health data and detecting abnormalities, means for notifying the user of the abnormality, and means for retraining the machine learning model based on feedback from the user. This enables the server to quickly and efficiently provide an optimal treatment plan for each patient, and enables early detection and prompt response to abnormalities.

[0193] "Patient genetic information" refers to data about a patient's genes, such as their DNA sequence, including information about their disease and genetic characteristics.

[0194] "Clinical data" is a general term for clinical data such as a patient's age, sex, medical history, diagnostic information, and treatment history.

[0195] "Normalization to a standard format" is a technique for converting collected data into a unified format that makes the data easier to analyze.

[0196] "Preprocessing" refers to the process of data cleaning and transformation to convert raw data into an analyzable format.

[0197] "Past treatment data" refers to historical data such as treatment information and progression of disease status for each patient that has been accumulated to date.

[0198] A "machine learning model" is an algorithm that learns patterns and correlations based on large amounts of data and makes predictions and judgments.

[0199] An "optimal treatment plan" is the most effective treatment or treatment schedule designed based on a patient's specific condition and characteristics.

[0200] A "terminal" is an electronic device such as a computer or smartphone that allows a user to input and output information.

[0201] "Real-time collection" refers to the process of collecting data instantly, without delay.

[0202] "Adjusting the treatment plan" refers to reviewing the treatment content and schedule based on data during treatment and making changes as necessary.

[0203] "Feedback to a machine learning model" is the process of adding new data to a model and retraining it using that data.

[0204] "Daily health data" refers to data relating to the patient's daily lifestyle and physical condition, including, for example, heart rate, number of steps, and sleep data.

[0205] "Anomaly detection" is the process of finding abnormal conditions or unexpected data patterns.

[0206] "Sending a notification of an abnormality to the user" refers to the act of notifying the user of information about the detected abnormality.

[0207] "Feedback-based retraining" is the process of retraining a model based on user reactions and opinions to improve its accuracy.

[0208] The present invention relates to a system that collects and analyzes a patient's daily health data, genetic information, and clinical data, detects abnormalities using machine learning, and generates an optimal treatment plan. Specific embodiments are described below.

[0209] 1. System Overview

[0210] This system works by having the user (doctor or patient) input data via a device and send that data to a server. The server analyzes the received data, monitors the patient's health, and detects abnormalities and generates treatment plans as needed. The generated plans and alerts are sent to the device and provided to the user. Data is collected in real time during treatment and in daily life, and the system self-improves based on feedback.

[0211] 2. Hardware and Software

[0212] The following hardware and software are used to implement this system:

[0213] Smartphone: Used as a device for users to input data.

[0214] Server: A central system that analyzes data and trains machine learning models.

[0215] Healthcare app: An application that collects and records health data.

[0216] Machine learning libraries: Software for building machine learning models, such as TensorFlow and Scikit-learn.

[0217] 3. Data collection

[0218] Users use a healthcare app on their smartphone to collect daily health data (heart rate, number of steps, sleep data, etc.) and, if necessary, use a genetic analyzer to obtain genetic information and clinical data, which are then sent from the device to a server.

[0219] 4. Data Preprocessing and Analysis

[0220] The server normalizes the received health and genetic data into a standard format and performs data cleaning and pre-processing, removing incomplete data and outliers to make the data suitable for analysis.

[0221] 5. Machine Learning for Anomaly Detection and Treatment Plan Generation

[0222] The server uses the data to train a machine learning model using past treatment data. This model generates optimal treatment plans for each patient and has the ability to detect abnormal patterns. If an abnormality is detected, the server immediately sends a notification to the user's smartphone.

[0223] 6. Real-time data collection and feedback

[0224] Users collect real-time data about their health and treatment progress and provide feedback to the server, allowing the system to adjust and retrain treatment plans and improve the accuracy of the model.

[0225] Prompt Sentence Examples

[0226] "Analyze user heart rate data and generate a model to detect future anomalies. Create a system that detects and alerts users of sudden increases or decreases in heart rate early."

[0227] As a result, the present invention provides a system that comprehensively monitors the health condition of a user, enables early detection of abnormalities, and provides an optimal treatment plan.

[0228] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0229] Step 1:

[0230] Data collection

[0231] Subject: Device

[0232] The device collects the user's daily health data (heart rate, number of steps, sleep data, etc.) through a healthcare app. If necessary, the user can obtain genetic information and clinical data using a genetic analyzer and input it into the device. This collected data is centralized and sent to a server. The input is health data, genetic information, and clinical data, and the output is the integrated data sent to the server.

[0233] Step 2:

[0234] Data preprocessing and normalization

[0235] Subject: Server

[0236] The server normalizes the received health and genetic data into a standard format. During this process, incomplete data is filled in and outliers are cleaned. The input is raw data, and the output is clean data that has been converted into a form suitable for analysis.

[0237] Step 3:

[0238] Training a machine learning model

[0239] Subject: Server

[0240] The server trains a machine learning model based on the standardized and preprocessed data. The model uses historical treatment data to learn patterns and correlations. The input is the clean data and historical treatment data, and the output is the trained machine learning model.

[0241] Step 4:

[0242] Anomaly detection and treatment plan generation

[0243] Subject: Server

[0244] The server uses a trained machine learning model to detect abnormal patterns in the collected data and generate optimal treatment plans as needed. The input is the user's latest health and genetic information, and the output is the detected abnormal data and the generated treatment plan.

[0245] Step 5:

[0246] Notifying users and gathering feedback

[0247] Subject: Device

[0248] If an abnormality is detected, the terminal notifies the user of the notification sent from the server. It also presents the generated treatment plan to the user. The user then provides feedback, which is sent to the server via the terminal. The input is the notification and treatment plan from the server, and the output is the alert and feedback data for the user.

[0249] Step 6:

[0250] Real-time data collection and model retraining

[0251] Subject: Server

[0252] The server collects real-time data during treatment, analyzes the data, adjusts the treatment plan, and retrains the machine learning model based on the new data collected and user feedback. The inputs are real-time data during treatment and feedback data, and the outputs are an adjusted treatment plan and a retrained machine learning model.

[0253] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0254] The present invention combines a system that provides an optimal treatment plan based on a patient's genetic information and clinical data with an emotion engine that recognizes the user's emotions and enables adjustment of the treatment plan taking these emotions into consideration. The following describes in detail the embodiments of the present invention.

[0255] System Overview

[0256] This system operates by sending genetic information, clinical data, and emotional data entered by the user (doctor or patient) using a terminal to a server. The server analyzes this data and generates an optimal treatment plan. The generated treatment plan is then sent back to the terminal and used by the user for treatment. Data is collected in real time during and after treatment, allowing the treatment plan to be adjusted and retrained. The emotional engine also takes the user's emotions into account and provides a plan to maximize the effectiveness of treatment.

[0257] Program processing

[0258] Data collection

[0259] The user (doctor or patient) uses a terminal to input basic patient information (age, gender, medical history, etc.) into the electronic medical record system, which then organizes the basic data.

[0260] The user runs a sample taken from the patient through a genetic analyzer, and the resulting analysis data is sent to a server via the device.

[0261] A user uses an emotion recognition device to record his / her emotional state, and this data is input into a terminal or automatically collected through the emotion recognition device and transmitted to a server.

[0262] Data preprocessing and analysis

[0263] The server normalizes the received genetic and clinical data into a standard format and performs preprocessing, including removing incomplete data and noise.

[0264] The server analyzes the emotion data and identifies the user's emotional state, and the emotion engine operates based on the results of this identification.

[0265] Training a machine learning model

[0266] The server trains the machine learning model using historical treatment data, which includes genetic, clinical, and emotional data.

[0267] The server uses the trained model to predict the patient's individual treatment response.

[0268] Treatment plan generation and presentation

[0269] The server then uses the trained model to generate an optimal treatment plan based on the user's genetic, clinical, and emotional information. Specifically, for cancer treatment, it selects targeted therapeutic drugs that correspond to genetic mutations and sets the administration schedule.

[0270] The server sends the generated treatment plan to the terminal and provides it to the user, who then confirms the plan and adopts it as the treatment policy.

[0271] Specific examples

[0272] In the case of cancer treatment

[0273] 1. Data Collection

[0274] - Users take blood samples from cancer patients and perform genetic analysis.

[0275] - The device sends the analysis data to the server.

[0276] - Users use emotion recognition devices to record and transmit their own or their patients' emotional states.

[0277] 2. Data Preprocessing and Analysis

[0278] - The server normalizes the received genetic and clinical data into a standard format and organizes the data.

[0279] - The server analyzes the user's emotional state using an emotion engine and integrates the emotion data with other medical data.

[0280] 3. Training the machine learning model

[0281] - The server trains the machine learning model using historical cancer treatment data, including sentiment data.

[0282] The server uses the trained model to predict treatment response.

[0283] 4. Treatment plan generation and presentation

[0284] - The server generates an optimal treatment plan based on the analyzed data. Based on the emotional data, approaches to reduce the patient's mental stress are also considered.

[0285] - The server sends the treatment plan to the terminal and provides it to the user, who then carries out the treatment based on it.

[0286] 5. Monitoring and adjustment during and after treatment

[0287] - The device collects new data from the patient in real time during and after treatment and sends it to the server.

[0288] - The server analyzes the collected data and adjusts the treatment plan as needed. Emotional data is also collected and analyzed periodically, and adjustments are made to reduce the patient's mental burden.

[0289] The present invention not only provides individually optimized treatment, but also makes it possible to implement a comprehensive treatment plan that takes into account the psychological aspects of the patient.

[0290] The processing flow will be explained below.

[0291] Step 1:

[0292] Data collection

[0293] A user (doctor or patient) uses a terminal to input basic patient information (age, sex, medical history, etc.) into the electronic medical record system, which then transmits the basic patient data to the server.

[0294] The user takes blood or tissue samples from the patient and runs them through a genetic analyzer, and the genetic data output from the analyzer is sent to a server via a terminal.

[0295] The user uses an emotion recognition device (such as a wearable device or dedicated app) to record their own or their patient's emotional state, and then synchronizes this data with the device and sends it to a server.

[0296] Step 2:

[0297] Data Preprocessing

[0298] The server normalizes the received genetic and clinical data into a standard format for analysis, a process that unifies the data and makes it easier to analyze.

[0299] The server performs a cleansing process to remove incomplete data and noise, and also completes missing data if any.

[0300] The server analyzes the emotion data and uses an emotion engine to recognize the user's emotional state (e.g., stress level, happiness level).

[0301] Step 3:

[0302] Training a machine learning model

[0303] The server trains machine learning models based on past treatment data, including genetic information, clinical data, and user emotional data.

[0304] The server uses the trained model to build predictive models for each patient data type to help plan future treatment.

[0305] Step 4:

[0306] Treatment plan generation

[0307] The server then applies the trained machine learning model to generate an optimal treatment plan based on the user's genetic, clinical, and emotional data. For example, in the case of cancer treatment, it would select a targeted drug for a specific gene mutation and set a dosing schedule based on the doctor's instructions.

[0308] The server uses an emotion engine to reflect the user's emotional state in the treatment plan. For example, if the patient is in a high stress state, stress reduction measures and psychological support will be added to the plan.

[0309] Step 5:

[0310] Presentation of treatment plan

[0311] The server transmits the generated treatment plan to the terminal and provides it to the user.

[0312] The device displays the received treatment plan in an easy-to-understand format for the user (doctor) and presents it as a treatment guideline. The doctor will then begin appropriate treatment for the patient based on this plan.

[0313] Step 6:

[0314] Treatment initiation and monitoring

[0315] The user starts treatment for the patient based on the treatment plan received from the server.

[0316] The device collects and transmits real-time vital signs, emotional state, and drug response data of patients undergoing treatment, including blood pressure, heart rate, blood drug concentration, and emotional state, to a server.

[0317] Step 7:

[0318] Real-time treatment prediction and adjustment

[0319] The server uses machine learning models to analyze the data collected in real time and predict the effectiveness of treatment.

[0320] Based on the predictions and emotion data, the server adjusts the treatment plan, for example by changing the drug dosage to minimize the risk of side effects.

[0321] Step 8:

[0322] Feedback and Retraining

[0323] The user (doctor) enters the progress of treatment and new data into the terminal and sends it to the server.

[0324] The server uses the newly collected data to retrain the machine learning model, improving the accuracy of future treatment plans.

[0325] The present invention not only provides an individually optimized treatment plan, but also takes into account the patient's mental and emotional state, thereby maximizing the overall effectiveness of the treatment.

[0326] Example 2

[0327] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0328] Conventional medical systems have not been able to adequately provide personalized medical plans based on genetic information and clinical data, and real-time collection of treatment data and plan adjustments have been limited. Furthermore, no measures have been taken to provide treatment plans that take into account the emotional data of patients and doctors. This has made it difficult to reduce patients' mental stress, and there have been cases where the effectiveness of treatment has not been maximized.

[0329] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: a means for inputting biomedical information and health data of a patient; a means for normalizing the biomedical information and health data into a standard format and preprocessing the data; a means for training a machine learning model based on past therapy data; a means for generating an optimal medical plan for each patient using the machine learning model; a means for transmitting the medical plan to a communication device and providing it to a user; a means for collecting data during the patient's treatment in real time and adjusting the medical plan; a means for feeding back the collected new data to the machine learning model and retraining the model; and a means for recognizing emotional data of the user, analyzing the emotional data, and reflecting the emotional data in the medical plan. This improves the accuracy and effectiveness of the personalized medical plan, making it possible to maximize the effectiveness of treatment while reducing mental stress on the patient.

[0330] "Biomedical information" refers to various biological data necessary for medical diagnosis and treatment, such as a patient's genetic information, clinical data, and vital signs.

[0331] "Health data" refers to data that includes various information used to assess a patient's health status, such as their lifestyle, diet, exercise, and stress level.

[0332] "Normalizing to a standard format" means converting data provided in different formats and units into a unified format and unit, and making it organized.

[0333] "Preprocessing" refers to the process of preparing data, such as filling in missing values ​​and removing outliers, before conducting data analysis.

[0334] "Therapy data" refers to data that includes the results and details of past treatments, recording the effectiveness and side effects of the treatments.

[0335] "Training a machine learning model" means training the model using past data to improve its predictive accuracy.

[0336] A "personalized medical plan" is a plan that proposes the most appropriate treatment method based on each patient's genetic information and clinical data.

[0337] A "communication device" is an electronic device used by a patient or doctor, such as a computer, tablet, or smartphone.

[0338] "Real-time collection" means continuously monitoring and collecting data the moment it occurs.

[0339] "Retraining" means using new data collected to retrain an existing machine learning model to further improve its accuracy.

[0340] "Emotional data" refers to data that indicates the user's psychological and emotional state, measured based on heart rate, electrodermal activity, etc.

[0341] An "emotion engine" is a software algorithm that analyzes and recognizes a user's emotional data.

[0342] This invention is a system that provides an optimal medical plan based on a patient's biomedical information and health data, and adjusts the plan taking into account the user's emotional state. The system consists of a series of steps: data collection, data preprocessing and analysis, training of a machine learning model, generation and presentation of a treatment plan, and monitoring and adjustment during and after treatment.

[0343] Data collection

[0344] A user (doctor or patient) uses a terminal to input basic patient information (age, gender, medical history, etc.) into the electronic medical record system. The terminal then sends this information to a server in a standard format. The user also collects a biological sample from the patient and subjects it to a genetic analysis device. The analysis results data are also sent to the server via the terminal. Furthermore, the user uses an emotion recognition device to record their emotional state, and this data is entered into the terminal or automatically sent to the server.

[0345] Data preprocessing and analysis

[0346] The server uses Python's pandas library to normalize the received genetic and clinical data into a standard format, impute missing values, and remove outliers.The server then uses libraries such as TensorFlow and PyTorch to analyze the emotion data, identify the user's emotional state, and activate the emotion engine.

[0347] Training a machine learning model

[0348] The server trains a machine learning model using Scikit-learn and TensorFlow on past treatment data. The training data includes genetic information, clinical data, and emotional data. The server trains the model using cross-validation to prevent overfitting and generate a model with high predictive performance.

[0349] Treatment plan generation and presentation

[0350] The server uses the trained model to generate an optimal treatment plan based on the user's genetic information, clinical data, and emotional data. For example, it selects a targeted drug based on genetic mutations and sets its administration schedule. The generated treatment plan is then sent from the server to the device for the user to review.

[0351] Monitoring and adjustment during and after treatment

[0352] The device sends new data from the patient in real time during and after treatment to the server, which analyzes this data and adjusts the treatment plan accordingly. Emotional data is also collected and analyzed periodically, and actions to reduce the patient's mental stress are reflected in the plan.

[0353] Examples of specific examples and prompts

[0354] Example: Cancer treatment

[0355] 1. Data Collection

[0356] Users take blood samples from cancer patients and perform genetic analysis.

[0357] The terminal transmits this analysis data to the server.

[0358] The user uses the emotion recognition device to record their own or their patient's emotional state and transmit it to the server.

[0359] 2. Data Preprocessing and Analysis

[0360] The server normalizes the received genetic and clinical data into a standard format.

[0361] The server analyzes the user's emotional state using an emotion engine and integrates the emotion data.

[0362] 3. Training the machine learning model

[0363] The server trains the machine learning model using historical cancer treatment data, including emotional data.

[0364] The server uses the trained model to predict treatment response.

[0365] 4. Treatment plan generation and presentation

[0366] The server generates an optimal treatment plan and takes into account approaches to reduce stress for the patient based on emotional data.

[0367] The server transmits the treatment plan to the terminal and provides it to the user.

[0368] 5. Monitoring and adjustment during and after treatment

[0369] The terminal transmits new data in real time to the server during and after treatment.

[0370] The server analyzes the collected data and adjusts the treatment plan as needed.

[0371] Prompt Sentence Examples

[0372] "I would like to create an optimal treatment plan for a cancer patient that takes into account their genetic information, clinical data, and emotional state. Please generate a treatment proposal based on the following data."

[0373] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0374] Step 1: Data collection

[0375] Input: Patient basic information, genetic sample, emotional data

[0376] Output: Genetic information, clinical data, and emotional data in a standard format sent to a server

[0377] Step 1.1: Enter patient basic information

[0378] The user logs into the electronic medical record system on the terminal and enters the patient's basic information (age, gender, medical history, etc.), enters the required data in the input fields, and clicks the "Save" button to send it to the server.

[0379] Specific actions: The user uses the device's keyboard to enter information and clicks the save button with the mouse.

[0380] Step 1.2: Genetic sample analysis and submission

[0381] Input: Patient genetic sample

[0382] Output: Genetic information sent to the server

[0383] The user places the collected gene sample into the genetic analyzer and begins analysis. When the analysis is complete, the device generates a data file.

[0384] The terminal retrieves data files from the analysis device via USB or network connection and automatically uploads them to the server.

[0385] Specific operation: The user collects a genetic sample and inserts it into the analysis device. After analysis, the device sends the data to the server.

[0386] Step 1.3: Collect emotion data

[0387] Input: Emotion data from an emotion recognition device

[0388] Output: Emotion data sent to the server

[0389] The user uses the emotion recognition device to record their emotional state, and the data is transmitted via Bluetooth to the device and then from the device to the server.

[0390] Specific operation: The user wears the emotion recognition device and the data is automatically sent to the terminal.

[0391] Step 2: Data preprocessing and analysis

[0392] Input: Genetic information, clinical data, and emotional data in a standard format sent to the server

[0393] Output: Normalized and parsed data

[0394] Step 2.1: Normalize the data

[0395] The server converts the received genetic and clinical data into a data frame using Python's pandas library, normalizes it to a standard format, imputes missing values, and removes outliers.

[0396] What happens: The server runs data processing steps using pandas to generate a clean dataset.

[0397] Step 2.2: Analyzing and integrating sentiment data

[0398] The server analyzes the received emotion data using TensorFlow, PyTorch, etc. to identify the user's emotional state, which is then integrated with other biomedical information.

[0399] Specific operation: The server receives the emotion data and runs an analysis algorithm to classify the emotional state. The results are integrated with the biomedical data.

[0400] Step 3: Train the machine learning model

[0401] Input: Normalized and parsed data

[0402] Output: A trained machine learning model

[0403] Step 3.1: Train the model using historical data

[0404] The server uses historical therapy data to train machine learning models using Scikit-learn and TensorFlow, including genetic, clinical, and emotional data.

[0405] What happens: The server runs the script using the training data to optimize the model parameters.

[0406] Step 3.2: Predicting with the trained model

[0407] The server uses the trained model to predict the patient's individual treatment response.

[0408] Specific operation: The server inputs new patient data into the model and generates predictions, including predictions of treatment efficacy and side effects.

[0409] Step 4: Generate and present the treatment plan

[0410] Input: Trained machine learning model, patient biomedical information, and emotion data

[0411] Output: Generated medical plan

[0412] Step 4.1: Generate an optimal treatment plan

[0413] The server uses the trained model to generate an optimal treatment plan based on the user's genetic, clinical, and emotional information. In the case of cancer treatment, it selects targeted therapeutic drugs and sets administration schedules based on genetic mutations.

[0414] Specific operations: The server inputs the data into the model and calculates the optimal treatment plan.

[0415] Step 4.2: Present the treatment plan

[0416] The server then sends the generated treatment plan to the communication device, where the user can check the treatment plan on their device and share the necessary information within the hospital.

[0417] Specific operations: The server generates a treatment plan and sends it to the terminal. The user checks the plan on the terminal and performs the treatment.

[0418] Step 5: Monitoring and adjusting during and after treatment

[0419] Input: New patient data collected in real time

[0420] Output: Adjusted treatment plan

[0421] Step 5.1: Collect real-time data

[0422] The device transmits new patient data (genetic information, clinical data, emotional data) collected during and after treatment to the server in real time.

[0423] Specific operation: The device acquires new data through sensors or manual input and sends it to the server over the network.

[0424] Step 5.2: Analyze data and adjust treatment plan

[0425] The server analyzes the new data and reassess whether the existing treatment plan is optimal, adjusts it if necessary, and suggests actions to reduce the patient's mental stress based on emotional data.

[0426] Specific operations: The server analyzes the new data and updates the treatment plan. The updated plan is sent to the device, and the user modifies the treatment.

[0427] (Application example 2)

[0428] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0429] Conventional autonomous driving systems do not select driving routes that take into account the emotional state of passengers, which means they are unable to reduce passenger stress or provide a comfortable driving experience.In addition, treatment plans based on patients' genetic information and clinical data do not take into account their emotional state, making it difficult to maximize treatment effectiveness.

[0430] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0431] In this invention, the server includes: a means for inputting a patient's genetic information and clinical data; a means for normalizing and preprocessing the genetic information and clinical data into a standard format; a means for training a machine learning model based on past treatment data; a means for generating an optimal treatment plan for each patient using the machine learning model; a means for transmitting the treatment plan to a terminal and providing it to a user; a means for collecting data during the patient's treatment in real time and adjusting the treatment plan; a means for feeding back the collected new data to the machine learning model and retraining the model; a means for collecting passengers' emotional states and selecting a route based on the collected data; and a means for transmitting emotional data and location information to the server and optimizing the driving route. This enables the selection of a driving route taking passengers' emotional states into consideration, thereby reducing stress and providing a comfortable driving experience. Furthermore, an optimal treatment plan taking individual patients' emotional states into consideration is provided, maximizing the effectiveness of treatment.

[0432] "Patient genetic information" refers to data on genetic structure and mutations obtained by subjecting a sample collected from a patient to a genetic analysis device.

[0433] "Clinical data" refers to any information collected in a medical setting, such as a patient's diagnosis, treatment history, or vital signs.

[0434] "Means for inputting" refers to means for transmitting data to the server using an electronic medical record system or an input device.

[0435] "Normalization to a standard format" is a process of converting data of different formats into a unified format in order to maintain data consistency.

[0436] "Preprocessing means" refers to means for removing noise and imperfections from data and preparing it in an analyzable format.

[0437] A "machine learning model" is an algorithm that is trained to make predictions or classifications based on collected data.

[0438] The "means for generating a treatment plan" is a means for using a machine learning model to determine the optimal treatment method and schedule based on individual patient data.

[0439] The "means for transmitting to the terminal and providing to the user" refers to a means for transmitting the generated treatment plan to the device of the user (doctor or patient) so that it can be viewed and used.

[0440] "Means for collecting and adjusting in real time" refers to means for instantly transmitting newly acquired data during treatment to a server and dynamically changing the treatment plan.

[0441] "Means for providing feedback to a machine learning model and re-learning" refers to means for inputting newly collected data into a machine learning model and re-training it to improve the accuracy of the model.

[0442] "Passenger emotional state" refers to the passenger's psychological and emotional state, such as stress, joy, anxiety, etc.

[0443] The "route selection means" is a means for determining the optimal driving route based on the emotional state of the passenger.

[0444] "Emotion data and location information" refers to data relating to the psychological state of passengers and data relating to the current location of passengers and vehicles.

[0445] The "means for optimizing a driving route" is a means for automatically selecting the most suitable driving route based on emotion data and location information.

[0446] The present invention provides a driving route planning system that takes into account the emotional state of passengers in an autonomous vehicle, and incorporates emotional data as an additional element in a system that provides optimal treatment plans based on the patient's genetic information and clinical data. Specific embodiments are described below.

[0447] System Overview

[0448] The system works by collecting emotional and location data through smart devices (e.g., smartphones, head-mounted displays, etc.) and sending it to a server. The server then analyzes this data and generates an optimal driving route. The system also provides a treatment plan based on the patient's genetic and clinical data, and adjusts the treatment plan based on real-time analysis of data collected during and after treatment.

[0449] Program processing

[0450] Emotion data collection and transmission

[0451] Users (passengers) record their emotional state in real time through their smart devices. Emotion recognition technology is used to analyze emotional states such as stress, joy, and anxiety, and the data is sent to a server. Libraries such as EmotionRecognizer are used for this collection process.

[0452] Data Analysis and Optimization

[0453] The server analyzes the submitted emotion data and location information. It normalizes and preprocesses the data into a standard format, then uses EmotionRecognizer to determine the user's emotional state. It then generates an optimal driving route based on this data using a machine learning model trained on past data.

[0454] Route selection and provision

[0455] The generated driving route is sent to the terminal and provided to the user. The user operates the autonomous vehicle based on this route. Data related to the treatment plan is also sent to the user's terminal and used for treatment.

[0456] Real-time data collection and reconciliation

[0457] Data on the patient's treatment and passengers' emotional state is collected in real time and sent to a server, which then dynamically adjusts the treatment plan and driving route based on this data. Newly collected data is fed back into the machine learning model, allowing it to be retrained.

[0458] Specific examples

[0459] If a passenger in an autonomous vehicle is stuck in traffic, the system will choose a gentler route if data indicates the passenger's emotional state is stressed.

[0460] During treatment, the treatment plan generated based on the patient's genetic information also takes into account the patient's emotional data, and adjustments are made to the plan to reduce the mental burden.

[0461] Prompt Sentence Examples

[0462] "If the passenger's emotional state is relaxed, suggest the optimal driving route for the autonomous vehicle. If the passenger is stressed, suggest a gentler route that avoids traffic jams."

[0463] Thus, the present invention allows for the optimization of driving routes based on the emotional state of passengers and the provision of treatment plans that take into account the emotional state of patients.

[0464] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0465] Step 1:

[0466] Emotional Data Collection

[0467] Users (passengers) record their emotional state in real time through smart devices (e.g., smartphones, head-mounted displays). Emotion recognition technology is used to analyze emotional states such as stress, joy, and anxiety. Specifically, image data collected from a camera is analyzed using libraries such as EmotionRecognizer to extract emotional data. The input is camera image data, and the output is emotional state data.

[0468] Step 2:

[0469] Emotion data transmission

[0470] The device sends the collected emotion data to the server in JSON format using the HTTP protocol. Specifically, the device converts the emotion data into an appropriate format and sends it to the server's receiving endpoint. The input is emotion data (in JSON format), and the output is the completion of data transmission to the server.

[0471] Step 3:

[0472] Data analysis and standard formatting

[0473] The server receives the emotion data and normalizes it into a standard format. It removes inconsistencies and noise from the data and makes it analyzable. The input is emotion data (JSON format), and the output is emotion data in a standard format.

[0474] Step 4:

[0475] Training a machine learning model

[0476] The server trains a machine learning model based on past emotion data and driving route information. Specifically, it uses the collected dataset to train the model using libraries such as TensorFlow and scikit-learn. The input is past emotion data and driving route data, and the output is the trained model.

[0477] Step 5:

[0478] Route Selection

[0479] The server uses a trained machine learning model to generate an optimal driving route based on the received emotion data. Specifically, the model inputs current emotion data and location information and predicts the optimal route. The input is the current emotion data and location information, and the output is the optimal driving route.

[0480] Step 6:

[0481] Providing driving directions

[0482] The server sends the generated driving route to the device. Specifically, it sends the route information using the HTTP protocol and displays it on the smartphone's navigation app. The input is the optimal driving route, and the output is the route information displayed on the device.

[0483] Step 7:

[0484] Real-time data collection and treatment plan adjustment

[0485] The terminal collects real-time patient data and passenger emotional state data during treatment and sends it to the server, which then dynamically adjusts the treatment plan and driving route based on this data. The input is the real-time collected data, and the output is the adjusted treatment plan and driving route.

[0486] Step 8:

[0487] Retraining a machine learning model

[0488] The server feeds newly collected data back into the machine learning model for re-learning. Specifically, new data is input into the model to improve its accuracy. The input is new emotional data and location information, and the output is the re-learned model.

[0489] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0490] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0491] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0492] [Second embodiment]

[0493] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0494] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0495] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0496] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0497] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0498] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0499] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0500] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0501] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0502] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0503] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0504] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0505] The present invention relates to a system for analyzing genetic information and clinical data of a patient and generating an optimal treatment plan using machine learning. The embodiments for carrying out the present invention will be described in the following means.

[0506] System Overview

[0507] In this system, the user (doctor or patient) enters genetic information and clinical data via a terminal and sends it to a server, which then generates an optimal treatment plan based on that data. The generated treatment plan is then sent to the terminal and used by the user for treatment. During treatment, data is collected in real time, and the treatment plan is adjusted and re-learned.

[0508] Program processing

[0509] Data collection

[0510] The user uses the terminal to input basic patient information (age, sex, medical history, etc.) into the electronic medical record system.

[0511] The user runs a sample taken from the patient through a genetic analyzer, and the genetic information output from the analyzer is sent to a server via the terminal.

[0512] Data Analysis and Learning

[0513] The server normalizes the received genetic and clinical data into a standard format and performs data preprocessing, imputing or cleaning incomplete or inappropriate data.

[0514] The server trains a machine learning model based on past treatment data, which is capable of detecting patterns in patient data and generating optimal treatment plans.

[0515] Treatment plan generation and presentation

[0516] The server uses machine learning models to generate optimal treatment plans for each patient. Specifically, in the case of cancer treatment, it selects targeted therapeutic drugs that correspond to the patient's genetic mutations and sets the administration schedule.

[0517] The server sends the generated treatment plan to the terminal and provides it to the user, who then begins treatment based on this plan.

[0518] Specific examples

[0519] In the case of cancer treatment

[0520] 1. Data Collection

[0521] - Users take blood samples from cancer patients and perform genetic analysis.

[0522] - The device sends the analysis data to the server.

[0523] 2. Data analysis and learning

[0524] - The server analyzes the genetic data of cancer patients and identifies specific genetic mutations.

[0525] - The server updates the machine learning model using data from similar past cases.

[0526] 3. Treatment plan generation

[0527] - The server uses machine learning models to generate targeted therapeutic drugs and their administration schedules that correspond to specific gene mutations.

[0528] - The server sends the generated treatment plan to the terminal and presents the treatment policy to the user.

[0529] 4. Data collection and prediction during treatment

[0530] - The device transmits the patient's vital signs and drug response data to a server in real time during treatment.

[0531] - The server analyzes the collected data, predicts treatment effectiveness, and adjusts the treatment plan as needed.

[0532] 5. Feedback and Retraining

[0533] - The user enters the progress of treatment and new data into the terminal and sends it to the server.

[0534] - The server retrains the machine learning model with new data to improve the accuracy of the next treatment plan.

[0535] In this way, the present invention can provide effective and safe treatment for patients by automatically generating individually optimized treatment plans and adjusting them in real time during treatment.

[0536] The processing flow will be explained below.

[0537] Step 1:

[0538] Data collection

[0539] The user (doctor or patient) inputs basic information about the patient (age, gender, medical history, etc.) into the terminal, which then organizes this information and sends it to the server.

[0540] The user takes blood or tissue samples from the patient and subjects them to a genetic analysis device, which then sends the genetic data output from the device to a server via a terminal.

[0541] Step 2:

[0542] Data Preprocessing

[0543] The server normalizes the received genetic and clinical data into a standard format, harmonizing different data formats.

[0544] The server performs a cleansing process, removing incomplete data and noise, and also complements the data as needed.

[0545] Step 3:

[0546] Training a machine learning model

[0547] The server trains the machine learning model using data from past treatments and similar cases, improving its pattern recognition capabilities.

[0548] The server uses normalized patient data as input to build predictive models for specific diseases and treatment responses.

[0549] Step 4:

[0550] Treatment plan generation

[0551] The server uses the trained machine learning model to generate an optimal treatment plan for each patient, such as selecting targeted drugs for specific gene mutations in cancer treatment.

[0552] The server creates a treatment plan that includes the treatment method, drugs to be used, and administration schedule.

[0553] Step 5:

[0554] Presentation of treatment plan

[0555] The server sends the generated treatment plan to the terminal.

[0556] The terminal displays the treatment plan to the user (doctor) in an easy-to-understand format and provides it as a treatment guideline.

[0557] Step 6:

[0558] Treatment initiation and monitoring

[0559] The user (doctor) starts treatment for the patient based on the treatment plan received from the server.

[0560] The device transmits real-time vital signs and drug response data of patients undergoing treatment to a server, including physiological data such as blood pressure, heart rate, and blood drug concentrations.

[0561] Step 7:

[0562] Real-time treatment prediction and adjustment

[0563] The server uses machine learning models to analyze real-time treatment data and predict treatment outcomes.

[0564] The server adjusts dosage and treatment schedule accordingly based on the predicted results.

[0565] Step 8:

[0566] Feedback and Retraining

[0567] The user (doctor) inputs the progress of treatment and new data into the terminal as needed and sends it to the server.

[0568] The server retrains the machine learning model using newly collected data, thereby improving the accuracy of future treatment plans.

[0569] This allows the system to continuously learn and provide optimal treatment plans for each patient.

[0570] Example 1

[0571] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0572] With conventional medical systems, it has been difficult to quickly generate optimal treatment plans that effectively utilize a patient's individual genetic information and clinical data. It has also been difficult to collect data during treatment in real time and immediately adjust the treatment plan based on that data. This has led to issues such as not being able to maximize the effectiveness and safety of the treatment provided to patients.

[0573] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0574] In this invention, the server includes means for inputting a patient's genetic information and clinical data, means for normalizing and preprocessing the genetic information and clinical data into a standard format, means for training a machine learning model based on past treatment data, means for generating an optimal treatment plan for each patient using the machine learning model, means for transmitting the treatment plan to a terminal and providing it to a user, means for collecting data during the patient's treatment in real time and adjusting the treatment plan, means for feeding back the collected new data to the machine learning model and retraining the model, means for acquiring and analyzing vital signs and drug response data in real time, means for transmitting data to the server via Wi-Fi or Bluetooth, means for updating the machine learning model based on case data, and means for automatically generating an individualized treatment plan for the patient and notifying the terminal. This makes it possible to quickly and effectively provide an optimized treatment plan for each patient and adjust the plan in real time based on treatment data.

[0575] "Patient genetic information" refers to the sequence data of a patient's DNA or RNA, and is biological information used to diagnose disease and develop treatment plans.

[0576] "Clinical data" refers to all information related to the provision of medical services, such as a patient's treatment history, diagnosis results, medication history, and vital signs.

[0577] "Normalizing to a standard format" refers to the process of converting data entered in different formats into a uniform format to make it consistent.

[0578] "Preprocessing" refers to the process of organizing and processing raw data into an analyzable form, including, for example, imputing missing values ​​and cleaning the data.

[0579] "Training a machine learning model" refers to the process of using existing data to teach an algorithm patterns that give it the ability to make predictions or classifications on new data.

[0580] "Generating optimal treatment plans" refers to using machine learning models to develop individualized treatment methods and drug administration schedules for each patient.

[0581] "Real-time collection" refers to the immediate acquisition and recording of data during treatment without delay.

[0582] "Retraining" refers to adding new data to update the learning model and improve its accuracy and effectiveness.

[0583] "Vital signs" are data that indicate the basic vital signs of a patient's body, and generally include heart rate, respiratory rate, body temperature, blood pressure, etc.

[0584] "Drug response data" refers to data that shows how a patient's body reacts to a drug after taking it, including, for example, the drug's effects and side effects.

[0585] "Transmitting data using Wi-Fi or Bluetooth" refers to transferring data between devices using wireless communication technologies.

[0586] "Case data" refers to data that includes past patient treatment history and diagnostic information, and is used to create treatment plans for new patients.

[0587] An "individualized treatment plan" refers to formulating the optimal treatment method and administration schedule for a specific patient based on each patient's genetic information and clinical data.

[0588] The present invention relates to a system for analyzing genetic information and clinical data of a patient and generating an optimal treatment plan using machine learning. An embodiment of the present invention will be described in detail below.

[0589] System configuration

[0590] This system sends genetic information and clinical data entered by the user via a terminal to a server, which then generates an optimal treatment plan based on that data.The system consists of the following main components.

[0591] 1. Terminal

[0592] Hardware: Personal computers, tablets, smartphones, etc.

[0593] Software: Electronic medical record systems (e.g., EPIC, Cerner), data entry interfaces, and data submission applications.

[0594] 2. Server

[0595] Hardware: High performance computers (e.g. server racks).

[0596] Software: Database management systems, data preprocessing programs (e.g., Python scripts, Pandas library), machine learning platforms (e.g., TensorFlow, PyTorch), web frameworks (e.g., Flask, Django).

[0597] 3. Genetic analysis equipment

[0598] Hardware: Genetic analysis equipment (e.g., Illumina).

[0599] Software: Genetic data analysis program.

[0600] System Operation

[0601] 1. Data Collection

[0602] Using a terminal, the user inputs basic patient information (age, gender, medical history, etc.) into the electronic medical record system. In addition, a sample taken from the patient is put through a genetic analyzer, and the obtained genetic information is sent to a server via the terminal.

[0603] 2. Data analysis and learning

[0604] The server normalizes the received genetic and clinical data into a standard format and performs data preprocessing. Incomplete or inappropriate data is cleaned and imputed. Using historical treatment data, the server trains a machine learning model. This model detects patterns in the patient data and generates an optimal treatment plan.

[0605] 3. Treatment plan generation and presentation

[0606] The server uses machine learning models to generate optimal treatment plans for each patient. For example, in the case of cancer treatment, it selects targeted therapeutic drugs that correspond to the patient's genetic mutations and sets an administration schedule. The generated treatment plan is then sent to the device and provided to the user, who then begins treatment based on this plan.

[0607] 4. Data collection and prediction during treatment

[0608] During treatment, the device transmits the patient's vital signs and drug response data in real time to a server, which analyzes the collected data, predicts treatment effectiveness, and adjusts the treatment plan as needed.

[0609] 5. Feedback and Retraining

[0610] The user inputs treatment progress and new data into the device and sends it to the server, which then uses the new data to retrain the machine learning model and improve the accuracy of the next treatment plan.

[0611] Specific examples

[0612] In the case of cancer treatment

[0613] 1. Data Collection

[0614] Users take blood samples from cancer patients and perform genetic analysis.

[0615] The terminal transmits the analysis data to the server.

[0616] 2. Data analysis and learning

[0617] The server analyzes the genetic data of cancer patients and identifies specific genetic mutations.

[0618] The server uses data from similar past cases to update the machine learning model.

[0619] 3. Treatment plan generation

[0620] The server uses machine learning models to generate targeted therapeutic drugs and their administration schedules that correspond to specific gene mutations.

[0621] The server sends the generated treatment plan to the terminal and presents the treatment policy to the user.

[0622] 4. Data collection and prediction during treatment

[0623] The device transmits the patient's vital signs and drug response data to a server in real time during treatment.

[0624] The server analyzes the collected data, predicts treatment effectiveness, and adjusts the treatment plan as needed.

[0625] 5. Feedback and Retraining

[0626] The user enters the progress of treatment and new data into the terminal and sends it to the server.

[0627] The server retrains the machine learning model using new data to improve the accuracy of the next treatment plan.

[0628] Prompt Sentence Examples

[0629] "Please explain the system that analyzes genetic information and clinical data of cancer patients and generates individually optimized treatment plans using machine learning. Please describe the specific data collection methods, analysis and processing, generation of treatment plans, and real-time data collection and re-learning during treatment."

[0630] In this way, the present invention can provide effective and safe treatment for patients by automatically generating individually optimized treatment plans and adjusting them in real time during treatment.

[0631] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0632] Step 1: Data collection

[0633] The user uses a terminal to input basic patient information (age, gender, medical history, etc.) into the electronic medical record system. The input basic information is saved in the database, allowing the system to obtain basic patient information to be used in subsequent processing.

[0634] The user runs a sample taken from a patient through a genetic analyzer and transfers the resulting genetic information to a terminal. The terminal then sends this genetic information to a server, where it is stored in a database.

[0635] Step 2: Data Preprocessing

[0636] The server normalizes the received genetic and clinical data into a standard format, such as JSON, to maintain consistency in the data format.

[0637] The server preprocesses the normalized data, including imputing missing data and cleaning outliers. For example, the server cleans the data using the Pandas library and imputes missing values ​​with the mean using a Python script. The processed data is used as a clean dataset.

[0638] Step 3: Train the machine learning model

[0639] The server uses the cleaned data to train a machine learning model, which trains the algorithm based on past treatment data. For example, a deep learning model is built using TensorFlow or PyTorch and fitted to the dataset.

[0640] Using the cleaned data as input, we obtain an optimal predictive model as output, which is used to generate a treatment plan for each patient.

[0641] Step 4: Generate a treatment plan

[0642] The server uses the trained machine learning model to generate a treatment plan for each patient. For example, in the case of cancer treatment, it calculates the appropriate treatment, medication, and administration schedule based on the patient's genetic information.

[0643] Based on the input data of each patient's genetic information and clinical data, an optimized treatment plan is obtained as output, including specific treatment procedures and schedules.

[0644] Step 5: Provide a treatment plan

[0645] The server sends the generated treatment plan to the terminal, which receives the plan and presents it to the user, who can then review the plan and begin optimal treatment for the patient.

[0646] Based on the treatment plan as input data, presentation data as output is generated and sent to the terminal. This presentation data includes specific treatment implementation procedures.

[0647] Step 6: Real-time data collection and prediction

[0648] The device transmits the patient's vital signs and drug response data to a server in real time via Bluetooth or Wi-Fi during treatment, for example, through a smartwatch or medical monitoring device.

[0649] The server analyzes the collected data and predicts the effectiveness of treatment, for example, by using Apache Kafka or Flink for real-time analysis to determine whether treatment is progressing appropriately.

[0650] Real-time data is used as input data, and analytical results are output, which are used to adjust the treatment plan.

[0651] Step 7: Feedback and Retraining

[0652] The user inputs treatment progress and new data into the terminal and sends it to the server, for example, entering details of regular checkups or new test results.

[0653] The server retrains the machine learning model using new data, improving the accuracy of the next treatment plan. For example, it combines past and new data to update the model and make more accurate predictions.

[0654] New clinical data and treatment effects are used as inputs to obtain updated prediction models as outputs, which can be reused for subsequent treatment plan generation.

[0655] This series of processing steps enables the system to provide individually optimized treatment plans and monitor and adjust treatment progress in real time.

[0656] (Application example 1)

[0657] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0658] In the current healthcare system, providing optimal treatment plans for individual patients requires the collection and analysis of large amounts of data, a process that is time-consuming and inefficient. Furthermore, there is a lack of adequate management of patients' daily health data and early detection of abnormalities. Furthermore, there is a lack of a mechanism for responding quickly when abnormalities are detected, which could result in a decline in the quality of patient healthcare.

[0659] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0660] In this invention, the server includes means for inputting a patient's genetic information and clinical data, means for normalizing and preprocessing the genetic information and clinical data into a standard format, means for training a machine learning model based on past treatment data, means for generating an optimal treatment plan for each patient using the machine learning model, means for transmitting the treatment plan to a terminal and providing it to a user, means for collecting data during the patient's treatment in real time and adjusting the treatment plan, means for feeding back the collected new data to the machine learning model and retraining the model, means for collecting daily health data and detecting abnormalities, means for notifying the user of the abnormality, and means for retraining the machine learning model based on feedback from the user. This enables the server to quickly and efficiently provide an optimal treatment plan for each patient, and enables early detection and prompt response to abnormalities.

[0661] "Patient genetic information" refers to data about a patient's genes, such as their DNA sequence, including information about their disease and genetic characteristics.

[0662] "Clinical data" is a general term for clinical data such as a patient's age, sex, medical history, diagnostic information, and treatment history.

[0663] "Normalization to a standard format" is a technique for converting collected data into a unified format that makes the data easier to analyze.

[0664] "Preprocessing" refers to the process of data cleaning and transformation to convert raw data into an analyzable format.

[0665] "Past treatment data" refers to historical data such as treatment information and progression of disease status for each patient that has been accumulated to date.

[0666] A "machine learning model" is an algorithm that learns patterns and correlations based on large amounts of data and makes predictions and judgments.

[0667] An "optimal treatment plan" is the most effective treatment or treatment schedule designed based on a patient's specific condition and characteristics.

[0668] A "terminal" is an electronic device such as a computer or smartphone that allows a user to input and output information.

[0669] "Real-time collection" refers to the process of collecting data instantly, without delay.

[0670] "Adjusting the treatment plan" refers to reviewing the treatment content and schedule based on data during treatment and making changes as necessary.

[0671] "Feedback to a machine learning model" is the process of adding new data to a model and retraining it using that data.

[0672] "Daily health data" refers to data relating to the patient's daily lifestyle and physical condition, including, for example, heart rate, number of steps, and sleep data.

[0673] "Anomaly detection" is the process of finding abnormal conditions or unexpected data patterns.

[0674] "Sending a notification of an abnormality to the user" refers to the act of notifying the user of information about the detected abnormality.

[0675] "Feedback-based retraining" is the process of retraining a model based on user reactions and opinions to improve its accuracy.

[0676] The present invention relates to a system that collects and analyzes a patient's daily health data, genetic information, and clinical data, detects abnormalities using machine learning, and generates an optimal treatment plan. Specific embodiments are described below.

[0677] 1. System Overview

[0678] This system works by having the user (doctor or patient) input data via a device and send that data to a server. The server analyzes the received data, monitors the patient's health, and detects abnormalities and generates treatment plans as needed. The generated plans and alerts are sent to the device and provided to the user. Data is collected in real time during treatment and in daily life, and the system self-improves based on feedback.

[0679] 2. Hardware and Software

[0680] The following hardware and software are used to implement this system:

[0681] Smartphone: Used as a device for users to input data.

[0682] Server: A central system that analyzes data and trains machine learning models.

[0683] Healthcare app: An application that collects and records health data.

[0684] Machine learning libraries: Software for building machine learning models, such as TensorFlow and Scikit-learn.

[0685] 3. Data collection

[0686] Users use a healthcare app on their smartphone to collect daily health data (heart rate, number of steps, sleep data, etc.) and, if necessary, use a genetic analyzer to obtain genetic information and clinical data, which are then sent from the device to a server.

[0687] 4. Data Preprocessing and Analysis

[0688] The server normalizes the received health and genetic data into a standard format and performs data cleaning and pre-processing, removing incomplete data and outliers to make the data suitable for analysis.

[0689] 5. Machine Learning for Anomaly Detection and Treatment Plan Generation

[0690] The server uses the data to train a machine learning model using past treatment data. This model generates optimal treatment plans for each patient and has the ability to detect abnormal patterns. If an abnormality is detected, the server immediately sends a notification to the user's smartphone.

[0691] 6. Real-time data collection and feedback

[0692] Users collect real-time data about their health and treatment progress and provide feedback to the server, allowing the system to adjust and retrain treatment plans and improve the accuracy of the model.

[0693] Prompt Sentence Examples

[0694] "Analyze user heart rate data and generate a model to detect future anomalies. Create a system that detects and alerts users of sudden increases or decreases in heart rate early."

[0695] As a result, the present invention provides a system that comprehensively monitors the health condition of a user, enables early detection of abnormalities, and provides an optimal treatment plan.

[0696] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0697] Step 1:

[0698] Data collection

[0699] Subject: Device

[0700] The device collects the user's daily health data (heart rate, number of steps, sleep data, etc.) through a healthcare app. If necessary, the user can obtain genetic information and clinical data using a genetic analyzer and input it into the device. This collected data is centralized and sent to a server. The input is health data, genetic information, and clinical data, and the output is the integrated data sent to the server.

[0701] Step 2:

[0702] Data preprocessing and normalization

[0703] Subject: Server

[0704] The server normalizes the received health and genetic data into a standard format. During this process, incomplete data is filled in and outliers are cleaned. The input is raw data, and the output is clean data that has been converted into a form suitable for analysis.

[0705] Step 3:

[0706] Training a machine learning model

[0707] Subject: Server

[0708] The server trains a machine learning model based on the standardized and preprocessed data. The model uses historical treatment data to learn patterns and correlations. The input is the clean data and historical treatment data, and the output is the trained machine learning model.

[0709] Step 4:

[0710] Anomaly detection and treatment plan generation

[0711] Subject: Server

[0712] The server uses a trained machine learning model to detect abnormal patterns in the collected data and generate optimal treatment plans as needed. The input is the user's latest health and genetic information, and the output is the detected abnormal data and the generated treatment plan.

[0713] Step 5:

[0714] Notifying users and gathering feedback

[0715] Subject: Device

[0716] If an abnormality is detected, the terminal notifies the user of the notification sent from the server. It also presents the generated treatment plan to the user. The user then provides feedback, which is sent to the server via the terminal. The input is the notification and treatment plan from the server, and the output is the alert and feedback data for the user.

[0717] Step 6:

[0718] Real-time data collection and model retraining

[0719] Subject: Server

[0720] The server collects real-time data during treatment, analyzes the data, adjusts the treatment plan, and retrains the machine learning model based on the new data collected and user feedback. The inputs are real-time data during treatment and feedback data, and the outputs are an adjusted treatment plan and a retrained machine learning model.

[0721] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0722] The present invention combines a system that provides an optimal treatment plan based on a patient's genetic information and clinical data with an emotion engine that recognizes the user's emotions and enables adjustment of the treatment plan taking these emotions into consideration. The following describes in detail the embodiments of the present invention.

[0723] System Overview

[0724] This system operates by sending genetic information, clinical data, and emotional data entered by the user (doctor or patient) using a terminal to a server. The server analyzes this data and generates an optimal treatment plan. The generated treatment plan is then sent back to the terminal and used by the user for treatment. Data is collected in real time during and after treatment, allowing the treatment plan to be adjusted and retrained. The emotional engine also takes the user's emotions into account and provides a plan to maximize the effectiveness of treatment.

[0725] Program processing

[0726] Data collection

[0727] The user (doctor or patient) uses a terminal to input basic patient information (age, gender, medical history, etc.) into the electronic medical record system, which then organizes the basic data.

[0728] The user runs a sample taken from the patient through a genetic analyzer, and the resulting analysis data is sent to a server via the device.

[0729] A user uses an emotion recognition device to record his / her emotional state, and this data is input into a terminal or automatically collected through the emotion recognition device and transmitted to a server.

[0730] Data preprocessing and analysis

[0731] The server normalizes the received genetic and clinical data into a standard format and performs preprocessing, including removing incomplete data and noise.

[0732] The server analyzes the emotion data and identifies the user's emotional state, and the emotion engine operates based on the results of this identification.

[0733] Training a machine learning model

[0734] The server trains the machine learning model using historical treatment data, which includes genetic, clinical, and emotional data.

[0735] The server uses the trained model to predict the patient's individual treatment response.

[0736] Treatment plan generation and presentation

[0737] The server then uses the trained model to generate an optimal treatment plan based on the user's genetic, clinical, and emotional information. Specifically, for cancer treatment, it selects targeted therapeutic drugs that correspond to genetic mutations and sets the administration schedule.

[0738] The server sends the generated treatment plan to the terminal and provides it to the user, who then confirms the plan and adopts it as the treatment policy.

[0739] Specific examples

[0740] In the case of cancer treatment

[0741] 1. Data Collection

[0742] - Users take blood samples from cancer patients and perform genetic analysis.

[0743] - The device sends the analysis data to the server.

[0744] - Users use emotion recognition devices to record and transmit their own or their patients' emotional states.

[0745] 2. Data Preprocessing and Analysis

[0746] - The server normalizes the received genetic and clinical data into a standard format and organizes the data.

[0747] - The server analyzes the user's emotional state using an emotion engine and integrates the emotion data with other medical data.

[0748] 3. Training the machine learning model

[0749] - The server trains the machine learning model using historical cancer treatment data, including sentiment data.

[0750] The server uses the trained model to predict treatment response.

[0751] 4. Treatment plan generation and presentation

[0752] - The server generates an optimal treatment plan based on the analyzed data. Based on the emotional data, approaches to reduce the patient's mental stress are also considered.

[0753] - The server sends the treatment plan to the terminal and provides it to the user, who then carries out the treatment based on it.

[0754] 5. Monitoring and adjustment during and after treatment

[0755] - The device collects new data from the patient in real time during and after treatment and sends it to the server.

[0756] - The server analyzes the collected data and adjusts the treatment plan as needed. Emotional data is also collected and analyzed periodically, and adjustments are made to reduce the patient's mental burden.

[0757] The present invention not only provides individually optimized treatment, but also makes it possible to implement a comprehensive treatment plan that takes into account the psychological aspects of the patient.

[0758] The processing flow will be explained below.

[0759] Step 1:

[0760] Data collection

[0761] A user (doctor or patient) uses a terminal to input basic patient information (age, sex, medical history, etc.) into the electronic medical record system, which then transmits the basic patient data to the server.

[0762] The user takes blood or tissue samples from the patient and runs them through a genetic analyzer, and the genetic data output from the analyzer is sent to a server via a terminal.

[0763] The user uses an emotion recognition device (such as a wearable device or dedicated app) to record their own or their patient's emotional state, and then synchronizes this data with the device and sends it to a server.

[0764] Step 2:

[0765] Data Preprocessing

[0766] The server normalizes the received genetic and clinical data into a standard format for analysis, a process that unifies the data and makes it easier to analyze.

[0767] The server performs a cleansing process to remove incomplete data and noise, and also completes missing data if any.

[0768] The server analyzes the emotion data and uses an emotion engine to recognize the user's emotional state (e.g., stress level, happiness level).

[0769] Step 3:

[0770] Training a machine learning model

[0771] The server trains machine learning models based on past treatment data, including genetic information, clinical data, and user emotional data.

[0772] The server uses the trained model to build predictive models for each patient data type to help plan future treatment.

[0773] Step 4:

[0774] Treatment plan generation

[0775] The server then applies the trained machine learning model to generate an optimal treatment plan based on the user's genetic, clinical, and emotional data. For example, in the case of cancer treatment, it would select a targeted drug for a specific gene mutation and set a dosing schedule based on the doctor's instructions.

[0776] The server uses an emotion engine to reflect the user's emotional state in the treatment plan. For example, if the patient is in a high stress state, stress reduction measures and psychological support will be added to the plan.

[0777] Step 5:

[0778] Presentation of treatment plan

[0779] The server transmits the generated treatment plan to the terminal and provides it to the user.

[0780] The device displays the received treatment plan in an easy-to-understand format for the user (doctor) and presents it as a treatment guideline. The doctor will then begin appropriate treatment for the patient based on this plan.

[0781] Step 6:

[0782] Treatment initiation and monitoring

[0783] The user starts treatment for the patient based on the treatment plan received from the server.

[0784] The device collects and transmits real-time vital signs, emotional state, and drug response data of patients undergoing treatment, including blood pressure, heart rate, blood drug concentration, and emotional state, to a server.

[0785] Step 7:

[0786] Real-time treatment prediction and adjustment

[0787] The server uses machine learning models to analyze the data collected in real time and predict the effectiveness of treatment.

[0788] Based on the predictions and emotion data, the server adjusts the treatment plan, for example by changing the drug dosage to minimize the risk of side effects.

[0789] Step 8:

[0790] Feedback and Retraining

[0791] The user (doctor) enters the progress of treatment and new data into the terminal and sends it to the server.

[0792] The server uses the newly collected data to retrain the machine learning model, improving the accuracy of future treatment plans.

[0793] The present invention not only provides an individually optimized treatment plan, but also takes into account the patient's mental and emotional state, thereby maximizing the overall effectiveness of the treatment.

[0794] Example 2

[0795] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0796] Conventional medical systems have not been able to adequately provide personalized medical plans based on genetic information and clinical data, and real-time collection of treatment data and plan adjustments have been limited. Furthermore, no measures have been taken to provide treatment plans that take into account the emotional data of patients and doctors. This has made it difficult to reduce patients' mental stress, and there have been cases where the effectiveness of treatment has not been maximized.

[0797] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: a means for inputting biomedical information and health data of a patient; a means for normalizing the biomedical information and health data into a standard format and preprocessing the data; a means for training a machine learning model based on past therapy data; a means for generating an optimal medical plan for each patient using the machine learning model; a means for transmitting the medical plan to a communication device and providing it to a user; a means for collecting data during the patient's treatment in real time and adjusting the medical plan; a means for feeding back the collected new data to the machine learning model and retraining the model; and a means for recognizing emotional data of the user, analyzing the emotional data, and reflecting the emotional data in the medical plan. This improves the accuracy and effectiveness of the personalized medical plan, making it possible to maximize the effectiveness of treatment while reducing mental stress on the patient.

[0798] "Biomedical information" refers to various biological data necessary for medical diagnosis and treatment, such as a patient's genetic information, clinical data, and vital signs.

[0799] "Health data" refers to data that includes various information used to assess a patient's health status, such as their lifestyle, diet, exercise, and stress level.

[0800] "Normalizing to a standard format" means converting data provided in different formats and units into a unified format and unit, and making it organized.

[0801] "Preprocessing" refers to the process of preparing data, such as filling in missing values ​​and removing outliers, before conducting data analysis.

[0802] "Therapy data" refers to data that includes the results and details of past treatments, recording the effectiveness and side effects of the treatments.

[0803] "Training a machine learning model" means training the model using past data to improve its predictive accuracy.

[0804] A "personalized medical plan" is a plan that proposes the most appropriate treatment method based on each patient's genetic information and clinical data.

[0805] A "communication device" is an electronic device used by a patient or doctor, such as a computer, tablet, or smartphone.

[0806] "Real-time collection" means continuously monitoring and collecting data the moment it occurs.

[0807] "Retraining" means using new data collected to retrain an existing machine learning model to further improve its accuracy.

[0808] "Emotional data" refers to data that indicates the user's psychological and emotional state, measured based on heart rate, electrodermal activity, etc.

[0809] An "emotion engine" is a software algorithm that analyzes and recognizes a user's emotional data.

[0810] This invention is a system that provides an optimal medical plan based on a patient's biomedical information and health data, and adjusts the plan taking into account the user's emotional state. The system consists of a series of steps: data collection, data preprocessing and analysis, training of a machine learning model, generation and presentation of a treatment plan, and monitoring and adjustment during and after treatment.

[0811] Data collection

[0812] A user (doctor or patient) uses a terminal to input basic patient information (age, gender, medical history, etc.) into the electronic medical record system. The terminal then sends this information to a server in a standard format. The user also collects a biological sample from the patient and subjects it to a genetic analysis device. The analysis results data are also sent to the server via the terminal. Furthermore, the user uses an emotion recognition device to record their emotional state, and this data is entered into the terminal or automatically sent to the server.

[0813] Data preprocessing and analysis

[0814] The server uses Python's pandas library to normalize the received genetic and clinical data into a standard format, impute missing values, and remove outliers.The server then uses libraries such as TensorFlow and PyTorch to analyze the emotion data, identify the user's emotional state, and activate the emotion engine.

[0815] Training a machine learning model

[0816] The server trains a machine learning model using Scikit-learn and TensorFlow on past treatment data. The training data includes genetic information, clinical data, and emotional data. The server trains the model using cross-validation to prevent overfitting and generate a model with high predictive performance.

[0817] Treatment plan generation and presentation

[0818] The server uses the trained model to generate an optimal treatment plan based on the user's genetic information, clinical data, and emotional data. For example, it selects a targeted drug based on genetic mutations and sets its administration schedule. The generated treatment plan is then sent from the server to the device for the user to review.

[0819] Monitoring and adjustment during and after treatment

[0820] The device sends new data from the patient in real time during and after treatment to the server, which analyzes this data and adjusts the treatment plan accordingly. Emotional data is also collected and analyzed periodically, and actions to reduce the patient's mental stress are reflected in the plan.

[0821] Examples of specific examples and prompts

[0822] Example: Cancer treatment

[0823] 1. Data Collection

[0824] Users take blood samples from cancer patients and perform genetic analysis.

[0825] The terminal transmits this analysis data to the server.

[0826] The user uses the emotion recognition device to record their own or their patient's emotional state and transmit it to the server.

[0827] 2. Data Preprocessing and Analysis

[0828] The server normalizes the received genetic and clinical data into a standard format.

[0829] The server analyzes the user's emotional state using an emotion engine and integrates the emotion data.

[0830] 3. Training the machine learning model

[0831] The server trains the machine learning model using historical cancer treatment data, including emotional data.

[0832] The server uses the trained model to predict treatment response.

[0833] 4. Treatment plan generation and presentation

[0834] The server generates an optimal treatment plan and takes into account approaches to reduce stress for the patient based on emotional data.

[0835] The server transmits the treatment plan to the terminal and provides it to the user.

[0836] 5. Monitoring and adjustment during and after treatment

[0837] The terminal transmits new data in real time to the server during and after treatment.

[0838] The server analyzes the collected data and adjusts the treatment plan as needed.

[0839] Prompt Sentence Examples

[0840] "I would like to create an optimal treatment plan for a cancer patient that takes into account their genetic information, clinical data, and emotional state. Please generate a treatment proposal based on the following data."

[0841] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0842] Step 1: Data collection

[0843] Input: Patient basic information, genetic sample, emotional data

[0844] Output: Genetic information, clinical data, and emotional data in a standard format sent to a server

[0845] Step 1.1: Enter patient basic information

[0846] The user logs into the electronic medical record system on the terminal and enters the patient's basic information (age, gender, medical history, etc.), enters the required data in the input fields, and clicks the "Save" button to send it to the server.

[0847] Specific actions: The user uses the device's keyboard to enter information and clicks the save button with the mouse.

[0848] Step 1.2: Genetic sample analysis and submission

[0849] Input: Patient genetic sample

[0850] Output: Genetic information sent to the server

[0851] The user places the collected gene sample into the genetic analyzer and begins analysis. When the analysis is complete, the device generates a data file.

[0852] The terminal retrieves data files from the analysis device via USB or network connection and automatically uploads them to the server.

[0853] Specific operation: The user collects a genetic sample and inserts it into the analysis device. After analysis, the device sends the data to the server.

[0854] Step 1.3: Collect emotion data

[0855] Input: Emotion data from an emotion recognition device

[0856] Output: Emotion data sent to the server

[0857] The user uses the emotion recognition device to record their emotional state, and the data is transmitted via Bluetooth to the device and then from the device to the server.

[0858] Specific operation: The user wears the emotion recognition device and the data is automatically sent to the terminal.

[0859] Step 2: Data preprocessing and analysis

[0860] Input: Genetic information, clinical data, and emotional data in a standard format sent to the server

[0861] Output: Normalized and parsed data

[0862] Step 2.1: Normalize the data

[0863] The server converts the received genetic and clinical data into a data frame using Python's pandas library, normalizes it to a standard format, imputes missing values, and removes outliers.

[0864] What happens: The server runs data processing steps using pandas to generate a clean dataset.

[0865] Step 2.2: Analyzing and integrating sentiment data

[0866] The server analyzes the received emotion data using TensorFlow, PyTorch, etc. to identify the user's emotional state, which is then integrated with other biomedical information.

[0867] Specific operation: The server receives the emotion data and runs an analysis algorithm to classify the emotional state. The results are integrated with the biomedical data.

[0868] Step 3: Train the machine learning model

[0869] Input: Normalized and parsed data

[0870] Output: A trained machine learning model

[0871] Step 3.1: Train the model using historical data

[0872] The server uses historical therapy data to train machine learning models using Scikit-learn and TensorFlow, including genetic, clinical, and emotional data.

[0873] What happens: The server runs the script using the training data to optimize the model parameters.

[0874] Step 3.2: Predicting with the trained model

[0875] The server uses the trained model to predict the patient's individual treatment response.

[0876] Specific operation: The server inputs new patient data into the model and generates predictions, including predictions of treatment efficacy and side effects.

[0877] Step 4: Generate and present the treatment plan

[0878] Input: Trained machine learning model, patient biomedical information, and emotion data

[0879] Output: Generated medical plan

[0880] Step 4.1: Generate an optimal treatment plan

[0881] The server uses the trained model to generate an optimal treatment plan based on the user's genetic, clinical, and emotional information. In the case of cancer treatment, it selects targeted therapeutic drugs and sets administration schedules based on genetic mutations.

[0882] Specific operations: The server inputs the data into the model and calculates the optimal treatment plan.

[0883] Step 4.2: Present the treatment plan

[0884] The server then sends the generated treatment plan to the communication device, where the user can check the treatment plan on their device and share the necessary information within the hospital.

[0885] Specific operations: The server generates a treatment plan and sends it to the terminal. The user checks the plan on the terminal and performs the treatment.

[0886] Step 5: Monitoring and adjusting during and after treatment

[0887] Input: New patient data collected in real time

[0888] Output: Adjusted treatment plan

[0889] Step 5.1: Collect real-time data

[0890] The device transmits new patient data (genetic information, clinical data, emotional data) collected during and after treatment to the server in real time.

[0891] Specific operation: The device acquires new data through sensors or manual input and sends it to the server over the network.

[0892] Step 5.2: Analyze data and adjust treatment plan

[0893] The server analyzes the new data and reassess whether the existing treatment plan is optimal, adjusts it if necessary, and suggests actions to reduce the patient's mental stress based on emotional data.

[0894] Specific operations: The server analyzes the new data and updates the treatment plan. The updated plan is sent to the device, and the user modifies the treatment.

[0895] (Application example 2)

[0896] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0897] Conventional autonomous driving systems do not select driving routes that take into account the emotional state of passengers, which means they are unable to reduce passenger stress or provide a comfortable driving experience.In addition, treatment plans based on patients' genetic information and clinical data do not take into account their emotional state, making it difficult to maximize treatment effectiveness.

[0898] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0899] In this invention, the server includes: a means for inputting a patient's genetic information and clinical data; a means for normalizing and preprocessing the genetic information and clinical data into a standard format; a means for training a machine learning model based on past treatment data; a means for generating an optimal treatment plan for each patient using the machine learning model; a means for transmitting the treatment plan to a terminal and providing it to a user; a means for collecting data during the patient's treatment in real time and adjusting the treatment plan; a means for feeding back the collected new data to the machine learning model and retraining the model; a means for collecting passengers' emotional states and selecting a route based on the collected data; and a means for transmitting emotional data and location information to the server and optimizing the driving route. This enables the selection of a driving route taking passengers' emotional states into consideration, thereby reducing stress and providing a comfortable driving experience. Furthermore, an optimal treatment plan taking individual patients' emotional states into consideration is provided, maximizing the effectiveness of treatment.

[0900] "Patient genetic information" refers to data on genetic structure and mutations obtained by subjecting a sample collected from a patient to a genetic analysis device.

[0901] "Clinical data" refers to any information collected in a medical setting, such as a patient's diagnosis, treatment history, or vital signs.

[0902] "Means for inputting" refers to means for transmitting data to the server using an electronic medical record system or an input device.

[0903] "Normalization to a standard format" is a process of converting data of different formats into a unified format in order to maintain data consistency.

[0904] "Preprocessing means" refers to means for removing noise and imperfections from data and preparing it in an analyzable format.

[0905] A "machine learning model" is an algorithm that is trained to make predictions or classifications based on collected data.

[0906] The "means for generating a treatment plan" is a means for using a machine learning model to determine the optimal treatment method and schedule based on individual patient data.

[0907] The "means for transmitting to the terminal and providing to the user" refers to a means for transmitting the generated treatment plan to the device of the user (doctor or patient) so that it can be viewed and used.

[0908] "Means for collecting and adjusting in real time" refers to means for instantly transmitting newly acquired data during treatment to a server and dynamically changing the treatment plan.

[0909] "Means for providing feedback to a machine learning model and re-learning" refers to means for inputting newly collected data into a machine learning model and re-training it to improve the accuracy of the model.

[0910] "Passenger emotional state" refers to the passenger's psychological and emotional state, such as stress, joy, anxiety, etc.

[0911] The "route selection means" is a means for determining the optimal driving route based on the emotional state of the passenger.

[0912] "Emotion data and location information" refers to data relating to the psychological state of passengers and data relating to the current location of passengers and vehicles.

[0913] The "means for optimizing a driving route" is a means for automatically selecting the most suitable driving route based on emotion data and location information.

[0914] The present invention provides a driving route planning system that takes into account the emotional state of passengers in an autonomous vehicle, and incorporates emotional data as an additional element in a system that provides optimal treatment plans based on the patient's genetic information and clinical data. Specific embodiments are described below.

[0915] System Overview

[0916] The system works by collecting emotional and location data through smart devices (e.g., smartphones, head-mounted displays, etc.) and sending it to a server. The server then analyzes this data and generates an optimal driving route. The system also provides a treatment plan based on the patient's genetic and clinical data, and adjusts the treatment plan based on real-time analysis of data collected during and after treatment.

[0917] Program processing

[0918] Emotion data collection and transmission

[0919] Users (passengers) record their emotional state in real time through their smart devices. Emotion recognition technology is used to analyze emotional states such as stress, joy, and anxiety, and the data is sent to a server. Libraries such as EmotionRecognizer are used for this collection process.

[0920] Data Analysis and Optimization

[0921] The server analyzes the submitted emotion data and location information. It normalizes and preprocesses the data into a standard format, then uses EmotionRecognizer to determine the user's emotional state. It then generates an optimal driving route based on this data using a machine learning model trained on past data.

[0922] Route selection and provision

[0923] The generated driving route is sent to the terminal and provided to the user. The user operates the autonomous vehicle based on this route. Data related to the treatment plan is also sent to the user's terminal and used for treatment.

[0924] Real-time data collection and reconciliation

[0925] Data on the patient's treatment and passengers' emotional state is collected in real time and sent to a server, which then dynamically adjusts the treatment plan and driving route based on this data. Newly collected data is fed back into the machine learning model, allowing it to be retrained.

[0926] Specific examples

[0927] If a passenger in an autonomous vehicle is stuck in traffic, the system will choose a gentler route if data indicates the passenger's emotional state is stressed.

[0928] During treatment, the treatment plan generated based on the patient's genetic information also takes into account the patient's emotional data, and adjustments are made to the plan to reduce the mental burden.

[0929] Prompt Sentence Examples

[0930] "If the passenger's emotional state is relaxed, suggest the optimal driving route for the autonomous vehicle. If the passenger is stressed, suggest a gentler route that avoids traffic jams."

[0931] Thus, the present invention allows for the optimization of driving routes based on the emotional state of passengers and the provision of treatment plans that take into account the emotional state of patients.

[0932] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0933] Step 1:

[0934] Emotional Data Collection

[0935] Users (passengers) record their emotional state in real time through smart devices (e.g., smartphones, head-mounted displays). Emotion recognition technology is used to analyze emotional states such as stress, joy, and anxiety. Specifically, image data collected from a camera is analyzed using libraries such as EmotionRecognizer to extract emotional data. The input is camera image data, and the output is emotional state data.

[0936] Step 2:

[0937] Emotion data transmission

[0938] The device sends the collected emotion data to the server in JSON format using the HTTP protocol. Specifically, the device converts the emotion data into an appropriate format and sends it to the server's receiving endpoint. The input is emotion data (in JSON format), and the output is the completion of data transmission to the server.

[0939] Step 3:

[0940] Data analysis and standard formatting

[0941] The server receives the emotion data and normalizes it into a standard format. It removes inconsistencies and noise from the data and makes it analyzable. The input is emotion data (JSON format), and the output is emotion data in a standard format.

[0942] Step 4:

[0943] Training a machine learning model

[0944] The server trains a machine learning model based on past emotion data and driving route information. Specifically, it uses the collected dataset to train the model using libraries such as TensorFlow and scikit-learn. The input is past emotion data and driving route data, and the output is the trained model.

[0945] Step 5:

[0946] Route Selection

[0947] The server uses a trained machine learning model to generate an optimal driving route based on the received emotion data. Specifically, the model inputs current emotion data and location information and predicts the optimal route. The input is the current emotion data and location information, and the output is the optimal driving route.

[0948] Step 6:

[0949] Providing driving directions

[0950] The server sends the generated driving route to the device. Specifically, it sends the route information using the HTTP protocol and displays it on the smartphone's navigation app. The input is the optimal driving route, and the output is the route information displayed on the device.

[0951] Step 7:

[0952] Real-time data collection and treatment plan adjustment

[0953] The terminal collects real-time patient data and passenger emotional state data during treatment and sends it to the server, which then dynamically adjusts the treatment plan and driving route based on this data. The input is the real-time collected data, and the output is the adjusted treatment plan and driving route.

[0954] Step 8:

[0955] Retraining a machine learning model

[0956] The server feeds newly collected data back into the machine learning model for re-learning. Specifically, new data is input into the model to improve its accuracy. The input is new emotional data and location information, and the output is the re-learned model.

[0957] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0958] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0959] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0960] [Third embodiment]

[0961] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0962] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0963] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0964] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0965] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0966] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0967] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0968] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0969] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0970] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0971] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0972] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0973] The present invention relates to a system for analyzing genetic information and clinical data of a patient and generating an optimal treatment plan using machine learning. The embodiments for carrying out the present invention will be described in the following means.

[0974] System Overview

[0975] In this system, the user (doctor or patient) enters genetic information and clinical data via a terminal and sends it to a server, which then generates an optimal treatment plan based on that data. The generated treatment plan is then sent to the terminal and used by the user for treatment. During treatment, data is collected in real time, and the treatment plan is adjusted and re-learned.

[0976] Program processing

[0977] Data collection

[0978] The user uses the terminal to input basic patient information (age, sex, medical history, etc.) into the electronic medical record system.

[0979] The user runs a sample taken from the patient through a genetic analyzer, and the genetic information output from the analyzer is sent to a server via the terminal.

[0980] Data Analysis and Learning

[0981] The server normalizes the received genetic and clinical data into a standard format and performs data preprocessing, imputing or cleaning incomplete or inappropriate data.

[0982] The server trains a machine learning model based on past treatment data, which is capable of detecting patterns in patient data and generating optimal treatment plans.

[0983] Treatment plan generation and presentation

[0984] The server uses machine learning models to generate optimal treatment plans for each patient. Specifically, in the case of cancer treatment, it selects targeted therapeutic drugs that correspond to the patient's genetic mutations and sets the administration schedule.

[0985] The server sends the generated treatment plan to the terminal and provides it to the user, who then begins treatment based on this plan.

[0986] Specific examples

[0987] In the case of cancer treatment

[0988] 1. Data Collection

[0989] - Users take blood samples from cancer patients and perform genetic analysis.

[0990] - The device sends the analysis data to the server.

[0991] 2. Data analysis and learning

[0992] - The server analyzes the genetic data of cancer patients and identifies specific genetic mutations.

[0993] - The server updates the machine learning model using data from similar past cases.

[0994] 3. Treatment plan generation

[0995] - The server uses machine learning models to generate targeted therapeutic drugs and their administration schedules that correspond to specific gene mutations.

[0996] - The server sends the generated treatment plan to the terminal and presents the treatment policy to the user.

[0997] 4. Data collection and prediction during treatment

[0998] - The device transmits the patient's vital signs and drug response data to a server in real time during treatment.

[0999] - The server analyzes the collected data, predicts treatment effectiveness, and adjusts the treatment plan as needed.

[1000] 5. Feedback and Retraining

[1001] - The user enters the progress of treatment and new data into the terminal and sends it to the server.

[1002] - The server retrains the machine learning model with new data to improve the accuracy of the next treatment plan.

[1003] In this way, the present invention can provide effective and safe treatment for patients by automatically generating individually optimized treatment plans and adjusting them in real time during treatment.

[1004] The processing flow will be explained below.

[1005] Step 1:

[1006] Data collection

[1007] The user (doctor or patient) inputs basic information about the patient (age, gender, medical history, etc.) into the terminal, which then organizes this information and sends it to the server.

[1008] The user takes blood or tissue samples from the patient and subjects them to a genetic analysis device, which then sends the genetic data output from the device to a server via a terminal.

[1009] Step 2:

[1010] Data Preprocessing

[1011] The server normalizes the received genetic and clinical data into a standard format, harmonizing different data formats.

[1012] The server performs a cleansing process, removing incomplete data and noise, and also complements the data as needed.

[1013] Step 3:

[1014] Training a machine learning model

[1015] The server trains the machine learning model using data from past treatments and similar cases, improving its pattern recognition capabilities.

[1016] The server uses normalized patient data as input to build predictive models for specific diseases and treatment responses.

[1017] Step 4:

[1018] Treatment plan generation

[1019] The server uses the trained machine learning model to generate an optimal treatment plan for each patient, such as selecting targeted drugs for specific gene mutations in cancer treatment.

[1020] The server creates a treatment plan that includes the treatment method, drugs to be used, and administration schedule.

[1021] Step 5:

[1022] Presentation of treatment plan

[1023] The server sends the generated treatment plan to the terminal.

[1024] The terminal displays the treatment plan to the user (doctor) in an easy-to-understand format and provides it as a treatment guideline.

[1025] Step 6:

[1026] Treatment initiation and monitoring

[1027] The user (doctor) starts treatment for the patient based on the treatment plan received from the server.

[1028] The device transmits real-time vital signs and drug response data of patients undergoing treatment to a server, including physiological data such as blood pressure, heart rate, and blood drug concentrations.

[1029] Step 7:

[1030] Real-time treatment prediction and adjustment

[1031] The server uses machine learning models to analyze real-time treatment data and predict treatment outcomes.

[1032] The server adjusts dosage and treatment schedule accordingly based on the predicted results.

[1033] Step 8:

[1034] Feedback and Retraining

[1035] The user (doctor) inputs the progress of treatment and new data into the terminal as needed and sends it to the server.

[1036] The server retrains the machine learning model using newly collected data, thereby improving the accuracy of future treatment plans.

[1037] This allows the system to continuously learn and provide optimal treatment plans for each patient.

[1038] Example 1

[1039] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1040] With conventional medical systems, it has been difficult to quickly generate optimal treatment plans that effectively utilize a patient's individual genetic information and clinical data. It has also been difficult to collect data during treatment in real time and immediately adjust the treatment plan based on that data. This has led to issues such as not being able to maximize the effectiveness and safety of the treatment provided to patients.

[1041] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1042] In this invention, the server includes means for inputting a patient's genetic information and clinical data, means for normalizing and preprocessing the genetic information and clinical data into a standard format, means for training a machine learning model based on past treatment data, means for generating an optimal treatment plan for each patient using the machine learning model, means for transmitting the treatment plan to a terminal and providing it to a user, means for collecting data during the patient's treatment in real time and adjusting the treatment plan, means for feeding back the collected new data to the machine learning model and retraining the model, means for acquiring and analyzing vital signs and drug response data in real time, means for transmitting data to the server via Wi-Fi or Bluetooth, means for updating the machine learning model based on case data, and means for automatically generating an individualized treatment plan for the patient and notifying the terminal. This makes it possible to quickly and effectively provide an optimized treatment plan for each patient and adjust the plan in real time based on treatment data.

[1043] "Patient genetic information" refers to the sequence data of a patient's DNA or RNA, and is biological information used to diagnose disease and develop treatment plans.

[1044] "Clinical data" refers to all information related to the provision of medical services, such as a patient's treatment history, diagnosis results, medication history, and vital signs.

[1045] "Normalizing to a standard format" refers to the process of converting data entered in different formats into a uniform format to make it consistent.

[1046] "Preprocessing" refers to the process of organizing and processing raw data into an analyzable form, including, for example, imputing missing values ​​and cleaning the data.

[1047] "Training a machine learning model" refers to the process of using existing data to teach an algorithm patterns that give it the ability to make predictions or classifications on new data.

[1048] "Generating optimal treatment plans" refers to using machine learning models to develop individualized treatment methods and drug administration schedules for each patient.

[1049] "Real-time collection" refers to the immediate acquisition and recording of data during treatment without delay.

[1050] "Retraining" refers to adding new data to update the learning model and improve its accuracy and effectiveness.

[1051] "Vital signs" are data that indicate the basic vital signs of a patient's body, and generally include heart rate, respiratory rate, body temperature, blood pressure, etc.

[1052] "Drug response data" refers to data that shows how a patient's body reacts to a drug after taking it, including, for example, the drug's effects and side effects.

[1053] "Transmitting data using Wi-Fi or Bluetooth" refers to transferring data between devices using wireless communication technologies.

[1054] "Case data" refers to data that includes past patient treatment history and diagnostic information, and is used to create treatment plans for new patients.

[1055] An "individualized treatment plan" refers to formulating the optimal treatment method and administration schedule for a specific patient based on each patient's genetic information and clinical data.

[1056] The present invention relates to a system for analyzing genetic information and clinical data of a patient and generating an optimal treatment plan using machine learning. An embodiment of the present invention will be described in detail below.

[1057] System configuration

[1058] This system sends genetic information and clinical data entered by the user via a terminal to a server, which then generates an optimal treatment plan based on that data.The system consists of the following main components.

[1059] 1. Terminal

[1060] Hardware: Personal computers, tablets, smartphones, etc.

[1061] Software: Electronic medical record systems (e.g., EPIC, Cerner), data entry interfaces, and data submission applications.

[1062] 2. Server

[1063] Hardware: High performance computers (e.g. server racks).

[1064] Software: Database management systems, data preprocessing programs (e.g., Python scripts, Pandas library), machine learning platforms (e.g., TensorFlow, PyTorch), web frameworks (e.g., Flask, Django).

[1065] 3. Genetic analysis equipment

[1066] Hardware: Genetic analysis equipment (e.g., Illumina).

[1067] Software: Genetic data analysis program.

[1068] System Operation

[1069] 1. Data Collection

[1070] Using a terminal, the user inputs basic patient information (age, gender, medical history, etc.) into the electronic medical record system. In addition, a sample taken from the patient is put through a genetic analyzer, and the obtained genetic information is sent to a server via the terminal.

[1071] 2. Data analysis and learning

[1072] The server normalizes the received genetic and clinical data into a standard format and performs data preprocessing. Incomplete or inappropriate data is cleaned and imputed. Using historical treatment data, the server trains a machine learning model. This model detects patterns in the patient data and generates an optimal treatment plan.

[1073] 3. Treatment plan generation and presentation

[1074] The server uses machine learning models to generate optimal treatment plans for each patient. For example, in the case of cancer treatment, it selects targeted therapeutic drugs that correspond to the patient's genetic mutations and sets an administration schedule. The generated treatment plan is then sent to the device and provided to the user, who then begins treatment based on this plan.

[1075] 4. Data collection and prediction during treatment

[1076] During treatment, the device transmits the patient's vital signs and drug response data in real time to a server, which analyzes the collected data, predicts treatment effectiveness, and adjusts the treatment plan as needed.

[1077] 5. Feedback and Retraining

[1078] The user inputs treatment progress and new data into the device and sends it to the server, which then uses the new data to retrain the machine learning model and improve the accuracy of the next treatment plan.

[1079] Specific examples

[1080] In the case of cancer treatment

[1081] 1. Data Collection

[1082] Users take blood samples from cancer patients and perform genetic analysis.

[1083] The terminal transmits the analysis data to the server.

[1084] 2. Data analysis and learning

[1085] The server analyzes the genetic data of cancer patients and identifies specific genetic mutations.

[1086] The server uses data from similar past cases to update the machine learning model.

[1087] 3. Treatment plan generation

[1088] The server uses machine learning models to generate targeted therapeutic drugs and their administration schedules that correspond to specific gene mutations.

[1089] The server sends the generated treatment plan to the terminal and presents the treatment policy to the user.

[1090] 4. Data collection and prediction during treatment

[1091] The device transmits the patient's vital signs and drug response data to a server in real time during treatment.

[1092] The server analyzes the collected data, predicts treatment effectiveness, and adjusts the treatment plan as needed.

[1093] 5. Feedback and Retraining

[1094] The user enters the progress of treatment and new data into the terminal and sends it to the server.

[1095] The server retrains the machine learning model using new data to improve the accuracy of the next treatment plan.

[1096] Prompt Sentence Examples

[1097] "Please explain the system that analyzes genetic information and clinical data of cancer patients and generates individually optimized treatment plans using machine learning. Please describe the specific data collection methods, analysis and processing, generation of treatment plans, and real-time data collection and re-learning during treatment."

[1098] In this way, the present invention can provide effective and safe treatment for patients by automatically generating individually optimized treatment plans and adjusting them in real time during treatment.

[1099] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1100] Step 1: Data collection

[1101] The user uses a terminal to input basic patient information (age, gender, medical history, etc.) into the electronic medical record system. The input basic information is saved in the database, allowing the system to obtain basic patient information to be used in subsequent processing.

[1102] The user runs a sample taken from a patient through a genetic analyzer and transfers the resulting genetic information to a terminal. The terminal then sends this genetic information to a server, where it is stored in a database.

[1103] Step 2: Data Preprocessing

[1104] The server normalizes the received genetic and clinical data into a standard format, such as JSON, to maintain consistency in the data format.

[1105] The server preprocesses the normalized data, including imputing missing data and cleaning outliers. For example, the server cleans the data using the Pandas library and imputes missing values ​​with the mean using a Python script. The processed data is used as a clean dataset.

[1106] Step 3: Train the machine learning model

[1107] The server uses the cleaned data to train a machine learning model, which trains the algorithm based on past treatment data. For example, a deep learning model is built using TensorFlow or PyTorch and fitted to the dataset.

[1108] Using the cleaned data as input, we obtain an optimal predictive model as output, which is used to generate a treatment plan for each patient.

[1109] Step 4: Generate a treatment plan

[1110] The server uses the trained machine learning model to generate a treatment plan for each patient. For example, in the case of cancer treatment, it calculates the appropriate treatment, medication, and administration schedule based on the patient's genetic information.

[1111] Based on the input data of each patient's genetic information and clinical data, an optimized treatment plan is obtained as output, including specific treatment procedures and schedules.

[1112] Step 5: Provide a treatment plan

[1113] The server sends the generated treatment plan to the terminal, which receives the plan and presents it to the user, who can then review the plan and begin optimal treatment for the patient.

[1114] Based on the treatment plan as input data, presentation data as output is generated and sent to the terminal. This presentation data includes specific treatment implementation procedures.

[1115] Step 6: Real-time data collection and prediction

[1116] The device transmits the patient's vital signs and drug response data to a server in real time via Bluetooth or Wi-Fi during treatment, for example, through a smartwatch or medical monitoring device.

[1117] The server analyzes the collected data and predicts the effectiveness of treatment, for example, by using Apache Kafka or Flink for real-time analysis to determine whether treatment is progressing appropriately.

[1118] Real-time data is used as input data, and analytical results are output, which are used to adjust the treatment plan.

[1119] Step 7: Feedback and Retraining

[1120] The user inputs treatment progress and new data into the terminal and sends it to the server, for example, entering details of regular checkups or new test results.

[1121] The server retrains the machine learning model using new data, improving the accuracy of the next treatment plan. For example, it combines past and new data to update the model and make more accurate predictions.

[1122] New clinical data and treatment effects are used as inputs to obtain updated prediction models as outputs, which can be reused for subsequent treatment plan generation.

[1123] This series of processing steps enables the system to provide individually optimized treatment plans and monitor and adjust treatment progress in real time.

[1124] (Application example 1)

[1125] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1126] In the current healthcare system, providing optimal treatment plans for individual patients requires the collection and analysis of large amounts of data, a process that is time-consuming and inefficient. Furthermore, there is a lack of adequate management of patients' daily health data and early detection of abnormalities. Furthermore, there is a lack of a mechanism for responding quickly when abnormalities are detected, which could result in a decline in the quality of patient healthcare.

[1127] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1128] In this invention, the server includes means for inputting a patient's genetic information and clinical data, means for normalizing and preprocessing the genetic information and clinical data into a standard format, means for training a machine learning model based on past treatment data, means for generating an optimal treatment plan for each patient using the machine learning model, means for transmitting the treatment plan to a terminal and providing it to a user, means for collecting data during the patient's treatment in real time and adjusting the treatment plan, means for feeding back the collected new data to the machine learning model and retraining the model, means for collecting daily health data and detecting abnormalities, means for notifying the user of the abnormality, and means for retraining the machine learning model based on feedback from the user. This enables the server to quickly and efficiently provide an optimal treatment plan for each patient, and enables early detection and prompt response to abnormalities.

[1129] "Patient genetic information" refers to data about a patient's genes, such as their DNA sequence, including information about their disease and genetic characteristics.

[1130] "Clinical data" is a general term for clinical data such as a patient's age, sex, medical history, diagnostic information, and treatment history.

[1131] "Normalization to a standard format" is a technique for converting collected data into a unified format that makes the data easier to analyze.

[1132] "Preprocessing" refers to the process of data cleaning and transformation to convert raw data into an analyzable format.

[1133] "Past treatment data" refers to historical data such as treatment information and progression of disease status for each patient that has been accumulated to date.

[1134] A "machine learning model" is an algorithm that learns patterns and correlations based on large amounts of data and makes predictions and judgments.

[1135] An "optimal treatment plan" is the most effective treatment or treatment schedule designed based on a patient's specific condition and characteristics.

[1136] A "terminal" is an electronic device such as a computer or smartphone that allows a user to input and output information.

[1137] "Real-time collection" refers to the process of collecting data instantly, without delay.

[1138] "Adjusting the treatment plan" refers to reviewing the treatment content and schedule based on data during treatment and making changes as necessary.

[1139] "Feedback to a machine learning model" is the process of adding new data to a model and retraining it using that data.

[1140] "Daily health data" refers to data relating to the patient's daily lifestyle and physical condition, including, for example, heart rate, number of steps, and sleep data.

[1141] "Anomaly detection" is the process of finding abnormal conditions or unexpected data patterns.

[1142] "Sending a notification of an abnormality to the user" refers to the act of notifying the user of information about the detected abnormality.

[1143] "Feedback-based retraining" is the process of retraining a model based on user reactions and opinions to improve its accuracy.

[1144] The present invention relates to a system that collects and analyzes a patient's daily health data, genetic information, and clinical data, detects abnormalities using machine learning, and generates an optimal treatment plan. Specific embodiments are described below.

[1145] 1. System Overview

[1146] This system works by having the user (doctor or patient) input data via a device and send that data to a server. The server analyzes the received data, monitors the patient's health, and detects abnormalities and generates treatment plans as needed. The generated plans and alerts are sent to the device and provided to the user. Data is collected in real time during treatment and in daily life, and the system self-improves based on feedback.

[1147] 2. Hardware and Software

[1148] The following hardware and software are used to implement this system:

[1149] Smartphone: Used as a device for users to input data.

[1150] Server: A central system that analyzes data and trains machine learning models.

[1151] Healthcare app: An application that collects and records health data.

[1152] Machine learning libraries: Software for building machine learning models, such as TensorFlow and Scikit-learn.

[1153] 3. Data collection

[1154] Users use a healthcare app on their smartphone to collect daily health data (heart rate, number of steps, sleep data, etc.) and, if necessary, use a genetic analyzer to obtain genetic information and clinical data, which are then sent from the device to a server.

[1155] 4. Data Preprocessing and Analysis

[1156] The server normalizes the received health and genetic data into a standard format and performs data cleaning and pre-processing, removing incomplete data and outliers to make the data suitable for analysis.

[1157] 5. Machine Learning for Anomaly Detection and Treatment Plan Generation

[1158] The server uses the data to train a machine learning model using past treatment data. This model generates optimal treatment plans for each patient and has the ability to detect abnormal patterns. If an abnormality is detected, the server immediately sends a notification to the user's smartphone.

[1159] 6. Real-time data collection and feedback

[1160] Users collect real-time data about their health and treatment progress and provide feedback to the server, allowing the system to adjust and retrain treatment plans and improve the accuracy of the model.

[1161] Prompt Sentence Examples

[1162] "Analyze user heart rate data and generate a model to detect future anomalies. Create a system that detects and alerts users of sudden increases or decreases in heart rate early."

[1163] As a result, the present invention provides a system that comprehensively monitors the health condition of a user, enables early detection of abnormalities, and provides an optimal treatment plan.

[1164] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1165] Step 1:

[1166] Data collection

[1167] Subject: Device

[1168] The device collects the user's daily health data (heart rate, number of steps, sleep data, etc.) through a healthcare app. If necessary, the user can obtain genetic information and clinical data using a genetic analyzer and input it into the device. This collected data is centralized and sent to a server. The input is health data, genetic information, and clinical data, and the output is the integrated data sent to the server.

[1169] Step 2:

[1170] Data preprocessing and normalization

[1171] Subject: Server

[1172] The server normalizes the received health and genetic data into a standard format. During this process, incomplete data is filled in and outliers are cleaned. The input is raw data, and the output is clean data that has been converted into a form suitable for analysis.

[1173] Step 3:

[1174] Training a machine learning model

[1175] Subject: Server

[1176] The server trains a machine learning model based on the standardized and preprocessed data. The model uses historical treatment data to learn patterns and correlations. The input is the clean data and historical treatment data, and the output is the trained machine learning model.

[1177] Step 4:

[1178] Anomaly detection and treatment plan generation

[1179] Subject: Server

[1180] The server uses a trained machine learning model to detect abnormal patterns in the collected data and generate optimal treatment plans as needed. The input is the user's latest health and genetic information, and the output is the detected abnormal data and the generated treatment plan.

[1181] Step 5:

[1182] Notifying users and gathering feedback

[1183] Subject: Device

[1184] If an abnormality is detected, the terminal notifies the user of the notification sent from the server. It also presents the generated treatment plan to the user. The user then provides feedback, which is sent to the server via the terminal. The input is the notification and treatment plan from the server, and the output is the alert and feedback data for the user.

[1185] Step 6:

[1186] Real-time data collection and model retraining

[1187] Subject: Server

[1188] The server collects real-time data during treatment, analyzes the data, adjusts the treatment plan, and retrains the machine learning model based on the new data collected and user feedback. The inputs are real-time data during treatment and feedback data, and the outputs are an adjusted treatment plan and a retrained machine learning model.

[1189] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1190] The present invention combines a system that provides an optimal treatment plan based on a patient's genetic information and clinical data with an emotion engine that recognizes the user's emotions and enables adjustment of the treatment plan taking these emotions into consideration. The following describes in detail the embodiments of the present invention.

[1191] System Overview

[1192] This system operates by sending genetic information, clinical data, and emotional data entered by the user (doctor or patient) using a terminal to a server. The server analyzes this data and generates an optimal treatment plan. The generated treatment plan is then sent back to the terminal and used by the user for treatment. Data is collected in real time during and after treatment, allowing the treatment plan to be adjusted and retrained. The emotional engine also takes the user's emotions into account and provides a plan to maximize the effectiveness of treatment.

[1193] Program processing

[1194] Data collection

[1195] The user (doctor or patient) uses a terminal to input basic patient information (age, gender, medical history, etc.) into the electronic medical record system, which then organizes the basic data.

[1196] The user runs a sample taken from the patient through a genetic analyzer, and the resulting analysis data is sent to a server via the device.

[1197] A user uses an emotion recognition device to record his / her emotional state, and this data is input into a terminal or automatically collected through the emotion recognition device and transmitted to a server.

[1198] Data preprocessing and analysis

[1199] The server normalizes the received genetic and clinical data into a standard format and performs preprocessing, including removing incomplete data and noise.

[1200] The server analyzes the emotion data and identifies the user's emotional state, and the emotion engine operates based on the results of this identification.

[1201] Training a machine learning model

[1202] The server trains the machine learning model using historical treatment data, which includes genetic, clinical, and emotional data.

[1203] The server uses the trained model to predict the patient's individual treatment response.

[1204] Treatment plan generation and presentation

[1205] The server then uses the trained model to generate an optimal treatment plan based on the user's genetic, clinical, and emotional information. Specifically, for cancer treatment, it selects targeted therapeutic drugs that correspond to genetic mutations and sets the administration schedule.

[1206] The server sends the generated treatment plan to the terminal and provides it to the user, who then confirms the plan and adopts it as the treatment policy.

[1207] Specific examples

[1208] In the case of cancer treatment

[1209] 1. Data Collection

[1210] - Users take blood samples from cancer patients and perform genetic analysis.

[1211] - The device sends the analysis data to the server.

[1212] - Users use emotion recognition devices to record and transmit their own or their patients' emotional states.

[1213] 2. Data Preprocessing and Analysis

[1214] - The server normalizes the received genetic and clinical data into a standard format and organizes the data.

[1215] - The server analyzes the user's emotional state using an emotion engine and integrates the emotion data with other medical data.

[1216] 3. Training the machine learning model

[1217] - The server trains the machine learning model using historical cancer treatment data, including sentiment data.

[1218] The server uses the trained model to predict treatment response.

[1219] 4. Treatment plan generation and presentation

[1220] - The server generates an optimal treatment plan based on the analyzed data. Based on the emotional data, approaches to reduce the patient's mental stress are also considered.

[1221] - The server sends the treatment plan to the terminal and provides it to the user, who then carries out the treatment based on it.

[1222] 5. Monitoring and adjustment during and after treatment

[1223] - The device collects new data from the patient in real time during and after treatment and sends it to the server.

[1224] - The server analyzes the collected data and adjusts the treatment plan as needed. Emotional data is also collected and analyzed periodically, and adjustments are made to reduce the patient's mental burden.

[1225] The present invention not only provides individually optimized treatment, but also makes it possible to implement a comprehensive treatment plan that takes into account the psychological aspects of the patient.

[1226] The processing flow will be explained below.

[1227] Step 1:

[1228] Data collection

[1229] A user (doctor or patient) uses a terminal to input basic patient information (age, sex, medical history, etc.) into the electronic medical record system, which then transmits the basic patient data to the server.

[1230] The user takes blood or tissue samples from the patient and runs them through a genetic analyzer, and the genetic data output from the analyzer is sent to a server via a terminal.

[1231] The user uses an emotion recognition device (such as a wearable device or dedicated app) to record their own or their patient's emotional state, and then synchronizes this data with the device and sends it to a server.

[1232] Step 2:

[1233] Data Preprocessing

[1234] The server normalizes the received genetic and clinical data into a standard format for analysis, a process that unifies the data and makes it easier to analyze.

[1235] The server performs a cleansing process to remove incomplete data and noise, and also completes missing data if any.

[1236] The server analyzes the emotion data and uses an emotion engine to recognize the user's emotional state (e.g., stress level, happiness level).

[1237] Step 3:

[1238] Training a machine learning model

[1239] The server trains machine learning models based on past treatment data, including genetic information, clinical data, and user emotional data.

[1240] The server uses the trained model to build predictive models for each patient data type to help plan future treatment.

[1241] Step 4:

[1242] Treatment plan generation

[1243] The server then applies the trained machine learning model to generate an optimal treatment plan based on the user's genetic, clinical, and emotional data. For example, in the case of cancer treatment, it would select a targeted drug for a specific gene mutation and set a dosing schedule based on the doctor's instructions.

[1244] The server uses an emotion engine to reflect the user's emotional state in the treatment plan. For example, if the patient is in a high stress state, stress reduction measures and psychological support will be added to the plan.

[1245] Step 5:

[1246] Presentation of treatment plan

[1247] The server transmits the generated treatment plan to the terminal and provides it to the user.

[1248] The device displays the received treatment plan in an easy-to-understand format for the user (doctor) and presents it as a treatment guideline. The doctor will then begin appropriate treatment for the patient based on this plan.

[1249] Step 6:

[1250] Treatment initiation and monitoring

[1251] The user starts treatment for the patient based on the treatment plan received from the server.

[1252] The device collects and transmits real-time vital signs, emotional state, and drug response data of patients undergoing treatment, including blood pressure, heart rate, blood drug concentration, and emotional state, to a server.

[1253] Step 7:

[1254] Real-time treatment prediction and adjustment

[1255] The server uses machine learning models to analyze the data collected in real time and predict the effectiveness of treatment.

[1256] Based on the predictions and emotion data, the server adjusts the treatment plan, for example by changing the drug dosage to minimize the risk of side effects.

[1257] Step 8:

[1258] Feedback and Retraining

[1259] The user (doctor) enters the progress of treatment and new data into the terminal and sends it to the server.

[1260] The server uses the newly collected data to retrain the machine learning model, improving the accuracy of future treatment plans.

[1261] The present invention not only provides an individually optimized treatment plan, but also takes into account the patient's mental and emotional state, thereby maximizing the overall effectiveness of the treatment.

[1262] Example 2

[1263] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1264] Conventional medical systems have not been able to adequately provide personalized medical plans based on genetic information and clinical data, and real-time collection of treatment data and plan adjustments have been limited. Furthermore, no measures have been taken to provide treatment plans that take into account the emotional data of patients and doctors. This has made it difficult to reduce patients' mental stress, and there have been cases where the effectiveness of treatment has not been maximized.

[1265] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: a means for inputting biomedical information and health data of a patient; a means for normalizing the biomedical information and health data into a standard format and preprocessing the data; a means for training a machine learning model based on past therapy data; a means for generating an optimal medical plan for each patient using the machine learning model; a means for transmitting the medical plan to a communication device and providing it to a user; a means for collecting data during the patient's treatment in real time and adjusting the medical plan; a means for feeding back the collected new data to the machine learning model and retraining the model; and a means for recognizing emotional data of the user, analyzing the emotional data, and reflecting the emotional data in the medical plan. This improves the accuracy and effectiveness of the personalized medical plan, making it possible to maximize the effectiveness of treatment while reducing mental stress on the patient.

[1266] "Biomedical information" refers to various biological data necessary for medical diagnosis and treatment, such as a patient's genetic information, clinical data, and vital signs.

[1267] "Health data" refers to data that includes various information used to assess a patient's health status, such as their lifestyle, diet, exercise, and stress level.

[1268] "Normalizing to a standard format" means converting data provided in different formats and units into a unified format and unit, and making it organized.

[1269] "Preprocessing" refers to the process of preparing data, such as filling in missing values ​​and removing outliers, before conducting data analysis.

[1270] "Therapy data" refers to data that includes the results and details of past treatments, recording the effectiveness and side effects of the treatments.

[1271] "Training a machine learning model" means training the model using past data to improve its predictive accuracy.

[1272] A "personalized medical plan" is a plan that proposes the most appropriate treatment method based on each patient's genetic information and clinical data.

[1273] A "communication device" is an electronic device used by a patient or doctor, such as a computer, tablet, or smartphone.

[1274] "Real-time collection" means continuously monitoring and collecting data the moment it occurs.

[1275] "Retraining" means using new data collected to retrain an existing machine learning model to further improve its accuracy.

[1276] "Emotional data" refers to data that indicates the user's psychological and emotional state, measured based on heart rate, electrodermal activity, etc.

[1277] An "emotion engine" is a software algorithm that analyzes and recognizes a user's emotional data.

[1278] This invention is a system that provides an optimal medical plan based on a patient's biomedical information and health data, and adjusts the plan taking into account the user's emotional state. The system consists of a series of steps: data collection, data preprocessing and analysis, training of a machine learning model, generation and presentation of a treatment plan, and monitoring and adjustment during and after treatment.

[1279] Data collection

[1280] A user (doctor or patient) uses a terminal to input basic patient information (age, gender, medical history, etc.) into the electronic medical record system. The terminal then sends this information to a server in a standard format. The user also collects a biological sample from the patient and subjects it to a genetic analysis device. The analysis results data are also sent to the server via the terminal. Furthermore, the user uses an emotion recognition device to record their emotional state, and this data is entered into the terminal or automatically sent to the server.

[1281] Data preprocessing and analysis

[1282] The server uses Python's pandas library to normalize the received genetic and clinical data into a standard format, impute missing values, and remove outliers.The server then uses libraries such as TensorFlow and PyTorch to analyze the emotion data, identify the user's emotional state, and activate the emotion engine.

[1283] Training a machine learning model

[1284] The server trains a machine learning model using Scikit-learn and TensorFlow on past treatment data. The training data includes genetic information, clinical data, and emotional data. The server trains the model using cross-validation to prevent overfitting and generate a model with high predictive performance.

[1285] Treatment plan generation and presentation

[1286] The server uses the trained model to generate an optimal treatment plan based on the user's genetic information, clinical data, and emotional data. For example, it selects a targeted drug based on genetic mutations and sets its administration schedule. The generated treatment plan is then sent from the server to the device for the user to review.

[1287] Monitoring and adjustment during and after treatment

[1288] The device sends new data from the patient in real time during and after treatment to the server, which analyzes this data and adjusts the treatment plan accordingly. Emotional data is also collected and analyzed periodically, and actions to reduce the patient's mental stress are reflected in the plan.

[1289] Examples of specific examples and prompts

[1290] Example: Cancer treatment

[1291] 1. Data Collection

[1292] Users take blood samples from cancer patients and perform genetic analysis.

[1293] The terminal transmits this analysis data to the server.

[1294] The user uses the emotion recognition device to record their own or their patient's emotional state and transmit it to the server.

[1295] 2. Data Preprocessing and Analysis

[1296] The server normalizes the received genetic and clinical data into a standard format.

[1297] The server analyzes the user's emotional state using an emotion engine and integrates the emotion data.

[1298] 3. Training the machine learning model

[1299] The server trains the machine learning model using historical cancer treatment data, including emotional data.

[1300] The server uses the trained model to predict treatment response.

[1301] 4. Treatment plan generation and presentation

[1302] The server generates an optimal treatment plan and takes into account approaches to reduce stress for the patient based on emotional data.

[1303] The server transmits the treatment plan to the terminal and provides it to the user.

[1304] 5. Monitoring and adjustment during and after treatment

[1305] The terminal transmits new data in real time to the server during and after treatment.

[1306] The server analyzes the collected data and adjusts the treatment plan as needed.

[1307] Prompt Sentence Examples

[1308] "I would like to create an optimal treatment plan for a cancer patient that takes into account their genetic information, clinical data, and emotional state. Please generate a treatment proposal based on the following data."

[1309] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1310] Step 1: Data collection

[1311] Input: Patient basic information, genetic sample, emotional data

[1312] Output: Genetic information, clinical data, and emotional data in a standard format sent to a server

[1313] Step 1.1: Enter patient basic information

[1314] The user logs into the electronic medical record system on the terminal and enters the patient's basic information (age, gender, medical history, etc.), enters the required data in the input fields, and clicks the "Save" button to send it to the server.

[1315] Specific actions: The user uses the device's keyboard to enter information and clicks the save button with the mouse.

[1316] Step 1.2: Genetic sample analysis and submission

[1317] Input: Patient genetic sample

[1318] Output: Genetic information sent to the server

[1319] The user places the collected gene sample into the genetic analyzer and begins analysis. When the analysis is complete, the device generates a data file.

[1320] The terminal retrieves data files from the analysis device via USB or network connection and automatically uploads them to the server.

[1321] Specific operation: The user collects a genetic sample and inserts it into the analysis device. After analysis, the device sends the data to the server.

[1322] Step 1.3: Collect emotion data

[1323] Input: Emotion data from an emotion recognition device

[1324] Output: Emotion data sent to the server

[1325] The user uses the emotion recognition device to record their emotional state, and the data is transmitted via Bluetooth to the device and then from the device to the server.

[1326] Specific operation: The user wears the emotion recognition device and the data is automatically sent to the terminal.

[1327] Step 2: Data preprocessing and analysis

[1328] Input: Genetic information, clinical data, and emotional data in a standard format sent to the server

[1329] Output: Normalized and parsed data

[1330] Step 2.1: Normalize the data

[1331] The server converts the received genetic and clinical data into a data frame using Python's pandas library, normalizes it to a standard format, imputes missing values, and removes outliers.

[1332] What happens: The server runs data processing steps using pandas to generate a clean dataset.

[1333] Step 2.2: Analyzing and integrating sentiment data

[1334] The server analyzes the received emotion data using TensorFlow, PyTorch, etc. to identify the user's emotional state, which is then integrated with other biomedical information.

[1335] Specific operation: The server receives the emotion data and runs an analysis algorithm to classify the emotional state. The results are integrated with the biomedical data.

[1336] Step 3: Train the machine learning model

[1337] Input: Normalized and parsed data

[1338] Output: A trained machine learning model

[1339] Step 3.1: Train the model using historical data

[1340] The server uses historical therapy data to train machine learning models using Scikit-learn and TensorFlow, including genetic, clinical, and emotional data.

[1341] What happens: The server runs the script using the training data to optimize the model parameters.

[1342] Step 3.2: Predicting with the trained model

[1343] The server uses the trained model to predict the patient's individual treatment response.

[1344] Specific operation: The server inputs new patient data into the model and generates predictions, including predictions of treatment efficacy and side effects.

[1345] Step 4: Generate and present the treatment plan

[1346] Input: Trained machine learning model, patient biomedical information, and emotion data

[1347] Output: Generated medical plan

[1348] Step 4.1: Generate an optimal treatment plan

[1349] The server uses the trained model to generate an optimal treatment plan based on the user's genetic, clinical, and emotional information. In the case of cancer treatment, it selects targeted therapeutic drugs and sets administration schedules based on genetic mutations.

[1350] Specific operations: The server inputs the data into the model and calculates the optimal treatment plan.

[1351] Step 4.2: Present the treatment plan

[1352] The server then sends the generated treatment plan to the communication device, where the user can check the treatment plan on their device and share the necessary information within the hospital.

[1353] Specific operations: The server generates a treatment plan and sends it to the terminal. The user checks the plan on the terminal and performs the treatment.

[1354] Step 5: Monitoring and adjusting during and after treatment

[1355] Input: New patient data collected in real time

[1356] Output: Adjusted treatment plan

[1357] Step 5.1: Collect real-time data

[1358] The device transmits new patient data (genetic information, clinical data, emotional data) collected during and after treatment to the server in real time.

[1359] Specific operation: The device acquires new data through sensors or manual input and sends it to the server over the network.

[1360] Step 5.2: Analyze data and adjust treatment plan

[1361] The server analyzes the new data and reassess whether the existing treatment plan is optimal, adjusts it if necessary, and suggests actions to reduce the patient's mental stress based on emotional data.

[1362] Specific operations: The server analyzes the new data and updates the treatment plan. The updated plan is sent to the device, and the user modifies the treatment.

[1363] (Application example 2)

[1364] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1365] Conventional autonomous driving systems do not select driving routes that take into account the emotional state of passengers, which means they are unable to reduce passenger stress or provide a comfortable driving experience.In addition, treatment plans based on patients' genetic information and clinical data do not take into account their emotional state, making it difficult to maximize treatment effectiveness.

[1366] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1367] In this invention, the server includes: a means for inputting a patient's genetic information and clinical data; a means for normalizing and preprocessing the genetic information and clinical data into a standard format; a means for training a machine learning model based on past treatment data; a means for generating an optimal treatment plan for each patient using the machine learning model; a means for transmitting the treatment plan to a terminal and providing it to a user; a means for collecting data during the patient's treatment in real time and adjusting the treatment plan; a means for feeding back the collected new data to the machine learning model and retraining the model; a means for collecting passengers' emotional states and selecting a route based on the collected data; and a means for transmitting emotional data and location information to the server and optimizing the driving route. This enables the selection of a driving route taking passengers' emotional states into consideration, thereby reducing stress and providing a comfortable driving experience. Furthermore, an optimal treatment plan taking individual patients' emotional states into consideration is provided, maximizing the effectiveness of treatment.

[1368] "Patient genetic information" refers to data on genetic structure and mutations obtained by subjecting a sample collected from a patient to a genetic analysis device.

[1369] "Clinical data" refers to any information collected in a medical setting, such as a patient's diagnosis, treatment history, or vital signs.

[1370] "Means for inputting" refers to means for transmitting data to the server using an electronic medical record system or an input device.

[1371] "Normalization to a standard format" is a process of converting data of different formats into a unified format in order to maintain data consistency.

[1372] "Preprocessing means" refers to means for removing noise and imperfections from data and preparing it in an analyzable format.

[1373] A "machine learning model" is an algorithm that is trained to make predictions or classifications based on collected data.

[1374] The "means for generating a treatment plan" is a means for using a machine learning model to determine the optimal treatment method and schedule based on individual patient data.

[1375] The "means for transmitting to the terminal and providing to the user" refers to a means for transmitting the generated treatment plan to the device of the user (doctor or patient) so that it can be viewed and used.

[1376] "Means for collecting and adjusting in real time" refers to means for instantly transmitting newly acquired data during treatment to a server and dynamically changing the treatment plan.

[1377] "Means for providing feedback to a machine learning model and re-learning" refers to means for inputting newly collected data into a machine learning model and re-training it to improve the accuracy of the model.

[1378] "Passenger emotional state" refers to the passenger's psychological and emotional state, such as stress, joy, anxiety, etc.

[1379] The "route selection means" is a means for determining the optimal driving route based on the emotional state of the passenger.

[1380] "Emotion data and location information" refers to data relating to the psychological state of passengers and data relating to the current location of passengers and vehicles.

[1381] The "means for optimizing a driving route" is a means for automatically selecting the most suitable driving route based on emotion data and location information.

[1382] The present invention provides a driving route planning system that takes into account the emotional state of passengers in an autonomous vehicle, and incorporates emotional data as an additional element in a system that provides optimal treatment plans based on the patient's genetic information and clinical data. Specific embodiments are described below.

[1383] System Overview

[1384] The system works by collecting emotional and location data through smart devices (e.g., smartphones, head-mounted displays, etc.) and sending it to a server. The server then analyzes this data and generates an optimal driving route. The system also provides a treatment plan based on the patient's genetic and clinical data, and adjusts the treatment plan based on real-time analysis of data collected during and after treatment.

[1385] Program processing

[1386] Emotion data collection and transmission

[1387] Users (passengers) record their emotional state in real time through their smart devices. Emotion recognition technology is used to analyze emotional states such as stress, joy, and anxiety, and the data is sent to a server. Libraries such as EmotionRecognizer are used for this collection process.

[1388] Data Analysis and Optimization

[1389] The server analyzes the submitted emotion data and location information. It normalizes and preprocesses the data into a standard format, then uses EmotionRecognizer to determine the user's emotional state. It then generates an optimal driving route based on this data using a machine learning model trained on past data.

[1390] Route selection and provision

[1391] The generated driving route is sent to the terminal and provided to the user. The user operates the autonomous vehicle based on this route. Data related to the treatment plan is also sent to the user's terminal and used for treatment.

[1392] Real-time data collection and reconciliation

[1393] Data on the patient's treatment and passengers' emotional state is collected in real time and sent to a server, which then dynamically adjusts the treatment plan and driving route based on this data. Newly collected data is fed back into the machine learning model, allowing it to be retrained.

[1394] Specific examples

[1395] If a passenger in an autonomous vehicle is stuck in traffic, the system will choose a gentler route if data indicates the passenger's emotional state is stressed.

[1396] During treatment, the treatment plan generated based on the patient's genetic information also takes into account the patient's emotional data, and adjustments are made to the plan to reduce the mental burden.

[1397] Prompt Sentence Examples

[1398] "If the passenger's emotional state is relaxed, suggest the optimal driving route for the autonomous vehicle. If the passenger is stressed, suggest a gentler route that avoids traffic jams."

[1399] Thus, the present invention allows for the optimization of driving routes based on the emotional state of passengers and the provision of treatment plans that take into account the emotional state of patients.

[1400] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1401] Step 1:

[1402] Emotional Data Collection

[1403] Users (passengers) record their emotional state in real time through smart devices (e.g., smartphones, head-mounted displays). Emotion recognition technology is used to analyze emotional states such as stress, joy, and anxiety. Specifically, image data collected from a camera is analyzed using libraries such as EmotionRecognizer to extract emotional data. The input is camera image data, and the output is emotional state data.

[1404] Step 2:

[1405] Emotion data transmission

[1406] The device sends the collected emotion data to the server in JSON format using the HTTP protocol. Specifically, the device converts the emotion data into an appropriate format and sends it to the server's receiving endpoint. The input is emotion data (in JSON format), and the output is the completion of data transmission to the server.

[1407] Step 3:

[1408] Data analysis and standard formatting

[1409] The server receives the emotion data and normalizes it into a standard format. It removes inconsistencies and noise from the data and makes it analyzable. The input is emotion data (JSON format), and the output is emotion data in a standard format.

[1410] Step 4:

[1411] Training a machine learning model

[1412] The server trains a machine learning model based on past emotion data and driving route information. Specifically, it uses the collected dataset to train the model using libraries such as TensorFlow and scikit-learn. The input is past emotion data and driving route data, and the output is the trained model.

[1413] Step 5:

[1414] Route Selection

[1415] The server uses a trained machine learning model to generate an optimal driving route based on the received emotion data. Specifically, the model inputs current emotion data and location information and predicts the optimal route. The input is the current emotion data and location information, and the output is the optimal driving route.

[1416] Step 6:

[1417] Providing driving directions

[1418] The server sends the generated driving route to the device. Specifically, it sends the route information using the HTTP protocol and displays it on the smartphone's navigation app. The input is the optimal driving route, and the output is the route information displayed on the device.

[1419] Step 7:

[1420] Real-time data collection and treatment plan adjustment

[1421] The terminal collects real-time patient data and passenger emotional state data during treatment and sends it to the server, which then dynamically adjusts the treatment plan and driving route based on this data. The input is the real-time collected data, and the output is the adjusted treatment plan and driving route.

[1422] Step 8:

[1423] Retraining a machine learning model

[1424] The server feeds newly collected data back into the machine learning model for re-learning. Specifically, new data is input into the model to improve its accuracy. The input is new emotional data and location information, and the output is the re-learned model.

[1425] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1426] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1427] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1428] [Fourth embodiment]

[1429] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1430] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1431] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1432] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1433] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1434] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1435] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1436] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1437] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1438] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1439] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1440] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1441] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1442] The present invention relates to a system for analyzing genetic information and clinical data of a patient and generating an optimal treatment plan using machine learning. The embodiments for carrying out the present invention will be described in the following means.

[1443] System Overview

[1444] In this system, the user (doctor or patient) enters genetic information and clinical data via a terminal and sends it to a server, which then generates an optimal treatment plan based on that data. The generated treatment plan is then sent to the terminal and used by the user for treatment. During treatment, data is collected in real time, and the treatment plan is adjusted and re-learned.

[1445] Program processing

[1446] Data collection

[1447] The user uses the terminal to input basic patient information (age, sex, medical history, etc.) into the electronic medical record system.

[1448] The user runs a sample taken from the patient through a genetic analyzer, and the genetic information output from the analyzer is sent to a server via the terminal.

[1449] Data Analysis and Learning

[1450] The server normalizes the received genetic and clinical data into a standard format and performs data preprocessing, imputing or cleaning incomplete or inappropriate data.

[1451] The server trains a machine learning model based on past treatment data, which is capable of detecting patterns in patient data and generating optimal treatment plans.

[1452] Treatment plan generation and presentation

[1453] The server uses machine learning models to generate optimal treatment plans for each patient. Specifically, in the case of cancer treatment, it selects targeted therapeutic drugs that correspond to the patient's genetic mutations and sets the administration schedule.

[1454] The server sends the generated treatment plan to the terminal and provides it to the user, who then begins treatment based on this plan.

[1455] Specific examples

[1456] In the case of cancer treatment

[1457] 1. Data Collection

[1458] - Users take blood samples from cancer patients and perform genetic analysis.

[1459] - The device sends the analysis data to the server.

[1460] 2. Data analysis and learning

[1461] - The server analyzes the genetic data of cancer patients and identifies specific genetic mutations.

[1462] - The server updates the machine learning model using data from similar past cases.

[1463] 3. Treatment plan generation

[1464] - The server uses machine learning models to generate targeted therapeutic drugs and their administration schedules that correspond to specific gene mutations.

[1465] - The server sends the generated treatment plan to the terminal and presents the treatment policy to the user.

[1466] 4. Data collection and prediction during treatment

[1467] - The device transmits the patient's vital signs and drug response data to a server in real time during treatment.

[1468] - The server analyzes the collected data, predicts treatment effectiveness, and adjusts the treatment plan as needed.

[1469] 5. Feedback and Retraining

[1470] - The user enters the progress of treatment and new data into the terminal and sends it to the server.

[1471] - The server retrains the machine learning model with new data to improve the accuracy of the next treatment plan.

[1472] In this way, the present invention can provide effective and safe treatment for patients by automatically generating individually optimized treatment plans and adjusting them in real time during treatment.

[1473] The processing flow will be explained below.

[1474] Step 1:

[1475] Data collection

[1476] The user (doctor or patient) inputs basic information about the patient (age, gender, medical history, etc.) into the terminal, which then organizes this information and sends it to the server.

[1477] The user takes blood or tissue samples from the patient and subjects them to a genetic analysis device, which then sends the genetic data output from the device to a server via a terminal.

[1478] Step 2:

[1479] Data Preprocessing

[1480] The server normalizes the received genetic and clinical data into a standard format, harmonizing different data formats.

[1481] The server performs a cleansing process, removing incomplete data and noise, and also complements the data as needed.

[1482] Step 3:

[1483] Training a machine learning model

[1484] The server trains the machine learning model using data from past treatments and similar cases, improving its pattern recognition capabilities.

[1485] The server uses normalized patient data as input to build predictive models for specific diseases and treatment responses.

[1486] Step 4:

[1487] Treatment plan generation

[1488] The server uses the trained machine learning model to generate an optimal treatment plan for each patient, such as selecting targeted drugs for specific gene mutations in cancer treatment.

[1489] The server creates a treatment plan that includes the treatment method, drugs to be used, and administration schedule.

[1490] Step 5:

[1491] Presentation of treatment plan

[1492] The server sends the generated treatment plan to the terminal.

[1493] The terminal displays the treatment plan to the user (doctor) in an easy-to-understand format and provides it as a treatment guideline.

[1494] Step 6:

[1495] Treatment initiation and monitoring

[1496] The user (doctor) starts treatment for the patient based on the treatment plan received from the server.

[1497] The device transmits real-time vital signs and drug response data of patients undergoing treatment to a server, including physiological data such as blood pressure, heart rate, and blood drug concentrations.

[1498] Step 7:

[1499] Real-time treatment prediction and adjustment

[1500] The server uses machine learning models to analyze real-time treatment data and predict treatment outcomes.

[1501] The server adjusts dosage and treatment schedule accordingly based on the predicted results.

[1502] Step 8:

[1503] Feedback and Retraining

[1504] The user (doctor) inputs the progress of treatment and new data into the terminal as needed and sends it to the server.

[1505] The server retrains the machine learning model using newly collected data, thereby improving the accuracy of future treatment plans.

[1506] This allows the system to continuously learn and provide optimal treatment plans for each patient.

[1507] Example 1

[1508] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1509] With conventional medical systems, it has been difficult to quickly generate optimal treatment plans that effectively utilize a patient's individual genetic information and clinical data. It has also been difficult to collect data during treatment in real time and immediately adjust the treatment plan based on that data. This has led to issues such as not being able to maximize the effectiveness and safety of the treatment provided to patients.

[1510] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1511] In this invention, the server includes means for inputting a patient's genetic information and clinical data, means for normalizing and preprocessing the genetic information and clinical data into a standard format, means for training a machine learning model based on past treatment data, means for generating an optimal treatment plan for each patient using the machine learning model, means for transmitting the treatment plan to a terminal and providing it to a user, means for collecting data during the patient's treatment in real time and adjusting the treatment plan, means for feeding back the collected new data to the machine learning model and retraining the model, means for acquiring and analyzing vital signs and drug response data in real time, means for transmitting data to the server via Wi-Fi or Bluetooth, means for updating the machine learning model based on case data, and means for automatically generating an individualized treatment plan for the patient and notifying the terminal. This makes it possible to quickly and effectively provide an optimized treatment plan for each patient and adjust the plan in real time based on treatment data.

[1512] "Patient genetic information" refers to the sequence data of a patient's DNA or RNA, and is biological information used to diagnose disease and develop treatment plans.

[1513] "Clinical data" refers to all information related to the provision of medical services, such as a patient's treatment history, diagnosis results, medication history, and vital signs.

[1514] "Normalizing to a standard format" refers to the process of converting data entered in different formats into a uniform format to make it consistent.

[1515] "Preprocessing" refers to the process of organizing and processing raw data into an analyzable form, including, for example, imputing missing values ​​and cleaning the data.

[1516] "Training a machine learning model" refers to the process of using existing data to teach an algorithm patterns that give it the ability to make predictions or classifications on new data.

[1517] "Generating optimal treatment plans" refers to using machine learning models to develop individualized treatment methods and drug administration schedules for each patient.

[1518] "Real-time collection" refers to the immediate acquisition and recording of data during treatment without delay.

[1519] "Retraining" refers to adding new data to update the learning model and improve its accuracy and effectiveness.

[1520] "Vital signs" are data that indicate the basic vital signs of a patient's body, and generally include heart rate, respiratory rate, body temperature, blood pressure, etc.

[1521] "Drug response data" refers to data that shows how a patient's body reacts to a drug after taking it, including, for example, the drug's effects and side effects.

[1522] "Transmitting data using Wi-Fi or Bluetooth" refers to transferring data between devices using wireless communication technologies.

[1523] "Case data" refers to data that includes past patient treatment history and diagnostic information, and is used to create treatment plans for new patients.

[1524] An "individualized treatment plan" refers to formulating the optimal treatment method and administration schedule for a specific patient based on each patient's genetic information and clinical data.

[1525] The present invention relates to a system for analyzing genetic information and clinical data of a patient and generating an optimal treatment plan using machine learning. An embodiment of the present invention will be described in detail below.

[1526] System configuration

[1527] This system sends genetic information and clinical data entered by the user via a terminal to a server, which then generates an optimal treatment plan based on that data.The system consists of the following main components.

[1528] 1. Terminal

[1529] Hardware: Personal computers, tablets, smartphones, etc.

[1530] Software: Electronic medical record systems (e.g., EPIC, Cerner), data entry interfaces, and data submission applications.

[1531] 2. Server

[1532] Hardware: High performance computers (e.g. server racks).

[1533] Software: Database management systems, data preprocessing programs (e.g., Python scripts, Pandas library), machine learning platforms (e.g., TensorFlow, PyTorch), web frameworks (e.g., Flask, Django).

[1534] 3. Genetic analysis equipment

[1535] Hardware: Genetic analysis equipment (e.g., Illumina).

[1536] Software: Genetic data analysis program.

[1537] System Operation

[1538] 1. Data Collection

[1539] Using a terminal, the user inputs basic patient information (age, gender, medical history, etc.) into the electronic medical record system. In addition, a sample taken from the patient is put through a genetic analyzer, and the obtained genetic information is sent to a server via the terminal.

[1540] 2. Data analysis and learning

[1541] The server normalizes the received genetic and clinical data into a standard format and performs data preprocessing. Incomplete or inappropriate data is cleaned and imputed. Using historical treatment data, the server trains a machine learning model. This model detects patterns in the patient data and generates an optimal treatment plan.

[1542] 3. Treatment plan generation and presentation

[1543] The server uses machine learning models to generate optimal treatment plans for each patient. For example, in the case of cancer treatment, it selects targeted therapeutic drugs that correspond to the patient's genetic mutations and sets an administration schedule. The generated treatment plan is then sent to the device and provided to the user, who then begins treatment based on this plan.

[1544] 4. Data collection and prediction during treatment

[1545] During treatment, the device transmits the patient's vital signs and drug response data in real time to a server, which analyzes the collected data, predicts treatment effectiveness, and adjusts the treatment plan as needed.

[1546] 5. Feedback and Retraining

[1547] The user inputs treatment progress and new data into the device and sends it to the server, which then uses the new data to retrain the machine learning model and improve the accuracy of the next treatment plan.

[1548] Specific examples

[1549] In the case of cancer treatment

[1550] 1. Data Collection

[1551] Users take blood samples from cancer patients and perform genetic analysis.

[1552] The terminal transmits the analysis data to the server.

[1553] 2. Data analysis and learning

[1554] The server analyzes the genetic data of cancer patients and identifies specific genetic mutations.

[1555] The server uses data from similar past cases to update the machine learning model.

[1556] 3. Treatment plan generation

[1557] The server uses machine learning models to generate targeted therapeutic drugs and their administration schedules that correspond to specific gene mutations.

[1558] The server sends the generated treatment plan to the terminal and presents the treatment policy to the user.

[1559] 4. Data collection and prediction during treatment

[1560] The device transmits the patient's vital signs and drug response data to a server in real time during treatment.

[1561] The server analyzes the collected data, predicts treatment effectiveness, and adjusts the treatment plan as needed.

[1562] 5. Feedback and Retraining

[1563] The user enters the progress of treatment and new data into the terminal and sends it to the server.

[1564] The server retrains the machine learning model using new data to improve the accuracy of the next treatment plan.

[1565] Prompt Sentence Examples

[1566] "Please explain the system that analyzes genetic information and clinical data of cancer patients and generates individually optimized treatment plans using machine learning. Please describe the specific data collection methods, analysis and processing, generation of treatment plans, and real-time data collection and re-learning during treatment."

[1567] In this way, the present invention can provide effective and safe treatment for patients by automatically generating individually optimized treatment plans and adjusting them in real time during treatment.

[1568] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1569] Step 1: Data collection

[1570] The user uses a terminal to input basic patient information (age, gender, medical history, etc.) into the electronic medical record system. The input basic information is saved in the database, allowing the system to obtain basic patient information to be used in subsequent processing.

[1571] The user runs a sample taken from a patient through a genetic analyzer and transfers the resulting genetic information to a terminal. The terminal then sends this genetic information to a server, where it is stored in a database.

[1572] Step 2: Data Preprocessing

[1573] The server normalizes the received genetic and clinical data into a standard format, such as JSON, to maintain consistency in the data format.

[1574] The server preprocesses the normalized data, including imputing missing data and cleaning outliers. For example, the server cleans the data using the Pandas library and imputes missing values ​​with the mean using a Python script. The processed data is used as a clean dataset.

[1575] Step 3: Train the machine learning model

[1576] The server uses the cleaned data to train a machine learning model, which trains the algorithm based on past treatment data. For example, a deep learning model is built using TensorFlow or PyTorch and fitted to the dataset.

[1577] Using the cleaned data as input, we obtain an optimal predictive model as output, which is used to generate a treatment plan for each patient.

[1578] Step 4: Generate a treatment plan

[1579] The server uses the trained machine learning model to generate a treatment plan for each patient. For example, in the case of cancer treatment, it calculates the appropriate treatment, medication, and administration schedule based on the patient's genetic information.

[1580] Based on the input data of each patient's genetic information and clinical data, an optimized treatment plan is obtained as output, including specific treatment procedures and schedules.

[1581] Step 5: Provide a treatment plan

[1582] The server sends the generated treatment plan to the terminal, which receives the plan and presents it to the user, who can then review the plan and begin optimal treatment for the patient.

[1583] Based on the treatment plan as input data, presentation data as output is generated and sent to the terminal. This presentation data includes specific treatment implementation procedures.

[1584] Step 6: Real-time data collection and prediction

[1585] The device transmits the patient's vital signs and drug response data to a server in real time via Bluetooth or Wi-Fi during treatment, for example, through a smartwatch or medical monitoring device.

[1586] The server analyzes the collected data and predicts the effectiveness of treatment, for example, by using Apache Kafka or Flink for real-time analysis to determine whether treatment is progressing appropriately.

[1587] Real-time data is used as input data, and analytical results are output, which are used to adjust the treatment plan.

[1588] Step 7: Feedback and Retraining

[1589] The user inputs treatment progress and new data into the terminal and sends it to the server, for example, entering details of regular checkups or new test results.

[1590] The server retrains the machine learning model using new data, improving the accuracy of the next treatment plan. For example, it combines past and new data to update the model and make more accurate predictions.

[1591] New clinical data and treatment effects are used as inputs to obtain updated prediction models as outputs, which can be reused for subsequent treatment plan generation.

[1592] This series of processing steps enables the system to provide individually optimized treatment plans and monitor and adjust treatment progress in real time.

[1593] (Application example 1)

[1594] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1595] In the current healthcare system, providing optimal treatment plans for individual patients requires the collection and analysis of large amounts of data, a process that is time-consuming and inefficient. Furthermore, there is a lack of adequate management of patients' daily health data and early detection of abnormalities. Furthermore, there is a lack of a mechanism for responding quickly when abnormalities are detected, which could result in a decline in the quality of patient healthcare.

[1596] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1597] In this invention, the server includes means for inputting a patient's genetic information and clinical data, means for normalizing and preprocessing the genetic information and clinical data into a standard format, means for training a machine learning model based on past treatment data, means for generating an optimal treatment plan for each patient using the machine learning model, means for transmitting the treatment plan to a terminal and providing it to a user, means for collecting data during the patient's treatment in real time and adjusting the treatment plan, means for feeding back the collected new data to the machine learning model and retraining the model, means for collecting daily health data and detecting abnormalities, means for notifying the user of the abnormality, and means for retraining the machine learning model based on feedback from the user. This enables the server to quickly and efficiently provide an optimal treatment plan for each patient, and enables early detection and prompt response to abnormalities.

[1598] "Patient genetic information" refers to data about a patient's genes, such as their DNA sequence, including information about their disease and genetic characteristics.

[1599] "Clinical data" is a general term for clinical data such as a patient's age, sex, medical history, diagnostic information, and treatment history.

[1600] "Normalization to a standard format" is a technique for converting collected data into a unified format that makes the data easier to analyze.

[1601] "Preprocessing" refers to the process of data cleaning and transformation to convert raw data into an analyzable format.

[1602] "Past treatment data" refers to historical data such as treatment information and progression of disease status for each patient that has been accumulated to date.

[1603] A "machine learning model" is an algorithm that learns patterns and correlations based on large amounts of data and makes predictions and judgments.

[1604] An "optimal treatment plan" is the most effective treatment or treatment schedule designed based on a patient's specific condition and characteristics.

[1605] A "terminal" is an electronic device such as a computer or smartphone that allows a user to input and output information.

[1606] "Real-time collection" refers to the process of collecting data instantly, without delay.

[1607] "Adjusting the treatment plan" refers to reviewing the treatment content and schedule based on data during treatment and making changes as necessary.

[1608] "Feedback to a machine learning model" is the process of adding new data to a model and retraining it using that data.

[1609] "Daily health data" refers to data relating to the patient's daily lifestyle and physical condition, including, for example, heart rate, number of steps, and sleep data.

[1610] "Anomaly detection" is the process of finding abnormal conditions or unexpected data patterns.

[1611] "Sending a notification of an abnormality to the user" refers to the act of notifying the user of information about the detected abnormality.

[1612] "Feedback-based retraining" is the process of retraining a model based on user reactions and opinions to improve its accuracy.

[1613] The present invention relates to a system that collects and analyzes a patient's daily health data, genetic information, and clinical data, detects abnormalities using machine learning, and generates an optimal treatment plan. Specific embodiments are described below.

[1614] 1. System Overview

[1615] This system works by having the user (doctor or patient) input data via a device and send that data to a server. The server analyzes the received data, monitors the patient's health, and detects abnormalities and generates treatment plans as needed. The generated plans and alerts are sent to the device and provided to the user. Data is collected in real time during treatment and in daily life, and the system self-improves based on feedback.

[1616] 2. Hardware and Software

[1617] The following hardware and software are used to implement this system:

[1618] Smartphone: Used as a device for users to input data.

[1619] Server: A central system that analyzes data and trains machine learning models.

[1620] Healthcare app: An application that collects and records health data.

[1621] Machine learning libraries: Software for building machine learning models, such as TensorFlow and Scikit-learn.

[1622] 3. Data collection

[1623] Users use a healthcare app on their smartphone to collect daily health data (heart rate, number of steps, sleep data, etc.) and, if necessary, use a genetic analyzer to obtain genetic information and clinical data, which are then sent from the device to a server.

[1624] 4. Data Preprocessing and Analysis

[1625] The server normalizes the received health and genetic data into a standard format and performs data cleaning and pre-processing, removing incomplete data and outliers to make the data suitable for analysis.

[1626] 5. Machine Learning for Anomaly Detection and Treatment Plan Generation

[1627] The server uses the data to train a machine learning model using past treatment data. This model generates optimal treatment plans for each patient and has the ability to detect abnormal patterns. If an abnormality is detected, the server immediately sends a notification to the user's smartphone.

[1628] 6. Real-time data collection and feedback

[1629] Users collect real-time data about their health and treatment progress and provide feedback to the server, allowing the system to adjust and retrain treatment plans and improve the accuracy of the model.

[1630] Prompt Sentence Examples

[1631] "Analyze user heart rate data and generate a model to detect future anomalies. Create a system that detects and alerts users of sudden increases or decreases in heart rate early."

[1632] As a result, the present invention provides a system that comprehensively monitors the health condition of a user, enables early detection of abnormalities, and provides an optimal treatment plan.

[1633] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1634] Step 1:

[1635] Data collection

[1636] Subject: Device

[1637] The device collects the user's daily health data (heart rate, number of steps, sleep data, etc.) through a healthcare app. If necessary, the user can obtain genetic information and clinical data using a genetic analyzer and input it into the device. This collected data is centralized and sent to a server. The input is health data, genetic information, and clinical data, and the output is the integrated data sent to the server.

[1638] Step 2:

[1639] Data preprocessing and normalization

[1640] Subject: Server

[1641] The server normalizes the received health and genetic data into a standard format. During this process, incomplete data is filled in and outliers are cleaned. The input is raw data, and the output is clean data that has been converted into a form suitable for analysis.

[1642] Step 3:

[1643] Training a machine learning model

[1644] Subject: Server

[1645] The server trains a machine learning model based on the standardized and preprocessed data. The model uses historical treatment data to learn patterns and correlations. The input is the clean data and historical treatment data, and the output is the trained machine learning model.

[1646] Step 4:

[1647] Anomaly detection and treatment plan generation

[1648] Subject: Server

[1649] The server uses a trained machine learning model to detect abnormal patterns in the collected data and generate optimal treatment plans as needed. The input is the user's latest health and genetic information, and the output is the detected abnormal data and the generated treatment plan.

[1650] Step 5:

[1651] Notifying users and gathering feedback

[1652] Subject: Device

[1653] If an abnormality is detected, the terminal notifies the user of the notification sent from the server. It also presents the generated treatment plan to the user. The user then provides feedback, which is sent to the server via the terminal. The input is the notification and treatment plan from the server, and the output is the alert and feedback data for the user.

[1654] Step 6:

[1655] Real-time data collection and model retraining

[1656] Subject: Server

[1657] The server collects real-time data during treatment, analyzes the data, adjusts the treatment plan, and retrains the machine learning model based on the new data collected and user feedback. The inputs are real-time data during treatment and feedback data, and the outputs are an adjusted treatment plan and a retrained machine learning model.

[1658] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1659] The present invention combines a system that provides an optimal treatment plan based on a patient's genetic information and clinical data with an emotion engine that recognizes the user's emotions and enables adjustment of the treatment plan taking these emotions into consideration. The following describes in detail the embodiments of the present invention.

[1660] System Overview

[1661] This system operates by sending genetic information, clinical data, and emotional data entered by the user (doctor or patient) using a terminal to a server. The server analyzes this data and generates an optimal treatment plan. The generated treatment plan is then sent back to the terminal and used by the user for treatment. Data is collected in real time during and after treatment, allowing the treatment plan to be adjusted and retrained. The emotional engine also takes the user's emotions into account and provides a plan to maximize the effectiveness of treatment.

[1662] Program processing

[1663] Data collection

[1664] The user (doctor or patient) uses a terminal to input basic patient information (age, gender, medical history, etc.) into the electronic medical record system, which then organizes the basic data.

[1665] The user runs a sample taken from the patient through a genetic analyzer, and the resulting analysis data is sent to a server via the device.

[1666] A user uses an emotion recognition device to record his / her emotional state, and this data is input into a terminal or automatically collected through the emotion recognition device and transmitted to a server.

[1667] Data preprocessing and analysis

[1668] The server normalizes the received genetic and clinical data into a standard format and performs preprocessing, including removing incomplete data and noise.

[1669] The server analyzes the emotion data and identifies the user's emotional state, and the emotion engine operates based on the results of this identification.

[1670] Training a machine learning model

[1671] The server trains the machine learning model using historical treatment data, which includes genetic, clinical, and emotional data.

[1672] The server uses the trained model to predict the patient's individual treatment response.

[1673] Treatment plan generation and presentation

[1674] The server then uses the trained model to generate an optimal treatment plan based on the user's genetic, clinical, and emotional information. Specifically, for cancer treatment, it selects targeted therapeutic drugs that correspond to genetic mutations and sets the administration schedule.

[1675] The server sends the generated treatment plan to the terminal and provides it to the user, who then confirms the plan and adopts it as the treatment policy.

[1676] Specific examples

[1677] In the case of cancer treatment

[1678] 1. Data Collection

[1679] - Users take blood samples from cancer patients and perform genetic analysis.

[1680] - The device sends the analysis data to the server.

[1681] - Users use emotion recognition devices to record and transmit their own or their patients' emotional states.

[1682] 2. Data Preprocessing and Analysis

[1683] - The server normalizes the received genetic and clinical data into a standard format and organizes the data.

[1684] - The server analyzes the user's emotional state using an emotion engine and integrates the emotion data with other medical data.

[1685] 3. Training the machine learning model

[1686] - The server trains the machine learning model using historical cancer treatment data, including sentiment data.

[1687] The server uses the trained model to predict treatment response.

[1688] 4. Treatment plan generation and presentation

[1689] - The server generates an optimal treatment plan based on the analyzed data. Based on the emotional data, approaches to reduce the patient's mental stress are also considered.

[1690] - The server sends the treatment plan to the terminal and provides it to the user, who then carries out the treatment based on it.

[1691] 5. Monitoring and adjustment during and after treatment

[1692] - The device collects new data from the patient in real time during and after treatment and sends it to the server.

[1693] - The server analyzes the collected data and adjusts the treatment plan as needed. Emotional data is also collected and analyzed periodically, and adjustments are made to reduce the patient's mental burden.

[1694] The present invention not only provides individually optimized treatment, but also makes it possible to implement a comprehensive treatment plan that takes into account the psychological aspects of the patient.

[1695] The processing flow will be explained below.

[1696] Step 1:

[1697] Data collection

[1698] A user (doctor or patient) uses a terminal to input basic patient information (age, sex, medical history, etc.) into the electronic medical record system, which then transmits the basic patient data to the server.

[1699] The user takes blood or tissue samples from the patient and runs them through a genetic analyzer, and the genetic data output from the analyzer is sent to a server via a terminal.

[1700] The user uses an emotion recognition device (such as a wearable device or dedicated app) to record their own or their patient's emotional state, and then synchronizes this data with the device and sends it to a server.

[1701] Step 2:

[1702] Data Preprocessing

[1703] The server normalizes the received genetic and clinical data into a standard format for analysis, a process that unifies the data and makes it easier to analyze.

[1704] The server performs a cleansing process to remove incomplete data and noise, and also completes missing data if any.

[1705] The server analyzes the emotion data and uses an emotion engine to recognize the user's emotional state (e.g., stress level, happiness level).

[1706] Step 3:

[1707] Training a machine learning model

[1708] The server trains machine learning models based on past treatment data, including genetic information, clinical data, and user emotional data.

[1709] The server uses the trained model to build predictive models for each patient data type to help plan future treatment.

[1710] Step 4:

[1711] Treatment plan generation

[1712] The server then applies the trained machine learning model to generate an optimal treatment plan based on the user's genetic, clinical, and emotional data. For example, in the case of cancer treatment, it would select a targeted drug for a specific gene mutation and set a dosing schedule based on the doctor's instructions.

[1713] The server uses an emotion engine to reflect the user's emotional state in the treatment plan. For example, if the patient is in a high stress state, stress reduction measures and psychological support will be added to the plan.

[1714] Step 5:

[1715] Presentation of treatment plan

[1716] The server transmits the generated treatment plan to the terminal and provides it to the user.

[1717] The device displays the received treatment plan in an easy-to-understand format for the user (doctor) and presents it as a treatment guideline. The doctor will then begin appropriate treatment for the patient based on this plan.

[1718] Step 6:

[1719] Treatment initiation and monitoring

[1720] The user starts treatment for the patient based on the treatment plan received from the server.

[1721] The device collects and transmits real-time vital signs, emotional state, and drug response data of patients undergoing treatment, including blood pressure, heart rate, blood drug concentration, and emotional state, to a server.

[1722] Step 7:

[1723] Real-time treatment prediction and adjustment

[1724] The server uses machine learning models to analyze the data collected in real time and predict the effectiveness of treatment.

[1725] Based on the predictions and emotion data, the server adjusts the treatment plan, for example by changing the drug dosage to minimize the risk of side effects.

[1726] Step 8:

[1727] Feedback and Retraining

[1728] The user (doctor) enters the progress of treatment and new data into the terminal and sends it to the server.

[1729] The server uses the newly collected data to retrain the machine learning model, improving the accuracy of future treatment plans.

[1730] The present invention not only provides an individually optimized treatment plan, but also takes into account the patient's mental and emotional state, thereby maximizing the overall effectiveness of the treatment.

[1731] Example 2

[1732] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1733] Conventional medical systems have not been able to adequately provide personalized medical plans based on genetic information and clinical data, and real-time collection of treatment data and plan adjustments have been limited. Furthermore, no measures have been taken to provide treatment plans that take into account the emotional data of patients and doctors. This has made it difficult to reduce patients' mental stress, and there have been cases where the effectiveness of treatment has not been maximized.

[1734] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: a means for inputting biomedical information and health data of a patient; a means for normalizing the biomedical information and health data into a standard format and preprocessing the data; a means for training a machine learning model based on past therapy data; a means for generating an optimal medical plan for each patient using the machine learning model; a means for transmitting the medical plan to a communication device and providing it to a user; a means for collecting data during the patient's treatment in real time and adjusting the medical plan; a means for feeding back the collected new data to the machine learning model and retraining the model; and a means for recognizing emotional data of the user, analyzing the emotional data, and reflecting the emotional data in the medical plan. This improves the accuracy and effectiveness of the personalized medical plan, making it possible to maximize the effectiveness of treatment while reducing mental stress on the patient.

[1735] "Biomedical information" refers to various biological data necessary for medical diagnosis and treatment, such as a patient's genetic information, clinical data, and vital signs.

[1736] "Health data" refers to data that includes various information used to assess a patient's health status, such as their lifestyle, diet, exercise, and stress level.

[1737] "Normalizing to a standard format" means converting data provided in different formats and units into a unified format and unit, and making it organized.

[1738] "Preprocessing" refers to the process of preparing data, such as filling in missing values ​​and removing outliers, before conducting data analysis.

[1739] "Therapy data" refers to data that includes the results and details of past treatments, recording the effectiveness and side effects of the treatments.

[1740] "Training a machine learning model" means training the model using past data to improve its predictive accuracy.

[1741] A "personalized medical plan" is a plan that proposes the most appropriate treatment method based on each patient's genetic information and clinical data.

[1742] A "communication device" is an electronic device used by a patient or doctor, such as a computer, tablet, or smartphone.

[1743] "Real-time collection" means continuously monitoring and collecting data the moment it occurs.

[1744] "Retraining" means using new data collected to retrain an existing machine learning model to further improve its accuracy.

[1745] "Emotional data" refers to data that indicates the user's psychological and emotional state, measured based on heart rate, electrodermal activity, etc.

[1746] An "emotion engine" is a software algorithm that analyzes and recognizes a user's emotional data.

[1747] This invention is a system that provides an optimal medical plan based on a patient's biomedical information and health data, and adjusts the plan taking into account the user's emotional state. The system consists of a series of steps: data collection, data preprocessing and analysis, training of a machine learning model, generation and presentation of a treatment plan, and monitoring and adjustment during and after treatment.

[1748] Data collection

[1749] A user (doctor or patient) uses a terminal to input basic patient information (age, gender, medical history, etc.) into the electronic medical record system. The terminal then sends this information to a server in a standard format. The user also collects a biological sample from the patient and subjects it to a genetic analysis device. The analysis results data are also sent to the server via the terminal. Furthermore, the user uses an emotion recognition device to record their emotional state, and this data is entered into the terminal or automatically sent to the server.

[1750] Data preprocessing and analysis

[1751] The server uses Python's pandas library to normalize the received genetic and clinical data into a standard format, impute missing values, and remove outliers.The server then uses libraries such as TensorFlow and PyTorch to analyze the emotion data, identify the user's emotional state, and activate the emotion engine.

[1752] Training a machine learning model

[1753] The server trains a machine learning model using Scikit-learn and TensorFlow on past treatment data. The training data includes genetic information, clinical data, and emotional data. The server trains the model using cross-validation to prevent overfitting and generate a model with high predictive performance.

[1754] Treatment plan generation and presentation

[1755] The server uses the trained model to generate an optimal treatment plan based on the user's genetic information, clinical data, and emotional data. For example, it selects a targeted drug based on genetic mutations and sets its administration schedule. The generated treatment plan is then sent from the server to the device for the user to review.

[1756] Monitoring and adjustment during and after treatment

[1757] The device sends new data from the patient in real time during and after treatment to the server, which analyzes this data and adjusts the treatment plan accordingly. Emotional data is also collected and analyzed periodically, and actions to reduce the patient's mental stress are reflected in the plan.

[1758] Examples of specific examples and prompts

[1759] Example: Cancer treatment

[1760] 1. Data Collection

[1761] Users take blood samples from cancer patients and perform genetic analysis.

[1762] The terminal transmits this analysis data to the server.

[1763] The user uses the emotion recognition device to record their own or their patient's emotional state and transmit it to the server.

[1764] 2. Data Preprocessing and Analysis

[1765] The server normalizes the received genetic and clinical data into a standard format.

[1766] The server analyzes the user's emotional state using an emotion engine and integrates the emotion data.

[1767] 3. Training the machine learning model

[1768] The server trains the machine learning model using historical cancer treatment data, including emotional data.

[1769] The server uses the trained model to predict treatment response.

[1770] 4. Treatment plan generation and presentation

[1771] The server generates an optimal treatment plan and takes into account approaches to reduce stress for the patient based on emotional data.

[1772] The server transmits the treatment plan to the terminal and provides it to the user.

[1773] 5. Monitoring and adjustment during and after treatment

[1774] The terminal transmits new data in real time to the server during and after treatment.

[1775] The server analyzes the collected data and adjusts the treatment plan as needed.

[1776] Prompt Sentence Examples

[1777] "I would like to create an optimal treatment plan for a cancer patient that takes into account their genetic information, clinical data, and emotional state. Please generate a treatment proposal based on the following data."

[1778] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1779] Step 1: Data collection

[1780] Input: Patient basic information, genetic sample, emotional data

[1781] Output: Genetic information, clinical data, and emotional data in a standard format sent to a server

[1782] Step 1.1: Enter patient basic information

[1783] The user logs into the electronic medical record system on the terminal and enters the patient's basic information (age, gender, medical history, etc.), enters the required data in the input fields, and clicks the "Save" button to send it to the server.

[1784] Specific actions: The user uses the device's keyboard to enter information and clicks the save button with the mouse.

[1785] Step 1.2: Genetic sample analysis and submission

[1786] Input: Patient genetic sample

[1787] Output: Genetic information sent to the server

[1788] The user places the collected gene sample into the genetic analyzer and begins analysis. When the analysis is complete, the device generates a data file.

[1789] The terminal retrieves data files from the analysis device via USB or network connection and automatically uploads them to the server.

[1790] Specific operation: The user collects a genetic sample and inserts it into the analysis device. After analysis, the device sends the data to the server.

[1791] Step 1.3: Collect emotion data

[1792] Input: Emotion data from an emotion recognition device

[1793] Output: Emotion data sent to the server

[1794] The user uses the emotion recognition device to record their emotional state, and the data is transmitted via Bluetooth to the device and then from the device to the server.

[1795] Specific operation: The user wears the emotion recognition device and the data is automatically sent to the terminal.

[1796] Step 2: Data preprocessing and analysis

[1797] Input: Genetic information, clinical data, and emotional data in a standard format sent to the server

[1798] Output: Normalized and parsed data

[1799] Step 2.1: Normalize the data

[1800] The server converts the received genetic and clinical data into a data frame using Python's pandas library, normalizes it to a standard format, imputes missing values, and removes outliers.

[1801] What happens: The server runs data processing steps using pandas to generate a clean dataset.

[1802] Step 2.2: Analyzing and integrating sentiment data

[1803] The server analyzes the received emotion data using TensorFlow, PyTorch, etc. to identify the user's emotional state, which is then integrated with other biomedical information.

[1804] Specific operation: The server receives the emotion data and runs an analysis algorithm to classify the emotional state. The results are integrated with the biomedical data.

[1805] Step 3: Train the machine learning model

[1806] Input: Normalized and parsed data

[1807] Output: A trained machine learning model

[1808] Step 3.1: Train the model using historical data

[1809] The server uses historical therapy data to train machine learning models using Scikit-learn and TensorFlow, including genetic, clinical, and emotional data.

[1810] What happens: The server runs the script using the training data to optimize the model parameters.

[1811] Step 3.2: Predicting with the trained model

[1812] The server uses the trained model to predict the patient's individual treatment response.

[1813] Specific operation: The server inputs new patient data into the model and generates predictions, including predictions of treatment efficacy and side effects.

[1814] Step 4: Generate and present the treatment plan

[1815] Input: Trained machine learning model, patient biomedical information, and emotion data

[1816] Output: Generated medical plan

[1817] Step 4.1: Generate an optimal treatment plan

[1818] The server uses the trained model to generate an optimal treatment plan based on the user's genetic, clinical, and emotional information. In the case of cancer treatment, it selects targeted therapeutic drugs and sets administration schedules based on genetic mutations.

[1819] Specific operations: The server inputs the data into the model and calculates the optimal treatment plan.

[1820] Step 4.2: Present the treatment plan

[1821] The server then sends the generated treatment plan to the communication device, where the user can check the treatment plan on their device and share the necessary information within the hospital.

[1822] Specific operations: The server generates a treatment plan and sends it to the terminal. The user checks the plan on the terminal and performs the treatment.

[1823] Step 5: Monitoring and adjusting during and after treatment

[1824] Input: New patient data collected in real time

[1825] Output: Adjusted treatment plan

[1826] Step 5.1: Collect real-time data

[1827] The device transmits new patient data (genetic information, clinical data, emotional data) collected during and after treatment to the server in real time.

[1828] Specific operation: The device acquires new data through sensors or manual input and sends it to the server over the network.

[1829] Step 5.2: Analyze data and adjust treatment plan

[1830] The server analyzes the new data and reassess whether the existing treatment plan is optimal, adjusts it if necessary, and suggests actions to reduce the patient's mental stress based on emotional data.

[1831] Specific operations: The server analyzes the new data and updates the treatment plan. The updated plan is sent to the device, and the user modifies the treatment.

[1832] (Application example 2)

[1833] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1834] Conventional autonomous driving systems do not select driving routes that take into account the emotional state of passengers, which means they are unable to reduce passenger stress or provide a comfortable driving experience.In addition, treatment plans based on patients' genetic information and clinical data do not take into account their emotional state, making it difficult to maximize treatment effectiveness.

[1835] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1836] In this invention, the server includes: a means for inputting a patient's genetic information and clinical data; a means for normalizing and preprocessing the genetic information and clinical data into a standard format; a means for training a machine learning model based on past treatment data; a means for generating an optimal treatment plan for each patient using the machine learning model; a means for transmitting the treatment plan to a terminal and providing it to a user; a means for collecting data during the patient's treatment in real time and adjusting the treatment plan; a means for feeding back the collected new data to the machine learning model and retraining the model; a means for collecting passengers' emotional states and selecting a route based on the collected data; and a means for transmitting emotional data and location information to the server and optimizing the driving route. This enables the selection of a driving route taking passengers' emotional states into consideration, thereby reducing stress and providing a comfortable driving experience. Furthermore, an optimal treatment plan taking individual patients' emotional states into consideration is provided, maximizing the effectiveness of treatment.

[1837] "Patient genetic information" refers to data on genetic structure and mutations obtained by subjecting a sample collected from a patient to a genetic analysis device.

[1838] "Clinical data" refers to any information collected in a medical setting, such as a patient's diagnosis, treatment history, or vital signs.

[1839] "Means for inputting" refers to means for transmitting data to the server using an electronic medical record system or an input device.

[1840] "Normalization to a standard format" is a process of converting data of different formats into a unified format in order to maintain data consistency.

[1841] "Preprocessing means" refers to means for removing noise and imperfections from data and preparing it in an analyzable format.

[1842] A "machine learning model" is an algorithm that is trained to make predictions or classifications based on collected data.

[1843] The "means for generating a treatment plan" is a means for using a machine learning model to determine the optimal treatment method and schedule based on individual patient data.

[1844] The "means for transmitting to the terminal and providing to the user" refers to a means for transmitting the generated treatment plan to the device of the user (doctor or patient) so that it can be viewed and used.

[1845] "Means for collecting and adjusting in real time" refers to means for instantly transmitting newly acquired data during treatment to a server and dynamically changing the treatment plan.

[1846] "Means for providing feedback to a machine learning model and re-learning" refers to means for inputting newly collected data into a machine learning model and re-training it to improve the accuracy of the model.

[1847] "Passenger emotional state" refers to the passenger's psychological and emotional state, such as stress, joy, anxiety, etc.

[1848] The "route selection means" is a means for determining the optimal driving route based on the emotional state of the passenger.

[1849] "Emotion data and location information" refers to data relating to the psychological state of passengers and data relating to the current location of passengers and vehicles.

[1850] The "means for optimizing a driving route" is a means for automatically selecting the most suitable driving route based on emotion data and location information.

[1851] The present invention provides a driving route planning system that takes into account the emotional state of passengers in an autonomous vehicle, and incorporates emotional data as an additional element in a system that provides optimal treatment plans based on the patient's genetic information and clinical data. Specific embodiments are described below.

[1852] System Overview

[1853] The system works by collecting emotional and location data through smart devices (e.g., smartphones, head-mounted displays, etc.) and sending it to a server. The server then analyzes this data and generates an optimal driving route. The system also provides a treatment plan based on the patient's genetic and clinical data, and adjusts the treatment plan based on real-time analysis of data collected during and after treatment.

[1854] Program processing

[1855] Emotion data collection and transmission

[1856] Users (passengers) record their emotional state in real time through their smart devices. Emotion recognition technology is used to analyze emotional states such as stress, joy, and anxiety, and the data is sent to a server. Libraries such as EmotionRecognizer are used for this collection process.

[1857] Data Analysis and Optimization

[1858] The server analyzes the submitted emotion data and location information. It normalizes and preprocesses the data into a standard format, then uses EmotionRecognizer to determine the user's emotional state. It then generates an optimal driving route based on this data using a machine learning model trained on past data.

[1859] Route selection and provision

[1860] The generated driving route is sent to the terminal and provided to the user. The user operates the autonomous vehicle based on this route. Data related to the treatment plan is also sent to the user's terminal and used for treatment.

[1861] Real-time data collection and reconciliation

[1862] Data on the patient's treatment and passengers' emotional state is collected in real time and sent to a server, which then dynamically adjusts the treatment plan and driving route based on this data. Newly collected data is fed back into the machine learning model, allowing it to be retrained.

[1863] Specific examples

[1864] If a passenger in an autonomous vehicle is stuck in traffic, the system will choose a gentler route if data indicates the passenger's emotional state is stressed.

[1865] During treatment, the treatment plan generated based on the patient's genetic information also takes into account the patient's emotional data, and adjustments are made to the plan to reduce the mental burden.

[1866] Prompt Sentence Examples

[1867] "If the passenger's emotional state is relaxed, suggest the optimal driving route for the autonomous vehicle. If the passenger is stressed, suggest a gentler route that avoids traffic jams."

[1868] Thus, the present invention allows for the optimization of driving routes based on the emotional state of passengers and the provision of treatment plans that take into account the emotional state of patients.

[1869] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1870] Step 1:

[1871] Emotional Data Collection

[1872] Users (passengers) record their emotional state in real time through smart devices (e.g., smartphones, head-mounted displays). Emotion recognition technology is used to analyze emotional states such as stress, joy, and anxiety. Specifically, image data collected from a camera is analyzed using libraries such as EmotionRecognizer to extract emotional data. The input is camera image data, and the output is emotional state data.

[1873] Step 2:

[1874] Emotion data transmission

[1875] The device sends the collected emotion data to the server in JSON format using the HTTP protocol. Specifically, the device converts the emotion data into an appropriate format and sends it to the server's receiving endpoint. The input is emotion data (in JSON format), and the output is the completion of data transmission to the server.

[1876] Step 3:

[1877] Data analysis and standard formatting

[1878] The server receives the emotion data and normalizes it into a standard format. It removes inconsistencies and noise from the data and makes it analyzable. The input is emotion data (JSON format), and the output is emotion data in a standard format.

[1879] Step 4:

[1880] Training a machine learning model

[1881] The server trains a machine learning model based on past emotion data and driving route information. Specifically, it uses the collected dataset to train the model using libraries such as TensorFlow and scikit-learn. The input is past emotion data and driving route data, and the output is the trained model.

[1882] Step 5:

[1883] Route Selection

[1884] The server uses a trained machine learning model to generate an optimal driving route based on the received emotion data. Specifically, the model inputs current emotion data and location information and predicts the optimal route. The input is the current emotion data and location information, and the output is the optimal driving route.

[1885] Step 6:

[1886] Providing driving directions

[1887] The server sends the generated driving route to the device. Specifically, it sends the route information using the HTTP protocol and displays it on the smartphone's navigation app. The input is the optimal driving route, and the output is the route information displayed on the device.

[1888] Step 7:

[1889] Real-time data collection and treatment plan adjustment

[1890] The terminal collects real-time patient data and passenger emotional state data during treatment and sends it to the server, which then dynamically adjusts the treatment plan and driving route based on this data. The input is the real-time collected data, and the output is the adjusted treatment plan and driving route.

[1891] Step 8:

[1892] Retraining a machine learning model

[1893] The server feeds newly collected data back into the machine learning model for re-learning. Specifically, new data is input into the model to improve its accuracy. The input is new emotional data and location information, and the output is the re-learned model.

[1894] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1895] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1896] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1897] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1898] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1899] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1900] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1901] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1902] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1903] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1904] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1905] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1906] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1907] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1908] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data proces...

Claims

1. a means for inputting genetic and clinical data of a patient; means for normalizing and preprocessing said genetic and clinical data into a standard format; a means of training a machine learning model based on historical treatment data; and a means for generating an optimal treatment plan for each patient using the machine learning model; means for transmitting the treatment plan to a terminal and providing it to a user; means for collecting real-time data during a patient's treatment and adjusting said treatment plan; means for feeding back the collected new data to the machine learning model to retrain the model; A system including:

2. 10. The system of claim 1, further comprising means for monitoring patient vital signs and drug response data in real time and optimizing the predictive model based on that data.

3. The system according to claim 1, wherein the means for analyzing genetic information of a patient includes a means for selecting a targeted therapeutic drug corresponding to a specific genetic mutation.

Images