Method for predicting breakthrough pain in subject

Abstract

To provide a method for predicting breakthrough pain in a cancer patient using an artificial intelligence model that processes time-series data collected from the cancer patient.SOLUTION: A method for predicting breakthrough pain in a subject comprises the steps of: receiving, by an analysis device, pain score data collected from a subject for a predetermined time; pre-processing, by the analysis device, the pain score data; and inputting, by the analysis device, the pre-processed pain score data into a pre-trained deep learning model and predicting whether or not breakthrough pain will be generated in the subject at a future time point based on a predicted value output by the deep learning model.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a technique for predicting breakthrough pain in cancer patients using artificial intelligence. [Background technology]

[0002] Breakthrough pain refers to a phenomenon in which the pain experienced by cancer patients suddenly and transiently worsens. Breakthrough pain leads to a decrease in the quality of life of cancer patients. Currently, pain control in clinical practice is performed by combining a long-acting analgesic with a fast-acting analgesic. However, even with fast-acting analgesics, cancer patients have no choice but to suffer from breakthrough pain until the drug takes effect after administration. Summary of the Invention [Problem to be solved by the invention]

[0003] The present invention seeks to predict breakthrough pain in cancer patients utilizing information collected from the cancer patient over time. The present invention seeks to predict breakthrough pain in cancer patients utilizing an artificial intelligence model that processes time series data collected from the cancer patient. [Means for solving the problem]

[0004] The method for predicting sudden pain in a subject includes a step of receiving pain score data collected from the subject for a certain period of time by an analysis device, a step of the analysis device preprocessing the pain score data, and a step of the analysis device inputting the preprocessed pain score data into a pre-trained deep learning model and predicting whether the subject will have sudden pain at a future time point based on a predicted value output by the deep learning model.

[0005] The analysis device for predicting sudden pain in a subject includes an interface device that receives input of pain score data collected from the subject for a certain period of time, a storage device that stores a deep learning model that predicts whether or not sudden pain will occur in response to the input of the patient's pain information, and a calculation device that preprocesses the input pain score data, inputs the preprocessed pain score data into a previously trained deep learning model, and predicts whether or not the subject will experience sudden pain at a future point in time based on a predicted value output. Effect of the Invention

[0006] The present invention makes it possible to predict the occurrence of sudden pain based on clinical information of cancer patients collected clinically at medical institutions, thereby enabling preemptive measures to be taken. Furthermore, the present invention can be used not only for pain regulation, but also for actual treatment research for cancer patients and development of biomarkers related to prognosis. [Brief description of the drawings]

[0007] [Figure 1] 1 is an exemplary diagram of a system for predicting sudden pain using information of a cancer patient; [Diagram 2] FIG. 2 is an exemplary diagram of a learning process (200) of the deep learning model. [Diagram 3] FIG. 13 is an exemplary diagram of a process for pre-processing pain data. [Figure 4] FIG. 1 is an exemplary diagram of a deep learning model that predicts future breakthrough pain based on input of a patient's pre-processed pain information. [Diagram 5] FIG. 13 is an illustrative diagram of a verification process of a deep learning model for predicting sudden pain. [Figure 6] This is the AUC curve for the LSTM-based prediction model. [Figure 7] 1 is an exemplary diagram of an analysis device for predicting sudden pain; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] The present invention can be modified in various ways and can have various embodiments, and a specific embodiment will be described in detail below with reference to the drawings. However, the present invention is not limited to the specific embodiment, and it should be understood that the present invention includes all modifications, equivalents, and alternatives that fall within the spirit and technical scope of the technology described below.

[0009] Terms such as first, second, A, B, etc. may be used to describe various components, but the components are not limited by the terms and are used only to distinguish one component from another. For example, a first component may be named a second component, and similarly, the second component may be named a first component, without departing from the scope of the present invention. The term "and / or" includes a combination of multiple related listed items or any of multiple related listed items.

[0010] In the terms used in this specification, the singular expression should be understood to include the plural expressions unless the context clearly indicates otherwise, and the term "comprise" or the like should be understood to mean the presence of a described feature, number, step, operation, component, part, or combination thereof, but not to exclude the presence or additional possibility of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0011] Before describing the drawings in detail, it should be made clear that the components in this specification are merely classified according to the main function of each component. That is, two or more components described below may be incorporated into one component, or one component may be divided into two or more components according to more specific functions. Furthermore, each component described below may additionally perform some or all of the functions of other components in addition to its own main function, and some functions of the main function of each component may be exclusively performed by other components.

[0012] Furthermore, in performing a method or method of operation, each step constituting the method may be performed in a different order than that specified unless the context clearly indicates otherwise, i.e., each step may be performed in the same order as, substantially simultaneously with, or in the reverse order of, the steps specified.

[0013] The present invention is a technique for predicting breakthrough pain in cancer patients. Furthermore, the technique of the present invention can be used to predict breakthrough pain in patients with a specific type of disease, regardless of the type of disease.

[0014] The present invention predicts breakthrough pain using time series data that can be collected from cancer patients. The time series data can include pain scores assessed over time and other clinical information, including age, sex, disease type, and other EMR (Electronic Medical Record) data.

[0015] Hereinafter, the analysis device will be described as predicting sudden pain based on time-series data of a cancer patient using a learning model. The analysis device can be realized as various devices capable of processing data and controlling the operation of the learning model. For example, the analysis device can be realized as a PC, a server on a network, a smart device, a chipset with a dedicated program, etc.

[0016] The learning model may be any one of various types of models. For example, the learning model may be a decision tree, a random forest, KNN (K-nearest neighbor), Naive Bayes, SVM (support vector machine), ANN (artificial neural network), etc. In particular, the learning model may be a deep learning model capable of processing time series data.

[0017] 1 is an example of a system 100 for predicting breakthrough pain using information of a cancer patient. In FIG. 1, an example of an analysis device is shown as a computer terminal 130 and a server 140.

[0018] The user terminal 110 collects a pain score (NRS) for a subject (patient). The NRS score is in the range of [0, 10]. The NRS score is divided into mild pain, moderate pain, and severe pain according to the score. The pain score may be information calculated by medical staff evaluating the subject's condition over time. The user terminal 110 may store the collected pain score (NRS) in an EMR (Electronic Medical Record) 120 or a separate database (DB).

[0019] The learning device 50 analyzes patient information to construct a deep learning model for predicting sudden pain. The learning device 50 refers to a computer device capable of preprocessing patient data and learning a deep learning model. The learning device 50 can construct a deep learning model using predetermined learning data. The learning process and model structure will be described later. The computer terminal 130 and the server 140 obtain the constructed deep learning model and use it for subject analysis.

[0020] In FIG. 1 , user A can analyze the patient's pain score and clinical information using computer terminal 130. Computer terminal 130 can receive the patient's pain score and clinical information from user terminal 110 or EMR 120 via a wired or wireless network. In some cases, computer terminal 130 can be a device physically connected to user terminal 110. Computer terminal 130 can pre-process the patient's pain score and / or clinical information to a certain extent. Computer terminal 130 can predict sudden pain based on a value output by a deep learning model that receives the patient's pain score and clinical information as input. User A can check the analysis results on computer terminal 130.

[0021] The server 140 may receive the patient's pain score and clinical information from the user terminal 110 or the EMR 120 via a wireless network. The server 140 may pre-process the patient's pain score and / or clinical information in a certain manner. The server 140 may predict sudden pain based on a value output by a deep learning model that receives the patient's pain score and clinical information as input. The server 140 may transmit the analysis result to the user A's terminal.

[0022] The computer terminal 130 and / or server 140 may also store the results of the analysis in the EMR 120 .

[0023] Below, we will explain the deep learning model for predicting sudden pain in cancer patients and the learning process of the deep learning model.

[0024] The inventors used a dataset of 3,431 patients out of 34,301 patients admitted to the Department of Hematology and Oncology at Samsung Seoul Hospital, their affiliated research institution, between July 2016 and February 2020, excluding 2,697 patients who underwent surgery and 28,173 patients with an NRS (non-zero numerical rating scale) score of less than 20 points.

[0025] 2 is an example of a learning process 200 of the deep learning model. The deep learning model is a model that predicts (classifies) sudden pain using patient information. Therefore, the deep learning model may be called a predictive model.

[0026] The database DB can store the pain scores and clinical information of the patients included in the data set. At this time, the pain scores correspond to time series data collected over a certain period of time. The medical team collected the pain scores of the patients according to the NRS scale at certain intervals. The medical team collected the pain scores at 05:00, 13:00, and 21:00 every day. In addition, the medical team also collected information on sudden pain that occurred from the patients at other times. The clinical information may include age, sex, and other items. The present inventor defined an NRS score of 4, which is the standard for administering a narcotic analgesic according to the guidelines, as sudden pain in cancer patients. In this case, an NRS score of 4 or more corresponds to sudden pain.

[0027] The learner may perform some pre-processing of the patient's raw data (step 210).

[0028] Figure 3 shows an example of the process of pre-processing pain data.

[0029] The learning device segments the pain score, which is time series information, into fixed time intervals. The learning device assigns a pain score to each interval according to a number of time intervals (bins). In this case, if there are multiple pain scores in one interval, the learning device can set the score of the relevant interval as the highest score. One bin can be defined as a fixed time length (e.g., τ time). Figure 3(A) is an example of segmenting pain scores into fixed time intervals (τ=3 hours).

[0030] Breakthrough pain can be assessed differently for a single patient or between different patients. For example, breakthrough pain can have a specific pattern for each patient depending on the patient's medical condition. Breakthrough pain can also be assessed differently for each patient depending on the patient's management and condition. The learning device can process the entire data in units of a certain time period. The inventor processed pain score data in 24-hour units (0:00 to 24:00). In addition, the learning device can zero-pad parts that are not in the original data to set the start and end of the pain score data to 0:00. Figure 3(B) is an example of a process of processing pain score data collected continuously for n days in 24-hour units.

[0031] FIG. 3 illustrates that the pain score data is divided into a certain time interval (τ=3 hours) and then divided into days, but the order of the process may be reversed.

[0032] The learning device can convert the pain score data for n days divided into τ time bins from a 1×((24 / τ)) vector form to a (24 / τ)×n matrix form. Figure 3(C) is an example of pain score data processed in 24-hour units converted to a matrix form. One row in Figure 3(C) is pain score data for a one-day time interval, and each column is an example of pain score data collected in n-day units.

[0033] Thus, the input data may further utilize clinical information such as the gender and age of the patient in addition to the pain score.

[0034] The learning device can then build a prediction model using the pain score data preprocessed in the form of a matrix. Furthermore, the learning device can also build a prediction model by further using clinical information together with the pain score data, which is time-series data.

[0035] The present inventor constructed six different types of deep learning models. The deep learning models include a recurrent neural network (RNN), a long short-term memory (LSTM), a gated recurrent unit (GRU), a bidirectional long short-term memory (Bi-LSTM), a hybrid of the convolutional neural network, long short-term memory (CNN-LSTM), and a transformer. The present inventor then diversified the length of the time interval of the data and evaluated the performance of the constructed models. The present inventor constructed the models by dividing the time interval length into units τ ∈ {1, 2, 3, 4, 6, 8, 12}.

[0036] The learning device divides the collected whole data into learning data and validation data (step 220). The inventors used 80% of the data of 2,745 people in the data set of 3,431 people as learning data, and 20% of the data of 686 people as test data.

[0037] The learning device performs learning of the prediction model using the learning data (step 220). The learning device extracts one input data from the learning data and performs the learning process. The learning device compares the value (sudden pain prediction value) output by the prediction model that receives the input data with the correct answer value and updates the parameters of the prediction model. The learning device repeats the learning process using data that belongs to the learning data.

[0038] Once the learning process is complete, the learning device performs verification of the trained prediction model (step 230). The learning device performs the verification process by extracting one of the verification data. The learning device inputs the selected data into the prediction model, outputs a sudden pain prediction value, and performs verification by comparing the predicted result with the correct value.

[0039] FIG. 4 is an example of a deep learning model that receives preprocessed pain information of a patient and predicts a sudden pain at a future time point. The analysis device receives pain score data of a patient at a past time point, which is a prediction target. The analysis device preprocesses the pain score data in a certain way. The preprocessing process is the same as that described above. The analysis device can convert the pain score data for n days, which is divided into bins of τ time length, into a 24 / τ×n matrix form. FIG. 4 is an example of τ time=3 hours. The analysis device inputs the pain data in the matrix form into the constructed deep learning model. The deep learning model can be composed of a number of convolutional layers (e.g., Layer 1 to Layer 3) and a dense layer. The dense layer can finally output information predicting the possibility of occurrence of a sudden pain for each time interval (bin) using an activation function. The analysis device can predict whether or not a sudden pain will occur within 24 hours at the final time point when the information on the patient was collected, based on the information output by the deep learning model. For example, the analysis device can predict that sudden pain is likely to occur in the second interval (03:00 to 06:00), the fourth interval (09:00 to 12:00), and the fifth interval (12:00 to 15:00) in Figure 4.

[0040] Figure 5 is an example of a verification process for a deep learning model that predicts sudden pain. The analysis device predicts sudden pain for the next 24 hours using pain score data for 72 hours. At this time, the analysis device can predict the possibility of sudden pain occurring based on the pain score predicted by the deep learning model for each time period. For example, if the pain score predicted for a specific time period is 4 or more, the analysis device can determine that sudden pain will occur in that period (binary value 1), and if the pain score predicted for a specific time period is less than 4, the analysis device can determine that sudden pain will not occur in that period (binary value 0).

[0041] The analysis device can verify the performance of the model by comparing the predicted value of sudden pain predicted in the time interval with the true value according to the value output by the deep learning model. The verification index can use MCC (Matthews correlation coefficient). MCC is a value in the range of [-1, 1], and the closer to +1, the higher the accuracy. Table 1 below shows the performance of each model. In Table 1, the input data is divided into the past 24 hours data, 72 hours data, and 120 hours data. In addition, the input data used were data with different time intervals τ∈{1, 2, 3, 4, 6, 8, 12}.

[0042] [Table 1]

[0043] As shown in Table 1, the LSTM-based models performed well overall. The LSTM model performed best with an MCC of 0.4927 in the example where a 12-hour time interval was used for 120 hours of data.

[0044] Figure 6 shows the AUC curves for the LSTM-based prediction model. Figure 6(A) shows the results using pain score data from the past 24 hours, Figure 6(B) shows the results using pain score data from the past 72 hours, and Figure 6(C) shows the results using pain score data from the past 120 hours. The LSTM-based prediction model showed significant performance for data from various time intervals.

[0045] 7 is an example of an analysis device 300 for predicting sudden pain. The analysis device 300 corresponds to the above-mentioned analysis devices (130 and 140 in FIG. 1). The analysis device 300 can be physically embodied in various forms. For example, the analysis device 300 can be in the form of a computer device such as a personal computer, a network server, a chipset dedicated to data processing, etc.

[0046] The analysis device 300 may include a storage device 310 , a memory 320 , a processing device 330 , an interface device 340 , a communication device 350 , and an output device 360 ​​.

[0047] The storage device 310 can store the patient's past pain score data. The pain score data can be data collected for a predetermined period of time, such as the past 24 hours, the past 72 hours, or the past 120 hours.

[0048] The storage device 310 may store clinical information of the patient, such as gender and age.

[0049] The storage device 310 may store a deep learning model for predicting sudden pain. In this case, the storage device 310 may store a plurality of models constructed using time data of different lengths.

[0050] The storage device 310 can store the analysis results.

[0051] The memory 320 may store data and information generated in the process of the analysis device 300 predicting sudden pain using the patient's pain score data.

[0052] The interface device 340 is a device that receives predetermined commands and data from the outside.

[0053] The interface device 340 may receive the subject's pain score data from a physically connected input device or an external storage device, and may receive the subject's clinical information from a physically connected input device or an external storage device.

[0054] The interface device 340 may also communicate the predicted result of the breakthrough pain to an external object. The predicted result may comprise a breakthrough pain prediction value for a 24-hour period from the end of the patient's data collection.

[0055] The communication device 350 refers to a configuration for receiving and transmitting predetermined information through a wired or wireless network.

[0056] The communication device 350 may receive pain score data of the subject from an external object. The communication device 350 may receive clinical information of the subject.

[0057] Alternatively, the communication device 350 may transmit the result of the sudden traffic prediction to an external object, such as a user terminal.

[0058] Meanwhile, the interface device 340 means that it includes an interface that transmits data or information received from the communication device 350 to the inside of the analysis device 300 .

[0059] The output device 360 ​​is a device that outputs predetermined information, and can output interfaces, analysis results, and the like required for data processing.

[0060] The computing device 330 may pre-process the initial pain score data of the subject in a certain manner. As described above, the pre-processing may include dividing the data into time intervals and generating pain score data in a matrix form by processing the data in 24-hour units.

[0061] The computing device 330 inputs the (preprocessed) pain score data into a pre-trained deep learning model, and can predict whether or not the subject has experienced sudden pain based on the probability value output by the deep learning model.

[0062] In this case, a deep learning model that matches the input data according to the time length of past data collected from the patient and / or the length of the time interval unit into which the pain data is divided can be used.

[0063] The computing device 330 may determine whether or not a sudden pain will occur in a specific section of the future time section based on the output value of the deep learning model.

[0064] The computing device 330 may be a device such as a processor, AP, or a chip with a built-in program that processes data and performs a predetermined operation.

[0065] In addition, the method for predicting sudden pain in a cancer patient as described above may be embodied in a program (or application) including an executable algorithm that can be executed by a computer. The program may be provided by being stored in a non-transitory or non-transitory computer-readable medium.

[0066] A non-transitory readable medium refers to a medium that stores data semi-permanently and can be read by a device, rather than a medium that stores data for a short moment such as a register, cache, memory, etc. In particular, the various applications or programs described above can be provided by being stored in a non-transitory readable medium such as a CD, DVD, hard disk, Blu-ray disk, USB, memory card, ROM (read-only memory), PROM (programmable read-only memory), EPROM (Erasable PROM), EPROM or EEPROM (Electrically EPROM), or flash memory.

[0067] The temporary readable medium refers to various types of RAM such as Static RAM, SRAM, Dynamic RAM, DRAM, Synchronous DRAM, SDRAM, Double Data Rate SDRAM, DDRSDRAM, Enhanced SDRAM, ESDRAM, Synclink DRAM, SLDRAM, and Direct Rambus RAM (DRRAM).

[0068] The present embodiment and the drawings attached to this specification merely clearly show a part of the technical ideas contained in the present invention, and it is self-evident that any modified examples and embodiments that can be easily inferred by a person skilled in the art within the scope of the technical ideas contained in the above-mentioned specification and drawings of the present invention all fall within the scope of the claims of the present invention.

Claims

1. receiving pain score data collected from the subject over a period of time by the analysis device; said analysis device pre-processing said pain score data; A method for predicting sudden pain in a subject, comprising: a step in which the analysis device inputs the preprocessed pain score data into a pre-trained deep learning model, and predicts whether the subject will have sudden pain at a future time based on the predicted value output by the deep learning model.

2. The pretreatment step includes: The analysis device divides the pain score data into a certain time period. The method of claim 1 , further comprising: dividing the pain score data divided by the fixed time length into units of fixed time intervals by the analysis device, and setting a pain score for each unit of the fixed time interval.

3. The method for predicting sudden pain in a subject according to claim 2 , wherein the deep learning model outputs a probability value of sudden pain occurrence in the fixed time interval unit.

4. an interface device for receiving input of pain score data collected from a subject for a certain period of time; A storage device for storing a deep learning model that receives input of a patient's pain information and predicts whether or not sudden pain will occur; An analysis device for predicting sudden pain in a subject, comprising: a calculation device that preprocesses the input pain score data, inputs the preprocessed pain score data into a pre-trained deep learning model, and predicts whether the subject will have sudden pain at a future time based on the predicted value output.

5. The analysis device for predicting sudden pain in a subject as described in claim 4, wherein the calculation device divides the pain score data by a certain time length, further divides the certain time length into units of a certain time section, and sets a pain score for each unit of the certain time section.

6. The analysis device for predicting sudden pain in a subject according to claim 5 , wherein the deep learning model outputs a probability value of sudden pain occurrence in units of the fixed time interval.

Images