Painless ward construction method and system based on big data

Abstract

The invention relates to the field of pain management and rehabilitation treatment, in particular to a painless ward construction method and system based on big data, and aims to improve pain management efficiency and fracture patient rehabilitation quality through big data and artificial intelligence means. By integrating various information technologies, an artificial intelligence algorithm and a big data analysis technology, the functions of encrypted storage of fracture patient information, multi-dimensional pain assessment, personalized analgesia scheme formulation, real-time monitoring and early warning, comprehensive assessment of recovery conditions and the like are realized. Meanwhile, the method also considers the prediction of the pain trend and the intelligent generation of the training plan, solves the problems that the making of most rehabilitation training plans at present still depends on the experience and judgment of professionals and is lack of scientificity and systematicness, and provides a brand new solution for pain management and rehabilitation treatment based on big data.

Description

Technical Field

[0001] The present invention relates to the field of pain management and rehabilitation therapy, and in particular to a method and system for constructing a pain-free ward based on big data. Background Art

[0002] Elderly fracture patients have more complex and diverse pain management needs due to decreased physiological functions and the presence of chronic diseases. Traditional pain management methods mainly rely on the subjective assessment and experience of medical staff, which is not only inefficient but also difficult to achieve precise and personalized treatment.

[0003] In modern medicine, pain is regarded as the fifth vital sign, and its assessment and management have an important impact on the overall treatment effect and quality of life of fracture patients. However, existing pain assessment methods, such as digital scoring, visual analog scoring, and facial expression scoring, have improved the objectivity of the assessment to a certain extent, but still have problems such as long assessment cycle and poor real-time performance.

[0004] In addition, during the rehabilitation process, elderly fracture patients need to consider physiological, psychological, and social factors to develop a personalized rehabilitation plan. However, at present, the development of most rehabilitation training plans still relies on the experience and judgment of professionals, lacking scientificity and systematicness. Summary of the invention

[0005] In order to solve the above problems, this patent proposes a method and system for building a pain-free ward based on big data. By integrating information technology, artificial intelligence algorithms and big data analysis technology, it realizes the functions of encrypted storage of fracture patient information, multi-dimensional pain assessment, formulation of personalized analgesia plans, real-time monitoring and early warning, and comprehensive assessment of fracture recovery status. At the same time, the method also takes into account the prediction of pain trends and the intelligent generation of training plans, providing a new solution for pain management and rehabilitation treatment of elderly fracture patients.

[0006] In order to achieve the above-mentioned object of the invention, the present invention provides the following technical solutions: A method for constructing a painless ward based on big data, comprising the following steps: Step 1, read the ID card, medical insurance card or medical card of the fracture patient through the identity recognition reading device; accurately enter the detailed information of the fracture patient through the information entry terminal, including the basic information of name, age, gender, hospitalization number, medical history, allergy history, past surgical history, family medical history, and related information of pain attacks, including the first attack time, attack frequency, attack cause, and description of pain nature; at the same time, update the current status information of the fracture patient in real time, including whether the condition is aggravated or relieved, whether new symptoms appear, and the adjustment of the treatment plan, and store all the information of the fracture patient in the database, wherein a multi-layer encryption algorithm is used for data storage, including a symmetric encryption algorithm and an asymmetric encryption algorithm, to ensure the security of the fracture patient information; Step 2: Integrate multiple pain assessment scales including digital scoring method, visual analog scoring method, and facial expression scoring method on the visual interface. Medical staff select the corresponding scale for assessment. During the assessment, the system can automatically record the start time, end time, and assessment results of the assessment, and generate an assessment record curve; and set an assessment reminder function to automatically remind medical staff to conduct pain assessment through sound or pop-up windows according to the preset time interval; Step 3, based on the artificial intelligence algorithm and the clinical knowledge base formed by past treatment experience, a preliminary personalized analgesia plan is generated by inputting the assessment results and condition information of the fracture patient, including the type of analgesic drug, dosage, route of administration, and time interval of administration. The doctor will review and adjust it in detail through the review interface. During the adjustment process, the system will give real-time medication suggestions, including drug interaction prompts and potential risk warnings, and generate the final personalized analgesia plan; the final personalized analgesia plan is input into multiple reasonable medication evaluation models and the corresponding evaluation results are obtained. Based on the evaluation results, a comprehensive assessment is made on whether the medication is reasonable, and an early warning is issued if it is unreasonable; the reasonable medication evaluation model includes a drug indication matching model, which is used to compare the condition of the fracture patient with the drug indication to ensure that the drug selection matches the condition of the fracture patient; a dosage suitability assessment model, which is used to evaluate whether the drug dosage is appropriate based on the age, weight, and liver and kidney function of the fracture patient; a drug side effect prediction model, which is used to predict potential drug side effects and compare them with the previous medical history and biochemical index data of the fracture patient to ensure that the adverse reaction risk value is lower than the preset threshold, where the adverse reaction risk value T = Σ(Wi×Vi), Wi represents the weight of drug i, and Vi represents the risk value of drug i; Step 4: The doctor issues analgesia-related medical instructions, including the specific name of the drug, dosage, time and route of use, and special precautions. The precautions include key points to observe after taking the drug, possible adverse reactions and countermeasures, and contraindications for taking with other drugs. After the medical instructions are issued, they are automatically sent to the corresponding execution department, and the execution status of the medical instructions is tracked in real time, including whether the drug is given on time and the actual reaction of the fracture patient after taking the drug. Step 5, the heart rate, blood pressure, respiratory rate, and blood oxygen saturation of the fracture patient are acquired in real time through a variety of vital sign monitoring devices, and the intelligent analysis algorithm automatically analyzes the correlation between the vital sign data and the pain assessment results. When the pain score exceeds the preset reasonable range or the vital sign fluctuates abnormally, an early warning signal is immediately sent to the medical staff through a variety of methods such as sound and light alarms and SMS push notifications, and the early warning information is highlighted on the system interface through a significant color mark or flashing prompt; Step 6: Perform multi-dimensional statistical analysis on the pain data, analgesic effect, and vital sign data of fracture patients, where the comprehensive effect index of analgesic effect is I = a×(PR) 2 + b×(AR) 2 , PR represents the percentage of pain relief, AR represents the percentage of adverse reaction incidence, and a and b are coefficients set according to importance; classified statistics are conducted according to different fracture patients, and the changing trends of pain scores and analgesic effects are displayed in units of hours, days, weeks, etc., and the pain characteristics and analgesic needs of different fracture patients are compared; analysis reports are generated based on the statistical analysis results, including a summary report on the pain situation of fracture patients, which lists in detail the historical data of pain assessment for each fracture patient, the specific details of each assessment and the changing trends; an analgesic effect evaluation report is generated based on the statistical analysis results, showing the comparison of the effects of different analgesic schemes, including the degree of pain relief and the incidence of adverse reactions; a medical work statistical report is generated based on the statistical analysis results, including the number of assessment operations performed by medical staff and the execution of medical orders, to provide comprehensive and accurate data support for medical decision-making.

[0007] Preferably, step 2 also includes pain trend prediction: using Fourier transform or wavelet transform to parse time-stamped pain assessment data to identify periodic and non-periodic characteristics of pain events; using autoregressive differential moving average model or long short-term memory network model to achieve time series-based pain intensity and frequency prediction, and tracking the changes in pain patterns of fracture patients over time through time series analysis technology; and analyzing the dynamic relationship between pain patterns and other physiological parameters through vector autoregression model; the pain trend prediction adopts an adaptive learning mechanism, using online learning or incremental learning strategy to integrate new pain assessment data in real time and update model parameters.

[0008] Preferably, the method further comprises: step 7, performing regular three-dimensional imaging scans of the fracture site by high-resolution imaging equipment to obtain detailed morphological data of the fracture site, and ensuring the accuracy and clarity of the imaging by automatic calibration and image optimization operations; quickly and accurately processing the acquired image data of the fracture site, analyzing the changes in the fracture line, the progress of callus formation, and the displacement changes of the fracture site, and performing comparative analysis on the data at multiple time points; detecting specific biomarkers related to fracture recovery in the blood or body fluids of fracture patients, including but not limited to osteocalcin and alkaline phosphatase; monitoring the motion parameters of fracture patients during rehabilitation training in real time by wearable sensors, including but not limited to joint range of motion and muscle strength; based on big data and machine learning algorithms, combining fracture analysis data, biomarker data, and rehabilitation training data, comprehensively evaluating the recovery status of fracture patients, and further calculating the fracture healing degree value H=α×B1+β×B2+γ×B3 Among them, B1, B2, and B3 are the quantitative values ​​of fracture analysis data, biomarker data, and rehabilitation training data, respectively. α, β, and γ are weight coefficients determined based on clinical data to generate an intuitive recovery status assessment report, which includes the fracture healing degree, rehabilitation progress, and potential risk warnings.

[0009] Preferably, before step 5, it also includes comprehensively collecting the fracture patient's basic personal information, fracture type, fracture site, and treatment progress information, using professional assessment methods and tools to accurately assess the fracture patient's current fracture status, based on the fracture patient's physical condition and fracture status assessment results, and combined with the fracture patient's athletic ability and endurance level, as well as the expected recovery time, reasonably setting phased and overall training goals, the goals include but are not limited to restoring joint flexibility, enhancing muscle strength, and improving body balance ability; using intelligent algorithms to automatically generate personalized training plans, the plans include the selection of training items, the setting of training intensity, and the arrangement of training time and frequency.

[0010] The present invention also provides a painless ward system based on big data, comprising the following modules: The patient information management module is used to read the ID card, medical insurance card or medical card of the fracture patient through the identity recognition reading device; accurately enter the detailed information of the fracture patient through the information entry terminal, including the name, age, gender, hospitalization number, medical history, allergy history, past surgical history, family medical history, and related information of pain attacks, including the first attack time, attack frequency, attack cause, and description of pain nature; at the same time, the module can also update the current status information of the fracture patient in real time, including whether the condition is aggravated or relieved, whether new symptoms appear, and the adjustment of the treatment plan, and store all the information of the fracture patient in the database, wherein a multi-layer encryption algorithm is used for data storage, including symmetric encryption algorithm and asymmetric encryption algorithm, to ensure the security of the fracture patient information; The pain assessment module is used to integrate multiple pain assessment scales including digital scoring method, visual analog scoring method, and facial expression scoring method on a visual interface. Medical staff select the corresponding scale for assessment. During the assessment, the system can automatically record the start time, end time, and assessment results of the assessment, and generate an assessment record curve; and set the assessment reminder function to automatically remind medical staff to conduct pain assessment through sound or pop-up windows according to the preset time interval; The analgesic program formulation module is based on the artificial intelligence algorithm and the clinical knowledge base formed by past treatment experience. It generates a preliminary personalized analgesic program by inputting the assessment results and condition information of the fracture patient, including the type of analgesic drug, dosage, route of administration, and time interval of administration. The doctor can view and adjust it in detail through the review interface. During the adjustment process, the system will give real-time medication suggestions, including drug interaction prompts and potential risk warnings, and generate the final personalized analgesic program; the final personalized analgesic program is input into multiple reasonable medication evaluation models and the corresponding evaluation results are obtained. Based on the evaluation results, it is comprehensively evaluated whether the medication is reasonable, and if it is unreasonable, an early warning is issued; the reasonable medication evaluation model includes a drug indication matching model, which is used to compare the condition of the fracture patient with the drug indication to ensure that the drug selection matches the condition of the fracture patient; a dosage suitability evaluation model, which is used to evaluate whether the drug dosage is appropriate based on the age, weight, liver and kidney function of the fracture patient; a drug side effect prediction model, which is used to predict potential drug side effects and compare them with the previous medical history and biochemical index data of the fracture patient to ensure that the adverse reaction risk value is lower than the preset threshold, where the adverse reaction risk value T = Σ(Wi×Vi), Wi represents drug i The weight of Vi represents the risk value of drug i; the analgesia program formulation module and the pain assessment module are linked through real-time data interaction to ensure timely update of information; The doctor's order management module is used to issue analgesia-related doctor's orders, including the specific name of the drug, dosage, time and route of use, and special precautions, including key points to observe after taking the drug, possible adverse reactions and countermeasures, and contraindications to taking the drug with other drugs. After the doctor's order is issued, it is automatically sent to the corresponding execution department, and the execution status of the order is tracked in real time, including whether the drug is given on time and the actual reaction of the fracture patient after taking the drug. The connection with other information systems of the hospital is achieved through a secure interface protocol that meets the standards of the medical industry to ensure the accuracy and stability of data transmission. The real-time monitoring and early warning module is used to connect with a variety of vital signs monitoring devices wirelessly or wired to obtain the heart rate, blood pressure, respiratory rate, and blood oxygen saturation of the fracture patient's vital signs data in real time, and automatically analyze the correlation between the vital signs data and the pain assessment results through an intelligent analysis algorithm. When the pain score exceeds the preset reasonable range or the vital signs fluctuate abnormally, an early warning signal is immediately sent to medical staff through sound and light alarms and SMS push notifications, and the early warning information is highlighted on the system interface through prominent color markings or flashing prompts; The data analysis module is used to conduct multi-dimensional statistical analysis on the pain data, analgesic effect, and vital signs data of fracture patients, among which the comprehensive effect index of analgesic effect is I = a×(PR) 2 + b×(AR) 2 , PR represents the percentage of pain relief, AR represents the percentage of adverse reaction incidence, and a and b are coefficients set according to importance; classified statistics are conducted according to different fracture patients, and the changing trends of pain scores and analgesic effects are displayed in units of hours, days, and weeks, and the pain characteristics and analgesic needs of different fracture patients are compared; analysis reports are generated based on the statistical analysis results, including a summary report on the pain situation of fracture patients, which lists in detail the historical data of pain assessment for each fracture patient, the specific details of each assessment, and the changing trends; an analgesic effect evaluation report is generated based on the statistical analysis results, showing the comparison of the effects of different analgesic schemes, including the degree of pain relief and the incidence of adverse reactions; a medical work statistical report is generated based on the statistical analysis results, including the number of assessment operations performed by medical staff and the execution of medical orders, to provide comprehensive and accurate data support for medical decision-making.

[0011] Preferably, the pain assessment module also includes a pain trend prediction unit, which is used to analyze the time-stamped pain assessment data using Fourier transform or wavelet transform to identify the periodic and non-periodic characteristics of pain events; use an autoregressive differential moving average model or a long short-term memory network model to achieve time series-based pain intensity and frequency prediction, and track the changes in the pain patterns of fracture patients over time through time series analysis technology; and analyze the dynamic relationship between pain patterns and other physiological parameters through a vector autoregression model; the pain trend prediction unit adopts an adaptive learning mechanism and uses online learning or incremental learning strategies to integrate new pain assessment data in real time and update model parameters.

[0012] Preferably, the system further comprises a fracture recovery status detection module, comprising the following units: The fracture data acquisition unit includes high-resolution imaging equipment, which is used to perform regular three-dimensional imaging scans of the fracture site to obtain detailed morphological data of the fracture site. Through automatic calibration and image optimization operations, the accuracy and clarity of the imaging are ensured; The data analysis and processing unit is used to quickly and accurately process the collected image data of the fracture site, analyze the changes in the fracture line, the progress of callus formation and the displacement changes of the fracture site, and compare and analyze the data at multiple time points; and transmit the analysis results to the recovery status evaluation unit in real time; A biomarker detection unit, used to detect specific biomarkers related to fracture recovery in the blood or body fluids of fracture patients, including but not limited to osteocalcin and alkaline phosphatase, and transmit the test results to the recovery status assessment unit in real time; A rehabilitation training monitoring unit, including a wearable sensor, is used to monitor in real time the movement parameters of the fracture patient during rehabilitation training, including but not limited to joint range of motion and muscle strength, and synchronously transmit the sensor data to the data recovery status evaluation unit; The recovery status assessment unit, based on big data and machine learning algorithms, combines fracture analysis data, biomarker data, and rehabilitation training data to conduct a comprehensive assessment of the recovery status of fracture patients, and further calculates the fracture healing degree value H = α×B1+β×B2+γ×B3, where B1, B2, and B3 are the quantitative values ​​of fracture analysis data, biomarker data, and rehabilitation training data, respectively, and α, β, and γ are weight coefficients determined based on clinical data. An intuitive recovery status assessment report is generated, which includes the fracture healing degree value, rehabilitation progress, and potential risk warnings; Preferably, the system also includes a training plan module for comprehensively collecting the fracture patient's basic personal information, fracture type, fracture site, and treatment progress information, using professional assessment methods and tools to accurately assess the fracture patient's current fracture status, based on the fracture patient's physical condition and fracture status assessment results, and combined with the fracture patient's athletic ability and endurance level, as well as the expected recovery time, reasonably setting phased and overall training goals, the goals include but are not limited to restoring joint flexibility, enhancing muscle strength, and improving body balance; using intelligent algorithms to automatically generate personalized training plans, the plans include the selection of training items, the setting of training intensity, and the arrangement of training time and frequency.

[0013] By adopting the above technology, compared with the prior art, the beneficial effects of the present invention are: 1. The present invention integrates multiple pain assessment scales, such as digital scoring, visual analog scoring, and facial expression scoring, combined with artificial intelligence algorithms and natural language processing technology, to capture and analyze the pain status of fracture patients in real time. At the same time, the prediction of pain trends is also considered. Through multi-dimensional pain assessment methods, the accuracy and response speed of pain management are significantly improved, which helps to adjust the treatment plan in time and improve the pain experience of fracture patients.

[0014] 2. The present invention uses artificial intelligence algorithms and clinical knowledge bases to generate preliminary personalized analgesia plans based on the assessment results and condition information of fracture patients. Doctors can view the details of the plan in detail through the review interface and make adjustments based on the medication recommendations provided by the system, including drug interaction prompts and potential risk warnings. In addition, the system also includes multiple reasonable medication evaluation models, such as drug indication matching models, dosage suitability evaluation models, and drug side effect prediction models to ensure the rationality and safety of medication plans. The formulation of personalized and precise analgesia plans can help improve treatment effects, reduce adverse reactions, and accelerate the recovery process of fracture patients.

[0015] 3. The present invention uses high-resolution imaging equipment and wearable sensors to regularly perform three-dimensional imaging scans and motion parameter monitoring on the fracture site to obtain detailed morphological data and physiological indicators. Combined with biomarker detection and big data machine learning algorithms, the system can comprehensively evaluate the degree of fracture healing, rehabilitation progress, and potential risks, and further calculate the fracture healing degree value to generate an intuitive recovery status assessment report. It helps medical staff to understand the rehabilitation status of fracture patients in a timely manner, adjust rehabilitation training plans, and prevent the occurrence of complications, thereby improving the rehabilitation effect and the quality of life of fracture patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0017] FIG1 is a schematic diagram of the steps of a method for constructing a pain-free ward based on big data provided in this embodiment.

[0018] FIG2 is a schematic diagram of the structure of a pain-free ward system based on big data provided in this embodiment. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present invention and its application or use. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Example 1 like Figure 1 As shown, this embodiment provides a method for constructing a painless ward based on big data, comprising the following steps: Step 1, read the ID card, medical insurance card or medical card of the fracture patient through the identity recognition reading device; accurately enter the detailed information of the fracture patient through the information entry terminal, including the basic information of name, age, gender, hospitalization number, medical history, allergy history, past surgical history, family medical history, and related information of pain attacks, including the first attack time, attack frequency, attack cause, and description of pain nature; at the same time, update the current status information of the fracture patient in real time, including whether the condition is aggravated or relieved, whether new symptoms appear, and the adjustment of the treatment plan, and store all the information of the fracture patient in the database, wherein a multi-layer encryption algorithm is used for data storage, including a symmetric encryption algorithm and an asymmetric encryption algorithm, to ensure the security of the fracture patient information; Step 2: Integrate multiple pain assessment scales including digital scoring method, visual analog scoring method, and facial expression scoring method on the visual interface. Medical staff select the corresponding scale for assessment. During the assessment, the system can automatically record the start time, end time, and assessment results of the assessment, and generate an assessment record curve; and set an assessment reminder function to automatically remind medical staff to conduct pain assessment through sound or pop-up windows according to the preset time interval; Step 3, based on the artificial intelligence algorithm and the clinical knowledge base formed by past treatment experience, a preliminary personalized analgesia plan is generated by inputting the assessment results and condition information of the fracture patient, including the type of analgesic drug, dosage, route of administration, and time interval of administration. The doctor will review and adjust it in detail through the review interface. During the adjustment process, the system will give real-time medication suggestions, including drug interaction prompts and potential risk warnings, and generate the final personalized analgesia plan; the final personalized analgesia plan is input into multiple reasonable medication evaluation models and the corresponding evaluation results are obtained. Based on the evaluation results, a comprehensive assessment is made on whether the medication is reasonable, and an early warning is issued if it is unreasonable; the reasonable medication evaluation model includes a drug indication matching model, which is used to compare the condition of the fracture patient with the drug indication to ensure that the drug selection matches the condition of the fracture patient; a dosage suitability assessment model, which is used to evaluate whether the drug dosage is appropriate based on the age, weight, and liver and kidney function of the fracture patient; a drug side effect prediction model, which is used to predict potential drug side effects and compare them with the previous medical history and biochemical index data of the fracture patient to ensure that the adverse reaction risk value is lower than the preset threshold, where the adverse reaction risk value T = Σ(Wi×Vi), Wi represents the weight of drug i, and Vi represents the risk value of drug i.

[0021] Example of a personalized pain management plan: 1. Upper limb fracture, mild pain (NRS 1 - 3 points) Types of analgesics: Nonsteroidal anti-inflammatory drugs, such as ibuprofen.

[0022] Dosage: Adults 0.3 - 0.6g each time.

[0023] Route of administration: Oral.

[0024] Dosage interval: once every 4-6 hours, not exceeding 2.4g in 24 hours.

[0025] 2. Upper limb fracture, moderate pain (NRS 4 - 6 points) Types of analgesics: Nonsteroidal anti-inflammatory drugs combined with weak opioids, such as acetaminophen plus tramadol.

[0026] Acetaminophen: 0.3 - 0.6g each time.

[0027] Tramadol: 50 - 100 mg per dose for adults.

[0028] Route of administration: Oral.

[0029] Dosage interval: acetaminophen once every 4-6 hours, not exceeding 2g in 24 hours; tramadol once every 4-6 hours, not exceeding 400mg in 24 hours.

[0030] 3. Upper limb fracture, severe pain (NRS 7 - 10 points) Types of pain medications: Strong opioids, such as morphine.

[0031] Dosage: Initial dose: 5 - 10 mg may be given to opioid-naive adult patients.

[0032] Adjust the dose based on individual patient response and pain control.

[0033] Route of administration: Intravenous injection: Rapid onset of action, suitable for acute and severe pain that requires rapid relief. Oral: Suitable for patients with relatively stable pain who can eat orally. Oral immediate-release morphine tablets, initial dose 5 - 10 mg. If morphine sustained-release tablets are used, the dose should be determined based on the dosage of the immediate-release tablets.

[0034] Dosing interval: Intravenous injection: Depending on the patient's pain relief and vital signs, the dose can be repeated every 15-30 minutes if necessary, but vital signs such as breathing and blood pressure need to be closely monitored. Oral immediate-release morphine tablets: once every 4 hours; oral sustained-release tablets: once every 12 hours.

[0035] Step 4: The doctor issues analgesia-related medical instructions, including the specific name of the drug, dosage, time and route of use, and special precautions. The precautions include key points to observe after taking the drug, possible adverse reactions and countermeasures, and contraindications for taking with other drugs. After the medical instructions are issued, they are automatically sent to the corresponding execution department, and the execution status of the medical instructions is tracked in real time, including whether the drug is given on time and the actual reaction of the fracture patient after taking the drug. Step 5, using a variety of vital sign monitoring devices to obtain the fracture patient's heart rate, blood pressure, respiratory rate, and blood oxygen saturation vital sign data in real time, and the intelligent analysis algorithm automatically analyzes the correlation between the vital sign data and the pain assessment results. When the pain score exceeds the preset reasonable range or the vital sign fluctuates abnormally, an early warning signal is immediately sent to the medical staff through sound and light alarms and SMS push notifications, and the early warning information is highlighted on the system interface through a significant color mark or flashing prompt; Step 6: Perform multi-dimensional statistical analysis on the pain data, analgesic effect, and vital sign data of fracture patients, where the comprehensive effect index of analgesic effect is I = a×(PR) 2 + b×(AR) 2, PR represents the percentage of pain relief, AR represents the percentage of adverse reaction incidence, and a and b are coefficients set according to importance; classified statistics are conducted according to different fracture patients, and the changing trends of pain scores and analgesic effects are displayed in units of hours, days, and weeks, and the pain characteristics and analgesic needs of different fracture patients are compared; analysis reports are generated based on the statistical analysis results, including a summary report on the pain situation of fracture patients, which lists in detail the historical data of pain assessment for each fracture patient, the specific details of each assessment, and the changing trends; an analgesic effect evaluation report is generated based on the statistical analysis results, showing the comparison of the effects of different analgesic schemes, including the degree of pain relief and the incidence of adverse reactions; a medical work statistical report is generated based on the statistical analysis results, including the number of assessment operations performed by medical staff and the execution of medical orders, to provide comprehensive and accurate data support for medical decision-making.

[0036] Example 2 like Figure 2 As shown, this embodiment provides a painless ward system based on big data, including the following modules: The patient information management module is used to read the ID card, medical insurance card or medical card of the fracture patient through the identity recognition reading device; accurately enter the detailed information of the fracture patient through the information entry terminal, including the name, age, gender, hospitalization number, medical history, allergy history, past surgical history, family medical history, and related information of pain attacks, including the first attack time, attack frequency, attack cause, and description of pain nature; at the same time, the module can also update the current status information of the fracture patient in real time, including whether the condition is aggravated or relieved, whether new symptoms appear, and the adjustment of the treatment plan, and store all the information of the fracture patient in the database, wherein a multi-layer encryption algorithm is used for data storage, including symmetric encryption algorithm and asymmetric encryption algorithm, to ensure the security of the fracture patient information; The pain assessment module is used to integrate multiple pain assessment scales including digital scoring method, visual analog scoring method, and facial expression scoring method on a visual interface. Medical staff select the corresponding scale for assessment. During the assessment, the system can automatically record the start time, end time, and assessment results of the assessment, and generate an assessment record curve; and set the assessment reminder function to automatically remind medical staff to conduct pain assessment through sound or pop-up windows according to the preset time interval; The analgesic program formulation module is used to generate a preliminary personalized analgesic program based on the clinical knowledge base formed by artificial intelligence algorithms and past treatment experience by inputting the assessment results and condition information of the fracture patient, including the type of analgesic drug, dosage, route of administration, and time interval of administration. The doctor will review and adjust it in detail through the review interface. During the adjustment process, the system will give real-time medication suggestions, including drug interaction prompts and potential risk warnings, and generate the final personalized analgesic program; the final personalized analgesic program is input into multiple reasonable medication evaluation models and the corresponding evaluation results are obtained. Based on the evaluation results, a comprehensive evaluation is made on whether the medication is reasonable, and an early warning is issued if it is unreasonable; the reasonable medication evaluation model includes a drug indication matching model, which is used to compare the condition of the fracture patient with the drug indication to ensure that the drug selection matches the condition of the fracture patient; a dosage suitability evaluation model, which is used to evaluate whether the drug dosage is appropriate based on the age, weight, and liver and kidney function of the fracture patient; a drug side effect prediction model, which is used to predict potential drug side effects and compare them with the previous medical history and biochemical index data of the fracture patient to ensure that the adverse reaction risk value is lower than the preset threshold, where the adverse reaction risk value T = Σ(Wi×Vi), Wi represents drug i The weight of Vi represents the risk value of drug i; the analgesia program formulation module and the pain assessment module are linked through real-time data interaction to ensure timely update of information; The doctor's order management module is used to issue analgesia-related doctor's orders, including the specific name of the drug, dosage, time and route of use, and special precautions, including key points to observe after taking the drug, possible adverse reactions and countermeasures, and contraindications to taking the drug with other drugs. After the doctor's order is issued, it is automatically sent to the corresponding execution department, and the execution status of the order is tracked in real time, including whether the drug is given on time and the actual reaction of the fracture patient after taking the drug. The connection with other information systems of the hospital is achieved through a secure interface protocol that meets the standards of the medical industry to ensure the accuracy and stability of data transmission. The real-time monitoring and early warning module is used to connect with a variety of vital signs monitoring devices wirelessly or wired to obtain the heart rate, blood pressure, respiratory rate, and blood oxygen saturation of the fracture patient's vital signs data in real time, and automatically analyze the correlation between the vital signs data and the pain assessment results through an intelligent analysis algorithm. When the pain score exceeds the preset reasonable range or the vital signs fluctuate abnormally, an early warning signal is immediately sent to medical staff through sound and light alarms and SMS push notifications, and the early warning information is highlighted on the system interface through prominent color markings or flashing prompts; The data analysis module is used to conduct multi-dimensional statistical analysis on the pain data, analgesic effect, and vital signs data of fracture patients, among which the comprehensive effect index of analgesic effect is I = a×(PR) 2 + b×(AR) 2, PR represents the percentage of pain relief, AR represents the percentage of adverse reaction incidence, and a and b are coefficients set according to importance; classified statistics are conducted according to different fracture patients, and the changing trends of pain scores and analgesic effects are displayed in units of hours, days, and weeks, and the pain characteristics and analgesic needs of different fracture patients are compared; analysis reports are generated based on the statistical analysis results, including a summary report on the pain situation of fracture patients, which lists in detail the historical data of pain assessment for each fracture patient, the specific details of each assessment, and the changing trends; an analgesic effect evaluation report is generated based on the statistical analysis results, showing the comparison of the effects of different analgesic schemes, including the degree of pain relief and the incidence of adverse reactions; a medical work statistical report is generated based on the statistical analysis results, including the number of assessment operations performed by medical staff and the execution of medical orders, to provide comprehensive and accurate data support for medical decision-making.

[0037] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, computer devices, or computer-readable storage media. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware.

[0038] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0039] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. According to the technical essence of the present invention, within the spirit and principles of the present invention, any simple modification, equivalent replacement and improvement made to the above embodiment still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for constructing a painless ward based on big data, characterized in that: The following steps are involved: Step 1, read the ID card, medical insurance card or medical card of the fracture patient through the identity recognition reading device; accurately enter the detailed information of the fracture patient through the information entry terminal, including the basic information of name, age, gender, hospitalization number, medical history, allergy history, past surgical history, family medical history, and related information of pain attacks, including the first attack time, attack frequency, attack cause, and description of pain nature; at the same time, update the current status information of the fracture patient in real time, including whether the condition is aggravated or relieved, whether new symptoms appear, and the adjustment of the treatment plan, and store all the information of the fracture patient in the database, wherein a multi-layer encryption algorithm is used for data storage, including a symmetric encryption algorithm and an asymmetric encryption algorithm, to ensure the security of the fracture patient information; Step 2: Integrate multiple pain assessment scales including digital scoring method, visual analog scoring method, and facial expression scoring method on the visual interface. Medical staff select the corresponding scale for assessment. During the assessment, the system can automatically record the start time, end time, and assessment results of the assessment, and generate an assessment record curve; And set up an assessment reminder function to automatically remind medical staff to conduct pain assessment through sound or pop-up windows according to the preset time interval; Step 3: Based on the artificial intelligence algorithm and the clinical knowledge base formed by past treatment experience, a preliminary personalized analgesia plan is generated by inputting the assessment results and condition information of the fracture patient, including the type of analgesic drug, dosage, route of administration, and time interval of administration. The doctor will review and adjust it in detail through the review interface. During the adjustment process, the system will give real-time medication recommendations, including drug interaction prompts and potential risk warnings, to generate the final personalized analgesia plan; The final personalized analgesic regimen is input into multiple reasonable medication evaluation models and corresponding evaluation results are obtained. Based on the evaluation results, whether the medication is reasonable is comprehensively evaluated. If it is unreasonable, an early warning is issued; the reasonable medication evaluation model includes a drug indication matching model, which is used to compare the condition of the fracture patient with the drug indication to ensure that the drug selection matches the condition of the fracture patient; a dosage suitability evaluation model, which is used to evaluate whether the drug dosage is appropriate based on the age, weight, liver and kidney function of the fracture patient; a drug side effect prediction model, which is used to predict potential drug side effects and compare them with the previous medical history and biochemical index data of the fracture patient to ensure that the adverse reaction risk value is lower than the preset threshold, wherein the adverse reaction risk value T = Σ(Wi×Vi), Wi represents the weight of drug i, and Vi represents the risk value of drug i; Step 4: The doctor issues analgesia-related medical instructions, including the specific name of the drug, dosage, time and route of use, and special precautions. The precautions include key points to observe after taking the drug, possible adverse reactions and countermeasures, and contraindications for taking with other drugs. After the medical instructions are issued, they are automatically sent to the corresponding execution department, and the execution status of the medical instructions is tracked in real time, including whether the drug is given on time and the actual reaction of the fracture patient after taking the drug. Step 5, using a variety of vital sign monitoring devices to obtain the fracture patient's heart rate, blood pressure, respiratory rate, and blood oxygen saturation vital sign data in real time, and the intelligent analysis algorithm automatically analyzes the correlation between the vital sign data and the pain assessment results. When the pain score exceeds the preset reasonable range or the vital sign fluctuates abnormally, an early warning signal is immediately sent to the medical staff through sound and light alarms and SMS push notifications, and the early warning information is highlighted on the system interface through a significant color mark or flashing prompt; Step 6: Perform multi-dimensional statistical analysis on the pain data, analgesic effect, and vital sign data of fracture patients, where the comprehensive effect index of analgesic effect is I = a×(PR) 2 + b×(AR) 2 , PR represents the percentage of pain relief, AR represents the percentage of adverse reaction incidence, and a and b are coefficients set according to importance; classified statistics are conducted according to different fracture patients, and the changing trends of pain scores and analgesic effects are displayed in units of hours, days, and weeks, and the pain characteristics and analgesic needs of different fracture patients are compared; analysis reports are generated based on the statistical analysis results, including a summary report on the pain situation of fracture patients, which lists in detail the historical data of pain assessment for each fracture patient, the specific details of each assessment, and the changing trends; an analgesic effect evaluation report is generated based on the statistical analysis results, showing the comparison of the effects of different analgesic schemes, including the degree of pain relief and the incidence of adverse reactions; a medical work statistical report is generated based on the statistical analysis results, including the number of assessment operations performed by medical staff and the execution of medical orders, to provide comprehensive and accurate data support for medical decision-making.

2. A method for constructing a painless ward based on big data as claimed in claim 1, characterized in that: The step 2 also includes pain trend prediction: using Fourier transform or wavelet transform to analyze time-stamped pain assessment data to identify the periodic and non-periodic characteristics of pain events; using an autoregressive differential moving average model or a long short-term memory network model to achieve time series-based pain intensity and frequency prediction, and tracking changes in fracture patients' pain patterns over time through time series analysis technology.

3. A method for constructing a painless ward based on big data as claimed in claim 2, characterized in that: The step 2 also includes pain trend prediction: analyzing the dynamic relationship between pain patterns and other physiological parameters through a vector autoregression model; the pain trend prediction adopts an adaptive learning mechanism, using online learning or incremental learning strategies to integrate new pain assessment data in real time and update model parameters.

4. A method for constructing a painless ward based on big data as claimed in claim 1, characterized in that: It also includes: Step 7, performing regular three-dimensional imaging scans of the fracture site through high-resolution imaging equipment to obtain detailed morphological data of the fracture site, and ensuring the accuracy and clarity of the imaging through automatic calibration and image optimization operations; quickly and accurately processing the collected image data of the fracture site, analyzing the changes in the fracture line, the progress of callus formation, and the displacement changes of the fracture site, and comparing and analyzing the data at multiple time points; detecting specific biomarkers related to fracture recovery in the blood or body fluids of fracture patients, including but not limited to osteocalcin and alkaline phosphatase; real-time monitoring of the movement parameters of fracture patients during rehabilitation training through wearable sensors, including but not limited to joint range of motion and muscle strength; based on big data and machine learning algorithms, combined with fracture analysis data, biomarker data, and rehabilitation training data, a comprehensive assessment of the recovery status of fracture patients is conducted, and the fracture healing degree value H = α×B1+β×B2+γ×B3 is further calculated Among them, B1, B2, and B3 are the quantitative values ​​of fracture analysis data, biomarker data, and rehabilitation training data, respectively. α, β, and γ are weight coefficients determined based on clinical data to generate an intuitive recovery status assessment report, which includes the fracture healing degree, rehabilitation progress, and potential risk warnings.

5. The method for constructing a painless ward based on big data as claimed in claim 1, characterized in that: The step before step 5 also includes comprehensively collecting the fracture patient's basic personal information, fracture type, fracture site, and treatment progress information, using professional assessment methods and tools to accurately assess the fracture patient's current fracture status, and based on the fracture patient's physical condition and fracture status assessment results, and combined with the fracture patient's athletic ability and endurance level, as well as the expected recovery time, reasonably setting phased and overall training goals, the goals include but are not limited to restoring joint flexibility, enhancing muscle strength, and improving body balance; using intelligent algorithms to automatically generate personalized training plans, the plans include the selection of training items, the setting of training intensity, and the arrangement of training time and frequency.

6. A painless ward system based on big data, characterized in that: Includes the following modules: The patient information management module is used to read the ID card, medical insurance card or medical card of the fracture patient through the identity recognition reading device; accurately enter the detailed information of the fracture patient through the information entry terminal, including the name, age, gender, hospitalization number, medical history, allergy history, past surgical history, family medical history, and related information of pain attacks, including the first attack time, attack frequency, attack cause, and description of pain nature; at the same time, the module can also update the current status information of the fracture patient in real time, including whether the condition is aggravated or relieved, whether new symptoms appear, and the adjustment of the treatment plan, and store all the information of the fracture patient in the database, wherein a multi-layer encryption algorithm is used for data storage, including symmetric encryption algorithm and asymmetric encryption algorithm, to ensure the security of the fracture patient information; The pain assessment module is used to integrate multiple pain assessment scales including digital scoring method, visual analog scoring method, and facial expression scoring method on a visual interface. Medical staff select the corresponding scale for assessment. During the assessment, the system can automatically record the start time, end time, and assessment results of the assessment, and generate an assessment record curve; And set up an assessment reminder function to automatically remind medical staff to conduct pain assessment through sound or pop-up windows according to the preset time interval; The analgesia plan formulation module is used to generate a preliminary personalized analgesia plan based on the clinical knowledge base formed by artificial intelligence algorithms and past treatment experience by inputting the assessment results and condition information of fracture patients, including the type of analgesic drugs, dosage, route of administration, and time interval of administration. Doctors can review and adjust the plan in detail through the review interface. During the adjustment process, the system will give real-time medication recommendations, including drug interaction prompts and potential risk warnings, to generate the final personalized analgesia plan; The final personalized analgesic scheme is input into multiple reasonable medication evaluation models and corresponding evaluation results are obtained. Based on the evaluation results, whether the medication is reasonable is comprehensively evaluated. If it is unreasonable, an early warning is issued; the reasonable medication evaluation model includes a drug indication matching model, which is used to compare the fracture patient's condition with the drug indication to ensure that the drug selection matches the fracture patient's condition; a dosage suitability evaluation model, which is used to evaluate whether the drug dosage is appropriate based on the fracture patient's age, weight, liver and kidney function; a drug side effect prediction model, which is used to predict potential drug side effects and compare them with the fracture patient's past medical history and biochemical index data to ensure that the adverse reaction risk value is lower than the preset threshold, wherein the adverse reaction risk value T = Σ(Wi×Vi), Wi represents the weight of drug i, and Vi represents the risk value of drug i; the analgesic scheme formulation module and the pain assessment module are linked through real-time data interaction to ensure timely updating of information; The doctor's order management module is used to issue analgesia-related doctor's orders, including the specific name of the drug, dosage, time and route of use, and special precautions, including key points to observe after taking the drug, possible adverse reactions and countermeasures, and contraindications to taking the drug with other drugs. After the doctor's order is issued, it is automatically sent to the corresponding execution department, and the execution status of the order is tracked in real time, including whether the drug is given on time and the actual reaction of the fracture patient after taking the drug. The connection with other information systems of the hospital is achieved through a secure interface protocol that meets the standards of the medical industry to ensure the accuracy and stability of data transmission. The real-time monitoring and early warning module is used to connect with a variety of vital signs monitoring devices wirelessly or wired to obtain the heart rate, blood pressure, respiratory rate, and blood oxygen saturation of the fracture patient's vital signs data in real time, and automatically analyze the correlation between the vital signs data and the pain assessment results through an intelligent analysis algorithm. When the pain score exceeds the preset reasonable range or the vital signs fluctuate abnormally, an early warning signal is immediately sent to medical staff through sound and light alarms and SMS push notifications, and the early warning information is highlighted on the system interface through prominent color markings or flashing prompts; The data analysis module is used to conduct multi-dimensional statistical analysis on the pain data, analgesic effect, and vital signs data of fracture patients, among which the comprehensive effect index of analgesic effect is I = a×(PR) 2 + b×(AR) 2 , PR represents the percentage of pain relief, AR represents the percentage of adverse reaction incidence, and a and b are coefficients set according to importance; classified statistics are conducted according to different fracture patients, and the changing trends of pain scores and analgesic effects are displayed in units of hours, days, and weeks, and the pain characteristics and analgesic needs of different fracture patients are compared; analysis reports are generated based on the statistical analysis results, including a summary report on the pain situation of fracture patients, which lists in detail the historical data of pain assessment for each fracture patient, the specific details of each assessment, and the changing trends; an analgesic effect evaluation report is generated based on the statistical analysis results, showing the comparison of the effects of different analgesic schemes, including the degree of pain relief and the incidence of adverse reactions; a medical work statistical report is generated based on the statistical analysis results, including the number of assessment operations performed by medical staff and the execution of medical orders, to provide comprehensive and accurate data support for medical decision-making.

7. A painless ward system based on big data as claimed in claim 6, characterized in that: The pain assessment module also includes a pain trend prediction unit, which is used to analyze the pain assessment data with timestamps using Fourier transform or wavelet transform, and identify the periodic and non-periodic characteristics of pain events; use an autoregressive differential moving average model or a long short-term memory network model to achieve time series-based pain intensity and frequency prediction, and track the changes in the pain pattern of fracture patients over time through time series analysis technology.

8. A painless ward system based on big data as claimed in claim 7, characterized in that: The pain assessment module also includes a pain trend prediction unit, which analyzes the dynamic relationship between pain patterns and other physiological parameters through a vector autoregression model; the pain trend prediction unit adopts an adaptive learning mechanism and utilizes online learning or incremental learning strategies to integrate new pain assessment data in real time and update model parameters.

9. The big data-based painless ward system according to claim 6, characterized in that: The system also includes a fracture recovery status detection module, which includes the following units: The fracture data acquisition unit includes high-resolution imaging equipment, which is used to perform regular three-dimensional imaging scans of the fracture site to obtain detailed morphological data of the fracture site. Through automatic calibration and image optimization operations, the accuracy and clarity of the imaging are ensured; The data analysis and processing unit is used to quickly and accurately process the collected image data of the fracture site, analyze the changes in the fracture line, the progress of callus formation and the displacement changes of the fracture site, and compare and analyze the data at multiple time points; and transmit the analysis results to the recovery status evaluation unit in real time; A biomarker detection unit, used to detect specific biomarkers related to fracture recovery in the blood or body fluids of fracture patients, including but not limited to osteocalcin and alkaline phosphatase, and transmit the test results to the recovery status assessment unit in real time; A rehabilitation training monitoring unit, including a wearable sensor, for real-time monitoring of movement parameters of fracture patients during rehabilitation training, including but not limited to joint range of motion and muscle strength, and synchronously transmitting sensor data to a data recovery status evaluation unit; The recovery status assessment unit, based on big data and machine learning algorithms, combines fracture analysis data, biomarker data, and rehabilitation training data to conduct a comprehensive assessment of the recovery status of fracture patients, and further calculates the fracture healing degree value H=α×B1+β×B2+γ×B3, where B1, B2, and B3 are the quantitative values ​​of fracture analysis data, biomarker data, and rehabilitation training data, respectively, and α, β, and γ are weight coefficients determined based on clinical data. An intuitive recovery status assessment report is generated, which includes the fracture healing degree value, rehabilitation progress, and potential risk warnings.

10. The painless ward system based on big data as claimed in claim 6, characterized in that: The system also includes a training plan module for comprehensively collecting basic personal information, fracture type, fracture site, and treatment progress information of fracture patients, using professional assessment methods and tools to accurately assess the current fracture status of fracture patients, and based on the physical condition of fracture patients and the fracture status assessment results, and combined with the fracture patients' athletic ability and endurance level, as well as expected recovery time, reasonably setting phased and overall training goals, including but not limited to restoring joint flexibility, enhancing muscle strength, and improving body balance; using intelligent algorithms to automatically generate personalized training plans, the plans include the selection of training items, the setting of training intensity, and the arrangement of training time and frequency.

Images