Health assessment method and system based on body weight change of moderately and severely disabled population
By constructing a health metabolic data model for disabled individuals, and combining risk dimension deduction rules and weighting coefficients, the problem of data isolation in the health monitoring of disabled individuals was solved, enabling accurate assessment of health status and high-risk early warning, and improving the scientific nature and timeliness of nursing work.
Patent Information
- Application Number
- CN202610507768.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-04-17
- Publication Date
- 2026-07-03
AI Technical Summary
In the current technology for health monitoring of disabled people, excretion and weight monitoring are independent, lacking data linkage analysis, making it difficult to accurately determine health status, and lacking long-term quantitative assessment and high-risk trend early warning, resulting in a lack of scientific basis for nursing work.
By acquiring health metabolic monitoring data of people with moderate or severe disabilities, including intake, defecation, urination and weight trend data, a unified time axis data model is constructed. Combined with preset risk dimension deduction rules and weight coefficients, a comprehensive health risk value is calculated to achieve accurate judgment and generate first and second risk levels.
It has achieved standardized collection and integrated linkage of health metabolic data, provided complete data support, enabled rapid early warning of acute high-risk health problems, improved the scientificity, accuracy and timeliness of health assessment, and guided medical intervention and nursing adjustments.
Smart Images

Figure CN122337629A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of medical care and health monitoring technology, specifically to a health assessment method based on weight changes in moderately or severely disabled individuals. Background Technology
[0002] Currently, health monitoring and management for disabled individuals faces numerous challenges. Traditional methods for monitoring excretion often only provide a simple indication of the presence or absence of defecation. Furthermore, weight monitoring and excretion monitoring systems operate independently, making it difficult to link and analyze the data. This hinders healthcare professionals from accurately assessing a patient's health status based on the closed-loop data of "intake-excretion-weight." In addition, existing systems primarily focus on alarms for abnormal conditions, lacking long-term quantitative assessments of gastrointestinal function, nutrient metabolism, and fluid balance, as well as early warning mechanisms for high-risk trends. This results in a lack of scientific basis for nursing care, making precise care difficult.
[0003] Therefore, it is necessary to provide a health assessment method based on weight changes in people with moderate or severe disabilities to address the problems mentioned in the background section. Summary of the Invention
[0004] To achieve the above objectives, the present invention provides the following technical solution: a health assessment method based on weight changes in moderately and severely disabled individuals, comprising the following steps: S1. Obtain the target object's health metabolic monitoring data within a preset period, wherein the health metabolic monitoring data includes intake data, defecation data, urination data, and weight trend data; S2. Based on the health metabolism monitoring data, calculate the water balance risk value, defecation risk value and nutrition and weight risk value respectively by combining the preset deduction rules for each risk dimension, and calculate the comprehensive health risk value based on the preset weight to determine the corresponding first risk level. S3. Compare the health metabolism monitoring data with multiple preset judgment rules, and determine whether to generate a second risk level based on the comparison results; S4. If a second risk level is determined to be generated, the second risk level shall be used as the health assessment result; if no second risk level is determined to be generated, the first risk level shall be used as the health assessment result.
[0005] Preferably, the intake data is generated by collecting the food intake weight and liquid intake of the target subject; The defecation data is generated by collecting fecal weight change signals through a weight sensor on the pull-out toilet frame, and determining the fecal weight and defecation time based on the weight change signals. The urination data is generated by collecting the number of times the target subject urinates and the 24-hour urine volume. The weight change trend is obtained by collecting weight signals from weight sensors located at the four corners of the bed frame, and generating a weight change curve through a four-point synthesis algorithm. The weight change curve, defecation data, urination data, and intake data are unified onto the same time axis to construct a data model.
[0006] Preferably, the multiple preset judgment rules include a dehydration constipation and nutritional deficiency judgment rule, a water retention and rapid weight gain judgment rule, a diarrhea and decreased absorption rate judgment rule, and an acute abnormal defecation judgment rule; the health metabolic monitoring data is compared with each of the judgment rules, and when the data meets any of the preset judgment rules, a second risk level is generated.
[0007] Preferably, after determining and generating the second risk level, the risk type, determination basis, and medical intervention recommendations corresponding to the second risk level are generated simultaneously.
[0008] Preferably, before acquiring the target object's health metabolic monitoring data within a preset period, the following steps are also included: The target user type is pre-defined, including people with moderate or severe disabilities or non-disabled people; according to the set user type, a predetermined risk assessment threshold, deduction rules and weight coefficient corresponding to the user type are selected, and then the risk value is calculated and the risk level is determined based on the retrieved corresponding standard.
[0009] Preferably, in step S1, when acquiring the target object's health metabolic monitoring data within a preset period, the method further includes acquiring the target object's incontinence frequency and diaper change frequency; the method further includes assessing the nursing workload and pressure ulcer risk based on the incontinence frequency and diaper change frequency, and determining pressure ulcer risk prevention recommendations that match the assessment results.
[0010] Preferably, the formula for calculating the comprehensive risk value is: ; in, To assess overall health risk, This is the water balance risk value. For defecation risk values, Nutrition and weight risk values, , , These are the weighting coefficients.
[0011] Preferably, the specific criteria for determining the first risk level are as follows: When the comprehensive health risk score is 8 to 10, it is judged as a low-risk level; When the comprehensive health risk score is 6 to 7.9, it is judged as a mild to moderate risk level; When the comprehensive health risk score is 4 to 5.9, it is classified as a moderate risk level. When the comprehensive health risk score is between 0 and 3.9, it is considered a high-risk level.
[0012] A health assessment system based on weight changes in people with moderate or severe disabilities includes: a data acquisition module, used to acquire intake data, defecation data, urination data and weight trend data of the target subject within a preset period; A control module, which is communicatively connected to the data acquisition module, includes: The risk assessment unit is communicatively connected to the data acquisition module and is used to calculate the water balance risk value, defecation risk value, and nutrition and weight risk value based on the intake data, defecation data, urination data, and weight trend data, respectively, and to calculate the comprehensive health risk value based on preset weights to determine the corresponding first risk level. The linkage early warning unit is communicatively connected to the data acquisition module and is used to compare the data acquired by the data acquisition module with multiple preset judgment rules, and generate a second risk level based on the comparison results. The risk output module is communicatively connected to the control module and is used to output the second risk level when the linkage early warning unit generates a second risk level, and to output the first risk level when the linkage early warning unit does not generate a second risk level.
[0013] Preferably, the system further includes a user profile module, which is communicatively connected to the control module. This module is used to pre-store and configure user type information, risk assessment thresholds, deduction rules, and weighting coefficients for the target object, and to send corresponding assessment parameters to the control module according to the user type of the target object, so that the control module can perform risk calculation and level determination according to the matching parameters.
[0014] Compared with existing technologies, this invention provides a health assessment method and system based on weight changes in moderately and severely disabled individuals, which has the following beneficial effects: In this invention, by acquiring intake, defecation, urination, and weight trend data within a preset period and constructing a unified timeline data model, standardized and precise collection and linkage integration of health metabolic data are achieved, providing complete and relevant basic data support for risk assessment. By setting initial scores for each risk dimension and quantifying deductions according to preset conditions, combined with weighting coefficients, a comprehensive health risk value and a first risk level are calculated, achieving refined and quantitative judgment of health risks, replacing the traditional subjective judgment method. By pre-setting multiple judgment rules and matching data to generate a second risk level, a rapid early warning for acute and high-risk health problems can be achieved, making up for the shortcomings of existing methods that can only simply identify abnormalities and lack a precise early warning mechanism. The assessment results are determined and output according to priority, making the assessment results both comprehensive and targeted, which can directly guide medical intervention and nursing adjustments. This effectively improves the scientificity, accuracy and timeliness of health assessment for people with moderate and severe disabilities, and provides a reliable technical basis for protecting the health of people with disabilities. Attached Figure Description
[0015] Figure 1 This is a schematic diagram of a health assessment method based on weight changes in people with moderate or severe disabilities. Detailed Implementation
[0016] Please see Figure 1 This invention provides a health assessment method based on weight changes in moderately or severely disabled individuals. It is applicable to long-term bedridden elderly individuals or patients with moderate or severe disabilities (bedridden, wheelchair-bound, severely dependent on others for care), and can be used in scenarios such as home-based care, elderly care institutions, and rehabilitation centers. The method includes the following steps: Step 1: Obtain the target subject's health metabolic monitoring data within a preset period. The health metabolic monitoring data includes intake data, defecation data, urination data, and weight trend data. The acquisition of the health metabolic monitoring data relies on the integrated intelligent excretion monitoring and weight monitoring nursing mattress / nursing bed system to collect data.
[0017] Specifically, the intake data is generated by collecting the food intake weight and liquid intake of the target subject. The food intake weight includes the weight of solid or semi-solid food, and the liquid intake includes water, soup, beverages, etc. The intake data is recorded manually by meal. The defecation data is collected by a weight sensor on the pull-out toilet frame to collect fecal weight change signals. The system determines the fecal weight and defecation time based on the weight change signals to form the defecation data. When the weight change exceeds a preset threshold of the weight sensor (e.g., >50g), the system determines it as a defecation time, automatically records the start and end times of defecation and the weight of a single fecal event, and simultaneously, based on the Bristol fecal type, manually enters the fecal morphology to accumulate the defecation data and form periodic defecation data.
[0018] The urination data is generated by collecting the number of urinations and 24-hour urine volume of the target subject. Specifically, for catheterized patients, 24-hour urine volume is collected through a urine bag measuring module, ignoring the number of urinations. For non-catheterized patients, nursing staff enter the number of urinations, estimate the 24-hour urine volume using a measuring cup, and separately enter the number of nighttime urinations. The system automatically integrates these data to form the urination data. Alternatively, a wearable urination care system can be used to collect urination data, such as the Chinese patent with publication number CN120661337A entitled "An Intelligent Urination Care System and Method".
[0019] The weight change trend is obtained by collecting weight signals from weight sensors located at the four corners of the bed frame, and generating a weight change curve through a four-point synthesis algorithm. The four-point synthesis algorithm is: the sum of the readings of the weight sensors at the four corners - the weight of the bed itself - the weight of the mattress, which is the patient's actual weight. When collecting weight data periodically, it is necessary to exclude the influence of interfering items falling on the bed frame or sudden weight changes on the data accuracy, such as someone sitting on the edge of the bed or other items falling on the bed frame.
[0020] The weight change curve, defecation data, urination data, and intake data are unified onto the same time axis to construct a data model.
[0021] Step 2: Based on the health metabolism monitoring data, calculate the water balance risk value, defecation risk value, and nutrition and weight risk value respectively, and calculate the comprehensive health risk value based on the preset weights to determine the corresponding first risk level. The scoring rules for each risk dimension are as follows: each risk dimension has an initial score of 10 points, which is the maximum score and the lowest risk; when a certain risk condition is met, the corresponding score is deducted according to the rules, and when multiple conditions are met at the same time, the deduction is cumulative; the lowest score after deduction is 0 points, and negative scores will not occur; the water balance risk is scored on a daily cycle, and the defecation risk, nutrition and weight risk are scored by combining daily data and weekly averages to avoid misjudgment caused by fluctuations in daily data.
[0022] Specifically, the risk conditions for the fluid balance risk value include: deducting 3 points when 24-hour urine output is <500ml (severe oliguria); deducting 2 points when 24-hour urine output is 500-800ml; deducting 1 point when 24-hour urine output is >3000ml; deducting 2 points when fluid intake is <1000ml (insufficient intake); deducting 2 points when fluid intake is >2000ml and edema is present; deducting 2 points when nocturia occurs ≥3 times; and deducting 3 points when edema is present.
[0023] The risk conditions for the defecation risk value include: <3 bowel movements per week (chronic constipation trend), deduct 2 points; >3 bowel movements per day, mostly type 5-7, deduct 1-2 points (diarrhea risk); <100g of stool weight (daily average), predominantly type 1-2, deduct 2 points; >500g of stool weight (daily average), predominantly type 5-7, deduct 1 point; >15 minutes of defecation time, deduct 2 points; >50% of days with type 1-2 stool in a week, deduct 1-2 points. Stool type is referenced from the Bristol Stool Type Chart.
[0024] The risk conditions for the nutrition and weight risk value include: deducting 3 points when daily food intake is <1200g; deducting 2 points when the 7-day average absorption rate is <0.8; deducting 1 point when the 7-day average absorption rate is 0.8~0.85; deducting 2 points when the 7-day weight change rate is <-1.5%; and deducting 2 points when the 7-day weight change rate is <-3%.
[0025] The formula for calculating the comprehensive risk value is as follows: ; in, To assess overall health risk, This is the water balance risk value. For defecation risk values, Nutrition and weight risk values, , , These are the weighting coefficients; 0.4, Take 0.4, Take 0.2.
[0026] Specifically, the criteria for determining the first risk level are as follows: When the comprehensive health risk score is 8 to 10, it is considered a low-risk level, indicating that the current nursing plan is basically appropriate and the trend can be observed. When the comprehensive health risk score is 6 to 7.9, it is judged as a mild to moderate risk level, which means that caregivers / family members need to make minor adjustments: drink more water / adjust dietary fiber / increase turning over activities, etc. When the comprehensive health risk score is 4 to 5.9, it is considered a moderate risk level. It is recommended to have a doctor or nutritionist assess the risk within 48 hours and to have tests (blood and urine) done if necessary. When the comprehensive health risk score is 0 to 3.9, it is considered a high-risk level, which means that there may be severe dehydration, water retention, intestinal obstruction, severe diarrhea, rapid weight loss, etc., and immediate medical intervention is recommended.
[0027] Step 3: Compare the health metabolism monitoring data with multiple preset judgment rules, and determine whether to generate a second risk level based on the comparison results; The multiple preset judgment rules include the judgment rule for dehydration, constipation, and nutritional deficiency; the judgment rule for water retention and rapid weight gain; the judgment rule for diarrhea and decreased absorption rate; and the judgment rule for acute abnormal defecation. The health metabolic monitoring data is compared with each of the judgment rules. When the data meets any of the preset judgment rules, a second risk level is generated.
[0028] Specifically, the criteria for determining dehydration, constipation, and nutritional deficiency include: simultaneously meeting the following conditions: fluid intake <1000ml, 24h urine output <800ml, weekly bowel movement frequency <3 times, and daily fecal weight <100g. The criteria for determining rapid weight gain due to water retention are: a 7-day weight change rate > +3% and a 24-hour urine output < 800ml, and the occurrence of edema; The criteria for determining the decrease in absorption rate due to diarrhea are: more than 3 bowel movements per day, with stool form mainly of Bristol type 5-7, and an average digestibility and absorption rate of less than 0.80 over 7 days; The rule for determining acute defecation abnormality is: the target subject has no defecation data record for ≥72 consecutive hours.
[0029] After determining and generating the second risk level, the corresponding risk type, determination basis, and medical intervention recommendations are generated simultaneously.
[0030] Step 4: If a second risk level is determined to be generated, the second risk level shall be used as the health assessment result; if no second risk level is determined to be generated, the first risk level shall be used as the health assessment result.
[0031] Furthermore, before obtaining the target subject's health metabolic monitoring data within a preset period, the following steps are also included: The target user type is pre-defined, including people with moderate or severe disabilities or non-disabled people; according to the set user type, a predetermined risk assessment threshold, deduction rules and weight coefficient corresponding to the user type are selected, and then the risk value is calculated and the risk level is determined based on the retrieved corresponding standard.
[0032] Furthermore, in step S1, when acquiring the target object's health metabolic monitoring data within a preset period, the method also includes acquiring the target object's incontinence frequency and diaper change frequency; the method also includes assessing the nursing workload and pressure ulcer risk based on the incontinence frequency and diaper change frequency, and determining pressure ulcer risk prevention recommendations that match the assessment results.
[0033] Specifically, when acquiring health metabolic monitoring data within a preset period, the number of incontinence events (fecal incontinence and urinary incontinence are counted separately) and the number of diaper changes for the target subject are collected simultaneously. Based on the number of incontinence events and the number of diaper changes, the nursing workload index is calculated according to a preset formula: Nursing workload index = (number of fecal incontinence events × 3) + (number of urinary incontinence events × 1) + (number of diaper changes × 0.5). The coefficient is set according to the time and difficulty of the nursing operation. The higher the index, the greater the nursing workload. The workload index is divided into three levels: when the number of incontinence events ≥ 3 times / day or the diaper change interval > 2 times / hour, it is judged as high risk of pressure ulcers; when the number of incontinence events 1-2 times / day, it is judged as medium risk of pressure ulcers; and when there is no incontinence, it is judged as low risk of pressure ulcers.
[0034] Recommendations are matched according to risk level. For example, for high risk, the recommendations are: turn the patient over every 1 to 2 hours, clean the perianal skin and apply a protective agent, and use an anti-pressure sore mattress.
[0035] A health assessment system based on weight changes in moderately and severely disabled individuals includes: a data acquisition module, used to acquire intake data, defecation data, urination data and weight trend data of the target subject within a preset period. Each data acquisition method is implemented using the aforementioned method, and all collected data are unified to the same timeline according to timestamps to construct a healthy metabolic data model. Subsequently, the data model is synchronously transmitted to the control module to provide a complete and accurate data source for subsequent risk level determination. A control module, which is communicatively connected to the data acquisition module, includes: The risk assessment unit is communicatively connected to the data acquisition module and is used to calculate the water balance risk value, defecation risk value, and nutrition and weight risk value based on the intake data, defecation data, urination data, and weight trend data, respectively, and to calculate the comprehensive health risk value based on preset weights to determine the corresponding first risk level. The linkage early warning unit is communicatively connected to the data acquisition module and is used to compare the data acquired by the data acquisition module with multiple preset judgment rules, and generate a second risk level based on the comparison results. The risk output module is communicatively connected to the control module and is used to output the second risk level when the linkage early warning unit generates a second risk level, and to output the first risk level when the linkage early warning unit does not generate a second risk level.
[0036] Furthermore, the system also includes a user profile module, which is communicatively connected to the control module. This module is used to pre-store and configure user type information, risk assessment thresholds, deduction rules, and weighting coefficients for the target object, and to send corresponding assessment parameters to the control module according to the user type of the target object, so that the control module can perform risk calculation and level determination according to the matching parameters.
[0037] The functions of each module in this system correspond one-to-one with the steps of the aforementioned health assessment method based on weight changes in moderately and severely disabled individuals. Through the coordinated operation of each module, the entire assessment process is automated.
[0038] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.
Claims
1. A method for health assessment based on body weight changes in a population with moderate and above disability, characterized in that, Includes the following steps: S1. Obtain the target object's health metabolic monitoring data within a preset period, wherein the health metabolic monitoring data includes intake data, defecation data, urination data, and weight trend data; S2. Based on the health metabolism monitoring data, calculate the water balance risk value, defecation risk value and nutrition and weight risk value respectively by combining the preset deduction rules for each risk dimension, and calculate the comprehensive health risk value based on the preset weight to determine the corresponding first risk level. S3. Compare the health metabolism monitoring data with preset multi-class judgment rules, and determine whether to generate a second risk level based on the comparison results; S4. If a second risk level is determined, the second risk level shall be used as the health assessment result. If no second risk level is determined, the first risk level will be used as the health assessment result.
2. The method of claim 1, wherein, The intake data is generated by collecting the food intake weight and liquid intake of the target subject. The defecation data is generated by collecting fecal weight change signals through a weight sensor on the pull-out toilet frame, and determining the fecal weight and defecation time based on the weight change signals. The urination data is generated by collecting the number of times the target subject urinates and the 24-hour urine volume. The weight change trend is obtained by collecting weight signals from weight sensors located at the four corners of the bed frame, and generating a weight change curve through a four-point synthesis algorithm. The weight change curve, defecation data, urination data, and intake data are unified onto the same time axis to construct a data model.
3. The method of claim 1, wherein, The multiple preset judgment rules include the judgment rules for dehydration, constipation and malnutrition, water retention and rapid weight gain, diarrhea and decreased absorption rate, and acute abnormal defecation. The health metabolism monitoring data is compared with each of the aforementioned judgment rules. When the data meets any of the preset judgment rules, a second risk level is generated.
4. The method of claim 3, wherein, After determining and generating the second risk level, the corresponding risk type, determination basis, and medical intervention recommendations are generated simultaneously.
5. The method of claim 1, wherein, Before acquiring the target subject's health metabolic monitoring data within a preset period, the following steps are also included: The target user type is pre-defined, including people with moderate or severe disabilities or non-disabled people; according to the set user type, a predetermined risk assessment threshold, deduction rules and weight coefficient corresponding to the user type are selected, and then the risk value is calculated and the risk level is determined based on the retrieved corresponding standard.
6. The method of claim 1, wherein, In step S1, when acquiring the target subject's health metabolic monitoring data within a preset period, the method also includes acquiring the target subject's incontinence frequency and diaper change frequency; the method further includes assessing the nursing workload and pressure ulcer risk based on the incontinence frequency and diaper change frequency, and determining pressure ulcer risk prevention recommendations that match the assessment results.
7. The method of claim 5, wherein, The formula for calculating the comprehensive risk value is as follows: ; wherein, is a comprehensive health risk value, is a water balance risk value, is a defecation risk value, is a nutrition and body weight risk value, , , is a weighting factor.
8. The method of claim 5, wherein, The specific criteria for determining the first risk level are as follows: When the comprehensive health risk score is 8 to 10, it is judged as a low-risk level; When the comprehensive health risk score is 6 to 7.9, it is judged as a mild to moderate risk level; When the comprehensive health risk score is 4 to 5.9, it is classified as a moderate risk level. When the comprehensive health risk score is between 0 and 3.9, it is considered a high-risk level.
9. A health assessment system based on weight changes in moderately and severely disabled individuals, characterized in that: include: The data acquisition module is used to acquire the target object's intake data, defecation data, urination data, and weight trend data within a preset period. A control module, which is communicatively connected to the data acquisition module, includes: The risk assessment unit is communicatively connected to the data acquisition module and is used to calculate the water balance risk value, defecation risk value, and nutrition and weight risk value based on the intake data, defecation data, urination data, and weight trend data, respectively, and to calculate the comprehensive health risk value based on preset weights to determine the corresponding first risk level. The linkage early warning unit is communicatively connected to the data acquisition module and is used to compare the data acquired by the data acquisition module with multiple preset judgment rules, and generate a second risk level based on the comparison results. The risk output module is communicatively connected to the control module and is used to output the second risk level when the linkage early warning unit generates a second risk level, and to output the first risk level when the linkage early warning unit does not generate a second risk level.
10. The system according to claim 9, characterized in that, The system also includes a user profile module, which is communicatively connected to the control module. It is used to pre-store and configure the user type information, risk assessment threshold, deduction rules and weight coefficients of the target object, and send the corresponding assessment parameters to the control module according to the user type of the target object, so that the control module can perform risk calculation and level determination according to the matching parameters.
Citation Information
Patent Citations
Urine collection intelligent nursing system and urine collection intelligent nursing method
CN120661337A
