CT (Computed Tomography) and MR (Magnetic Resonance) examination risk assessment method and system based on Internet hospital

Abstract

The invention relates to the technical field of medical treatment, and discloses a CT and MR examination risk assessment method and system based on an internet hospital, and the method comprises the following steps: S1, assessing the medical history of a patient, and considering the medical history in combination with genetic factors, lifestyles and basic health conditions; s2, determining the age, gender and individual difference of the patient and whether the patient accepts radiation and magnetic field influence caused by examination; s3, evaluating an iodine contrast agent allergy risk and a gadolinium contrast agent allergy risk; s4, the purpose, process, risk and result of CT or MR examination are explained; s5, questions of the patient are answered, understanding of the patient and family members of the patient is clear, and examination is agreed. By considering individual differences and medical histories of patients, personalized improvement of an evaluation process is realized, special requirements and safety consideration of the patients can be better met, and meanwhile, enhanced risk communication and more comprehensive risk evaluation can help the patients to better understand potential risks in an examination process, so that the examination efficiency is improved. And medical personnel and patients can determine a diagnosis method together, so that the risk is reduced.

Description

Technical Field

[0001] The present invention relates to the field of medical technology, and in particular to a CT and MR examination risk assessment method and system based on an Internet hospital. Background Art

[0002] CT scans use X-rays to penetrate the body and generate cross-sectional images based on the degree of absorption by various tissues. They are used to diagnose and evaluate abnormal growth and damage to organ structures. CT scans are commonly used to detect parts such as the head, chest, abdomen, and bones, and to evaluate cardiovascular conditions. MR scans use strong magnetic fields and harmless radio waves to generate cross-sectional images of the inside of the body. MR scans have advantages in examining soft tissues and are of great significance for diagnosing tumors, inflammation, vascular lesions, and neurological diseases.

[0003] Traditional assessment methods lack consideration of physical differences among patients, lack sufficient interaction regarding the impact of contrast agent risks on patients, and traditional assessments lack clear, detailed explanations and communication of the potential impacts and risk levels of CT or MR examinations, resulting in patients not fully understanding the risks during the examination. CT contrast agents are usually iodine contrast agents, which are mainly injected intravenously. The risks include allergic reactions, kidney damage, and thyroid dysfunction in patients. The risks of MR contrast agents are less common, but once they occur, they are no less serious than iodine contrast agents. MR contrast agents are mostly gadolinium contrast agents, which can cause serious side effects including nephrogenic systemic fibrosis. Therefore, the risks of gadolinium contrast agents should be taken seriously.

[0004] Therefore, those skilled in the art provide a CT and MR examination risk assessment method and system based on an Internet hospital to solve the problems raised in the above background technology. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a CT and MR examination risk assessment method and system based on an Internet hospital, which solves the problem that traditional assessment methods lack consideration of patients' physical differences and do not fully consider the impact of patients' genetic factors, lifestyle, basic health conditions and other factors on their tolerance to radiation or magnetic fields. In addition, traditional assessments lack clear and detailed explanations and communication of the potential impacts and risk levels of radiation or magnetic fields, resulting in patients' lack of understanding of the risks during the examination process.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a CT and MR examination risk assessment method based on an Internet hospital, comprising the following steps:

[0007] S1. Evaluate the patient's medical history, taking into account genetic factors, lifestyle, and underlying health conditions;

[0008] S2. Determine the patient's age, gender, individual differences, and whether they are willing to accept the radiation and magnetic field effects caused by the examination;

[0009] S3. Assess the risk of allergy to iodine contrast media and gadolinium contrast media;

[0010] S4. Explain the purpose, procedure, risks, and results of CT or MR examinations;

[0011] S5. Answer the patient's questions and make sure that the patient and his / her family understand and agree to the examination;

[0012] S6. Decide whether to perform CT or MRI examination based on the evaluation;

[0013] S7. Perform CT or MRI examination;

[0014] S8. Interpret the examination results, combine them with the clinical history and clinical indications, and write the examination report;

[0015] S9. Share the examination results with the patient and the medical team to discuss management and treatment plans, and interview patients who underwent CT or MR examinations to evaluate the effectiveness and impact of the examinations.

[0016] S10. Based on the monitoring results, adjust the evaluation process to provide feedback to medical staff and patients.

[0017] Preferably, in step S3, the patient's risk of allergy to contrast agents is evaluated by a decision tree model, and its algorithm formula is:

[0018]

[0019] Support vector machine is used for more accurate allergy risk classification, and its algorithm formula is:

[0020]

[0021] Among them, K(x i ,x) is the kernel function, α i and b are model parameters.

[0022] Preferably, in step S6, the decision support system combines the information of the previous steps to output a final decision, and its algorithm formula is:

[0023]

[0024] Among them, w i is the weight of each evaluation item;

[0025] In step S10, the risk assessment method is dynamically adjusted through a closed-loop feedback control system, and its algorithm formula is:

[0026] New evaluation process = old evaluation process + λ × feedback difference,

[0027] Among them, λ is the learning rate parameter.

[0028] Preferably, the decision support system is a computerized system used to assist the decision-making process, which can help medical professionals make accurate and reasonable decisions in complex situations;

[0029] The decision support system includes a data management module, a model management module, a knowledge base and a user interface module; the data management module is used to collect and manage relevant patient data; the model management module is used to process and analyze the collected data to generate relevant risk assessment and prediction results; the knowledge base provides standardized knowledge support for the system; the user interface module displays system analysis results, suggestions and decision support information to medical staff;

[0030] The closed-loop feedback control system is a control mechanism that continuously monitors and adjusts the behavior of the system during operation, continuously evaluates the output results of the system through a feedback loop, and adjusts itself according to the results to achieve the predetermined goals;

[0031] The closed-loop feedback control system includes sensors, controllers, actuators and feedback loops; the sensors are used to monitor and collect various data generated during the operation of the system; the controller analyzes the data collected by the sensors to determine whether the performance of the system meets the expected goals; the actuator adjusts the operation of the system according to the instructions of the controller; the feedback loop feeds back the output results of the system to the controller so that it can continuously adjust and optimize the system;

[0032] The core of the closed-loop feedback control system lies in its adaptive adjustment capability, which is usually achieved by the following algorithm formula:

[0033] Feedback difference calculation:

[0034] e(t)=r(t)-y(t),

[0035] Among them, e(t) is the error, r(t) is the expected result, and y(t) is the actual result;

[0036] Controller adjustment formula:

[0037]

[0038] Where u(t) is the control input, K p is the proportional gain, K i is the integral gain, K d is the differential gain;

[0039] System parameter update:

[0040] θ new =θ old +λ×e(t),

[0041] Among them, θ represents the system parameters and λ is the learning rate.

[0042] A CT and MR examination risk assessment system, comprising a patient information management module, an individual characteristic and tolerance assessment module, a CT examination risk module, an MR examination risk module, a decision-making module, an execution module, a monitoring module, and a feedback module;

[0043] The patient information management module is responsible for collecting relevant information of patients;

[0044] The individual characteristics and tolerance assessment module is used to clarify the patient's basic information and tolerance factors to radiation or magnetic fields;

[0045] The CT examination risk module is used to assess whether the patient can accept radiation and the impact of radiation on the patient's health;

[0046] The MR examination risk module is responsible for evaluating whether there are implants in the patient's body that are affected by the magnetic field;

[0047] The decision-making module decides whether to perform a CT or MR examination based on the personalized assessment;

[0048] The execution module is responsible for performing CT or MR examinations and ensuring that the operations comply with safety standards and guidelines;

[0049] The result interpretation and communication module is used to interpret the test results, combine them with the clinical history and clinical indications, and write the test report;

[0050] The monitoring module regularly monitors patients undergoing CT or MR examinations;

[0051] The feedback module adjusts the evaluation process according to the monitoring results.

[0052] Preferably, the patient information management module includes a patient data collection unit and an electronic medical record integration unit; the patient data collection unit is used to collect basic information of the patient; the electronic medical record integration unit extracts relevant medical history and examination records from the existing electronic medical record system;

[0053] The individual characteristic and tolerance assessment module includes an individual characteristic analysis unit and a tolerance prediction unit; the individual characteristic analysis unit analyzes the individual physiological characteristics of the patient; the tolerance prediction unit predicts the patient's tolerance to the examination process based on the individual characteristics and historical data;

[0054] The CT examination risk module includes a radiation risk assessment unit and an iodine contrast agent allergy assessment unit; the radiation risk assessment unit calculates the radiation dose caused by the CT scan to assess its short-term and long-term health effects on the patient; the iodine contrast agent allergy assessment unit assesses the patient's risk of allergy to iodine contrast agents;

[0055] The MR examination risk module includes a magnetic field impact assessment unit and a gadolinium contrast agent risk assessment unit; the magnetic field impact assessment unit assesses the impact of a strong magnetic field on a patient during an MR examination; the gadolinium contrast agent risk assessment unit assesses the risk of an allergic reaction of a patient to a gadolinium-based contrast agent.

[0056] Preferably, the decision-making module includes a risk integration analysis unit and a decision support unit; the risk integration analysis unit combines the risk data from the CT and MR risk assessment modules with the individual characteristics of the patient, and gives examination suggestions after integrated analysis; the decision support unit generates a decision suggestion on whether to perform a CT or MR examination based on the result of the integrated analysis, so as to present the suggestion to the medical staff;

[0057] The execution module includes an examination parameter optimization unit and an execution management unit; the examination parameter optimization unit customizes CT or MR examination parameters for the patient according to the suggestions of the decision support unit; the execution management unit coordinates and executes the CT or MR examination;

[0058] The monitoring module includes a real-time monitoring unit and an access unit; the real-time monitoring unit monitors the patient's physiological state in real time during the CT or MR examination; the access unit tracks the patient's health status after the examination, and records and analyzes potential side effects or adverse reactions;

[0059] The feedback module includes a feedback analysis unit and a system optimization unit; the feedback analysis unit analyzes the data after the inspection and evaluates the effect of the inspection decision; the system optimization unit dynamically adjusts and optimizes the evaluation model and parameters of the system according to the results provided by the feedback analysis unit.

[0060] Preferably, the individual characteristic analysis unit is used to analyze the multivariate regression model formula of the patient's physiological characteristics:

[0061]

[0062] Among them, Feature i Represents various physiological characteristics, β i is the weight coefficient;

[0063] The tolerance prediction unit uses a Bayesian classifier to predict tolerance, and the algorithm formula is:

[0064]

[0065] Among them, P (Tolerance) is the prior probability of tolerance, and P (Features) is the joint probability of features;

[0066] The risk assessment of the implant being affected by the magnetic field in the magnetic field impact assessment unit can use an expert system or a rule engine, and its algorithm formula is:

[0067]

[0068] Among them, R i is the risk value evaluated by each rule, W i is the weight of the rule;

[0069] The gadolinium contrast agent risk assessment unit uses a logistic regression model to assess the risk of gadolinium contrast agent allergy, and its algorithm formula is:

[0070]

[0071] Preferably, the risk integration analysis unit integrates risk data through a multi-criteria decision analysis algorithm, the algorithm formula is:

[0072]

[0073] Among them, w i is the weight of each risk factor, RiskScore i is the risk score;

[0074] The decision support unit generates decision suggestions based on Bayesian decision theory, and the algorithm formula is:

[0075] OptimalDecision=argmax d ∑ j P(R j |d)×U(R j ,d),

[0076] Where d is the decision option, P(R j |d) is the result R that occurs under decision d j The probability of U(R j ,d) is the corresponding utility;

[0077] The real-time monitoring unit monitors the patient's physiological parameters through time series analysis, and the algorithm formula is:

[0078]

[0079] in, is the predicted physiological parameter, φ i is the autoregressive coefficient, ∈ t is the error term.

[0080] Preferably, the feedback analysis unit uses linear discriminant analysis to evaluate the decision effect using multivariate analysis, and the algorithm formula is:

[0081]

[0082] Among them, w i is the weight, x i is the feedback variable;

[0083] The system optimization unit uses a gradient descent algorithm with an adaptive learning rate to optimize system parameters. The algorithm formula is:

[0084]

[0085] Among them, θ t is the parameter vector, η t is the learning rate, J(θ t ) is the loss function.

[0086] The present invention provides a CT and MR examination risk assessment method and system based on an Internet hospital.

[0087] It has the following beneficial effects:

[0088] 1. The present invention improves the personalization of the evaluation process by considering the individual differences and medical history of patients, which can better meet the special needs and safety considerations of patients. At the same time, enhanced risk communication and more comprehensive risk assessment can help patients better understand the potential risks during the examination process, and help medical staff and patients jointly decide on diagnostic methods to reduce risks.

[0089] 2. Through multiple data and comprehensive considerations, the present invention enables the medical team to make better decisions and provide diagnostic plans for patients, thereby improving the accuracy and efficiency of treatment. The establishment of a continuous detection and feedback mechanism helps to detect potential problems in a timely manner and take appropriate measures to ensure the safety and health of patients. At the same time, through clear and detailed communication, the understanding between doctors and patients is enhanced, which is conducive to establishing a good doctor-patient relationship and improving patients' satisfaction and compliance with the medical process. BRIEF DESCRIPTION OF THE DRAWINGS

[0090] Figure 1 is a flow chart of the present invention;

[0091] Figure 2 is a system diagram of the present invention;

[0092] Figure 3 is a schematic diagram of a patient information management module of the present invention;

[0093] Figure 4Schematic diagram of the individual characteristics and tolerance assessment module of the present invention;

[0094] Figure 5 This is a schematic diagram of a CT examination risk module of the present invention;

[0095] Figure 6 It is a schematic diagram of the MR examination risk module of the present invention;

[0096] Figure 7 It is a schematic diagram of the decision-making module of the present invention;

[0097] Figure 8 It is a schematic diagram of an execution module of the present invention;

[0098] Fig. 9 It is a schematic diagram of the monitoring module of the present invention;

[0099] Fig.10 It is a schematic diagram of the feedback module of the present invention. DETAILED DESCRIPTION

[0100] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0101] The present invention is described in detail below in conjunction with the accompanying drawings:

[0102] Example:

[0103] Please refer to the attached Figure 1 -Attached Fig.10 The embodiment of the present invention provides a CT and MR examination risk assessment method based on an Internet hospital, comprising the following steps:

[0104] S1. Evaluate the patient's medical history, taking into account genetic factors, lifestyle, and underlying health conditions;

[0105] S2. Determine the patient's age, gender, individual differences, and whether they are willing to accept the radiation and magnetic field effects caused by the examination;

[0106] S3. Assess the risk of allergy to iodine contrast media and gadolinium contrast media;

[0107] S4. Explain the purpose, procedure, risks, and results of CT or MR examinations;

[0108] S5. Answer the patient's questions and make sure the patient and his / her family understand and agree to the examination;

[0109] S6. Decide whether to perform CT or MRI examination based on the evaluation;

[0110] S7. Perform CT or MRI examination;

[0111] S8. Interpret the examination results, combine them with the clinical history and clinical indications, and write the examination report;

[0112] S9. Share the examination results with the patient and the medical team to discuss management and treatment plans, and interview patients who underwent CT or MR examinations to evaluate the effectiveness and impact of the examinations.

[0113] S10. Based on the monitoring results, adjust the evaluation process to provide feedback to medical staff and patients.

[0114] Benefit S1 can identify potential health problems that may affect the results of the examination or increase the risk of the examination, which helps to develop a personalized examination plan, adjust the examination process according to the patient's specific situation, and improve the safety and effectiveness of the examination; Benefit S2 reduces unnecessary exposure to radiation and magnetic fields during the examination; Benefit S3 effectively assesses the patient's risk of allergy to contrast agents and avoids the occurrence of severe allergic reactions. The assessment results can prompt medical staff to consider other examination methods or use different types of contrast agents to reduce unnecessary medical risks; Benefit S4 increases the patient's understanding and trust in the examination, helps relieve the patient's tension, and thus improves the success rate and accuracy of the examination; Benefit S5 Effective communication with patients and their families helps to build trust and improve the quality of the doctor-patient relationship; Benefit S6 helps save medical resources, concentrate resources on patients who need them most, and improve the quality of medical services; Benefit S7 obtains accurate imaging information, supports clinical diagnosis and treatment decisions, and reduces the risks caused by operational errors; Benefit S8 provides more accurate diagnostic opinions, improves the accuracy and clinical value of reports; Benefit S9 promotes multidisciplinary collaboration, develops the best treatment plan, and increases the effectiveness of treatment; Benefit S10 improves the accuracy of the system and helps improve future examinations and treatments.

[0115] In step S3, the decision tree model is used to evaluate the patient's risk of allergy to contrast agents. The algorithm formula is:

[0116]

[0117] Support vector machine is used for more accurate allergy risk classification, and its algorithm formula is:

[0118]

[0119] Among them, K(x i ,x) is the kernel function, α i and b are model parameters.

[0120] The decision tree recursively features and divides the data according to the feature values ​​to build a tree structure for predicting classification results. In step S3, the decision tree can gradually evaluate the patient's risk of allergy to contrast agents based on his or her historical data, which helps doctors understand and explain it to patients.

[0121] Support vector machines achieve accurate classification of allergy risks by constructing a hyperplane that maximizes the classification interval. The application of kernel functions allows support vector machines to work in nonlinear feature spaces and process complex allergic reaction patterns. Support vector machines are insensitive to a small number of abnormal points, which helps to stably assess allergy risks and avoid misjudgments due to individual abnormal data points.

[0122] In step S6, the decision support system combines the information from the previous steps to output the final decision. The algorithm formula is:

[0123]

[0124] Among them, w i is the weight of each evaluation item;

[0125] In step S10, the risk assessment method is dynamically adjusted through a closed-loop feedback control system, and its algorithm formula is:

[0126] New evaluation process = old evaluation process + λ × feedback difference,

[0127] Among them, λ is the learning rate parameter.

[0128] The decision support system integrates the risk information of the assessment items and outputs a comprehensive score, which represents the overall risk level. This score helps doctors decide whether to perform CT or MR examinations, and provides more targeted decision-making suggestions to reduce the influence of human subjective factors.

[0129] The closed-loop feedback control system dynamically adjusts the model parameters through a feedback mechanism to ensure that the model can continuously adapt to new data and new environments, improve assessment accuracy, gradually reduce risk assessment errors, improve the model's predictive performance, ensure patient safety and diagnostic accuracy, and improve the overall performance and reliability of the system.

[0130] Decision support systems are computerized systems used to assist the decision-making process and can help medical professionals make accurate and reasonable decisions in complex situations;

[0131] The decision support system includes a data management module, a model management module, a knowledge base and a user interface module; the data management module is used to collect and manage relevant patient data; the model management module is used to process and analyze the collected data to generate relevant risk assessment and prediction results; the knowledge base provides standardized knowledge support for the system; the user interface module displays system analysis results, suggestions and decision support information to medical staff;

[0132] A closed-loop feedback control system is a control mechanism that continuously monitors and adjusts the behavior of the system during its operation. It continuously evaluates the output of the system through a feedback loop to adjust itself according to the results and achieve the predetermined goals.

[0133] A closed-loop feedback control system includes sensors, controllers, actuators, and feedback loops. Sensors are used to monitor and collect various data generated during the operation of the system. The controller analyzes the data collected by the sensors to determine whether the system's performance meets the expected goals. The actuator adjusts the system's operation according to the controller's instructions. The feedback loop feeds the system's output results back to the controller, allowing it to continuously adjust and optimize the system.

[0134] The core of the closed-loop feedback control system lies in its adaptive adjustment capability, which is usually achieved by the following algorithm formula:

[0135] Feedback difference calculation:

[0136] e(t)=r(t)-y(t),

[0137] Among them, e(t) is the error, r(t) is the expected result, and y(t) is the actual result;

[0138] Controller adjustment formula:

[0139]

[0140] Where u(t) is the control input, K p is the proportional gain, K i is the integral gain, K d is the differential gain;

[0141] System parameter update:

[0142] θ new =θ old +λ×e(t),

[0143] Among them, θ represents the system parameters and λ is the learning rate.

[0144] A CT and MR examination risk assessment system, comprising a patient information management module, an individual characteristic and tolerance assessment module, a CT examination risk module, an MR examination risk module, a decision-making module, an execution module, a monitoring module, and a feedback module;

[0145] The patient information management module is responsible for collecting relevant information about the patient; the individual characteristics and tolerance assessment module is used to clarify the patient's basic information and tolerance factors to radiation or magnetic fields; the CT examination risk module is used to assess whether the patient can accept radiation and the impact of radiation on the patient's health; the MR examination risk module is responsible for assessing whether there are implants in the patient's body that are affected by magnetic fields; the decision-making module decides whether to perform a CT or MR examination based on personalized assessments; the execution module is responsible for performing CT or MR examinations and ensuring that the operations comply with safety standards and guidelines; the result interpretation and communication module is used to interpret the examination results, combine them with clinical history and clinical indications, and write examination reports; the monitoring module regularly monitors patients undergoing CT or MR examinations; and the feedback module adjusts the evaluation process based on the monitoring results.

[0146] The patient information management module includes a patient data collection unit and an electronic medical record integration unit; the patient data collection unit is used to collect basic information about the patient; the electronic medical record integration unit extracts relevant medical history and examination records from the existing electronic medical record system; the individual characteristics and tolerance assessment module includes an individual characteristics analysis unit and a tolerance prediction unit; the individual characteristics analysis unit analyzes the individual physiological characteristics of the patient; the tolerance prediction unit predicts the patient's tolerance to the examination process based on individual characteristics and historical data; the CT examination risk module includes a radiation risk assessment unit and an iodine contrast agent allergy assessment unit; the radiation risk assessment unit calculates the radiation dose caused by CT scanning to assess its short-term and long-term health effects on the patient; the iodine contrast agent allergy assessment unit assesses the patient's risk of allergy to iodine contrast agents; the MR examination risk module includes a magnetic field impact assessment unit and a gadolinium contrast agent risk assessment unit; the magnetic field impact assessment unit assesses the impact of strong magnetic fields on patients during MR examinations; the gadolinium contrast agent risk assessment unit assesses the patient's risk of allergic reaction to gadolinium-based contrast agents; the decision-making module includes a risk integration unit and a gadolinium contrast agent risk assessment unit; The integrated analysis unit and the decision support unit are as follows: the risk integrated analysis unit combines the risk data from the CT and MR risk assessment modules with the individual characteristics of the patient, and gives examination recommendations after integrated analysis; the decision support unit generates decision recommendations on whether to perform CT or MR examinations based on the results of the integrated analysis, and presents the recommendations to medical staff; the execution module includes the examination parameter optimization unit and the execution management unit; the examination parameter optimization unit customizes CT or MR examination parameters for the patient according to the recommendations of the decision support unit; the execution management unit coordinates and executes CT or MR examinations; the monitoring module includes the real-time monitoring unit and the access unit; the real-time monitoring unit monitors the patient's physiological state in real time during the CT or MR examination; the access unit tracks the patient's health status after the examination, and records and analyzes potential side effects or adverse reactions; the feedback module includes the feedback analysis unit and the system optimization unit; the feedback analysis unit analyzes the data after the examination and evaluates the effectiveness of the examination decision; the system optimization unit dynamically adjusts and optimizes the evaluation model and parameters of the system according to the results provided by the feedback analysis unit.

[0147] Benefits of the Patient Information Management Module: Effectively collect and integrate the patient's basic information, medical history, and related medical data, ensuring that the information used by the system in subsequent evaluations is comprehensive and accurate, simplifying the data processing process, and reducing data omissions and errors; Benefits of the Individual Characteristics and Tolerance Assessment Module: Accurately assess their tolerance to radiation or magnetic fields, ensure the safety of the examination, and avoid excessive or insufficient examinations; Benefits of the CT Examination Risk Module: Helps decide whether a CT examination should be performed, reduces the risk of radiation exposure, and prevents unnecessary CT examinations for patients who are susceptible to radiation; Benefits of the MR Examination Risk Module: Effectively assesses whether the patient has implants that are affected by magnetic fields, avoids safety issues caused by MR examinations, and prevents potential dangerous conditions; Benefits of the Decision-Making Module: Systematically supports medical Benefits of the execution module: Ensure that the execution of CT or MR examinations complies with standardized operating procedures and safety guidelines, reduce operational risks, ensure the accuracy and effectiveness of the examination, and ensure the safety and comfort of patients during the examination; Benefits of the result interpretation and communication module: Provide more comprehensive and accurate diagnostic information, help formulate subsequent treatment plans, and improve compliance; Benefits of the monitoring module: Regularly monitor the patients undergoing examinations, promptly deal with any health problems, evaluate the long-term effects of examinations and treatments, intervene in time, and reduce risks after examinations; Benefits of the feedback module: Adjust evaluation methods and standards, further personalize medical services, and maintain advancement and effectiveness.

[0148] Individual characteristic analysis unit, used to analyze the multivariate regression model formula of the patient's physiological characteristics:

[0149]

[0150] Among them, Feature i Represents various physiological characteristics, β i is the weight coefficient;

[0151] Tolerance prediction unit, using Bayesian classifier to predict tolerance, algorithm formula:

[0152]

[0153] Among them, P (Tolerance) is the prior probability of tolerance, and P (Features) is the joint probability of features;

[0154] The risk assessment of the impact of magnetic field on implants in the magnetic field impact assessment unit can use an expert system or rule engine, and its algorithm formula is:

[0155]

[0156] Among them, R iis the risk value evaluated by each rule, W i is the weight of the rule;

[0157] The gadolinium contrast agent risk assessment unit uses a logistic regression model to assess the risk of gadolinium contrast agent allergy. The algorithm formula is:

[0158]

[0159] The multivariate regression model evaluates the contribution of each physiological characteristic to the patient's overall risk by multiplying each physiological characteristic by its corresponding weight coefficient and summing up the influencing factors, which helps to identify high-risk patients and formulate effective treatment or examination plans;

[0160] The Bayesian classifier effectively handles uncertainty, allowing reasonable predictions when data is insufficient or noisy, helping to consider uncertainty in medical decision-making and helping doctors determine whether patients can tolerate specific tests or treatments;

[0161] The role of the expert system or rule engine ensures the scientificity and authority of the evaluation process, and can provide decision support for doctors to help determine whether patients should undergo MR examinations and ensure the safety of the examinations;

[0162] The role of the logistic regression model reflects the contribution of each feature to the risk of allergy, and the probability value output by the model can be used as an important decision-making basis for whether to use gadolinium contrast agents.

[0163] The risk integration analysis unit integrates risk data through a multi-criteria decision analysis algorithm. The algorithm formula is:

[0164]

[0165] Among them, w i is the weight of each risk factor, RiskScore i is the risk score;

[0166] The decision support unit generates decision suggestions based on Bayesian decision theory. The algorithm formula is:

[0167] OptimalDecision=argmax d ∑ j P(R j |d)×U(R j ,d),

[0168] Where d is the decision option, P(R j |d) is the result R that occurs under decision d j The probability of U(R j ,d) is the corresponding utility;

[0169] The real-time monitoring unit monitors the patient's physiological parameters through time series analysis. The algorithm formula is:

[0170]

[0171] in, is the predicted physiological parameter, φ i is the autoregressive coefficient, ∈ t is the error term.

[0172] The multi-criteria decision analysis algorithm is used in the risk integration analysis unit to comprehensively consider multiple risk factors and generate standardized risk scores, which helps doctors make comprehensive and personalized decisions;

[0173] Bayesian decision theory is used in decision support units to deal with uncertainty and provide probabilistic and personalized decision suggestions through the principle of utility maximization to ensure the optimality of medical plans;

[0174] Time series analysis helps doctors monitor and predict patients’ health status in real time through dynamic modeling and prediction of patients’ physiological data in real-time monitoring units, ensuring timely intervention and adjustment.

[0175] The feedback analysis unit uses multivariate analysis to evaluate the linear discriminant analysis of decision-making effects. The algorithm formula is:

[0176]

[0177] Among them, w i is the weight, x i is the feedback variable;

[0178] The system optimization unit uses the gradient descent algorithm with adaptive learning rate to optimize system parameters. The algorithm formula is:

[0179]

[0180] Among them, θ t is the parameter vector, η t is the learning rate, J(θ t ) is the loss function.

[0181] Linear discriminant analysis is used in the feedback analysis unit to evaluate the effect of decision-making, help identify effective decision-making strategies and improve unsatisfactory parts, thereby optimizing the decision-making process;

[0182] The gradient descent algorithm with adaptive learning rate is used in the system optimization unit to dynamically adjust system parameters, gradually improve the performance and accuracy of the system by minimizing the loss function, and achieve more accurate risk assessment and decision-making.

[0183] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A CT and MR examination risk assessment method based on an Internet hospital, characterized in that: The steps include: S1. Evaluate the patient's medical history, taking into account genetic factors, lifestyle, and underlying health conditions; S2. Determine the patient's age, gender, individual differences, and whether they are willing to accept the radiation and magnetic field effects caused by the examination; S3. Assess the risk of allergy to iodine contrast media and gadolinium contrast media; S4. Explain the purpose, procedure, risks, and results of CT or MR examinations; S5. Answer the patient's questions and make sure that the patient and his / her family understand and agree to the examination; S6. Decide whether to perform CT or MRI examination based on the evaluation; S7. Perform CT or MRI examination. S8. Interpret the examination results, combine them with the clinical history and clinical indications, and write the examination report; S9. Share the examination results with the patient and the medical team to discuss management and treatment plans, and interview patients who underwent CT or MR examinations to evaluate the effectiveness and impact of the examinations. S10. Based on the monitoring results, adjust the evaluation process to provide feedback to medical staff and patients.

2. A CT and MR examination risk assessment method based on an Internet hospital according to claim 1, characterized in that: In the step S3, the risk of allergy to contrast agents in patients is evaluated by a decision tree model, and the algorithm formula is: Support vector machine is used for more accurate allergy risk classification, and its algorithm formula is: Among them, K(x i ,x) is the kernel function, α i and b are model parameters.

3. The method for risk assessment of CT and MR examinations based on an Internet hospital according to claim 1, characterized in that: In step S6, the decision support system combines the information of the previous steps to output the final decision, and its algorithm formula is: Among them, w i is the weight of each evaluation item; In step S10, the risk assessment method is dynamically adjusted through a closed-loop feedback control system, and its algorithm formula is: New evaluation process = old evaluation process + λ × feedback difference, Among them, λ is the learning rate parameter.

4. The method for risk assessment of CT and MR examinations based on an Internet hospital according to claim 3, characterized in that: The decision support system is a computerized system used to assist the decision-making process and can help medical professionals make accurate and reasonable decisions in complex situations; The decision support system includes a data management module, a model management module, a knowledge base and a user interface module; the data management module is used to collect and manage relevant patient data; the model management module is used to process and analyze the collected data to generate relevant risk assessment and prediction results; the knowledge base provides standardized knowledge support for the system; the user interface module displays system analysis results, suggestions and decision support information to medical staff; The closed-loop feedback control system is a control mechanism that continuously monitors and adjusts the behavior of the system during operation, continuously evaluates the output results of the system through a feedback loop, and adjusts itself according to the results to achieve the predetermined goals; The closed-loop feedback control system includes sensors, controllers, actuators and feedback loops; the sensors are used to monitor and collect various data generated during the operation of the system; the controller analyzes the data collected by the sensors to determine whether the performance of the system meets the expected goals; the actuator adjusts the operation of the system according to the instructions of the controller; the feedback loop feeds back the output results of the system to the controller so that it can continuously adjust and optimize the system; The core of the closed-loop feedback control system lies in its adaptive adjustment capability, which is usually achieved by the following algorithm formula: Feedback difference calculation: e(t)=r(t)-y(t), Among them, e(t) is the error, r(t) is the expected result, and y(t) is the actual result; Controller adjustment formula: Where u(t) is the control input, K p is the proportional gain, K i is the integral gain, K d is the differential gain; System parameter update: i new =θ old +λ×e(t), Among them, θ represents the system parameters and λ is the learning rate.

5. A CT and MR examination risk assessment system, according to the CT and MR examination risk assessment method based on an Internet hospital according to any one of claims 1 to 4, characterized in that: It includes patient information management module, individual characteristics and tolerance assessment module, CT examination risk module, MR examination risk module, decision-making module, execution module, monitoring module and feedback module; The patient information management module is responsible for collecting relevant information of patients; The individual characteristics and tolerance assessment module is used to clarify the patient's basic information and tolerance factors to radiation or magnetic fields; The CT examination risk module is used to assess whether the patient can accept radiation and the impact of radiation on the patient's health; The MR examination risk module is responsible for evaluating whether there are implants in the patient's body that are affected by the magnetic field; The decision-making module decides whether to perform a CT or MR examination based on the personalized assessment; The execution module is responsible for performing CT or MR examinations and ensuring that the operations comply with safety standards and guidelines; The result interpretation and communication module is used to interpret the test results, combine them with the clinical history and clinical indications, and write the test report; The monitoring module regularly monitors patients undergoing CT or MR examinations; The feedback module adjusts the evaluation process according to the monitoring results.

6. A CT and MR examination risk assessment system according to claim 5, characterized in that: The patient information management module includes a patient data collection unit and an electronic medical record integration unit; the patient data collection unit is used to collect basic information of the patient; the electronic medical record integration unit extracts relevant medical history and examination records through the existing electronic medical record system; The individual characteristic and tolerance assessment module includes an individual characteristic analysis unit and a tolerance prediction unit; the individual characteristic analysis unit analyzes the individual physiological characteristics of the patient; the tolerance prediction unit predicts the patient's tolerance to the examination process based on the individual characteristics and historical data; The CT examination risk module includes a radiation risk assessment unit and an iodine contrast agent allergy assessment unit; the radiation risk assessment unit calculates the radiation dose caused by the CT scan to assess its short-term and long-term health effects on the patient; the iodine contrast agent allergy assessment unit assesses the patient's risk of allergy to iodine contrast agents; The MR examination risk module includes a magnetic field impact assessment unit and a gadolinium contrast agent risk assessment unit; the magnetic field impact assessment unit assesses the impact of a strong magnetic field on a patient during an MR examination; the gadolinium contrast agent risk assessment unit assesses the risk of an allergic reaction of a patient to a gadolinium-based contrast agent.

7. A CT and MR examination risk assessment system according to claim 5, characterized in that: The decision-making module includes a risk integration analysis unit and a decision support unit; the risk integration analysis unit combines the risk data from the CT and MR risk assessment modules with the individual characteristics of the patient, and gives examination recommendations after integrated analysis; the decision support unit generates a decision recommendation on whether to perform a CT or MR examination based on the results of the integrated analysis, and displays the recommendation to medical staff; The execution module includes an inspection parameter optimization unit and an execution management unit; The examination parameter optimization unit customizes CT or MR examination parameters for the patient according to the suggestions of the decision support unit; the execution management unit coordinates and executes the CT or MR examination; The monitoring module includes a real-time monitoring unit and an access unit; the real-time monitoring unit monitors the patient's physiological state in real time during the CT or MR examination; the access unit tracks the patient's health status after the examination, and records and analyzes potential side effects or adverse reactions; The feedback module includes a feedback analysis unit and a system optimization unit; the feedback analysis unit analyzes the data after the inspection and evaluates the effect of the inspection decision; the system optimization unit dynamically adjusts and optimizes the evaluation model and parameters of the system according to the results provided by the feedback analysis unit.

8. A CT and MR examination risk assessment system according to claim 6, characterized in that: The individual characteristic analysis unit is used to analyze the multivariate regression model formula of the patient's physiological characteristics: Among them, Feature i Represents various physiological characteristics, β i is the weight coefficient; The tolerance prediction unit uses a Bayesian classifier to predict tolerance, and the algorithm formula is: Among them, P (Tolerance) is the prior probability of tolerance, and P (Features) is the joint probability of features; The risk assessment of the implant being affected by the magnetic field in the magnetic field impact assessment unit can use an expert system or a rule engine, and its algorithm formula is: Among them, R i is the risk value evaluated by each rule, W i is the weight of the rule; The gadolinium contrast agent risk assessment unit uses a logistic regression model to assess the risk of gadolinium contrast agent allergy, and its algorithm formula is:

9. A CT and MR examination risk assessment system according to claim 7, characterized in that: The risk integration analysis unit integrates risk data through a multi-criteria decision analysis algorithm, the algorithm formula is: Among them, w i is the weight of each risk factor, RiskScore i is the risk score; The decision support unit generates decision suggestions based on Bayesian decision theory, and the algorithm formula is: OptimalDecision=argmax d ∑ j P(R j |d)×U(R j ,d), Where d is the decision option, P(R j |d) is the result R that occurs under decision d j The probability of U(R j ,d) is the corresponding utility; The real-time monitoring unit monitors the patient's physiological parameters through time series analysis, and the algorithm formula is: in, is the predicted physiological parameter, φ i is the autoregressive coefficient, ∈ t is the error term.

10. A CT and MR examination risk assessment system according to claim 7, characterized in that: The feedback analysis unit uses multivariate analysis to evaluate the linear discriminant analysis of decision-making effects. The algorithm formula is: Among them, w i is the weight, x i is the feedback variable; The system optimization unit uses a gradient descent algorithm with an adaptive learning rate to optimize system parameters. The algorithm formula is: Among them, θ t is the parameter vector, η t is the learning rate, J(θ t ) is the loss function.

Images