Clinical test information management method and system based on big data

Abstract

The invention discloses a clinical test information management method and system based on big data, and belongs to the technical field of big data processing and medical information management, and the method comprises the steps: integrating data from an electronic medical record system, a laboratory information system and wearable equipment through a multi-source data collection technology, and guaranteeing the comprehensiveness and consistency of the data; real-time statistical analysis is performed on the data through a sliding window mechanism, so that the change trend of the data can be quickly captured, and an analysis result is generated; the results are input into an anomaly detection model constructed based on exponential weighted moving average (EWMA) to realize dynamic monitoring and anomaly recognition of the data; meanwhile, for abnormal conditions, the system can realize instant notification through an API (Application Program Interface) so as to ensure that related personnel can quickly respond and deal with the abnormal conditions. According to the method, the efficiency and safety of clinical test information management are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of big data processing and medical information management, and in particular to a clinical trial information management method and system based on big data. Background Art

[0002] Traditional clinical trial information management methods mostly rely on manual entry and structured databases. This method effectively supports the conduct of trials in the early stages. However, with the rapid increase in the amount of trial data, especially the emergence of heterogeneous data from multiple sources (such as electronic medical records, laboratory information, and data generated by wearable devices), traditional technology has gradually revealed its limitations.

[0003] The severity of the data island phenomenon makes it difficult to integrate information from different sources, and the efficiency and accuracy of data processing are greatly affected. In addition, the lack of real-time data analysis capabilities makes it impossible to quickly respond to abnormal situations that may arise during clinical trials, further restricting the flexibility of the trials and the effectiveness of decision-making.

[0004] At present, the existing related technologies face many shortcomings. First, the effectiveness and comprehensiveness of the data preprocessing link are insufficient, resulting in uneven data quality, affecting the reliability of subsequent analysis results; second, there is a lack of anomaly detection mechanism based on real-time analysis, and many potential problems are not discovered in time, resulting in decision delays or errors in the trial process; traditional anomaly detection methods mostly rely on static threshold settings and cannot adapt to the dynamically changing clinical environment, resulting in insufficient sensitivity to data, which in turn affects the safety and effectiveness of clinical trials.

[0005] Therefore, how to efficiently and accurately integrate data from different sources and conduct effective analysis on a real-time basis has become a key issue that needs to be urgently addressed in the field of clinical trial information management. Summary of the invention

[0006] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract of the specification and the title of the invention of this application to avoid blurring the purpose of this section, the abstract of the specification and the title of the invention, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0007] In view of the above existing problems, the present invention is proposed.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions: acquiring data from an electronic medical record system, a laboratory information system and a medical test wearable device through a multi-source data acquisition technology, and performing data preprocessing on the acquired data;

[0009] Using a sliding window mechanism, real-time statistical analysis is performed on the pre-processed data to generate analysis results;

[0010] Inputting the analysis results into an anomaly detection model constructed based on an exponentially weighted moving average to calculate control limits, and identifying abnormal data points based on the calculation results;

[0011] If the abnormal data point is identified, the collected data has abnormal conditions, and the abnormal information will be immediately sent to relevant personnel through the preset API call SMS and email sending services. At the same time, the management system will record the abnormal event and generate an audit log.

[0012] As a preferred solution of the clinical trial information management method based on big data described in the present invention, the multi-source data acquisition technology realizes data acquisition by establishing an API interface to connect with the electronic medical record system and the laboratory information system, wherein:

[0013] Establish standardized API interfaces with electronic medical record systems, laboratory information systems, medical image archiving and communication systems, and wearable devices to achieve automated data collection;

[0014] Embed sensors in wearable devices and medical instruments used by patients to collect biological signals and environmental data in real time through IoT technology;

[0015] Based on HL7 and FHIR medical data exchange standards, ensure data collection compatibility across systems;

[0016] The collected data is stored in a temporary buffer in a structured, unstructured or semi-structured form, wherein:

[0017] Structured data at least includes basic information about patients and laboratory test results;

[0018] Unstructured data at least includes medical images, doctors’ diagnosis reports, and pathological slice images;

[0019] Semi-structured data at least includes biological signals recorded by wearable devices and medical device log files.

[0020] As a preferred solution of the clinical trial information management method based on big data described in the present invention, basic information and test results of patients are collected from the electronic medical record system, wherein the basic information of patients at least includes name, gender, age, and medical history, and the test results at least include blood test results;

[0021] Collecting experimental data from the laboratory information system, wherein the experimental data at least includes test reports and imaging examination results;

[0022] Physiological data is obtained from the wearable device, where the physiological data at least includes heart rate, blood pressure, and activity level.

[0023] As a preferred solution of the clinical trial information management method based on big data described in the present invention, data preprocessing is performed on the collected data, including:

[0024] Mean imputation method was used to handle missing values, and Z-score method was used to detect and remove outliers;

[0025] Standardize date and time formats, standardize units, and use the same coding system to classify diseases;

[0026] The SHA-256 hash algorithm is used to convert patient identification information into irrelevant identifiers;

[0027] The output is a standardized and anonymized dataset with missing values ​​and outliers removed, in the form of a standardized structured data table.

[0028] As a preferred solution of the clinical trial information management method based on big data described in the present invention, the sliding window mechanism is used to perform real-time statistical analysis on the pre-processed data, including:

[0029] Set the window size to N;

[0030] Extract the latest N data points from the preprocessed time series data for analysis;

[0031] The input data format is a time series data table containing multiple feature columns, and the mean and standard deviation within the window are calculated.

[0032] As a preferred solution of the clinical trial information management method based on big data described in the present invention, the mathematical expression formula for calculating the mean and standard deviation within the window is as follows:

[0033]

[0034] Among them, μ t is the mean value in the window, σ t is the standard deviation, x t-i It is the data value of the current time point and the previous N time points.

[0035] As a preferred solution of the clinical trial information management method based on big data described in the present invention, the analysis results are input into an anomaly detection model based on exponentially weighted moving average to calculate the control limits, and abnormal data points are identified according to the calculation results, including:

[0036] EWMA t =α·X t +(1-α)·EWMAt-1

[0037] The control limits include an upper control limit and a lower control limit. The upper control limit UCL and the lower control limit LCL are set as:

[0038] UCL=μ t +kσ t

[0039] LCL=μ t -kσ t

[0040] Among them, EWMA t is the exponentially weighted moving average at the current time point, x t is the current data point, α is the smoothing factor, EWMA t-1 is the exponentially weighted moving average of the previous time point, and the value of k is 3, which is the triple standard deviation principle;

[0041] If EWMA t ≥UCL or LCL, it is marked as an abnormal data point.

[0042] As a preferred solution of the clinical trial information management system based on big data described in the present invention, it includes:

[0043] one or more processors;

[0044] A memory storing operable instructions, wherein when the instructions are executed by the one or more processors, the one or more processors perform operations, wherein the operations include the process of the aforementioned clinical trial information management method based on big data.

[0045] As a preferred solution of the clinical trial information management system based on big data described in the present invention, the system also includes a computer-readable medium for storing software, characterized in that: the software includes instructions that can be executed by one or more computers, and the instructions enable the one or more computers to perform operations through such execution, and the operations include the process of the aforementioned clinical trial information management method based on big data.

[0046] Beneficial effects of the present invention:

[0047] 1. Effective integration of multiple data sources, covering both structured and unstructured data, improves the comprehensiveness of data and ensures the reliability of data quality. Through standardization and anonymization, format differences between data can be eliminated to protect patient privacy;

[0048] 2. By setting the window size, the latest data points are extracted from the preprocessed data, and the real-time mean and standard deviation are calculated. Real-time statistical analysis enables researchers to quickly capture the changing trends of data and identify potential clinical abnormalities in a timely manner. Its dynamic response capability can adapt to changes in the clinical environment and ensure the timeliness and practicality of the data;

[0049] 3. By comparing the current data points with the control limits, potential abnormal data points can be effectively identified, thereby improving the safety of clinical trials. Through quantitative standards, the deviation of human judgment is reduced, ensuring the reliability of abnormal detection;

[0050] 4. Through the instant notification mechanism, relevant personnel can respond quickly to abnormal situations and reduce potential risks. The system's automatic recording and audit log generation functions not only improve management transparency, but also provide a basis for subsequent audits and compliance inspections. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0052] Figure 1 This is a flow chart of a clinical trial information management method based on big data shown in the present invention;

[0053] Figure 2 A schematic diagram of heart rate and blood pressure monitoring shown in the present invention;

[0054] Figure 3 It is a schematic diagram of response time comparison shown in the present invention. DETAILED DESCRIPTION

[0055] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0056] Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without making any creative work should fall within the scope of protection of the present invention.

[0057] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0058] According to an embodiment of the present invention, Figure 1 The flowchart shown is a clinical trial information management method based on big data, which specifically includes the following steps:

[0059] S1. Obtain data from electronic medical record systems, laboratory information systems, and wearable devices for medical trials through multi-source data acquisition technology, and perform data preprocessing on the collected data;

[0060] S2. Use the sliding window mechanism to perform real-time statistical analysis on the preprocessed data and generate analysis results;

[0061] S3, inputting the analysis results into an anomaly detection model based on exponentially weighted moving average to calculate the control limits, and identifying abnormal data points according to the calculation results;

[0062] S4. If an abnormal data point is identified, the collected data is abnormal, and the abnormal information is immediately sent to the relevant personnel through the preset API call SMS and email sending service. At the same time, the management system will record the abnormal event and generate an audit log.

[0063] Furthermore, in order to better illustrate the specific process of implementing the method of the present invention, this embodiment provides a detailed description of a clinical trial information management method based on big data provided by an embodiment of the present invention in combination with an actual clinical trial application scenario.

[0064]

Data collection

[0065] Obtain basic information and physiological data of clinical trial patients in real time to ensure the accuracy and safety of the trial;

[0066] Data sources include electronic medical record systems (EMR), laboratory information systems (LIS), and wearable devices (e.g., smart watches, heart rate monitors);

[0067] Set up API interface: Establish API interface with electronic medical record system (EMR) and laboratory information system (LIS), and use RESTful architecture for data interaction;

[0068] Exemplary data types and parameters collected by the EMR system:

[0069] Basic patient information: name (such as "Zhang San"), age (such as "45 years old"), medical history (such as "hypertension");

[0070] Test results: Blood test results (such as "white blood cell count: 7.5 × 10 9 / L”);

[0071] Exemplary data types and parameters collected by the LIS system:

[0072] Experimental data: laboratory test results (such as "liver function test"), imaging test results (such as "CT images"); exemplary data types and parameters collected by wearable devices:

[0073] Physiological data: heart rate (such as "75bpm"), blood pressure (such as "120 / 80mmHg"), activity level (such as "number of steps: 5000");

[0074] Data Storage:

[0075] The collected data is divided into structured (numerical values, categories, such as patient information) and unstructured (text, images, such as imaging examinations) and stored in a temporary buffer;

[0076] The final data format of the result expression form is a structured data table containing patient information and clinical parameters, and an unstructured data file of the image; as shown in Table 1 below:

[0077] Table 1. Structured data table of patient information and clinical parameters

[0078] Patient ID age gender blood pressure Heart rate Medical history 001 45 male 120 / 80 mmHg 75 diabetes

[0079]

Data preprocessing

[0080] Missing value processing: Use mean imputation to handle missing values. For example, if a patient's blood pressure data is missing, you can calculate the mean of all valid blood pressure data (such as "125mmHg") and use this value to fill in the missing data.

[0081] Outlier detection: Use the Z-score method to detect outliers. Assuming that the mean of blood pressure data is "120mmHg" and the standard deviation is "10mmHg", if a patient's blood pressure is "150mmHg":

[0082]

[0083] If the value of Z is greater than 3, it is marked as an outlier;

[0084] Unify date and time formats: unify all date formats into "YYYY-MM-DD", such as "2024-10-01", and unify time formats into "HH:MM", such as "12:30:00";

[0085] Standardized units: convert all physiological parameters into standard units, for example: blood pressure (mmHg): convert to "120 / 80mmHg", heart rate (bpm): keep it as "75bpm";

[0086] Coding system processing: unify disease classification into the same code, for example, use ICD-10 code, such as "E11" for "type 2 diabetes";

[0087] Result expression: The unified data will form a standardized data table, with each row corresponding to a patient and each column corresponding to a standardized parameter; as shown in Table 2 below:

[0088] Table 2. Data standardization table

[0089] Patient ID date blood pressure Heart rate Disease Code 001 2024-10-01 120 / 80 mmHg 75 E11

[0090] Select anonymization method: hash patient identity information using the SHA-256 hash algorithm;

[0091] Hashing: For example, the patient's name "Zhang San" is hashed with SHA-256 to generate a unique unrelated identifier;

[0092] Data output: replace the original sensitive information with irrelevant identifiers, such as patient name and ID number; result expression: the anonymized data table still retains all other information, but the sensitive information is replaced; as shown in Table 3 below:

[0093] Table 3. Anonymized data table

[0094]

[0095]

Real-time statistical analysis

[0096] Set window size: Select the window size N (for example, N=30, which means the most recent 30 data points);

[0097] Initialize the window: Set the time series data to an array or data frame with timestamp as index;

[0098] Window sliding: As new data arrives, the window slides forward and updates the most recent N data points;

[0099] For example, extract the latest 30 heart rate data from the data series;

[0100] The heart rate data in the window is an array or list, such as "[72,75,78,...,74]";

[0101] For example, if the current time point is T, the data in the window is:

[0102] Window Data

[0103] =[72,75,78,76,80,74,73,75,77,78,76,75,74,73,72,71,70,74,75,76,78,79,80,81,82,75,74,

[0104] 73,72,75]

[0105] Calculate the mean μ and standard deviation σ of the heart rate in the window:

[0106]

[0107] It should be noted that by calculating the mean and standard deviation, the subsequent anomaly detection model can determine whether the data is within a reasonable range, thereby providing an accurate threshold for anomaly detection;

[0108] By setting the window size N and extracting the latest N data points from the preprocessed time series data for analysis, the dynamic changes of the data can be quickly captured. Compared with traditional static analysis methods, this method significantly improves the response speed and flexibility to changes in clinical data, and is particularly suitable for rapidly changing medical environments.

[0109]

Anomaly Detection

[0110] Exponentially Weighted Moving Average (EWMA) calculation:

[0111] Calculate the exponentially weighted moving average at the current time point:

[0112] EWMA t =α·X t +(1-α)·EWMA t-1

[0113] Define α = 0.2, assuming the previous EWMA value is "75bpm": EWMA t =0.2·80+0.8·75=76bpm;

[0114] Set Control Limits: Set the Upper Control Limit (UCL) and Lower Control Limit (LCL):

[0115] UCL=EWMA+k·σ=76+3·2.5=83.5bpm

[0116] LCL=EWMA-k·σ=76-3·2.5=68.5bpm

[0117] Abnormal data point identification: If the current heart rate data (such as "85bpm") is greater than UCL, it is marked as an abnormal data point;

[0118] For example, the current data heart rate is 82bpm, assuming that the EWMA is 76bpm and the standard deviation is 2bpm, then:

[0119] UCL=76+3*2=82bpm

[0120] LCL=76-3*2=70bpm

[0121] Since 82 bpm ≥ UCL, it is marked as an abnormal data point;

[0122] It is not difficult to understand that inputting the statistical analysis results into the EWMA model for control limit calculation can adapt to the time-varying characteristics of the data. Compared with the traditional fixed threshold method, the adaptive ability of the EWMA model enables it to more effectively identify abnormal data points. By dynamically adjusting the control limits, the model can significantly reduce the false alarm rate and improve the accuracy of detection;

[0123] By setting control limits (UCL and LCL), once a data point exceeds the range, it can be marked as an anomaly. This method ensures the efficiency of anomaly detection, especially in clinical trials with large amounts of data and rapid changes. Timely identification and handling of abnormal situations helps to ensure the safety and effectiveness of the trial;

[0124]

Abnormal warning and recording

[0125] Abnormal notification: Call SMS and email sending services through preset APIs to send abnormal information to researchers (such as "the patient's heart rate is abnormal, the current heart rate is 85bpm");

[0126] For example, the notification content sent is:

[0127] SMS content: "An abnormal heart rate of patient 001 has been detected, the current value is 82bpm, and the event has been recorded";

[0128] Event log example:

[0129] Time: 2024-10-01 10:30;

[0130] Patient ID: 001;

[0131] Abnormal type: abnormal heart rate;

[0132] Current value: 82bpm;

[0133] Audit log recording: Record abnormal events, including abnormal type, time and processing status, and generate audit logs for subsequent analysis.

[0134] Preferably, through the above implementation process, the big data-based clinical trial information management method provided in this embodiment can effectively collect, preprocess and analyze data, identify abnormal situations in real time, and notify relevant personnel in a timely manner to ensure the safety and efficiency of clinical trials.

[0135] In order to better verify the technical effect of the method of the present invention, this embodiment selects the traditional method and the method of the present invention for comparative testing, and compares the test results by means of scientific demonstration to verify the real effect of the method.

[0136] Traditional technical solutions usually adopt methods based on static data analysis, which often face defects such as delayed data updates, untimely processing of abnormal data, and lack of early warning mechanisms. These defects lead to inefficient management of clinical trial data and inaccurate decision-making basis, thus affecting the reliability and effectiveness of clinical trials. For example, in traditional methods, data collection relies on manual input, which is prone to human errors, and data processing delays make real-time monitoring impossible.

[0137] In order to verify that the method of the present invention has higher real-time performance, accuracy and response speed than the traditional method, this embodiment will use the traditional data processing method and the method of the present invention to conduct real-time measurement and comparison of the data management efficiency of the simulated clinical trial management system; the test objects are heart rate, blood pressure and response time of abnormal event detection.

[0138] The experimental conditions are:

[0139] Number of participants: 60;

[0140] Measurement parameters: heart rate (bpm), blood pressure (mmHg), abnormal event markers;

[0141] Experimental period: 1 hour;

[0142] Data collection frequency: once every 5 seconds;

[0143] Experimental process:

[0144] Traditional method: Data is collected through manual recording and input; heart rate and blood pressure are manually recorded by researchers every 5 seconds and entered into the database;

[0145] Data analysis uses static statistical methods and generates statistical reports every 15 minutes;

[0146] The processing and feedback of abnormal data are delayed, and relevant personnel are not notified in time;

[0147] The method of the present invention: data is automatically collected from electronic medical records and wearable device data through API, and heart rate and blood pressure are automatically recorded every 5 seconds;

[0148] Analyze data in real time and use the sliding window mechanism to calculate the mean and standard deviation of current heart rate and blood pressure;

[0149] Apply an anomaly detection model based on exponentially weighted moving average (EWMA) to identify abnormal data in real time and notify relevant personnel via SMS and email.

[0150] Reference Figure 2 and Figure 3 It should be noted that, in this experiment, a total of 6 participants were selected, and each participant continuously monitored his heart rate and blood pressure within 60 minutes. The data collection frequency was once every 5 seconds. Such a frequency ensures that subtle changes in heart rate and blood pressure can be captured; through the above experiment, it can be observed that the heart rate fluctuates between 75bpm and 82bpm, and the blood pressure varies between 115 / 76mmHg and 130 / 85mmHg. The design of this experiment is to verify the effectiveness and real-time performance of the method of the present invention in actual clinical data processing.

[0151] For monitoring of heart rate and blood pressure, such as Figure 2 The results shown indicate that the method of the present invention can record and analyze data in real time, ensuring accurate transmission of information and timely feedback of abnormal situations. Compared with traditional methods, monitoring of heart rate and blood pressure not only improves the efficiency of data collection, but also shortens the response time to abnormal situations, ultimately improving the timeliness and effectiveness of clinical decision-making.

[0152] Reference Figure 3 In the comparison of response time, the traditional method takes 47.5 seconds, while the method of the present invention takes only 3.5 seconds. This significant time difference proves the high efficiency of the method of the present invention, which can provide medical personnel with faster feedback and handle possible abnormal events in a timely manner, thereby effectively reducing potential clinical risks.

[0153] It should be noted that other aspects disclosed in the embodiments of the present invention also propose a clinical trial information management system based on big data, including: one or more processors and a memory.

[0154] The memory is used to store operable instructions, which, when executed by the one or more processors, cause the one or more processors to perform operations, including the process of the clinical trial information management method based on big data in the aforementioned embodiment, especially Figure 1 The process of the method shown.

[0155] The system also includes a computer-readable medium storing software, the software including instructions executable by one or more computers, the instructions causing one or more computers to perform operations by such execution, the operations including the process of the clinical trial information management method based on big data of the aforementioned embodiment, in particular Figure 1 The process of the method shown.

[0156] It should be appreciated that embodiments of the present invention can be implemented or carried out by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable memory.

[0157] The method may be implemented in a computer program using standard programming techniques, including a non-transitory computer-readable storage medium configured with a computer program, wherein the storage medium so configured causes a computer to operate in a specific and predefined manner.

[0158] Each program can be implemented in a high-level procedural or object-oriented programming language to communicate with a computer system, however, the program can be implemented in assembly or machine language if desired.

[0159] In any case, the language may be a compiled or interpreted language.

[0160] Furthermore, the program can be run on an application specific integrated circuit programmed for this purpose.

[0161] The processes described herein (or variations and / or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) that is executed collectively on one or more processors, by hardware, or a combination thereof. The computer program includes a plurality of instructions that can be executed by one or more processors.

[0162] Further, the method may be implemented in any type of computing platform operably connected to a suitable computer, including but not limited to a personal computer, a minicomputer, a mainframe, a workstation, a network or distributed computing environment, a separate or integrated computer platform, or in communication with a charged particle tool or other imaging device.

[0163] Various aspects of the present invention may be implemented in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optical read and / or write storage media, RAM, ROM, etc., so that it can be read by a programmable computer, which, when the storage medium or device is read by the computer, can be used to configure and operate the computer to perform the processes described herein.

[0164] Additionally, the machine-readable code, or portions thereof, can be transmitted over a wired or wireless network.

[0165] The invention described herein includes these and other various types of non-transitory computer-readable storage media when such media include instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor.

[0166] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A clinical trial information management method based on big data, characterized in that: include: Acquire data from electronic medical record systems, laboratory information systems, and medical trial wearable devices through multi-source data acquisition technology, and perform data preprocessing on the acquired data; Using a sliding window mechanism, real-time statistical analysis is performed on the pre-processed data to generate analysis results; Inputting the analysis results into an anomaly detection model constructed based on an exponentially weighted moving average to calculate control limits, and identifying abnormal data points based on the calculation results; If the abnormal data point is identified, the collected data has abnormal conditions, and the abnormal information will be immediately sent to relevant personnel through the preset API call SMS and email sending services. At the same time, the management system will record the abnormal event and generate an audit log.

2. The clinical trial information management method based on big data according to claim 1, characterized in that: The multi-source data collection technology is to achieve data collection by establishing an API interface to connect with the electronic medical record system and the laboratory information system, where: Establish standardized API interfaces with electronic medical record systems, laboratory information systems, medical image archiving and communication systems, and wearable devices to achieve automated data collection; Embed sensors in wearable devices and medical instruments used by patients to collect biological signals and environmental data in real time through IoT technology; Based on HL7 and FHIR medical data exchange standards, ensure data collection compatibility across systems; The collected data is stored in a temporary buffer in a structured, unstructured or semi-structured form, wherein: Structured data at least includes basic information about patients and laboratory test results; Unstructured data at least includes medical images, doctors’ diagnosis reports, and pathological slice images; Semi-structured data at least includes biological signals recorded by wearable devices and medical device log files.

3. The clinical trial information management method based on big data according to claim 1, characterized in that: Collecting basic patient information and test results from the electronic medical record system, wherein the basic patient information includes at least name, gender, age, and medical history, and the test results include at least blood test results; Collecting experimental data from the laboratory information system, wherein the experimental data at least includes test reports and imaging examination results; Physiological data is obtained from the wearable device, where the physiological data at least includes heart rate, blood pressure, and activity level.

4. The clinical trial information management method based on big data according to claim 1 or 3, characterized in that: Perform data preprocessing on the collected data, including: Mean imputation method was used to handle missing values, and Z-score method was used to detect and remove outliers; Standardize date and time formats, standardize units, and use the same coding system to classify diseases; The SHA-256 hash algorithm is used to convert patient identification information into irrelevant identifiers; The output is a standardized and anonymized dataset with missing values ​​and outliers removed, in the form of a standardized structured data table.

5. The clinical trial information management method based on big data according to claim 1, characterized in that: The method of using a sliding window mechanism to perform real-time statistical analysis on the pre-processed data includes: Set the window size to N; Extract the latest N data points from the preprocessed time series data for analysis; The input data format is a time series data table containing multiple feature columns, and the mean and standard deviation within the window are calculated.

6. The clinical trial information management method based on big data according to claim 5, characterized in that: The mathematical formula for calculating the mean and standard deviation within the window is as follows: Among them, μ t is the mean value in the window, σ t is the standard deviation, x t-i It is the data value of the current time point and the previous N time points.

7. The clinical trial information management method based on big data according to claim 1, characterized in that: The analysis results are input into an anomaly detection model based on an exponentially weighted moving average to calculate the control limits, and the abnormal data points are identified according to the calculation results, including: EWMA t =α·X t +(1-a)·EWMA t-1 The control limits include an upper control limit and a lower control limit. The upper control limit UCL and the lower control limit LCL are set as: UCL=μ t +kσ t LCL=μ t -kσ t Among them, EWMA t is the exponentially weighted moving average at the current time point, x is the current data point, α is the smoothing factor, EWMA t-1 is the exponentially weighted moving average of the previous time point, and the value of k is 3, which is the triple standard deviation principle; If EWMA t ≥UCL or LCL, it is marked as an abnormal data point.

8. A clinical trial information management system based on big data, characterized in that: include: one or more processors; A memory storing operable instructions, wherein when the instructions are executed by the one or more processors, the one or more processors perform operations, wherein the operations include the process of the clinical trial information management method based on big data as described in any one of claims 1 to 7.

9. A computer-readable medium storing software, characterized in that: The software includes instructions that can be executed by one or more computers, and the instructions enable the one or more computers to perform operations through such execution, and the operations include the process of the clinical trial information management method based on big data as described in any one of claims 1 to 7.

Images