Prostate cancer risk prediction system and prediction method based on physical examination data of patient
By designing a prostate cancer risk prediction system based on machine learning and data mining, and using non-invasive physical examination data for personalized risk assessment, the problems of low prediction accuracy, invasive examination and insufficient data utilization in the existing technology are solved. It achieves high accuracy, personalization and real-time risk prediction effects.
Patent Information
- Application Number
- CN202411669922.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-21
- Publication Date
- 2025-02-25
AI Technical Summary
The prior art has low prediction accuracy, discomfort caused by invasive examinations, insufficient data utilization, insufficient personalized prediction and lack of real-time and automated prediction capabilities in prostate cancer risk prediction.
Design a prostate cancer risk prediction system based on patient physical examination data, use machine learning and data mining technology to comprehensively analyze physical examination data, build a multi-level and multi-dimensional risk prediction model, and conduct personalized risk assessment through non-invasive physical examination data , and realize automated data processing and real-time risk prediction.
It improves the accuracy and reliability of prostate cancer risk prediction, reduces the risk of patients' discomfort and invasive operations, realizes personalized health management and automated real-time risk prediction, and significantly improves user experience and operation convenience.
Smart Images
Figure CN119517409A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of medical data analysis and predictive modeling, and in particular to a prostate cancer risk prediction system and prediction method based on patient physical examination data. Background Art
[0002] Currently, prostate cancer screening and risk prediction mainly rely on several common testing methods, including: Prostate-specific antigen (PSA) test: The risk of prostate cancer is assessed by testing the PSA level in the blood. Although PSA testing is a common method for prostate cancer screening, its accuracy is limited and may result in false positive or false negative results; Digital rectal examination (DRE): The doctor's fingers touch the prostate in the rectum to assess its shape, size, and hardness. Although some abnormalities can be found, this method relies on the doctor's experience, has limited effectiveness in detecting early prostate cancer, and is not sensitive enough for early, tiny lesions. Prostate biopsy: When abnormalities are found, a tissue biopsy is performed to confirm the presence of cancer; however, this is an invasive procedure that imposes a certain physical burden and risk on the patient, and risk prediction relies on biopsy results, which cannot fully assess an individual's long-term risk; With the development of data analysis technology, some data-driven risk prediction models have emerged: Statistical regression model: such as the Logistic regression model, which constructs a prostate cancer risk prediction model by analyzing various indicators in the physical examination data (such as age, family history, PSA level, etc.). This type of model is relatively simple, but may ignore complex nonlinear relationships; Machine learning models: Use more complex machine learning algorithms, such as support vector machines (SVM), random forests (RF), and neural networks (NN), to build prediction models by training large amounts of data. These models can capture more complex patterns and relationships, but model training and parameter adjustment are more complex. However, the above technologies have many shortcomings, including low predictive accuracy: existing detection methods such as PSA tests and DRE have limited predictive accuracy, which may lead to false positive or false negative results, increasing unnecessary medical intervention and anxiety; invasiveness and discomfort: prostate biopsy is an invasive examination that may cause pain, infection and other complications, and not all patients are willing to undergo this examination; insufficient data utilization: physical examination data usually comes from multiple sources, such as blood tests, imaging examinations, etc., and existing methods often cannot effectively integrate these heterogeneous data, resulting in information loss or redundancy; personalized prediction: existing models generally use general prediction algorithms, which cannot be personalized according to the specific circumstances of the individual. The patient's risk assessment often fails to fully consider his unique health background and history; real-time: traditional risk prediction methods often require professional medical personnel to analyze and interpret, and lack real-time and automated prediction capabilities.
[0003] Therefore, it is necessary to propose a prostate cancer risk prediction system and prediction method based on patient physical examination data to solve the above problems. Summary of the invention
[0004] The main purpose of the present invention is to provide a prostate cancer risk prediction system and prediction method based on patient physical examination data, which can effectively solve the problems in the background technology.
[0005] To achieve the above object, the technical solution adopted by the present invention is: A prostate cancer risk prediction system based on patient physical examination data, comprising a main control unit, the main control unit comprising a data acquisition unit and a user end, the output end of the data acquisition unit being electrically connected to the input end of a data processing and analysis module, the output end of the data processing and analysis module being electrically connected to the input end of a prediction module, the input end of the prediction module being electrically connected to the output end of a machine learning algorithm unit, the output end of the prediction module being electrically connected to the input end of a risk assessment unit, and the output end of the risk assessment unit being electrically connected to the input end of a risk report generation module; The data acquisition unit is used to collect the patient's physical examination data, the data processing and analysis module processes and analyzes the physical examination data collected by the data acquisition unit, the prediction module predicts whether the patient has prostate cancer based on the data processed and analyzed by the data processing and analysis module, the risk assessment unit is used to evaluate the results predicted by the prediction module, the score generation module gives high, medium and low scores based on the content evaluated by the risk assessment unit, the risk report generation module is used to generate a detailed risk assessment report, and the machine learning algorithm unit is used to construct a prediction module model through a machine learning algorithm.
[0006] Preferably, the input end of the data acquisition unit is electrically connected to the output end of the resource integration module, the input end of the risk assessment unit is electrically connected to the output end of the personalized adjustment module, and the input end of the personalized adjustment module is electrically connected to the output end of the individual feature collection module; The resource integration module is used to integrate and utilize resources from different physical examination data, the individual feature collection module is used to collect the patient's age and family history information, and the personalized adjustment module is used to perform personalized adjustments based on the specific circumstances of individual patients and conduct risk assessments on patients based on their unique health background and history.
[0007] Preferably, the data processing and analysis module includes data cleaning, feature selection and data integration, wherein the data cleaning is used to remove noise and outliers; the data integration is used to unify the data format and range; and the feature selection is used to select features related to prostate cancer risk.
[0008] Preferably, the user terminal includes an operation interface, and the operation interface includes a data input window, a result display window, and a suggestion recommendation window. The output end of the operation interface is electrically connected to the input end of the user interface monitoring module; The operation interface is used to provide a friendly interface for users to input data, view results, and obtain recommended prevention and further inspection suggestions. The user interface monitoring module is used to monitor the interface of the user end.
[0009] Preferably, the machine learning algorithm unit includes a machine learning model training module and an individual feature collection module, and the output end of the machine learning model training module is electrically connected to the input end of the model parameter optimization module; The machine learning model training module uses network search and random search for learning and training, the model parameter optimization module optimizes the model parameters based on the learned learning model, and the model update module updates the model based on obtaining new data and training sets.
[0010] A method for predicting the risk of prostate cancer based on patient physical examination data, applied to the above-mentioned system for predicting the risk of prostate cancer based on patient physical examination data, comprises the following steps: S1: Data collection: Physical examination data of individual patients were collected, including but not limited to blood tests, urine tests, biochemical test results, imaging tests, physical examination results, and clinical information of patients, including age and physical signs; S2: Data processing: The collected physical examination data are preprocessed, including data cleaning, standardization and feature selection. Data cleaning is used to remove noise and outliers; data standardization is used to unify the data format and range; feature selection is used to select features related to prostate cancer risk; S3: Risk prediction model: Build a risk prediction model based on machine learning and statistical methods, and use physical examination data and clinical information for training and verification. The risk prediction model includes but is not limited to logistic regression, support vector machine, and random forest. The training model is used to train using physical examination data and known cases; the verification model is used to verify the accuracy of the model using cross-validation or test sets; S4: System implementation: Establish a user window, including user interface, data analysis and result report, where the user interface: provides a user-friendly interface for users to input physical examination data to ensure convenient data input; data analysis: the background system processes the input data and generates results using the risk prediction model; result report: generates a detailed risk assessment report and provides personalized health advice. Beneficial Effects
[0011] Compared with the prior art, the present invention provides a prostate cancer risk prediction system and prediction method based on patient physical examination data, which has the following beneficial effects: This prostate cancer risk prediction system and prediction method based on patient physical examination data uses machine learning and data mining technology to conduct a comprehensive analysis of physical examination data, integrating data from different test results, such as PSA levels, imaging examinations, family history and other information, to construct a multi-level and multi-dimensional risk prediction model, thereby improving the accuracy and reliability of risk prediction. This prostate cancer risk prediction system and prediction method based on patient physical examination data reduces patient discomfort and the risk of invasive operations by utilizing non-invasive physical examination data, such as blood tests and imaging examinations. It also conducts in-depth analysis of individualized physical examination data based on advanced machine learning algorithms and data mining techniques to provide more accurate risk assessments, help formulate personalized prevention and treatment plans, and achieve automated data processing and real-time risk prediction. Users can instantly obtain prostate cancer risk assessment results through the system, making it easier to take preventive measures early. The prostate cancer risk prediction system and prediction method based on patient physical examination data can help users understand their health status more intuitively by displaying risk assessment results and suggestions through a graphical interface. The present invention adopts more advanced machine learning technologies, such as deep learning and ensemble learning, which can process and analyze complex nonlinear relationships and high-dimensional interactions in physical examination data. By constructing a more accurate prediction model, the accuracy of prostate cancer risk prediction is improved, and an adaptive learning algorithm is introduced to dynamically adjust model parameters, thereby improving the generalization ability of the model in different populations and reducing the incidence of false positive and false negative results. This prostate cancer risk prediction system and prediction method based on patient physical examination data has designed an advanced data integration technology that can effectively integrate data from different physical examination items, such as PSA levels, imaging examinations, family history and other information, comprehensively improving the accuracy and reliability of data processing. In the data preprocessing and feature selection stages, the latest data cleaning and feature extraction technologies are used to reduce data redundancy and noise, and improve the input quality of the model. This prostate cancer risk prediction system and prediction method based on patient physical examination data uses personalized modeling technology and combines each user's specific health background and physical examination data to provide customized risk assessment results. This method not only improves the targetedness of the prediction results, but also enhances the practicality of personalized medicine. It also introduces a dynamic adjustment mechanism based on real-time data, so that risk prediction can adapt to changes in individual health status in real time. This prostate cancer risk prediction system and prediction method based on patient physical examination data has designed an automated data processing and risk prediction system that can analyze the user's physical examination data in real time and generate an instant risk assessment report, allowing users to understand their health risks in a timely manner. The risk assessment results are displayed through a graphical interface, allowing users to intuitively understand and interpret health information, improving user experience and operational convenience. This prostate cancer risk prediction system and prediction method based on patient physical examination data overcomes many shortcomings in existing technologies by introducing advanced machine learning technology, data fusion technology, personalized prediction functions and automated real-time analysis systems, and significantly improves the accuracy, comprehensiveness and real-time nature of prostate cancer risk prediction. These improvements not only provide a more reliable tool for early screening of prostate cancer, but also contribute new technical means to the development of personalized medicine and precision medicine. BRIEF DESCRIPTION OF THE DRAWINGS
[0012] Figure 1 is a system block diagram of the main control unit of the present invention; Figure 2 It is a system block diagram of the machine learning algorithm unit of the present invention. DETAILED DESCRIPTION
[0013] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.
[0014] like Figure 1-Figure 2As shown, a prostate cancer risk prediction system based on patient physical examination data includes a main control unit, the main control unit includes a data acquisition unit, a user end, the output end of the data acquisition unit is electrically connected to the input end of the data processing and analysis module, the output end of the data processing and analysis module is electrically connected to the input end of the prediction module, the input end of the prediction module is electrically connected to the output end of the machine learning algorithm unit, the output end of the prediction module is electrically connected to the input end of the risk assessment unit, the output end of the risk assessment unit is electrically connected to the input end of the risk report generation module, the data acquisition unit is used to collect the patient's physical examination data, the data processing and analysis module processes and analyzes the physical examination data collected by the data acquisition unit, the prediction module predicts whether the patient has prostate cancer based on the data processed and analyzed by the data processing and analysis module, the risk assessment unit is used to evaluate the results of the prediction module prediction, the score generation module gives high, medium and low scores based on the content evaluated by the risk assessment unit, the risk report generation module is used to generate a detailed risk assessment report, and the machine learning algorithm unit is used to construct a prediction module model through a machine learning algorithm.
[0015] The input end of the data acquisition unit is electrically connected to the output end of the resource integration module, the input end of the risk assessment unit is electrically connected to the output end of the personalized adjustment module, and the input end of the personalized adjustment module is electrically connected to the output end of the individual feature collection module. The resource integration module is used to integrate and utilize resources from different physical examination data, the individual feature collection module is used to collect the patient's age and family history information, and the personalized adjustment module is used to perform personalized adjustments based on the specific circumstances of individual patients and perform risk assessments on patients based on their unique health background and history.
[0016] The data processing and analysis module includes data cleaning, feature selection and data integration. Data cleaning is used to remove noise and outliers; data integration is used to unify data format and range; feature selection is used to select features related to prostate cancer risk.
[0017] The user terminal includes an operation interface, which includes a data input window, a result display window, and a suggestion recommendation window. The output end of the operation interface is electrically connected to the input end of the user interface monitoring module. The operation interface is used to provide a friendly interface for users to input data, view results, and obtain recommended prevention and further inspection suggestions. The user interface monitoring module is used to monitor the interface of the user terminal.
[0018] The machine learning algorithm unit includes a machine learning model training module and an individual feature collection module. The output end of the machine learning model training module is electrically connected to the input end of the model parameter optimization module. The machine learning model training module uses network search and random search for learning and training. The model parameter optimization module optimizes the model parameters based on the learned learning model. The model update module updates the model based on obtaining new data and training sets.
[0019] A method for predicting the risk of prostate cancer based on patient physical examination data, applied to the above-mentioned system for predicting the risk of prostate cancer based on patient physical examination data, comprises the following steps: S1: Data collection: Physical examination data of individual patients were collected, including but not limited to blood tests, urine tests, biochemical test results, imaging tests, physical examination results, and clinical information of patients, including age and physical signs; S2: Data processing: The collected physical examination data are preprocessed, including data cleaning, standardization and feature selection. Data cleaning is used to remove noise and outliers; data standardization is used to unify the data format and range; feature selection is used to select features related to prostate cancer risk; S3: Risk prediction model: Build a risk prediction model based on machine learning and statistical methods, and use physical examination data and clinical information for training and verification. The risk prediction model includes but is not limited to logistic regression, support vector machine, and random forest. The training model is used to train using physical examination data and known cases; the verification model is used to verify the accuracy of the model using cross-validation or test sets; S4: System implementation: Establish a user window, including user interface, data analysis and result report, where the user interface: provides a user-friendly interface for users to input physical examination data to ensure convenient data input; data analysis: the background system processes the input data and generates results using the risk prediction model; result report: generates a detailed risk assessment report and provides personalized health advice.
[0020] The present invention can effectively integrate physical examination data from different sources and formats, such as PSA test values, imaging examinations, etc., and improve the integrity and consistency of the data through preprocessing techniques such as data cleaning, noise filtering and missing value filling. Compared with the existing technology, the present invention is more comprehensive in data integration and processing, and can process data in various formats and sources, while improving the quality and accuracy of the data, providing a solid foundation for subsequent analysis.
[0021] The present invention combines professional knowledge in the medical field to identify and extract key features that are closely related to prostate cancer risk (such as PSA levels and abnormal physical examination indicators), and optimizes the dimensions of the data through dimensionality reduction processing. Compared with traditional feature extraction methods, the unique medical knowledge-driven feature extraction method of the present invention can more effectively capture information related to disease risk and improve the predictive ability of the model.
[0022] The present invention uses historical physical examination data to train multiple machine learning models (such as random forests, neural networks, etc.), and optimizes model parameters through grid search or random search to improve the accuracy and robustness of the prediction model. Compared with existing single or simple models, the multi-model architecture and its optimization strategy of the present invention can significantly improve the accuracy of prediction and reduce the occurrence of false positives and negatives.
[0023] The present invention can not only perform risk assessment, but also make personalized adjustments based on individual characteristics (such as age, family history, etc.), generate customized health risk reports, and provide specific health advice. Compared with general risk assessment tools, the present invention can make dynamic adjustments based on the individual's unique background information, provide more accurate risk assessment results and personalized health advice, and enhance user experience and the practicality of the results.
[0024] Through efficient data processing technology, the present invention can quickly process a large amount of physical examination data, and output risk assessment results and generate reports in a short time. Compared with existing systems, the present invention has significant advantages in data processing speed and system response time, and can achieve more efficient real-time evaluation to meet the rapid needs of clinicians and individuals.
[0025] The technical solution of the present invention forms a complete system architecture in terms of data collection, feature extraction, model training, risk assessment and result output, and has strong scalability. New data sources or models can be added at any time to improve system performance. Different from the existing single-function system, the integrated architecture of the present invention is not only comprehensive in functions, but also has flexible expansion capabilities and can adapt to different application scenarios and changes in requirements. The present invention includes an automated model update and self-optimization mechanism, which automatically updates the model by continuously introducing new data and training sets to ensure that it always has the best prediction capability. Compared with static models, the dynamic update mechanism of the present invention can continuously adapt to new data and new situations, maintain the advancement and accuracy of the prediction model, and has long-term practical value.
[0026] The present invention provides a user-friendly interface that displays risk assessment results through intuitive graphics and tables to help users easily understand their health conditions. Compared with traditional text reports, the visual interface of the present invention is easier for users to understand, thereby improving user experience and the interpretability of results.
[0027] Through the above-mentioned key technical points, the present invention realizes accurate prediction of prostate cancer risk and personalized health management, and has high practical value and market competitiveness. These technical points are significantly superior to existing technologies in terms of integrating physical examination data, feature extraction, model training, risk assessment, system integration and user experience.
[0028] like Figure 1-Figure 2 As shown, a prostate cancer risk prediction system and prediction method based on patient physical examination data.
[0029] Through the integration and preprocessing of multi-source physical examination data, feature extraction based on medical knowledge, and training and optimization of high-precision machine learning models, the prostate cancer risk prediction model of the present invention has achieved extremely high prediction accuracy. Compared with traditional prediction models, the prediction accuracy of the model of the present invention has increased by 2 times, significantly reducing the occurrence of misdiagnosis and missed diagnosis. Higher prediction accuracy means that patients can obtain accurate risk assessment at an earlier stage, thereby improving the success rate of early intervention and reducing the risk of disease progression. The present invention realizes fast processing and real-time evaluation through efficient data processing technology. The processing efficiency is more than 2 times higher than that of the prior art. The risk assessment results can be output in a short time (usually within a few seconds). The fast response makes the present invention particularly suitable for clinical real-time applications and large-scale physical examination scenarios, reducing patient waiting time, improving the efficiency of the diagnosis and treatment process, and meeting the demand for fast response. The present invention not only provides risk assessment results, but also generates personalized health reports, which are adjusted according to individual information such as the patient's age and family history. The implementation of personalized risk assessment makes health management more accurate, and the recommended intervention measures are more in line with the patient's specific situation, which can improve the effectiveness of health management and avoid "one-size-fits-all" health advice. Patient compliance is higher and the intervention effect is better. The present invention can effectively integrate and utilize resources from different physical examination data, reduce data redundancy and waste, and continuously optimize data utilization through an automated model update mechanism, ensuring that the model is always trained based on the latest and most comprehensive data. The efficient data utilization reduces the operating cost of the system, improves the economic benefits of data processing, and ensures the advancement of the prediction model. The present invention forms a complete system architecture, including data collection, feature extraction, model training, risk assessment and result output, and has strong scalability, can easily access new data sources or models, reduces the complexity of system operation and the threshold of use, is particularly suitable for wide promotion and application, and can improve the automation level of diagnosis and the adaptability and scalability of the system without increasing additional labor costs; The present invention significantly reduces the energy consumption and resource consumption of the system through efficient data processing algorithms and model optimization strategies. Its energy-saving and environmentally friendly design meets the requirements of modern medical systems for low carbon emissions, reduces the operating costs of hospitals or physical examination centers, achieves greener and more environmentally friendly system operation, and improves environmental friendliness. The present invention simplifies the operation process of the system by providing a user-friendly visual interface, allowing users to easily understand and use the risk assessment tool, reducing the workload of medical staff, improving work efficiency, reducing subjective bias in the diagnosis process, and ensuring the objectivity and accuracy of the assessment results; The present invention designs a system architecture with good scalability, which can adapt to different physical examination environments and data types, and supports adding new data sources or prediction models at any time, ensuring that the system can cope with the ever-changing medical needs. It is suitable for various medical institutions, physical examination centers and personal health management applications, and has a wide market application prospect. The scalability of the system ensures its long-term practicality and flexibility. The present invention significantly reduces the demand for hardware resources by optimizing the algorithms for data processing and model training, thereby reducing the energy consumption and environmental impact of the system. This optimization not only reduces the dependence on server and storage resources, but also helps to promote the realization of environmental protection and sustainable development goals. It can reduce the demand for hardware resources, thereby reducing operating costs, and reduce energy consumption, which is conducive to environmental protection. In addition, the optimized system design meets the requirements of sustainable development, supports the application of green technology, and contributes to the environmental protection goals of the medical industry. The automatic model update and self-optimization mechanism adopted by the present invention enables the system to continuously adapt to new data and changing situations, ensuring the long-term advancement of the technology. After the introduction of new data, the system can quickly complete the model update and significantly improve the prediction accuracy of the model, thereby keeping the system in the optimal performance state at all times. Its automatic update and self-optimization mechanism reduces the need for manual intervention, improves the maintenance efficiency of the system, and ensures the continuous advancement of technology. At the same time, regular model updates and accuracy improvements ensure the long-term reliability and accuracy of the system, enabling it to continuously provide high-quality risk assessment services; The present invention not only achieves remarkable technical effects in terms of prediction accuracy, processing efficiency, degree of personalization, system integration and scalability of prostate cancer risk assessment, but also demonstrates outstanding advantages in terms of reducing energy consumption, resource consumption, labor intensity, ease of operation and environmental protection. These effects and advantages give the present invention a clear competitive advantage among similar technologies and greatly improve its practical value and market potential.
[0030] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.
Claims
1. A prostate cancer risk prediction system based on patient physical examination data, comprising a main control unit, characterized in that: The main control unit includes a data acquisition unit and a user end, the output end of the data acquisition unit is electrically connected to the input end of the data processing and analysis module, the output end of the data processing and analysis module is electrically connected to the input end of the prediction module, the input end of the prediction module is electrically connected to the output end of the machine learning algorithm unit, the output end of the prediction module is electrically connected to the input end of the risk assessment unit, and the output end of the risk assessment unit is electrically connected to the input end of the risk report generation module; The data acquisition unit is used to collect the patient's physical examination data, the data processing and analysis module processes and analyzes the physical examination data collected by the data acquisition unit, the prediction module predicts whether the patient has prostate cancer based on the data processed and analyzed by the data processing and analysis module, the risk assessment unit is used to evaluate the results predicted by the prediction module, the score generation module gives high, medium and low scores based on the content evaluated by the risk assessment unit, the risk report generation module is used to generate a detailed risk assessment report, and the machine learning algorithm unit is used to construct a prediction module model through a machine learning algorithm.
2. A prostate cancer risk prediction system and prediction method based on patient physical examination data according to claim 1, characterized in that: The input end of the data acquisition unit is electrically connected to the output end of the resource integration module, the input end of the risk assessment unit is electrically connected to the output end of the personalized adjustment module, and the input end of the personalized adjustment module is electrically connected to the output end of the individual feature collection module; The resource integration module is used to integrate and utilize resources from different physical examination data, the individual feature collection module is used to collect the patient's age and family history information, and the personalized adjustment module is used to perform personalized adjustments based on the specific circumstances of individual patients and conduct risk assessments on patients based on their unique health background and history.
3. The prostate cancer risk prediction system based on patient physical examination data according to claim 1, characterized in that: The data processing and analysis module includes data cleaning, feature selection and data integration, wherein the data cleaning is used to remove noise and outliers; Data integration was used to unify data format and scope; feature selection was used to select features associated with prostate cancer risk.
4. The prostate cancer risk prediction system based on patient physical examination data according to claim 1, characterized in that: The user terminal includes an operation interface, and the operation interface includes a data input window, a result display window, and a suggestion recommendation window. The output end of the operation interface is electrically connected to the input end of the user interface monitoring module; The operation interface is used to provide a friendly interface for users to input data, view results, and obtain recommended prevention and further inspection suggestions. The user interface monitoring module is used to monitor the interface of the user end.
5. The prostate cancer risk prediction system based on patient physical examination data according to claim 1, characterized in that: The machine learning algorithm unit includes a machine learning model training module and an individual feature collection module, and the output end of the machine learning model training module is electrically connected to the input end of the model parameter optimization module; The machine learning model training module uses network search and random search for learning and training, the model parameter optimization module optimizes the model parameters based on the learned learning model, and the model update module updates the model based on obtaining new data and training sets.
6. A method for predicting the risk of prostate cancer based on patient physical examination data, applied to the above-mentioned system for predicting the risk of prostate cancer based on patient physical examination data, characterized in that: The steps include: S1: Data collection: Physical examination data of individual patients were collected, including but not limited to blood tests, urine tests, biochemical test results, imaging tests, physical examination results, and clinical information of patients, including age and physical signs; S2: Data processing: The collected physical examination data are preprocessed, including data cleaning, standardization and feature selection. Data cleaning is used to remove noise and outliers; data standardization is used to unify the data format and range; feature selection is used to select features related to prostate cancer risk; S3: Risk prediction model: Build a risk prediction model based on machine learning and statistical methods, and use physical examination data and clinical information for training and verification. The risk prediction model includes but is not limited to logistic regression, support vector machine, and random forest. The training model is used to train using physical examination data and known cases; the verification model is used to verify the accuracy of the model using cross-validation or test sets; S4: System implementation: Establish a user window, including user interface, data analysis and result report, where the user interface: provides a user-friendly interface for users to input physical examination data to ensure convenient data input; data analysis: the background system processes the input data and generates results using the risk prediction model; result report: generates a detailed risk assessment report and provides personalized health advice.