A method and system for identifying poverty caused by disease based on medical data

Abstract

The application provides a disease-caused poverty personnel identification method and system based on medical data, and belongs to the technical field of data processing, and specifically comprises the following steps: determining the concerned diagnosis and treatment mode of the associated disease type based on the similarity of the diagnosis and treatment mode of the associated disease type and other disease types in the monitoring target department; determining the monitoring result of the diagnosis and treatment data of the different concerned diagnosis and treatment modes of the monitoring target department in different medical institutions; and determining the data analysis and processing strategy of the medical institution in combination with the association of the disease characteristics of the associated disease type corresponding to the different concerned diagnosis and treatment modes and the target disease type. The screening processing of the monitoring target of the potential identification personnel caused by poverty due to disease is carried out based on the data analysis result, and the efficiency of the identification processing of the disease-caused poverty personnel is improved.

Description

Technical Field

[0001] This invention belongs to the field of data processing technology, and in particular relates to a method and system for identifying people impoverished due to illness based on medical data. Background Technology

[0002] Existing technical solutions often require community staff to conduct regular visits or diagnose the target disease type before identifying people impoverished due to illness. If the funding policy is determined only after the target disease type is confirmed, the cost of the target disease may be too high, and the funding policy may not be able to intervene in time, resulting in ineffective treatment. Therefore, how to identify users at risk of being diagnosed with the target disease type and provide targeted funding policies has become an urgent technical problem to be solved.

[0003] To address the aforementioned technical issues, this application specifically provides a method and system for identifying individuals impoverished due to illness based on medical data. Summary of the Invention

[0004] To achieve the objectives of this invention, the following technical solution is adopted: Specifically, this application provides a method for identifying people impoverished due to illness based on medical data, which includes: S1 uses medical data from the target region to determine the correlation between different disease types and the disease characteristics of the target disease type at different disease stages. Based on the correlation, it determines the associated disease types within the disease types. Then, based on the correlation between the associated disease types of a department and different target disease types, it determines the monitoring target departments within the departments. S2 determines the treatment methods to be focused on for related disease types based on the similarity between the related disease types in the monitored target department and the treatment methods for other disease types; S3 uses the monitoring results of different treatment methods in different departments of different medical institutions, and combines the correlation between the disease types corresponding to different treatment methods and the disease characteristics of the target disease type to determine the data analysis and processing strategy of medical institutions. Based on the data analysis results, it screens and processes the monitoring targets of potential people impoverished due to illness.

[0005] The beneficial effects of this invention are as follows: By monitoring the similarity of treatment methods for related disease types in target departments with those for other disease types, the system identifies the treatment methods to focus on for related disease types. This allows for the identification of examination methods with a high degree of correlation between related disease types and other disease types based on the deviation of examination methods. This lays the foundation for determining differentiated data analysis and processing strategies for medical institutions using examination methods with a high degree of correlation.

[0006] By analyzing the monitoring results of different treatment methods in different departments of different medical institutions, and the correlation between the disease characteristics of the associated disease types corresponding to different treatment methods and the target disease type, the data analysis and processing strategies of medical institutions are determined. This takes into account the number of examinations under different examination methods, as well as the similarity between the disease characteristics of different examination methods and the corresponding associated disease types and the target disease type. This enables differentiated data analysis and processing of medical institutions based on examination methods, which not only improves the efficiency of data analysis and processing, but also enhances the timeliness and reliability of the identification and treatment of patients with associated disease types.

[0007] A further technical solution is that the disease stages are divided into early, middle and late stages.

[0008] A further technical solution is that the method for determining the associated disease type in the disease type is as follows: Based on the correlation between the disease type and the disease characteristics of the target disease type at different disease stages, determine the similarity of the indicator data range of the examination indicators with different target disease types at different disease stages. Based on the similarities described, identify similar disease types among target disease types at different disease stages; Whether a disease type is a related disease type is determined by the number of similar disease types in different disease stages.

[0009] A further technical solution is that the method for determining the target monitoring department within the aforementioned department is as follows: The number of associated disease types for the department is determined based on the associated disease types of the department; Based on the number of the associated disease types, determine whether the department is a target department for monitoring.

[0010] Secondly, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-described method for identifying people impoverished due to illness based on medical data when running the computer program.

[0011] Other features and advantages will be set forth in the following description, and the objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0012] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0013] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0014] Figure 1 This is a flowchart of a method for identifying people impoverished due to illness based on medical data; Figure 2 This is a flowchart illustrating the method for determining associated disease types within disease types; Figure 3 This is a flowchart illustrating the method for determining the target monitoring departments within a department; Figure 4 This is a flowchart illustrating the methods for determining data analysis and processing strategies in medical institutions. Detailed Implementation

[0015] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0016] Example 1 like Figure 1 As shown, this application provides a method for identifying people impoverished due to illness based on medical data, specifically including: S1 uses medical data from the target region to determine the correlation between different disease types and the disease characteristics of the target disease type at different disease stages. Based on the correlation, it determines the associated disease types within the disease types. Then, based on the correlation between the associated disease types of a department and different target disease types, it determines the monitoring target departments within the departments. Furthermore, the disease stages are divided into early, middle, and late stages.

[0017] It should be noted that the target disease type is determined based on the treatment cost. Specifically, the disease type with treatment costs within a preset range is selected as the target disease type, that is, the disease type with higher treatment costs.

[0018] Specifically, the methods include the following: Method 1: Percentage Method Calculate the total cost of all diseases over the past year and sort them from highest to lowest.

[0019] The diseases that rank in the top 10% of total costs are defined as "target disease types." This approach ensures that the focus remains on the highest-cost segment of diseases.

[0020] Method 2: Absolute value threshold method A clear fee threshold should be set based on the region's economic level and policy objectives.

[0021] For example, diseases with single hospitalization costs exceeding 50,000 yuan or annual cumulative treatment costs exceeding 100,000 yuan can be included in the target disease category. This method is intuitive, easy to understand, and easy to promote.

[0022] Method 3: Family Burden Ratio Method A more scientific approach is to consider household income. The World Health Organization defines "catastrophic health expenditure" as out-of-pocket medical expenses exceeding 40% of a household's disposable income.

[0023] The system can calculate whether the average out-of-pocket cost for treating a certain disease exceeds a certain percentage (such as 50%) of the per capita disposable income of local urban residents. If it does, the disease will be included.

[0024] 3. Example of a comprehensive preset range: A comprehensive preset range could be: primary criterion: the median total treatment cost for a single disease diagnosis ranks among the top 10% in the hospital / city within the year; secondary criterion: the median out-of-pocket expenses for treating the disease exceed 40% of the local annual per capita disposable income; dynamic adjustment: this preset range should be dynamically adjusted annually based on changes in the price index and medical costs.

[0025] Specifically, such as Figure 2 As shown, the method for determining the associated disease types in the aforementioned disease types is as follows: Based on the correlation between the disease type and the disease characteristics of the target disease type at different disease stages, determine the similarity of the indicator data range of the examination indicators with different target disease types at different disease stages. Based on the similarities described, identify similar disease types among target disease types at different disease stages; Whether a disease type is a related disease type is determined by the number of similar disease types in different disease stages.

[0026] It is understood that the similar disease types are target disease types in which the number of examination indicators with overlapping indicator data ranges is greater than a preset threshold for the number of examination indicators.

[0027] Specifically, if the number of similar disease types in different disease stages is greater than a preset threshold for the number of similar disease types, then the disease type is determined to be an associated disease type.

[0028] For specific examples, the target disease type is a predefined set of major or typical diseases with clear characteristics and a well-defined range of examination indicators. Long-term medication for these diseases may lead to poverty due to the disease, such as "Type 2 Diabetes (T2DM)," "Chronic Heart Failure (CHF)," and "Chronic Kidney Disease (CKD)."

[0029] Disease type to be evaluated: We need to determine whether it is related to the above target diseases. In this example, "non-alcoholic fatty liver disease (NAFLD)" is used as the disease to be evaluated.

[0030] Associated disease types: These refer to diseases whose diagnostic indicators consistently show a high degree of similarity to multiple target disease types across multiple disease stages. This usually indicates that they may share a common pathophysiological basis (such as insulin resistance or chronic inflammation), and is an important signal for comorbidity management.

[0031] II. Data preparation and parameter setting; Defining disease stages and key diagnostic indicators: We divide NAFLD into three disease stages: Stage 1: Simple fatty liver stage; Stage 2: Non-alcoholic steatohepatitis (NASH); Stage 3: Liver fibrosis / cirrhosis.

[0032] Key testing indicators: We selected indicators that reflect metabolism, inflammation and organ function, such as fasting plasma glucose (FPG), fasting insulin (FINS), homeostasis model assessment of insulin resistance index (HOMA-IR), total cholesterol (TC), low-density lipoprotein cholesterol (LDL-C), alanine aminotransferase (ALT), and aspartate aminotransferase (AST).

[0033] Set the data range for the target disease type: Target disease A: Type 2 diabetes mellitus (T2DM), FPG: ≥7.0 mmol / L, HOMA-IR: ≥2.5; Target disease B: Atherosclerotic cardiovascular disease (ASCVD), LDL-C: ≥3.4 mmol / L, TC: ≥5.2 mmol / L; Target disease C: Chronic kidney disease (CKD), eGFR: <60 mL / min / 1.73m² (Although not directly listed in this example, it can be used as an implicit indicator); Set the judgment threshold: The preset threshold for the number of inspection indicators is 1. This means that if the data range of any one core inspection indicator overlaps, it is considered "similar" in that indicator.

[0034] The preset threshold for the number of similar disease types is 2. That is, at a certain stage of a disease, it must be similar to at least 2 different target disease types.

[0035] III. Correlation Analysis Process; Step 1: Conduct indicator similarity comparisons in stages; Stage 1: Simple fatty liver; NAFLD characteristics: Patients often present with elevated HOMA-IR (>2.5), mildly elevated LDL-C, and normal or mildly elevated ALT / AST.

[0036] Similarity comparison: vs T2DM: Their HOMA-IR ranges overlap (both > 2.5). → Similarity count +1; vs ASCVD: Their ranges overlap on the LDL-C metric (both above ideal levels). → Similarity count +1; vs CKD: At this stage, indicators such as eGFR usually do not show significant overlap. → Dissimilar; Conclusion of this stage: Two similar disease types (T2DM and ASCVD) were found. 2> Preset threshold (2), this stage passed.

[0037] Phase Two: Nonalcoholic Steatohepatitis (NASH); NAFLD characteristics: All of the above indicators are more significantly abnormal, and a systemic inflammatory state is present.

[0038] Similarity comparison: vs T2DM: HOMA-IR overlap is higher, and FPG may also begin to enter the prediabetic range (e.g., ≥6.1). → Similar vs ASCVD: LDL-C and TC abnormalities are more pronounced. → Similar vs CKD: Due to systemic inflammation and metabolic disturbances, early signs of kidney damage begin to appear (such as elevated urinary microalbumin). → Possibly similar Conclusion of this stage: At least two similar disease types (T2DM and ASCVD) were found. 2 ≥ preset threshold (2), this stage is passed.

[0039] Stage 3: Liver fibrosis / cirrhosis; NAFLD characteristics: persistent metabolic disorder, with impaired liver function and portal hypertension.

[0040] Similarity comparison: vs. T2DM: Insulin resistance still exists. → Similar vs ASCVD: Persistent dyslipidemia. → Similar vs CKD: Hepatorenal syndrome may lead to a significant decrease in eGFR, with overlapping indicator ranges. → Similar Conclusion of this stage: Three similar disease types were found. 3> Preset threshold (2), this stage passed.

[0041] Step 2: Make a final judgment based on the results of each stage. Check each disease stage: the number of similar disease types in stage one, stage two, and stage three is greater than or equal to the preset threshold (2).

[0042] Final decision: Since NAFLD shows similarity in indicative characteristics to a sufficient number of target disease types across all defined disease stages, the system determines that "non-alcoholic fatty liver disease (NAFLD)" is an "associated disease type" with T2DM, ASCVD, and CKD.

[0043] Specifically, such as Figure 3 As shown, the method for determining the monitoring target departments within the aforementioned departments is as follows: The number of associated disease types for the department is determined based on the associated disease types of the department; Based on the number of the associated disease types, determine whether the department is a target department for monitoring.

[0044] Understandably, when the number of associated disease types exceeds the threshold for the number of associated disease types, real-time data collection and analysis are performed on patients visiting the department, and these patients with the associated disease types are used as monitoring targets. Early intervention is conducted through on-site visits. When the number of associated disease types does not exceed the threshold for the number of associated disease types, it is determined whether the number of associated disease types in the department is within a preset range. If so, the department is identified as a monitoring target department; otherwise, it is determined that the department is not a monitoring target department.

[0045] Specifically, in one possible embodiment: In the intelligent poverty prevention system of hospital management, accurately identifying the clinical departments that need key monitoring is the starting point of the entire process. This implementation method establishes a scientific hierarchical management mechanism by quantitatively analyzing the correlation between each department and diseases that cause poverty due to illness.

[0046] First, based on a medical knowledge base and historical data, we identified the types of diseases associated with poverty-causing illnesses in each department. For example, the nephrology department manages diseases closely related to uremia, such as stage 3 chronic kidney disease, refractory hypertensive nephropathy, and diabetic nephropathy; while the cardiology department is responsible for diseases that may develop into severe heart failure, such as refractory hypertension and complex arrhythmias. These diseases are referred to as "associated disease types," and they represent early stages or warning signs of major poverty-causing illnesses.

[0047] In the implementation process, we established clear quantitative standards. When a department has three or more associated disease types, the system classifies it as a department with the highest monitoring level. Taking nephrology as an example, the three associated diseases it manages automatically place it at the highest monitoring level. For such departments, the system initiates real-time data collection and analysis, connects to the hospital information system, and automatically identifies patients diagnosed with these associated diseases. More importantly, the medical social work department will conduct on-site visits within 24-48 hours to conduct a dual assessment of medical and economic risks, proactively connecting patients with medical insurance policies and charitable resources to prevent the risk of impoverishment due to illness from the outset.

[0048] For departments with 1-2 associated disease types, they are designated as monitoring target departments. By analyzing the medical data, potential individuals at risk of falling into poverty due to illness are identified in a targeted manner.

[0049] For departments with zero associated disease types, such as thyroid surgery and other departments that primarily provide routine medical care, the system does not include them in the special monitoring scope and manages them according to standard procedures. This tiered system ensures that limited medical management resources are accurately allocated to the areas most in need, establishing an efficient and effective early warning system for poverty prevention.

[0050] Optionally, the method for determining the target monitoring departments within the aforementioned departments is as follows: The number of associated disease types for the department is determined based on the associated disease types of the department; The total number of similar disease types for the department is determined based on the number of similar disease types for different related disease types. Based on the total number of similar disease types, determine whether the department is a target department for monitoring.

[0051] Understandably, when the total number of similar disease types exceeds a threshold for the number of similar disease types, real-time data collection and analysis are conducted on patients visiting the department, and patients with the associated disease types are used as monitoring targets. Early intervention is implemented through on-site visits, and assistance policies are explained in advance. Based on diagnostic results from multiple medical institutions, it is determined whether a patient requires assistance. When the number of similar disease types does not exceed the threshold for the number of similar disease types, it is determined whether the number of similar disease types in the department is within a preset range. If so, the department is identified as a monitoring target department; otherwise, it is determined that the department is not a monitoring target department.

[0052] S2 determines the treatment methods to be focused on for related disease types based on the similarity between the related disease types in the monitored target department and the treatment methods for other disease types; Specifically, the method for determining the relevant treatment methods for the associated disease types is as follows: Based on the similarity between the associated disease types in the monitored target department and the diagnosis and treatment methods of other disease types, the examination type of the associated disease type is determined and used as the matching examination type; Based on the historical occurrence data of other disease types in the monitored target department for the matched examination type, determine the average number of examinations for patients with different matched examination types in other disease types. Based on the average number of examinations for different matching examination types in other disease types, determine whether the matching examination type is a focus of diagnosis and treatment.

[0053] It is understandable that when the average number of examinations for different matching examination types in other disease types is less than a preset examination number threshold, the matching examination type is determined to be the treatment method of interest.

[0054] To illustrate with a specific example, the core objective is to identify specific examinations within the target department (such as nephrology) that primarily serve related diseases rather than routine illnesses. These examinations are often the watershed in diagnosing key poverty-causing diseases and assessing the severity of conditions; monitoring them can seize the golden window for early intervention.

[0055] Related disease types: such as the pre-stage of major diseases that can lead to poverty, as mentioned above, such as stage 3 chronic kidney disease (CKD).

[0056] Other disease types: refers to routine and mild diseases treated in this department, such as urinary tract infections and simple renal cysts.

[0057] Matching test types: Tests that can be used to diagnose both "related diseases" and "other diseases". For example, a kidney biopsy can be used to diagnose both CKD and certain types of nephritis.

[0058] Focus on diagnostic methods: These refer to "matching test types" that are rarely used in "other diseases" but are crucial in the diagnosis of "related diseases." They are key signals for identifying potentially high-risk patients.

[0059] II. Data preparation and parameter setting; Preset parameters: Preset threshold for the number of examinations: 1.2 times. This is an empirical value, representing the average number of examinations performed per patient.

[0060] Data range: Time window: Analyze historical medical data from the past year.

[0061] Target department: Nephrology.

[0062] Associated disease type: Stage 3 chronic kidney disease (CKD); other disease types: acute cystitis, simple renal cyst, benign glomerular hematuria; matching test types to be evaluated: renal biopsy, 24-hour urine protein quantification.

[0063] III. Analysis Process and Specific Calculations; Step 1: Determine the type of match check; A systematic analysis of nephrology examinations revealed that kidney biopsy and 24-hour urine protein quantification are used to diagnose CKD stage 3 (associated disease) and occasionally to diagnose certain complex nephritis or nephrotic syndrome (which can be classified as "other disease types"). Therefore, they were listed as "matching examination types".

[0064] Step 2: Calculate the average number of examinations for "other disease types"; The system screened all patients diagnosed with "acute cystitis", "simple renal cyst", and "benign glomerular hematuria" from historical data, and then calculated the average number of times they underwent the above two examinations. For "renal biopsy": In the past year, a total of 400 patients were diagnosed with the above "other disease types", of which only 5 underwent renal biopsy due to the complexity of their condition and suspected secondary factors. The average number of examinations = total number of examinations / total number of patients = 5 / 400 = 0.0125 times.

[0065] Regarding the "24-hour urine protein quantification": Among these 400 patients, 100 patients underwent this test to assess their condition or rule out proteinuria, with an average number of tests = 100 / 400 = 0.25 times.

[0066] Step 3: Determine whether it falls under the category of "focusing on treatment methods"; The calculated average number of inspections is compared with the preset inspection threshold (1.2 times).

[0067] judge: 0.0125 times (kidney biopsy) < 1.2 times, condition met; 0.25 times (24-hour urine protein) < 1.2 times, condition met.

[0068] Conclusion: Since the average number of examinations for these two "matching examination types" in "other disease types" is less than the preset threshold, the system identifies "renal biopsy" and "24-hour urine protein quantification" as "focused treatment methods".

[0069] IV. Decision-making applications and value; Once an examination is marked as a "careful treatment approach," it takes on new significance in clinical pathways and risk management: it becomes a high-risk warning signal. In nephrology, when a patient initially diagnosed with "chronic nephritis" requests a "kidney biopsy," the system immediately identifies this as a high-risk signal. This means that the patient's condition may no longer be simple and is moving towards a stage that requires a clear pathological diagnosis, more complex treatment, and higher costs (CKD stage 3 and beyond).

[0070] Triggering the early intervention process: This early warning system can automatically trigger early intervention by medical social workers. Social workers can contact patients before the biopsy to understand their financial situation and psychological burden, as a kidney biopsy itself is expensive, and subsequent treatment plans, such as immunosuppressants, based on the pathology results may be even more costly. Early intervention allows for cost estimation, psychological counseling, and resource linkage, preventing patients from abandoning treatment due to financial pressure after diagnosis.

[0071] In summary, the core value of this method lies in its ability to cleverly identify "critical examinations" that indicate an escalation of disease severity by using routine medical data within the department as a benchmark. By monitoring the application of these "focused treatment approaches," the system can accurately identify patients at the "crossroads to poverty" before exorbitant medical expenses occur, thus achieving the earliest and most effective poverty prevention intervention.

[0072] S3 uses the monitoring results of different treatment methods in different departments of different medical institutions, and combines the correlation between the disease types corresponding to different treatment methods and the disease characteristics of the target disease type to determine the data analysis and processing strategy of medical institutions. Based on the data analysis results, it screens and processes the monitoring targets of potential people impoverished due to illness.

[0073] Specifically, such as Figure 4 As shown, the method for determining the data analysis and processing strategy of the medical institution is as follows: Based on the monitoring results of the treatment data of different focus treatment methods in the monitoring target departments of the medical institution, determine the proportion of examination times for different focus treatment methods in the related disease types. Based on the association between the disease characteristics of the associated disease types and the target disease type corresponding to different attention and treatment methods, determine the number of similar disease types corresponding to the associated disease types of different attention and treatment methods; Based on the proportion of examinations conducted by different treatment methods in related disease types and the number of similar disease types, the data analysis and processing strategy of the medical institution is determined.

[0074] Understandably, the data analysis and processing strategy for the medical institution is determined based on the proportion of examinations conducted under different treatment methods within the associated disease types and the number of similar disease types. This strategy specifically includes: The percentage of examinations conducted by different treatment methods in related disease types was used to determine the sum of the percentages of examinations conducted by different treatment methods in different related disease types, and this sum was used as the total percentage of examinations. When there is a treatment method that is of concern with a total number of examinations that accounts for a greater than a preset percentage, the data analysis and processing of patients in the monitoring target department of the medical institution will be carried out when the number of examinations of the treatment method with the largest percentage of total examinations exceeds a preset threshold. When there is no treatment method with a total number of examinations that is greater than the preset value, the characteristic value of different treatment methods in different associated disease types is determined by multiplying the proportion of examinations of different treatment methods in the associated disease types by the number of similar disease types. When there are different associated disease types and the sum of their characteristic values ​​is greater than a preset characteristic threshold, the data analysis and processing of patients in the monitoring target department of the medical institution is carried out when the number of examinations of the treatment method with the largest sum of characteristic values ​​is greater than a preset number threshold. When there is no treatment method of interest where the sum of the feature values ​​of different associated disease types is greater than the preset feature threshold, the treatment method of interest with the highest feature value of different associated disease types is used as the basis for determining the matching treatment methods for different associated disease types. When the product of the number of examinations and the feature value of any matching treatment method is greater than the preset weight threshold, data analysis and processing of patients in the monitoring target department of the medical institution is performed. Otherwise, data analysis and processing of patients in the monitoring target department of the medical institution is not required.

[0075] 1. Core concepts; Focus on diagnostic and treatment methods: In the target departments, those examinations that are crucial for diagnosing related diseases but are rarely used for routine diseases (such as "kidney biopsy" in nephrology).

[0076] Percentage of examinations: This refers to the proportion of times a particular "focused treatment method" is used to diagnose a specific "related disease" out of all the times that examination is used.

[0077] Number of similar disease types: This refers to how many "target diseases" (impoverishing diseases) are highly similar to the "associated disease" in terms of disease characteristics, reflecting the breadth of the potential risk of the associated disease.

[0078] 2. Preset parameters; Preset percentage (R_threshold): 60%, preset number of times threshold (C_threshold): 50 times / month, preset feature threshold (F_threshold): 1.

[0079] II. Data Preparation and Scenario Construction; Suppose we monitor the nephrology department of a medical institution, and its core associated disease is stage 3 chronic kidney disease (CKD), while the corresponding poverty-causing target diseases are uremia and refractory hypertensive heart disease.

[0080] We focus on two key treatment approaches: Pay attention to treatment method A: kidney biopsy; pay attention to treatment method B: 24-hour urine protein quantification. The data analysis results for the past month are as follows: Percentage of examinations: A (renal biopsy) accounted for 85% of the number of times it was used to diagnose related disease types, and B (24-hour urine protein) accounted for 40% of the number of times it was used to diagnose CKD stage 3. Number of similar disease types: CKD stage 3 is associated with the target disease (uremia, refractory hypertensive heart disease), so the number of similar disease types is 2.

[0081] Absolute number of checks: A (renal biopsy) was performed 60 times this month, and B (24-hour urine protein) was performed 200 times this month.

[0082] III. Strategic Decision-Making Process; Step 1: Calculate the percentage of total inspections A's total percentage = 85%, B's total percentage = 40%. Step Two: First-Level Decision - Determine if there are any treatment methods with a total percentage exceeding the preset percentage (60%). A (85%>60%), the condition is true.

[0083] Therefore, proceed to this branch decision: Determine: The patient with the largest percentage of total examinations is A (85%), with 60 examinations > the preset threshold of 50. The condition is met, and the decision is: Initiate comprehensive data analysis and processing for all patients visiting the nephrology department of this medical institution.

[0084] IV. Alternative Decision Path Deduction (Hypothetical Scenario); To fully illustrate the logic, let's assume a different scenario: if the number of examinations this month for treatment method A (renal biopsy) is only 45 (<50).

[0085] Therefore, the decision-making process will branch off from the second step onwards: Second step result: Although the total proportion of A (85%) is greater than 60%, its number of checks (45) is less than the preset number threshold (50). Therefore, the first-level decision condition is not met.

[0086] Step 3: Second-level decision - Calculate feature value, feature value = percentage of examinations × number of similar disease types, sum of feature values ​​of A = 85% × 2 = 1.7, sum of feature values ​​of B = 40% × 2 = 0.80, determine whether there is a feature value sum > preset feature threshold (1), the feature value sum of A is 1.7 which is greater than 1, at this time if A is greater than 40 times, the condition is met, decision result: start comprehensive data analysis and processing of patients in the nephrology department of this medical institution.

[0087] Step 4: Third-level decision-making - Matching diagnosis and treatment based on the largest eigenvalue If A only checks 20 times this month, the largest eigenvalue is A (0.85). Decision rule: Calculate: Number of checks A × Eigenvalue of A = 20 × 0.85 = 17. Judgment: Assuming the preset weight threshold is 20, then 17 < 20, the condition is not met.

[0088] Final decision: Under this hypothetical scenario, the system ultimately determines that "there is no need to perform data analysis and processing on the patients in the target departments of the medical institution".

[0089] V. Decision Output and Action; In the initial real-world data scenario of this implementation (60 A tests), the system's final output is: immediately initiate in-depth data analysis of nephrology patients.

[0090] Analysis content: This may include the cost structure, out-of-pocket ratio, family economic status model prediction, and simulation of subsequent treatment pathways for all CKD stage 3 patients who have undergone renal biopsy. The ultimate goal is to guide medical social workers in conducting precise home visits, help hospital management optimize resource allocation, and provide data support for medical insurance policies, thereby systematically and proactively preventing the risk of "impoverishment due to illness".

[0091] Specifically, the screening and processing of monitoring targets for potential individuals impoverished due to illness, based on data analysis results, includes: Patients with related disease types are identified as potential targets for monitoring, and early intervention is carried out through on-site visits.

[0092] Example 2 Secondly, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-described method for identifying people impoverished due to illness based on medical data when running the computer program.

[0093] In another possible embodiment, the method for determining the data analysis and processing strategy of the medical institution is as follows: Based on the monitoring results of the treatment data of different focus treatment methods in the monitoring target departments of the medical institution, determine the proportion of examination times for different focus treatment methods in the related disease types. It is understandable that in the above steps, if the number of treatment methods under observation is less than the preset threshold for the number of treatment methods, the total number of examinations for different treatment methods under observation will be used as the basis. When the total number of examinations for different treatment methods under observation is greater than the preset threshold for the number of examinations, data analysis and processing of patients in the monitored target department of the medical institution will be performed.

[0094] Additionally, it should be noted that when the number of treatment methods under focus is not less than the preset threshold for the number of treatment methods, the simultaneous presence of patients with different treatment methods under focus in the same associated disease type will lead to excessive interference risk based on the number of examinations for each treatment method under focus. Therefore, in this case, the sum of the proportions of the number of examinations for different treatment methods under focus in different associated disease types is determined by the proportion of the number of examinations for different treatment methods under focus in the associated disease type, and this sum is used as the total proportion of the number of examinations. If there is a treatment method with a higher percentage of total examinations than a preset percentage, then the data analysis and processing of patients in the monitored target department of the medical institution will be carried out when the number of examinations of the treatment method with the highest percentage of total examinations exceeds a preset threshold.

[0095] In another possible embodiment, if there is no treatment method with a total number of examinations exceeding a preset percentage, but there are treatment methods with different associated disease types whose examination counts all exceed a preset percentage, then when the number of examinations for any treatment method with different associated disease types exceeding a preset percentage exceeds a preset threshold, data analysis and processing of patients in the monitored target department of the medical institution will be performed; otherwise, the process will proceed to the next step.

[0096] Based on the association between the disease characteristics of the associated disease types and the target disease type corresponding to different attention treatment methods, the number of similar disease types corresponding to the associated disease types of different attention treatment methods is determined. Based on the product of the proportion of examinations of different attention treatment methods in the associated disease types and the number of similar disease types, the characteristic values ​​of different attention treatment methods in different associated disease types are determined. In one possible embodiment, in the above steps, when there are attention treatment methods whose sum of feature values ​​in different associated disease types is greater than a preset feature threshold, then when the number of examinations for any attention treatment method whose sum of feature values ​​is greater than the preset feature threshold is greater than a preset number threshold, data analysis and processing of patients in the monitoring target department of the medical institution is performed. Furthermore, when there is no treatment method of concern where the sum of the feature values ​​of different associated disease types is greater than the preset feature threshold, it is necessary to determine the matching treatment method for different associated disease types based on the treatment method of concern with the highest feature value of different associated disease types. When there is a treatment method of concern where the number of associated disease types belonging to the matching treatment method is greater than the preset type number threshold, and the number of examinations for the treatment method of concern where the number of associated disease types belonging to the matching treatment method is greater than the preset type number threshold is greater than the preset number threshold, data analysis and processing of patients in the monitoring target department of the medical institution will be performed. Otherwise, proceed to the next step.

[0097] The data analysis and processing strategy of the medical institution is determined by the number of examinations and the weight values ​​of different treatment methods.

[0098] It is understandable that when the product of the number of examinations and the feature value of any matching treatment method is greater than the preset weight threshold, data analysis and processing of patients in the monitoring target department of the medical institution will be performed; otherwise, data analysis and processing of patients in the monitoring target department of the medical institution is not required.

[0099] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0100] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0101] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A method for identifying individuals impoverished due to illness based on medical data, characterized in that, Specifically, it includes: Using medical data from the target region, the association between different disease types and the disease characteristics of the target disease type at different disease stages is determined. Based on the association, associated disease types within the stated disease types are identified. By analyzing the association between associated disease types within a department and different target disease types, the target departments for monitoring are determined. Based on the similarity between the treatment methods of related disease types in the monitored target departments and other disease types, the treatment methods to be focused on for related disease types are determined; By analyzing the monitoring results of different treatment methods in the target departments of different medical institutions, and combining the correlation between the associated disease types corresponding to different treatment methods and the disease characteristics of the target disease type, the data analysis and processing strategies of medical institutions are determined. Based on the data analysis results, the monitoring targets for potential impoverished individuals due to illness are screened and processed.

2. The method for identifying people impoverished due to illness based on medical data as described in claim 1, characterized in that, The disease stages are divided into early, middle, and late stages.

3. The method for identifying people impoverished due to illness based on medical data as described in claim 1, characterized in that, The method for determining the associated disease types in the aforementioned disease types is as follows: Based on the correlation between the disease type and the disease characteristics of the target disease type at different disease stages, determine the similarity of the indicator data range of the examination indicators with different target disease types at different disease stages. Based on the similarities described, identify similar disease types among target disease types at different disease stages; Whether a disease type is a related disease type is determined by the number of similar disease types in different disease stages.

4. The method for identifying people impoverished due to illness based on medical data as described in claim 3, characterized in that, The similar disease type is the target disease type in which the number of examination indicators with overlapping data ranges is greater than a preset threshold for the number of examination indicators.

5. The method for identifying people impoverished due to illness based on medical data as described in claim 3, characterized in that, If the number of similar disease types in different disease stages is greater than a preset threshold for the number of similar disease types, then the disease type is determined to be an associated disease type.

6. The method for identifying people impoverished due to illness based on medical data as described in claim 1, characterized in that, The method for determining the target monitoring departments within the aforementioned departments is as follows: The number of associated disease types of the department is determined based on the associated disease types of the department; Based on the number of the associated disease types, determine whether the department is a target department for monitoring.

7. The method for identifying people impoverished due to illness based on medical data as described in claim 6, characterized in that, When the number of associated disease types exceeds the threshold for the number of associated disease types, the patients visiting the department are collected and analyzed in real time, and the patients visiting the associated disease types are used as monitoring targets, and early intervention is carried out through on-site visits.

8. The method for identifying people impoverished due to illness based on medical data as described in claim 1, characterized in that, The method for determining the data analysis and processing strategy of the medical institution is as follows: Based on the monitoring results of the treatment data of different focus treatment methods in the monitoring target departments of the medical institution, determine the proportion of examination times for different focus treatment methods in the related disease types. Based on the association between the disease characteristics of the associated disease types and the target disease type corresponding to different attention and treatment methods, determine the number of similar disease types corresponding to the associated disease types of different attention and treatment methods; Based on the proportion of examinations conducted by different treatment methods in related disease types and the number of similar disease types, the data analysis and processing strategy of the medical institution is determined.

9. A computer system, comprising: A memory and processor connected by communication, and a computer program stored in the memory and capable of running on the processor, characterized in that, when the processor runs the computer program, it executes a method for identifying people impoverished due to illness based on medical data, as described in any one of claims 1-8.

Images