Intelligent decision-making breast cancer patient home care system

Abstract

The present application relates to medical care intelligent management system, specifically to a kind of intelligent decision-making type breast cancer patient home care system, including patient electronic archives system and intelligent decision-making algorithm system, the patient electronic archives system is linked with visual management module, visual management module includes patient data panorama view unit and health trend chart analysis unit, the intelligent decision-making algorithm system is built-in clinical rule and algorithm model, the intelligent decision-making algorithm system is linked with decision support module and early warning trigger module, the early warning trigger module is linked with individualized intervention scheme management module, the early warning trigger module is used for patient abnormal data real-time analysis risk early warning.The present application can realize the standardization and individualization of care, convert the recommendation of international clinical guidelines into structured and executable digital path, and ensure that each patient can receive evidence-based standard care.

Description

Technical Field

[0001] This invention relates to an intelligent management system for medical care, specifically to an intelligent decision-making home care system for breast cancer patients. Background Technology

[0002] Existing breast cancer care management platforms primarily focus on simple information recording, lacking a closed-loop decision engine for symptom intervention feedback. They typically still rely on NCI-CTCAE 4.0 text-based assessments for peripheral neuropathy, failing to automatically map subjective symptoms like numbness, tingling, and burning to non-pharmacological intervention plans. Furthermore, by only providing health education content, they cannot generate structured, quantifiable, and actionable personalized non-pharmacological intervention plans based on the patient's current symptoms, severity, and historical data, thus lacking personalized intervention guidance. Patient information, chemotherapy records, physiological indicators, and symptom assessments are scattered across different modules or systems, failing to effectively integrate into a unified, comprehensive patient view. Additionally, most information management systems remain at the data recording and viewing level, lacking rule-based intelligent algorithms for real-time analysis and risk warnings of abnormal data. They cannot proactively alert healthcare professionals before problems occur, and their passive response approach cannot meet high-standard care requirements. Moreover, due to weak decision support capabilities, they fail to fully utilize accumulated data to provide healthcare professionals with intelligent decision support through big data analysis and machine learning models, such as chemotherapy regimen optimization, toxicity prediction, and efficacy evaluation. Therefore, there is an urgent need for an intelligent decision-making home care system for breast cancer patients to solve the above problems. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide an intelligent decision-making home care system for breast cancer patients, addressing the shortcomings of existing technologies.

[0004] The technical problem to be solved by this invention is achieved through the following technical solution: This invention discloses an intelligent decision-making home care system for breast cancer patients, including a patient electronic record system and an intelligent decision-making algorithm system. The patient electronic record system is linked to a visualization management module, which includes a panoramic view unit of patient data and a health trend chart analysis unit. The intelligent decision-making algorithm system has built-in clinical rules and algorithm models. The algorithm model is used to perform real-time analysis of the data input from the patient electronic record system according to preset clinical rules. The intelligent decision-making algorithm system is linked to a decision support module and an early warning triggering module. The early warning triggering module is used to perform real-time risk warning analysis of abnormal patient data through algorithm mapping. The early warning triggering module is linked to a personalized intervention plan management module. The early warning triggering module has built-in threshold setting unit and automatic reminder unit. The automatic reminder unit is used to remind medical staff to intervene through the medical staff terminal after the threshold is triggered, and at the same time generate personalized intervention plan suggestions through the patient terminal.

[0005] Furthermore, the patient electronic record system is linked to a patient information management module, a chemotherapy full-cycle recording module, and a real-time health monitoring module. The real-time health monitoring module includes physiological indicator data units, symptom data units, and psychological state data units.

[0006] Furthermore, the physiological index data unit is used to collect and record sensor measurement data including heart rate, blood pressure, body temperature, and blood oxygen, and the symptom data unit is used to collect chemotherapy side effect symptom data.

[0007] Furthermore, the psychological state data unit is used to collect patient psychological state feedback data, and the psychological state data unit includes an emotional state module, a stress level module, and a coping strategy module.

[0008] Furthermore, the decision support module is used to provide decision support to medical staff based on data generated by the algorithm to provide personalized care guidance to patients. The decision support module includes a toxicity prediction unit, a efficacy assessment unit, a chemotherapy regimen optimization unit, and a report generation unit. The report generation unit is used to generate chemotherapy reports and health reports within a certain period.

[0009] Furthermore, the personalized intervention plan management module includes a management plan for outputting non-pharmacological interventions for peripheral neurotoxicity. The personalized intervention plan management module is linked to an intervention execution module. The intervention execution module includes a chemotherapy reminder module, an intervention plan reminder module, a functional exercise reminder module, a health monitoring reminder module, and a care plan management module for managing the entire intervention process. The care plan management module includes a daily care plan and an emergency care plan. The functional exercise reminder module is used to provide time-sequential reminders for the intervention methods and dosages in the intervention plan. The health monitoring reminder module includes a sleep reminder unit.

[0010] Furthermore, the output process of the non-pharmacological intervention management plan for peripheral neurotoxicity includes a process of matching personalized intervention plans for chemotherapy-induced peripheral neurotoxicity based on data from an intelligent decision-making algorithm system. The personalized matching items of the non-pharmacological intervention management plan for peripheral neurotoxicity include symptom grading information, recommended intervention methods, recommended intervention doses, and information on the rationale behind the intervention. The intelligent decision-making algorithm system can grade patients' symptoms based on patient data and automatically match intervention methods and doses while simultaneously displaying the rationale behind the current intervention method.

[0011] Furthermore, the personalized intervention program management module is linked to an intervention effect analysis module and an intervention program reporting module. The intervention effect analysis module is used to collect and record patient data during the implementation of the intervention program and to calculate and analyze the implementation effect of the intervention program by comparing historical data.

[0012] Furthermore, the intervention effect analysis module is used to perform health trend analysis on individual physiological parameters of patients in the form of charts, and the intervention plan report module is used to generate an overall intervention plan report by integrating the data from the intervention effect analysis module.

[0013] Compared with the prior art, the present invention has the following advantages: (1) This invention can achieve the standardization and personalization of care, transform the recommendations of international clinical guidelines into a structured and executable digital path, ensuring that every patient can receive evidence-based standardized care, and at the same time, through the algorithm, the intervention content is dynamically adjusted according to individual data to achieve personalized management for each individual. (2) This invention can improve the timeliness and effectiveness of toxicity management, and change the past model of relying on patients to actively and frequently return to the hospital to report problems. Through real-time symptom monitoring and intelligent graded early warning, the identification and management window of toxicity such as CIPN can be significantly advanced. Intervention can be carried out in the mild stage of symptoms (level 1-2), which may prevent it from progressing to serious irreversible toxicity, thereby ensuring the smooth completion of chemotherapy and quality of life. (3) This invention can optimize the allocation of medical resources and improve service efficiency. The system automates a large number of repetitive tasks such as data collection, preliminary analysis, reminders, and report generation, enabling medical staff to focus on high-value clinical decision-making and in-depth communication, and allowing limited medical resources to cover more patients. (4) By accumulating real clinical practice data, this invention feeds back into clinical research. The system can continuously collect structured patient home data, which can further optimize chemotherapy regimens, verify the effectiveness of intervention measures, and be used to train more accurate machine learning prediction models, forming a closed-loop optimization of "clinical-data-algorithm-clinical" to continuously improve the quality of medical care. Attached Figure Description

[0014] Figure 1 This is a schematic diagram of the overall principle structure of the intelligent decision-making home care system for breast cancer patients of this invention; Figure 2 This is a schematic diagram illustrating the working principle and structure of the personalized intervention management module of this invention. Detailed Implementation

[0015] like Figure 1-2As shown, this invention discloses an intelligent decision-making home care system for breast cancer patients, comprising a patient electronic record system and an intelligent decision-making algorithm system. The patient electronic record system is linked to a visualization management module, which includes a panoramic view of patient data and a health trend chart analysis unit. The system is also linked to a patient information management module, a chemotherapy full-cycle recording module, and a real-time health monitoring module. The real-time health monitoring module includes physiological indicator data units, symptom data units, and psychological state data units. The physiological indicator data units include sensors for measuring heart rate, blood pressure, body temperature, and blood oxygen saturation. The symptom data unit is used for collecting data on chemotherapy side effects. The psychological state data unit is used for collecting psychological state data feedback. The psychological state data unit includes modules for emotional state, stress level, and coping strategies. The patient's physiological indicator data can also include urinalysis, biochemistry, electromyography, nerve conduction velocity measurement, and breast tumor markers. The patient can synchronously update these physiological indicator data in the system during regular hospital checkups.

[0016] The aforementioned intelligent decision-making algorithm system incorporates clinical rules and algorithm models. It is linked to a decision support module and an early warning triggering module. The early warning triggering module is linked to a personalized intervention plan management module. The early warning triggering module is used for real-time analysis and risk warning of abnormal patient data. It includes a threshold setting unit and an automatic reminder unit. The personalized intervention plan management module generates intervention plan suggestions after the threshold is triggered. The decision support module includes a toxicity prediction unit, a efficacy evaluation unit, a chemotherapy regimen optimization unit, and a report generation unit. The report generation unit generates chemotherapy reports and health reports for a specific period.

[0017] The personalized intervention management module includes a management plan for outputting non-pharmacological interventions for peripheral neurotoxicity. This module is linked to an intervention execution module, which includes a chemotherapy reminder module, an intervention plan reminder module, a functional exercise reminder module, a health monitoring reminder module, and a care plan management module for managing the entire intervention process. The care plan management module includes daily care plans and emergency care plans. The functional exercise reminder module provides time-sequential reminders for the intervention methods and dosages within the intervention plan. The health monitoring reminder module includes a sleep reminder unit for managing the patient's sleep process.

[0018] The output process of the non-pharmacological intervention management plan for peripheral neurotoxicity includes the process of matching personalized intervention plans for chemotherapy-induced peripheral neurotoxicity based on data from an intelligent decision-making algorithm system. The personalized matching items of the non-pharmacological intervention management plan for peripheral neurotoxicity include symptom grading information, recommended intervention methods, recommended intervention doses, and information on the rationale behind the intervention. The intelligent decision-making algorithm system can grade patients' symptoms based on patient data and automatically match intervention methods and doses while simultaneously displaying the rationale behind the current intervention method.

[0019] The following table, based on domestic and international clinical guidelines and evidence-based research, explains how the system of this invention achieves personalized matching: Symptoms and Grading Recommended intervention methods Intervention dose Principles and Basis Level 1 (Mild): Asymptomatic or mild symptoms; only clinical or diagnostic findings; no disruption to daily life. 1. Exercise therapy: ① Aerobic exercise (e.g., walking); ② Balance training (e.g., Tai Chi) 2. Patient education: ① Fall prevention education; ② Avoidance of cold stimuli 1. Exercise: Moderate intensity, 3-5 times per week, 20-30 minutes each time. 2. Patient education: Continuous. Principle: For mild symptoms, prevention and slowing progression are key. Exercise can improve nerve blood flow, neurotrophic factor expression, and enhance proprioception and balance. Education improves self-management awareness. Basis: Multiple RCT studies have shown that regular exercise can significantly reduce the incidence and severity of CIPN (supported by ASCO guidelines). Grade 2 (Moderate): Symptoms affect instrumental daily living activities (such as cooking and shopping); but the patient is still able to perform daily living activities. 1. Exercise therapy (intensification): ① Targeted strength training (e.g., grip strength training); ② Balance training 2. Physical therapy: ① Neuromuscular electrical stimulation (NMES) 3. Thermotherapy: ① Cryotherapy (e.g., cold gloves) 1. Targeted strength training: Targeting small muscle groups in the hands / feet, 10-15 repetitions per set, 2-3 sets daily. 2. NMES: Frequency 50-100Hz, sensory stimulation, 20-30 minutes per session, 1-2 times daily. 3. Cryotherapy: Wear cold gloves / socks for 90 minutes during and after chemotherapy. Principle: Moderate symptoms require active intervention to improve function. Strength training combats muscle atrophy; NMES maintains neuromuscular function through electrical stimulation, preventing disuse atrophy; cryotherapy reduces the dose of chemotherapy drugs reaching the extremities through vasoconstriction. Basis: Multiple studies have confirmed that NMES and cryotherapy can significantly reduce the incidence and severity of CIPN (mentioned in ESMO guidelines, and recommended by NCCN guidelines). Grade 3 (Severe): Symptoms affect daily activities (such as eating, dressing, and toileting); the patient needs assistance. 1. Comprehensive rehabilitation: ① Occupational therapy (assistive tool use training) ② Physical therapy (forced movement therapy) 2. Consultation with a rehabilitation / neurology department is strongly recommended. 1. Rehabilitation training: Conducted under the guidance of a therapist, with personalized intensity and higher frequency (e.g., once daily). 2. System function: The system will issue a strong alarm and recommend immediate medical attention or adjustment of the chemotherapy regimen. Principle: Severe symptoms have led to disability. Non-pharmacological interventions aim to maximize functional recovery and prevent further harm, but the primary task is to assess the necessity of the chemotherapy regimen. Basis: For grade 3 and above CIPN, the National Clinical Research Center (NCCN) guidelines typically recommend reducing or discontinuing chemotherapy. Non-pharmacological interventions, as an important adjunct, must be conducted under professional guidance. The aforementioned personalized intervention program management module is also linked to an intervention effect analysis module and an intervention program reporting module. The intervention effect analysis module is used to collect and record patient data during the implementation of the intervention program and to calculate and analyze the implementation effect of the intervention program by comparing historical data. The intervention effect analysis module is used to perform health trend analysis on individual physiological parameters of patients in the form of charts. The intervention program reporting module is used to generate an overall intervention program report by integrating the data from the intervention effect analysis module.

[0020] This system features a dual-platform design: a healthcare team-facing end (the network management backend) and a patient-facing end (a mobile app) to meet the needs of different roles. It is a microservices-based intelligent medical information system. Its core principle is: collecting multidimensional patient data through IoT devices / manual patient input; integrating the data using big data storage and management technologies; analyzing and processing the data through intelligent algorithms and rule engines in the business logic layer (i.e., the Echo framework); and finally providing personalized care guidance to patients and decision support and early warnings to healthcare staff through the user interface layer.

[0021] The system of this invention achieves home care through the following aspects: 1. Information collection and monitoring: Patients regularly enter health data (heart rate, blood pressure, body temperature, blood oxygen), chemotherapy side effects (such as neurotoxicity, nausea, fatigue), and psychological state through mobile applications or automatically upload data through connected devices, enabling remote and continuous monitoring of patients' health status and replacing some examinations that require hospitalization.

[0022] 2. Data integration and visualization: The system integrates all data into a unified electronic patient record and conducts health trend analysis through charts and other forms. Medical staff can remotely and comprehensively grasp the overall situation of patients at home, rather than relying solely on fragmented patient complaints to understand the patient's condition.

[0023] 3. Intelligent Analysis and Decision Support: This is the system's brain. The built-in algorithms analyze the input data in real time according to preset clinical rules. For example, when a patient reports "numbness in the fingers, persistent, affecting fine motor skills but not daily life," the system may identify it as Grade 2 peripheral neurotoxicity. The system automatically triggers an alert to notify medical staff and immediately pushes a personalized non-pharmacological intervention plan for Grade 2 neurotoxicity to the patient.

[0024] 4. Personalized Intervention and Reminders: The system not only provides suggestions but also manages the entire intervention process, including through chemotherapy reminder modules, intervention plan reminder modules, functional exercise reminder modules, health monitoring reminder modules, and care plan management modules. This ensures that patients can follow the treatment and rehabilitation plan on time and correctly at home, extending hospital care standards to the home.

[0025] 5. Communication and Reporting: The system can automatically provide feedback and generate detailed intervention reports and health reports, which facilitates communication between doctors and patients and collaboration between doctors inside and outside the hospital. This establishes an effective information bridge between patients at home and professional medical care in the hospital, making home care an integral part of the entire treatment process.

[0026] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A smart decision-making home care system for breast cancer patients, characterized in that: The system includes a patient electronic record system and an intelligent decision-making algorithm system. The patient electronic record system is linked to a visualization management module, which includes a panoramic view of patient data and a health trend chart analysis unit. The intelligent decision-making algorithm system has built-in clinical rules and algorithm models. The algorithm models are used to perform real-time analysis of the data input from the patient electronic record system according to preset clinical rules. The intelligent decision-making algorithm system is linked to a decision support module and an early warning triggering module. The early warning triggering module is used to perform real-time risk warning analysis of abnormal patient data through algorithm mapping. The early warning triggering module is linked to a personalized intervention plan management module. The early warning triggering module has built-in threshold setting unit and automatic reminder unit. The automatic reminder unit is used to remind medical staff to intervene through the medical staff terminal after the threshold is triggered, and at the same time generate personalized intervention plan suggestions through the patient terminal.

2. The intelligent decision-making home care system for breast cancer patients according to claim 1, characterized in that: The patient electronic record system is linked to a patient information management module, a chemotherapy full-cycle recording module, and a real-time health monitoring module. The real-time health monitoring module includes physiological indicator data units, symptom data units, and psychological state data units.

3. The intelligent decision-making home care system for breast cancer patients according to claim 2, characterized in that: The physiological index data unit is used to collect and record sensor measurement data including heart rate, blood pressure, body temperature, and blood oxygen, while the symptom data unit is used to collect data on chemotherapy side effects symptoms.

4. The intelligent decision-making home care system for breast cancer patients according to claim 2, characterized in that: The psychological state data unit is used to collect patient psychological state feedback data, and the psychological state data unit includes an emotional state module, a stress level module, and a coping strategy module.

5. The intelligent decision-making home care system for breast cancer patients according to claim 1, characterized in that: The decision support module is used to provide decision support to medical staff based on data generated by the algorithm, so as to provide personalized care guidance to patients. The decision support module includes a toxicity prediction unit, a efficacy evaluation unit, a chemotherapy regimen optimization unit, and a report generation unit. The report generation unit is used to generate chemotherapy reports and health reports for a certain period of time.

6. The intelligent decision-making home care system for breast cancer patients according to claim 1, characterized in that: The personalized intervention plan management module includes a management plan for outputting non-pharmacological interventions for peripheral neurotoxicity. This module is linked to an intervention execution module, which includes a chemotherapy reminder module, an intervention plan reminder module, a functional exercise reminder module, a health monitoring reminder module, and a care plan management module for managing the entire intervention process. The care plan management module includes daily care plans and emergency care plans. The functional exercise reminder module provides time-sequential reminders for the intervention methods and dosages within the intervention plan. The health monitoring reminder module includes a sleep reminder unit.

7. The intelligent decision-making home care system for breast cancer patients according to claim 6, characterized in that: The output process of the non-pharmacological intervention management plan for peripheral neurotoxicity includes the process of matching personalized intervention plans for chemotherapy-induced peripheral neurotoxicity based on data from an intelligent decision-making algorithm system. The personalized matching items of the non-pharmacological intervention management plan for peripheral neurotoxicity include symptom grading information, recommended intervention methods, recommended intervention doses, and information on the rationale behind the intervention. The intelligent decision-making algorithm system can grade patients' symptoms based on patient data and automatically match intervention methods and doses while simultaneously displaying the rationale behind the current intervention method.

8. The intelligent decision-making home care system for breast cancer patients according to claim 6, characterized in that: The personalized intervention program management module is linked to an intervention effect analysis module and an intervention program reporting module. The intervention effect analysis module is used to collect and record patient data during the implementation of the intervention program and to calculate and analyze the implementation effect of the intervention program by comparing historical data.

9. The intelligent decision-making home care system for breast cancer patients according to claim 8, characterized in that: The intervention effect analysis module is used to perform health trend analysis on individual physiological parameters of patients in the form of charts, and the intervention plan report module is used to generate an overall intervention plan report by integrating the data from the intervention effect analysis module.

Images