Inflammatory bowel disease patient psychological trouble risk prediction system based on machine learning
By integrating static and dynamic data through a machine learning-based system and using an LSTM neural network to process psychological distress risk scores, the accuracy problem of psychological distress assessment in patients with inflammatory bowel disease in existing technologies is solved, and effective prediction and risk management of future psychological states are achieved.
Patent Information
- Application Number
- CN202510635129.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-16
- Publication Date
- 2025-09-09
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In existing technologies, the assessment of psychological distress in patients with inflammatory bowel disease has a high rate of missed diagnosis, is unable to capture changes in psychological state during the disease's fluctuation period, and ignores the interaction between biomedical indicators and social environmental factors, resulting in inaccurate assessments.
A machine learning-based system is used to integrate patients' static attributes, dynamic psychological assessment data, and disease activity index. An LSTM neural network is used to process the time series data of the psychological distress risk score. Combined with the temporal persistence and fluctuation amplitude of the psychological distress risk score, it provides objective quantitative indicators to reduce the subjective judgment bias of medical staff.
It achieves continuous and traceable risk management of the psychological state of patients with inflammatory bowel disease, effectively predicts future psychological state trends, and reduces the missed diagnosis rate and subjective judgment bias.
Smart Images
Figure CN120613115A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of psychological risk assessment, and in particular to a machine learning-based psychological distress risk prediction system for patients with inflammatory bowel disease. Background Art
[0002] Insufficient attention has been paid to the psychological distress of patients with inflammatory bowel disease both at home and abroad. Clinically, scales such as PHQ-9, SDS, and IBD-DS are often used for manual assessment of patients. However, these scales have certain limitations: manual screening is inefficient, with studies showing that more than 40% of moderate to severe patients are missed; static assessments cannot capture changes in the patient's psychological state during the fluctuation period of the disease; and psychological assessments ignore the interaction between the patient's biomedical indicators and social environmental factors, making it impossible to fundamentally and accurately assess the patient's psychological condition. Summary of the Invention
[0003] In response to the shortcomings of the existing technology, the present invention proposes a psychological distress risk prediction system for patients with inflammatory bowel disease based on machine learning. The present invention integrates the patient's static attributes, dynamic psychological assessment data, and disease activity index; uses an LSTM neural network to process the time series data of the psychological distress risk score, which can capture long-term dependencies and effectively predict future psychological state trends; the psychological distress risk score combines time persistence and fluctuation amplitude to provide objective quantitative indicators, reducing the subjective judgment bias of medical staff, and ensuring the continuity and traceability of risk management.
[0004] To achieve the above object, the technical solution of the present invention is as follows:
[0005] A machine learning-based psychological distress risk prediction system for patients with inflammatory bowel disease includes a cloud database, an information collection port, an information analysis port, and an information feedback port. The cloud database is used to store historical psychological assessment data, disease activity index, social support score, medication records, and treatment stage information of IBD patients; the information collection port is used to collect patients' static attribute data and dynamic psychological assessment data; the information analysis port is used to calculate the psychological distress risk score and the psychological distress change index; and the information feedback port is used to send risk warning signals or personalized intervention suggestions to medical staff.
[0006] A further improvement of the present invention is that the information collection port includes a patient attribute information collection module and a real-time psychological data collection module, the patient attribute information collection module is used to collect the patient's electronic medical record information; the patient's electronic medical record information includes age, gender, IBD type, course of disease, complications, current medication regimen, surgical history, and nutritional support status; the real-time psychological data collection module is used to collect the IBD patient's psychological pain score, social support assessment score, quality of life score, and emotional expression in the patient's medical diary.
[0007] A further improvement of the present invention is that the information analysis port includes a data retrieval module, a risk analysis module and a trend prediction module. The data retrieval module is used to retrieve the psychological distress scores, social support assessment scores, quality of life scores of similar patients matching the current patient in the cloud database, as well as the emotional expressions in the patient's medical diary; the risk analysis module is used to run the psychological distress risk score calculation strategy to calculate the psychological distress risk score; the trend prediction module is used to run the LSTM neural network model to predict future psychological distress risk trends.
[0008] A further improvement of the present invention is that the risk analysis module runs a psychological distress risk score calculation strategy, and the psychological distress risk score calculation strategy includes the following specific steps:
[0009] S11. Extract the time-varying curve of the patient's psychological assessment data during the current treatment phase, and obtain the range of changes in psychological scores for similar patients as a benchmark range;
[0010] S12. Calculate the psychological distress risk score. The calculation formula for the psychological distress risk score is:
[0011]
[0012] Among them, MDS i represents the patient's psychological distress risk score at the i-th assessment, k represents the k-th psychological indicator, ΔT k Indicates the number of days during the current evaluation period that the score of the kth item exceeds the benchmark range, ΔT max represents the total number of days in the evaluation period, ΔS k represents the standard deviation of the k-th score during the evaluation period, s norm It represents the average standard deviation of scores of similar patients, α and β are weight factors, and α+β=1.
[0013] S13, preset risk threshold MDS0, compare the patient's psychological distress risk score MDS at the i-th assessment i The relationship between the risk threshold MDS0 and the risk threshold MDS0 is as follows: i When the risk threshold MDS0 is greater than or equal to the risk threshold, a high-risk warning signal is sent to the information feedback port. i When the risk threshold MDS0 is less than the threshold, the warning is not activated and the patient's psychological distress risk score MDS i Transmitted to the trend prediction module.
[0014] A further improvement of the present invention is that the trend prediction module predicts the future psychological distress risk trend, and the predicting of the future psychological distress risk trend includes the following specific steps:
[0015] S21. Obtain the patient's psychological distress risk score from the previous i assessments, divide this data into a 70% training set and a 30% test set, and construct the input MDS i-2 、MDS i-1 、MDS i , the output is MDS i+1 The time series prediction model is trained using 70% of the training set to obtain the initial time series prediction model.
[0016] S22. Test the initial time series prediction model using a 30% coefficient test set, optimize the model parameters using mean square error, select the model with the smallest prediction error on the test set as the final time series prediction model, and predict the psychological distress risk score for the i+1th assessment;
[0017] S23. Output the predicted psychological distress risk score for the (i+1)th assessment.
[0018] A further improvement of the present invention is that the predicting of future psychological distress risk trends further includes:
[0019] S24. Extract the MDS score for the psychological distress risk at the i+1th assessment i+1 ;
[0020] S25. Calculate the patient's psychological distress change index, where the calculation formula for the psychological distress change index is:
[0021]
[0022] S26: Determine whether it is necessary to send a decision adjustment signal to the information feedback port.
[0023] A further improvement of the present invention is that the time series prediction model in S22 is an LSTM neural network model.
[0024] A further improvement of the present invention is that the specific content of S26 is: presetting a DTI threshold, when the psychological distress change index DTI is greater than the DTI threshold, continuing to execute the current nursing strategy; when the psychological distress change index DTI is less than or equal to the DTI threshold, sending a decision adjustment signal to the information feedback port.
[0025] The technical effects of the present invention are as follows:
[0026] A machine learning-based psychological distress risk prediction system for patients with inflammatory bowel disease is proposed. The invention integrates the patient's static attributes, dynamic psychological assessment data, and disease activity index; uses an LSTM neural network to process the time series data of the psychological distress risk score, which can capture long-term dependencies and effectively predict future psychological state trends; the psychological distress risk score combines time persistence and fluctuation amplitude to provide objective quantitative indicators, reducing the subjective judgment bias of medical staff and ensuring the continuity and traceability of risk management. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments made with reference to the following drawings:
[0028] Figure 1 This is a structural diagram of the machine learning-based system for predicting the risk of psychological distress in patients with inflammatory bowel disease. DETAILED DESCRIPTION
[0029] Example 1
[0030] This embodiment proposes a machine learning-based psychological distress risk prediction system for patients with inflammatory bowel disease. The present invention integrates the patient's static attributes, dynamic psychological assessment data, and disease activity index; uses an LSTM neural network to process time series data of the psychological distress risk score, which can capture long-term dependencies and effectively predict future psychological state trends; the psychological distress risk score combines time persistence and fluctuation amplitude to provide an objective quantitative indicator, reducing the subjective judgment bias of medical staff, and ensuring the continuity and traceability of risk management.
[0031] like Figure 1 As shown, a psychological distress risk prediction system for patients with inflammatory bowel disease based on machine learning includes a cloud database, an information collection port, an information analysis port and an information feedback port. The cloud database is used to store psychological assessment data, disease activity index, social support score, medication records and treatment stage information of IBD patients; the information collection port is used to collect patients' static attribute data and dynamic psychological assessment data; the information analysis port is used to calculate the psychological distress risk score and the psychological distress change index; the information feedback port is used to send risk warning signals or personalized intervention suggestions to medical staff.
[0032] In this embodiment, the information collection port includes a patient attribute information collection module and a real-time psychological data collection module. The patient attribute information collection module is used to collect the patient's electronic medical record information; the patient's electronic medical record information includes age, gender, IBD type, course of disease, complications, current medication regimen, surgical history, and nutritional support status; the real-time psychological data collection module is used to collect the patient's psychological pain score, social support assessment score, quality of life score, and emotional expression in the patient's medical diary.
[0033] In this embodiment, the information analysis port includes a data retrieval module, a risk analysis module and a trend prediction module. The data retrieval module is used to retrieve the psychological distress scores, social support assessment scores, quality of life scores of similar patients matching the current patient in the cloud database, as well as the emotional expressions in the patient's medical diary; the risk analysis module is used to run the psychological distress risk score calculation strategy to calculate the psychological distress risk score; the trend prediction module is used to run the LSTM neural network model to predict future psychological distress risk trends.
[0034] In this embodiment, the risk analysis module executes a psychological distress risk score calculation strategy, which includes the following specific steps:
[0035] S11. Extract the time-varying curve of the patient's psychological assessment data during the current treatment phase, and obtain the range of changes in psychological scores for similar patients as a benchmark range;
[0036] S12. Calculate the psychological distress risk score. The calculation formula for the psychological distress risk score is:
[0037]
[0038] Among them, MDS i represents the patient's psychological distress risk score at the i-th assessment, k represents the k-th psychological indicator, ΔT k Indicates the number of days during the current evaluation period that the score of the kth item exceeds the benchmark range, ΔT max represents the total number of days in the evaluation period, ΔS k represents the standard deviation of the k-th score during the evaluation period, s norm It represents the average value of the standard deviation of scores of similar patients, α and β are weight factors, and α+β=1.
[0039] S13, preset risk threshold MDS0, compare the patient's psychological distress risk score MDS at the i-th assessment i The relationship between the risk threshold MDS0 and the risk threshold MDS0 is as follows: i When the risk threshold MDS0 is greater than or equal to the risk threshold, a high-risk warning signal is sent to the information feedback port.i When the risk threshold MDS0 is less than the threshold, the warning is not activated and the patient's psychological distress risk score MDS i Transmitted to the trend prediction module.
[0040] In this embodiment, the trend prediction module predicts the future psychological distress risk trend, and the prediction of the future psychological distress risk trend includes the following specific steps:
[0041] S21. Obtain the patient's psychological distress risk score from the previous i assessments, divide this data into a 70% training set and a 30% test set, and construct the input MDS i-2 、MDS i-1 、MDS i , the output is MDS i+1 The time series prediction model is trained using 70% of the training set to obtain the initial time series prediction model.
[0042] S22. Test the initial time series prediction model using a 30% coefficient test set, optimize the model parameters using mean square error, select the model with the smallest prediction error on the test set as the final time series prediction model, and predict the psychological distress risk score for the i+1th assessment;
[0043] S23. Output the predicted psychological distress risk score for the (i+1)th assessment.
[0044] In this embodiment, predicting the future risk trend of psychological distress further includes:
[0045] S24. Extract the MDS score for the psychological distress risk at the i+1th assessment i+1 ;
[0046] S25. Calculate the patient's psychological distress change index, where the calculation formula for the psychological distress change index is:
[0047]
[0048] S26: Determine whether it is necessary to send a decision adjustment signal to the information feedback port.
[0049] In this embodiment, the time series prediction model in S22 is an LSTM neural network model.
[0050] In this embodiment, the specific content of S26 is: presetting the DTI threshold, when the psychological distress change index DTI is greater than the DTI threshold, continuing to execute the current nursing strategy; when the psychological distress change index DTI is less than or equal to the DTI threshold, sending a decision adjustment signal to the information feedback port.
[0051] It should be noted here that the patient's static attributes, dynamic psychological assessment data, and disease activity index are integrated; the LSTM neural network is used to process the time series data of the psychological distress risk score, which can capture long-term dependencies and effectively predict future psychological state trends; the psychological distress risk score combines time persistence and fluctuation amplitude to provide objective quantitative indicators, reducing the subjective judgment bias of medical staff and ensuring the continuity and traceability of risk management.
[0052] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0053] It should be understood that determining B based on A does not mean determining B based solely on A. B can also be determined based on A and / or other information.
[0054] The above embodiments can be implemented in whole or in part through software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions according to the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.
[0055] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.
[0056] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0057] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only one type. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0058] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.
[0059] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0060] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
[0061] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.
Claims
1. A machine learning-based psychological distress risk prediction system for patients with inflammatory bowel disease, characterized by: The system includes a cloud database, an information collection port, an information analysis port, and an information feedback port. The cloud database is used to store psychological assessment data, disease activity index, social support score, medication records, and treatment stage information of IBD patients; The information collection port is used to collect static attribute data and dynamic psychological assessment data of patients; the information analysis port is used to calculate the psychological distress risk score and the psychological distress change index; The information feedback port is used to send risk warning signals or personalized intervention suggestions to medical staff.
2. The machine learning-based psychological distress risk prediction system for patients with inflammatory bowel disease according to claim 1, characterized in that: The information collection port includes a patient attribute information collection module and a real-time psychological data collection module. The patient attribute information collection module is used to collect patient electronic medical record information; the patient electronic medical record information includes age, gender, IBD type, course of disease, complications, current medication regimen, surgical history, and nutritional support status; the real-time psychological data collection module is used to collect IBD patients' psychological pain scores, social support assessment scores, quality of life scores, and emotional expressions in patients' medical diaries.
3. The machine learning-based psychological distress risk prediction system for patients with inflammatory bowel disease according to claim 2, characterized in that: The information analysis port includes a data retrieval module, a risk analysis module, and a trend prediction module. The data retrieval module is used to retrieve the psychological distress scores, social support assessment scores, quality of life scores of similar patients matching the current patient in the cloud database, as well as the emotional expressions in the patient's medical diary; The risk analysis module is used to execute the psychological distress risk score calculation strategy to calculate the psychological distress risk score; The trend prediction module is used to run the LSTM neural network model to predict future psychological distress risk trends.
4. The machine learning-based psychological distress risk prediction system for patients with inflammatory bowel disease according to claim 3, characterized in that: The risk analysis module executes a psychological distress risk score calculation strategy, which includes the following specific steps: S11. Extract the time-varying curve of the patient's psychological assessment data during the current treatment phase, and obtain the range of changes in psychological scores for similar patients as a benchmark range; S12. Calculate the psychological distress risk score. The calculation formula for the psychological distress risk score is: Among them, MDS i represents the patient's psychological distress risk score at the i-th assessment, k represents the k-th psychological indicator, ΔT k Indicates the number of days during the current evaluation period that the score of the kth item exceeds the benchmark range, ΔT max represents the total number of days in the evaluation period, ΔS k represents the standard deviation of the k-th score during the evaluation period, s norm It represents the average value of the standard deviation of scores of similar patients, α and β are weight factors, and α+β=1. S13, preset risk threshold MDS0, compare the patient's psychological distress risk score MDS at the i-th assessment i The relationship between the risk threshold MDS0 and the risk threshold MDS0 is as follows: i When the risk threshold MDS0 is greater than or equal to the risk threshold, a high-risk warning signal is sent to the information feedback port. i When the risk threshold MDS0 is less than the threshold, the warning is not activated and the patient's psychological distress risk score MDS i Transmitted to the trend prediction module.
5. The machine learning-based psychological distress risk prediction system for patients with inflammatory bowel disease according to claim 4, characterized in that: The trend prediction module predicts the future psychological distress risk trend, and the prediction of the future psychological distress risk trend includes the following specific steps: S21. Obtain the patient's psychological distress risk score from the previous i assessments, divide this data into a 70% training set and a 30% test set, and construct the input MDS i-2 、MDS i-1 、MDS i , the output is MDS i+1 The time series prediction model is trained using 70% of the training set to obtain the initial time series prediction model. S22. Test the initial time series prediction model using a 30% coefficient test set, optimize the model parameters using mean square error, select the model with the smallest prediction error on the test set as the final time series prediction model, and predict the psychological distress risk score for the i+1th assessment; S23. Output the predicted psychological distress risk score for the (i+1)th assessment.
6. The machine learning-based psychological distress risk prediction system for patients with inflammatory bowel disease according to claim 5, characterized in that: The prediction of future psychological distress risk trends also includes: S24. Extract the MDS score for the psychological distress risk at the i+1th assessment i+1 ; S25. Calculate the patient's psychological distress change index, where the calculation formula for the psychological distress change index is: S26: Determine whether it is necessary to send a decision adjustment signal to the information feedback port.
7. The machine learning-based psychological distress risk prediction system for patients with inflammatory bowel disease according to claim 6, characterized in that: The time series prediction model in S22 is an LSTM neural network model.
8. The machine learning-based psychological distress risk prediction system for patients with inflammatory bowel disease according to claim 7, characterized in that: The specific content of S26 is: presetting a DTI threshold, when the psychological distress change index DTI is greater than the DTI threshold, continuing to execute the current nursing strategy; when the psychological distress change index DTI is less than or equal to the DTI threshold, sending a decision adjustment signal to the information feedback port.