Medical risk prediction system and method and storage medium
By building a medical risk prediction system, using the automated process of data entry, scoring and alarm devices, the problem of insufficient alarm mechanism in the existing technology is solved, and efficient and accurate medical risk management is achieved.
Patent Information
- Application Number
- CN202510356813.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-25
- Publication Date
- 2025-07-25
AI Technical Summary
The existing medical risk assessment technology lacks accurate and effective alarm mechanisms, resulting in frequent medical accidents and cannot meet the needs of complex medical scenarios.
Build a medical risk prediction system, including data entry devices, medical risk scoring devices and evaluation and alarm devices, and build an automated risk prediction process by integrating these devices, and use multiple sub-models to conduct comprehensive assessment and alarm prompts on medical risk accident data.
It significantly improves the accuracy and efficiency of medical risk assessment, reduces missed reports and false alarms, helps medical institutions to deal with high-risk events in a timely manner, and reduces the incidence of accidents.
Smart Images
Figure CN120376127A_ABST
Abstract
Description
Technical Field
[0001] The present invention mainly relates to the technical field, and particularly relates to a medical risk prediction system, method and storage medium. Background Art
[0002] At present, with the continuous development of the medical industry, the importance of medical risk assessment in improving medical quality and ensuring patient safety has become increasingly prominent. However, there are many defects in the existing medical risk assessment technologies, making it difficult to meet the needs of actual medical scenarios.
[0003] There are serious defects in the existing medical risk assessment and alarm systems. The assessment methods lack accuracy, often relying on subjective judgments or simple statistical analyses, and are unable to accurately predict complex medical risks. The alarm mechanism is also imperfect, with unreasonable alarm thresholds set, prone to false negatives and false positives. For example, in some high-risk surgeries, due to inaccurate assessments, alarms were not issued in a timely manner, resulting in medical accidents. Therefore, there is an urgent need for a more comprehensive, accurate and efficient medical risk prediction system to improve the level of medical risk management and ensure the medical safety of patients. Summary of the Invention
[0004] The technical problem to be solved by the present invention is to provide a medical risk prediction system, method and storage medium in view of the deficiencies of the prior art.
[0005] The technical solution of the present invention to solve the above technical problem is as follows: A medical risk prediction system includes a data input device, a medical risk scoring device and a medical risk assessment and alarm device;
[0006] The data input device is electrically connected to the medical risk scoring device, and the data input device is used to input medical risk accident data;
[0007] The medical risk scoring device is electrically connected to the medical risk assessment and alarm device. The medical risk scoring device is used to construct a medical scoring model, evaluate the medical risk accident data through the medical scoring model, and score the evaluation results to obtain a risk score;
[0008] The medical risk assessment and alarm device is used to perform risk prediction based on the risk score to obtain a medical risk prediction result and give an alarm prompt.
[0009] Another technical solution of the present invention to solve the above technical problem is as follows: A medical risk prediction method is applied to the medical risk prediction system as described above. The system includes a data input device, a medical risk scoring device and a medical risk assessment and alarm device; The method includes the following steps:
[0010] The data input device inputs medical risk accident data;
[0011] The medical risk scoring device constructs a medical scoring model, evaluates the medical risk accident data through the medical scoring model, and scores the evaluation result to obtain a risk score;
[0012] The medical risk assessment and alarm device performs risk prediction based on the risk score to obtain a medical risk prediction result.
[0013] Another technical solution for the present invention to solve the above technical problems is as follows: A medical risk prediction device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the medical risk prediction method as described above is implemented.
[0014] Another technical solution for the present invention to solve the above technical problems is as follows: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the medical risk prediction method as described above is implemented.
[0015] The beneficial effects of the present invention are: By integrating the data entry device, the medical risk scoring device, and the medical risk assessment and alarm device, a complete automated risk prediction process is constructed, avoiding the cumbersome operations of traditional manual evaluation and significantly improving the efficiency of medical risk assessment. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 It is a functional module block diagram of the medical risk prediction system provided by an embodiment of the present invention;
[0017] Figure 2 It is a flowchart of the medical risk prediction method provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0018] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.
[0019] Embodiment 1: As Figure 1 shown, an embodiment of the present invention provides a medical risk prediction system, including a data entry device, a medical risk scoring device, and a medical risk assessment and alarm device;
[0020] The data entry device is electrically connected to the medical risk scoring device, and the data entry device is used to enter medical risk accident data;
[0021] The medical risk scoring device is electrically connected to the medical risk assessment and alarm device. The medical risk scoring device is used to construct a medical scoring model, evaluate the medical risk accident data through the medical scoring model, and score the evaluation result to obtain a risk score;
[0022] The medical risk assessment and alarm device is used to perform risk prediction based on the risk score, obtain a medical risk prediction result, and give an alarm prompt.
[0023] In this embodiment, by integrating the data input device, the medical risk scoring device, and the medical risk assessment and alarm device, a complete automated risk prediction process is constructed, avoiding the cumbersome operations of traditional manual evaluation and significantly improving the efficiency of medical risk assessment.
[0024] Embodiment 2: The medical risk accident data includes the number of medical risk accidents, the total number of medical events, the loss type, the risk factor type, and the success rate of medical staff in surgeries;
[0025] In the risk assessment model, the evaluation of the medical risk accident data through the medical scoring model includes:
[0026] The medical scoring model includes a medical process risk probability sub-model, a risk result severity sub-model, a risk factor impact sub-model, and a medical staff adaptation sub-model.
[0027] Through the medical process risk probability sub-model, the number of medical risk accidents is evaluated based on the number of medical risk accidents and the total number of medical events to obtain the medical process risk probability. The medical process risk probability sub-model is:
[0028]
[0029] Where P is the risk probability of medical process i, n i is the number of accidents in medical process i, and m i is the total number of cases;
[0030] For example, in an appendectomy, there were 5 mistakes in the anesthesia process in the past 100 times. Calculated through the medical process risk probability sub-model:
[0031]
[0032] Furthermore, through the risk result severity sub-model, the risk severity of the loss type is evaluated to obtain a severity score. The risk result severity sub-model is:
[0033]
[0034] Among them, S is the severity score, ω j is the weight of loss type j, and L j is the loss quantification value;
[0035] For example, a surgical error causes a patient to be disabled, with a financial loss of 500,000 (weight 0.4), a serious reputation loss (quantification 80, weight 0.3), a high legal liability risk (quantification 70, weight 0.2), and great public opinion pressure (quantification 60, weight 0.1). Calculated through the risk result severity sub-model:
[0036] S = 0.4×50 + 0.3×80 + 0.2×70 + 0.1×60 = 64.
[0037] Moreover, through the risk factor impact sub-model, a risk impact assessment is carried out on the risk factor type to obtain a risk factor impact score. The risk factor impact sub-model is:
[0038]
[0039] Among them, R is the risk factor impact score, and p l is the probability of risk factor l, and I l is the impact degree of risk factor l;
[0040] For example, for the surgical infection risk factor, the probability is 0.1 (weight 0.6), and the impact degree is 80. For the instrument failure risk factor, the probability is 0.05 (weight 0.4), and the impact degree is 70. Calculated through the risk factor impact sub-model:
[0041] R = 0.6×0.1×80 + 0.4×0.05×70 = 6.2.
[0042] Moreover, through the medical staff adaptation sub-model, an assessment of the adaptability of medical staff to the surgical success rate of medical staff is carried out to obtain a medical staff adaptation rate. The medical staff adaptation sub-model is:
[0043]
[0044] Among them, A is the medical staff adaptation rate, which is used to measure the matching degree between medical staff and a specific medical event. |x s -y s | is the absolute value of the subtraction of the s-th eigenvalue x s of the ideal medical staff from the s-th eigenvalue y s of the actual medical staff, so as to measure the difference degree between the two on the s-th feature. The difference values of all features are accumulated and then divided by the total number of features t to obtain the average difference degree.
[0045] For example, if two features, namely the surgical success rate and the error rate (i.e., t = 2), are selected to evaluate the suitability of medical staff, the surgical success rate x1 of an ideal medical staff is 95%, and the error rate x2 is 5%; the surgical success rate y1 of the actual medical staff is 90%, and the error rate is 8%. Then
[0046]
[0047] That is, the suitability rate of this medical staff is 0.96.
[0048] In this embodiment, through four sub-models of the medical process risk probability, the severity of the result, the influence of risk factors, and the suitability of medical staff, the key influencing factors of medical risks are comprehensively covered, improving the comprehensiveness and accuracy of prediction; reducing subjective judgment errors and enhancing the objectivity of evaluation results. Secondly, the sub-models can dynamically adjust parameters (such as weights, quantization values), can be adapted to different medical scenarios (such as surgical types, department requirements), and expand the application scope.
[0049] Embodiment 3: In the risk assessment model, the evaluation results are scored to obtain a risk score, including:
[0050] Weight values are assigned to each evaluation result, and scoring is performed according to the comprehensive risk calculation formula to obtain a risk score. The comprehensive risk calculation formula is:
[0051] C = P×0.3 + S×0.25 + R×0.25 + (1 - A)×0.2
[0052] Where C is the risk score, P is the risk probability of medical process i, S is the severity score, R is the risk factor influence score, and A is the medical staff suitability rate.
[0053] In this embodiment, through the comprehensive risk calculation formula, the contributions of each sub-model to the total risk are reasonably balanced, avoiding a single factor dominating the evaluation result, and converting the complex evaluation result into an intuitive numerical score, which is convenient for medical staff to quickly understand the risk level and assist in decision-making.
[0054] Embodiment 4: According to the risk score, risk prediction is performed to obtain a medical risk prediction result, and alarm prompts are given, including:
[0055] If the risk score C < 30, it is a low medical risk;
[0056] If the risk score 30 < C < 60, it is a medium medical risk;
[0057] If the risk score C > 60, it is a high risk,
[0058] When the medical risk prediction result is a high medical risk, alarm prompts are given.
[0059] In this embodiment, by setting a threshold value, a clear division of risk levels is achieved to help medical institutions prioritize the handling of high-risk events. When the risk is high, an alarm prompt is triggered to prompt medical staff to take remedial measures in a timely manner, reducing the incidence of medical accidents.
[0060] Embodiment 5: As Figure 2 shown, the embodiment of the present invention also provides a medical risk prediction method, which is applied to the medical risk prediction system as described above. The system includes a data entry device, a medical risk scoring device, and a medical risk assessment and alarm device, and includes the following steps:
[0061] The data entry device enters medical risk accident data;
[0062] The medical risk scoring device constructs a medical scoring model, evaluates the medical risk accident data through the medical scoring model, and scores the evaluation results to obtain a risk score;
[0063] The medical risk assessment and alarm device performs risk prediction based on the risk score to obtain a medical risk prediction result.
[0064] Embodiment 6: The evaluation of the medical risk accident data through the medical scoring model includes:
[0065] The medical scoring model includes a medical process risk probability sub-model, a risk result severity sub-model, a risk factor impact sub-model, and a medical staff adaptation sub-model.
[0066] The medical process risk probability sub-model evaluates the number of medical risk accidents for the medical risk accident data and the total number of medical events to obtain a medical process risk probability. The medical process risk probability sub-model is:
[0067]
[0068] Among them, P is the risk probability of medical process i, n i is the number of accidents in medical process i, and m i is the total number of cases;
[0069] The risk result severity sub-model evaluates the risk severity of the loss type to obtain a severity score. The risk result severity sub-model is:
[0070]
[0071] Among them, S is the severity score, ω j is the weight of loss type j, and L j is the loss quantification value;
[0072] The risk factor impact sub-model is used to evaluate the risk impact of the risk factor type, and a risk factor impact score is obtained. The risk factor impact sub-model is as follows:
[0073]
[0074] where R is the risk factor impact score, p l is the probability of risk factor l, and I l is the impact degree of risk factor l;
[0075] The medical staff adaptability sub-model is used to evaluate the medical staff adaptability of the medical staff's surgical success rate, and a medical staff adaptability rate is obtained. The medical staff adaptability sub-model is as follows:
[0076]
[0077] where A is the medical staff adaptability rate, which is used to measure the matching degree between medical staff and a specific medical event. |x s -y s | is the absolute value of the difference between the s-th eigenvalue x s of the ideal medical staff and the s-th eigenvalue y s of the actual medical staff, which is used to measure the difference degree between the two on the s-th feature. The difference values of all features are accumulated and then divided by the total number of features t to obtain the average difference degree.
[0078] Example 7: Scoring the evaluation results to obtain a risk score, including:
[0079] Weight values are assigned to each evaluation result, and scoring is performed according to the comprehensive risk calculation formula to obtain a risk score. The comprehensive risk calculation formula is:
[0080] C = P×0.3 + S×0.25 + R×0.25 + (1 - A)×0.2
[0081] where C is the risk score, P is the risk probability of medical process i, S is the severity score, R is the risk factor impact score, and A is the medical staff adaptability rate.
[0082] Example 8: Performing risk prediction based on the risk score to obtain a medical risk prediction result and giving an alarm prompt, including:
[0083] If the risk score C < 30, it is judged as low medical risk;
[0084] If the risk score 30 < C < 60, it is judged as medium medical risk;
[0085] If the risk score C > 60, it is judged as high medical risk;
[0086] When the medical risk prediction result is a high medical risk, an alarm prompt is given.
[0087] Embodiment 9: The embodiment of the present invention further provides a medical risk prediction device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the medical risk prediction method as described above is implemented.
[0088] Embodiment 10: The embodiment of the present invention further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the medical risk prediction method as described above.
[0089] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.
[0090] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.
[0091] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention.
[0092] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A medical risk prediction system, characterized in that, It includes a data entry device, a medical risk scoring device, and a medical risk assessment and alarm device; The data entry device is electrically connected to the medical risk scoring device, and the data entry device is used to enter medical risk accident data; The medical risk scoring device is electrically connected to the medical risk assessment and alarm device. The medical risk scoring device is used to construct a medical scoring model, evaluate the medical risk accident data through the medical scoring model, score the evaluation results, and obtain a risk score; The medical risk assessment and alarm device is used to perform risk prediction based on the risk score, obtain a medical risk prediction result, and give an alarm prompt.
2. The medical risk prediction system according to claim 1, characterized in that, The medical risk accident data includes the number of medical risk accidents, the total number of medical events, loss types, risk factor types, and the surgical success rate of medical staff; In the risk assessment model, evaluating the medical risk accident data through the medical scoring model includes: The medical scoring model includes a medical process risk probability sub-model, a risk result severity sub-model, a risk factor impact sub-model, and a medical staff adaptability sub-model. Evaluating the number of medical risk accidents for the number of medical risk accidents and the total number of medical events through the medical process risk probability sub-model to obtain the medical process risk probability. The medical process risk probability sub-model is: Where P is the risk probability of medical procedure i, n i is the number of accidents during medical process i, m i is the total number of pieces; Evaluating the risk severity of the loss type through the risk result severity sub-model to obtain a severity score. The risk result severity sub-model is: Among them, S is the severity score, ω j is the weight of loss type j, L j is the loss quantification value; Evaluating the risk impact of the risk factor type through the risk factor impact sub-model to obtain a risk factor impact score. The risk factor impact sub-model is: Among them, R is the risk factor impact score, p l is the probability of risk factor l, I l is the impact degree of risk factor l; Evaluating the adaptability of medical staff for the surgical success rate of medical staff through the medical staff adaptability sub-model to obtain a medical staff adaptability rate. The medical staff adaptability sub-model is: Among them, A is the adaptability rate of medical staff, which is used to measure the matching degree between medical staff and specific medical events, |x s -y s | is to subtract the s-th eigenvalue x s of the ideal medical staff from the s-th eigenvalue y s of the actual medical staff, and then take the absolute value to measure the difference degree between the two on the s-th feature. The difference values of all features are accumulated and then divided by the total number of features t to obtain the average difference degree.
3. The medical risk prediction system according to claim 2, wherein In the risk assessment model, scoring the evaluation results to obtain a risk score includes: Assigning weights to each evaluation result and scoring according to the comprehensive risk calculation formula to obtain a risk score. The comprehensive risk calculation formula is: C = P×0.3 + S×0.25 + R×0.25 + (1 - A)×0.2 Where C is the risk score, P is the risk probability of medical process i, S is the severity score, R is the risk factor impact score, and A is the medical staff adaptability rate.
4. The medical risk prediction system according to claim 2, wherein Performing risk prediction based on the risk score to obtain a medical risk prediction result and giving an alarm prompt includes: If the risk score C < 30, it is a low medical risk; If the risk score 30 < C < 60, it is a medium medical risk; If the risk score C > 60, it is a high risk. When the medical risk prediction result is a high medical risk, an alarm prompt is given.
5. A medical risk prediction method, applied to the medical risk prediction system according to any one of claims 1 to 4, the system comprising a data entry device, a medical risk scoring device, and a medical risk assessment and alarm device; characterized in that, It includes the following steps: The data entry device enters medical risk accident data; The medical risk scoring device constructs a medical scoring model, evaluates the medical risk accident data through the medical scoring model, scores the evaluation results, and obtains a risk score; The medical risk assessment and alarm device performs risk prediction based on the risk score to obtain a medical risk prediction result.
6. The medical risk prediction method according to claim 5, wherein The evaluation of the medical risk accident data by the medical scoring model includes: The medical scoring model includes a medical process risk probability sub-model, a risk result severity sub-model, a risk factor impact sub-model, and a medical staff adaptability sub-model. The medical process risk probability sub-model evaluates the number of medical risk accidents and the total number of medical events to obtain the medical process risk probability. The medical process risk probability sub-model is: Among them, P is the risk probability of medical process i, and n i is the number of accidents in medical process i, and m i is the total number; The risk result severity sub-model evaluates the severity of the risk for the loss type to obtain a severity score. The risk result severity sub-model is: Among them, S is the severity score, ω j is the weight of loss type j, and L j is the loss quantification value; The risk factor impact sub-model evaluates the risk impact for the risk factor type to obtain a risk factor impact score. The risk factor impact sub-model is: Among them, R is the risk factor impact score, p l is the probability of risk factor l, I l is the impact degree of risk factor l; The medical staff adaptability sub-model evaluates the adaptability of the medical staff based on the surgical success rate of the medical staff to obtain a medical staff adaptability rate. The medical staff adaptability sub-model is: Among them, A is the adaptation rate of medical staff, which is used to measure the matching degree between medical staff and specific medical events, |x s -y s | is to subtract the s-th eigenvalue x of the ideal medical staff s from the s-th eigenvalue y of the actual medical staff s , then take the absolute value to measure the difference degree between the two on the s-th feature. The difference values of all features are accumulated and then divided by the total number of features t to obtain the average difference degree.
7. The medical risk prediction method according to claim 5, wherein The evaluation of the evaluation results to obtain a risk score includes: Assign weights to each evaluation result and perform scoring according to the comprehensive risk calculation formula to obtain a risk score. The comprehensive risk calculation formula is: C = P×0.3 + S×0.25 + R×0.25 + (1 - A)×0.2 Where C is the risk score, P is the medical process i risk probability, S is the severity score, R is the risk factor impact score, and A is the medical staff adaptability rate.
8. The medical risk prediction method according to claim 7, wherein The risk prediction is performed based on the risk score to obtain a medical risk prediction result, and an alarm prompt is given, including: If the risk score C < 30, it is judged as low medical risk; If the risk score 30 < C < 60, it is judged as medium medical risk; If the risk score C > 60, it is judged as high medical risk; When the medical risk prediction result is high medical risk, an alarm prompt is given.
9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, the medical risk prediction method according to any one of claims 5 to 8 is implemented.