A method and system for health risk assessment based on medical data

Abstract

The application discloses a kind of health risk assessment method and system based on medical data, it is related to risk assessment field, solve the problem that existing health risk assessment accuracy is insufficient, including: step S1: the medical record information of the person of hospitalization is acquired;Step S2: the external manifestation information of the person of hospitalization and diagnosis information are acquired, disease is analyzed in combination with susceptible disease list;External manifestation list of disease and diagnosis project of disease are obtained;From the diagnosis information of the person of hospitalization and diagnosis project of disease, the diagnosis list of disease is acquired;Step S3: the personal information of user is acquired, and the detection list and the diagnosis list of disease are analyzed according to the personal information of user, obtain the disease prediction value of user;Step S4: the health risk assessment of user is carried out, and risk assessment report is stored after encryption;The application can effectively improve health risk assessment accuracy, and provide risk early warning for user.

Description

Technical Field

[0001] This invention belongs to the field of medical and health care, and more specifically relates to the field of risk assessment, specifically a health risk assessment method and system based on medical data. Background Technology

[0002] Existing health risk assessment methods and systems based on medical data have the following specific shortcomings when conducting risk assessments:

[0003] 1. The health risk assessment of users mainly involves medical staff making a preliminary diagnosis based on the user's external manifestations (such as difficulty breathing and paleness) based on their own experience, arranging tests for the user based on the diagnosis results, and assessing the user's physical condition based on the test results. The assessment results are highly dependent on medical staff, and the accuracy of the assessment results has limitations.

[0004] 2. Existing health risk assessment methods and systems based on medical data mainly focus on analyzing user test data to assess the user's health. However, the assessment direction is not specific and the assessment cost is high.

[0005] 3. When conducting health risk assessments on users, a large amount of users' personal privacy data is involved. The health risk assessment results should be stored in encrypted form to protect the security of users' personal information.

[0006] To this end, we propose a health risk assessment method and system based on medical data. Summary of the Invention

[0007] In view of the shortcomings of existing technologies, the purpose of this invention is to provide a health risk assessment method and system based on medical data, and to improve the accuracy of health risk assessment.

[0008] To achieve the above objectives, the present invention adopts the following technical solution: a health risk assessment method based on medical data, characterized in that it includes:

[0009] Step S1: Obtain the medical record information of patients in the hospital, obtain the frequency of disease occurrence based on the medical record information, sort the frequency of disease occurrence in descending order, and obtain a list of susceptible diseases.

[0010] Step S2: Obtain the external manifestations and diagnostic information of patients based on medical record information, and analyze the diseases in conjunction with the list of susceptible diseases; statistically analyze the external manifestations of patients to obtain a list of external manifestations of diseases; judge the diagnostic information of patients to obtain the diagnostic items of diseases; obtain a list of disease diagnoses based on the diagnostic information of patients and the diagnostic items of diseases.

[0011] Step S3: Obtain the user's personal information, obtain the user's test items based on the user's personal information, statistically analyze the test results of the test items to obtain a test list; analyze the test list with the disease diagnosis list to obtain the user's disease prediction value;

[0012] Step S4: Conduct a health risk assessment on the user based on the user's disease prediction value, obtain a risk assessment report, and encrypt and store the risk assessment report.

[0013] Furthermore, the specific steps of step S1 are as follows:

[0014] Step S11: Obtain the number of patients in the hospital and record the number as 'as'; based on the number of patients, obtain their medical record information and record the medical record information as 'blx'. a ;

[0015] Step S12: Obtain the diseases of the patients based on their medical records, classify the diseases of as patients, and obtain the number of disease types bs; count the number of patients for each disease type to obtain the number of patients hrs. b ;

[0016] The frequency of disease occurrence is calculated based on the number of patients and the number of people seeking medical treatment, resulting in the frequency fpl. b ;

[0017] Sort the diseases in descending order according to their frequency of occurrence to obtain a list of susceptible diseases. The list of susceptible diseases is denoted as yhj, and the list elements in the list of susceptible diseases are denoted as yhj[b].

[0018] Furthermore, the specific steps of step S2 are as follows:

[0019] Step S21: Based on the external manifestation information of patients and the list of susceptible diseases, statistical analysis is conducted on patients with the same disease. The external manifestations of the disease are integrated based on the external manifestations of the patients to obtain the external manifestation text of the disease. The external manifestation text of the disease is then processed to obtain the external manifestation list of the disease.

[0020] Step S22: Obtain standard and fluctuating data of various human body indicators; screen the diagnostic information of patients based on the standard and fluctuating data to obtain disease-related detection indicators; and determine the diagnostic items of the disease based on the disease-related detection indicators.

[0021] Step S23: Combine the diagnostic items of the disease with the diagnostic information of the patient, calculate the specific range of the disease in each diagnostic item, and construct a diagnostic list of the disease based on the specific range of each diagnostic item.

[0022] Furthermore, the specific steps of step S22 are as follows:

[0023] Step S221: Record the standard data of various human body indicators as bzs and the floating data as fds; based on the standard data and floating data of various human body indicators, obtain the value range of various human body indicators.

[0024] Step S222: Based on the patient's diagnostic information, obtain the diagnostic data of various indicators of the patient, and record it as zds; calculate the diagnostic data of various indicators of the patient and the value range of various human body indicators to obtain the judgment value pdz.

[0025] Determine the disease-related test indicators based on the judgment values:

[0026] If pds > 1, it indicates that this indicator is a detection indicator;

[0027] If pds≤1, it indicates that this indicator is not a detection indicator;

[0028] The number of each indicator to be tested is denoted as sl; the indicators of each patient are judged to obtain the list of test indicators jzl for the patient; jzl = [zb(1), zb(2), ..., zb(sl)]; where zb(sl) represents the determined value of the sl-th test indicator. When the sl-th test indicator is a non-test indicator, zb(sl) is assigned the value of 0, and when it is a test indicator, zb(sl) is assigned the value of 1; the list of test indicators of multiple patients with the same disease is obtained and denoted as jzl1 to jzl. rs According to the list of detection indicators jzl1 to jzl rs The number of times a detection indicator appears in different patients is calculated. If more than half of all patients with the same disease have the same detection indicator, then that indicator is the detection indicator for the disease. The detection indicators for the disease are statistically analyzed to obtain a list of diagnostic items for the disease.

[0029] Furthermore, the specific steps of step S23 are as follows:

[0030] Step S231: Based on the list of diagnostic items for the disease, obtain the number of diagnostic items for the disease and record the number of diagnostic items as zs; record each diagnostic item in the list of diagnostic items as zdx(1) to zdx(zs) based on the number of diagnostic items.

[0031] Step S232: Obtain the data of patients with the corresponding disease, denoted as xs; combine the diagnostic items to obtain the diagnostic data of patients with the corresponding disease, denoted as hxy(x, z); hxy(x, z) represents the diagnostic data of the z-th diagnostic item of the x-th patient with the corresponding disease;

[0032] The mean of the disease is calculated based on the diagnostic data to obtain the diagnostic mean zjz(z).

[0033] The difference between the diagnostic mean and the diagnostic data is calculated, and the diagnostic mean and the difference between the diagnostic data are integrated to obtain the fluctuation value bdz(z) of the diagnostic data.

[0034] Based on the diagnostic mean zjz(z) and the fluctuation value bdz(z), the diagnostic range of the z-th diagnostic item of the disease is zjz(z) ± bdz(z); the diagnostic items zs are statistically analyzed to obtain the diagnostic list jzd of the disease; jzd = [zjz(1) ± bdz(1), zjz(2) ± bdz(2), ..., zjz(zs) ± bdz(zs)].

[0035] Furthermore, the specific steps of step S3 are as follows:

[0036] Step S31: Obtain a list of external manifestations of diseases; perform text matching on the user's personal information based on the list of external manifestations of diseases to obtain the diseases corresponding to the user's personal information; and statistically analyze the diseases corresponding to the user's personal information to obtain a list of detected diseases.

[0037] Step S32: Based on the disease test list, obtain the diagnostic item list for each disease to get the user's test items; perform tests on the user based on the user's test items to get the test results, and statistically analyze the test results to get the test list;

[0038] Step S33: Obtain the disease diagnosis list; extract the corresponding test results from the test list according to the disease diagnosis items, and calculate the test results in combination with the disease diagnosis list to obtain the user's disease prediction value; calculate the disease prediction value for each disease from the user's test disease list to obtain a disease prediction value list.

[0039] Furthermore, the specific steps of step S32 are as follows:

[0040] Step S321: Obtain the number of diseases in the disease detection list, denoted as js; obtain the list of diagnostic items for each disease, denoted as ydx. j The quantity in the diagnostic item list is denoted as ms; the diagnostic items in the diagnostic item list are denoted as ydx. j (1) to ydxj (ms);

[0041] Step S322: Based on the diagnostic item ydx j (1) to ydx j (ms) Perform detection on the user, obtain the detection result, and record the detection result as jcg. j (1) to jcg j (ms); Statistical analysis of the detection results yields the detection list jcl.

[0042] Furthermore, the specific steps of step S33 are as follows:

[0043] Step S331: Obtain the user's list of detected diseases, and obtain the diagnosis list of diseases based on the user's list of detected diseases, denoted as jzd. j jzd j This represents the diagnosis list of the j-th disease in the user's disease detection list;

[0044] Step S332: Obtain the test list, calculate the similarity between the test list and the disease diagnosis list, and obtain the similarity value xsz;

[0045] ;

[0046] Among them: xsz j This refers to the similarity value between the j-th disease in the user's detection list and the disease's diagnosis list; zjz j (m) represents the mean diagnostic value of the m-th diagnostic item in the diagnostic list for the j-th disease, bdz j (m) represents the diagnostic fluctuation value of the m-th diagnostic item in the diagnostic list for the j-th disease; jcg j (m) represents the test result of the m-th diagnostic item for the j-th disease in the test list;

[0047] Step S333: Obtain the ranking b of the disease in the list of susceptible diseases; calculate the predicted value ycz of the disease by combining the similarity value xsz;

[0048] The predicted values ​​of js diseases are statistically analyzed to obtain a list of predicted values ​​for each disease.

[0049] Furthermore, the specific steps of step S4 are as follows:

[0050] Step S41: Obtain the disease prediction value list, analyze the disease prediction value for each disease based on the list; extract the prediction value ycz for each disease, and evaluate the prediction value:

[0051] If ycz ≥ 1 / 2, the user is considered to be at high risk of having the disease.

[0052] If ycz < 1 / 2, the user is considered to have a low risk of having the disease.

[0053] Based on the analysis results, a health risk assessment is conducted on the user. For high-risk diseases, the user is reminded to undergo more detailed testing. For low-risk diseases, a risk assessment report is provided to the user based on the risk assessment of all diseases.

[0054] Step S42: Based on the user's personal information, obtain the user's unique identifier value, denoted as wbs, and use the user's unique identifier value as a key to encrypt the risk assessment report;

[0055] The specific encryption process is as follows:

[0056] The character code of each character in the risk assessment report is obtained and denoted as pzf(1) to pzf(fs), where pzf(fs) represents the character code of the fs-th character in the risk assessment report;

[0057] Each character is encrypted based on the user's unique identifier, resulting in the encrypted character "jmz".

[0058] ;

[0059] Where: mod represents the modulo operation; (wbs)mod(f) represents the modulo operation on wbs, where f represents the encoding of the f-th character; jmz(f) is the encrypted character of the f-th character, pzf(f) represents the character encoding of the f-th character, and f∈[1, fs];

[0060] The encrypted text is obtained by counting the encrypted characters, and the length of the unique identifier value (bcd) is obtained. Based on the length of the unique identifier value, the characters of the encrypted text are converted into binary and the binary file is stored.

[0061] When a user retrieves a risk assessment report, the user provides their unique identifier. The binary file is extracted based on the length of the unique identifier, and the text is decrypted using the unique identifier to obtain the risk assessment report.

[0062] A health risk assessment system based on medical data, the assessment system includes:

[0063] Information collection module: Acquires medical record information of patients in the hospital, obtains the frequency of disease occurrence based on the patient's medical record information, sorts the frequency of disease occurrence in descending order, and obtains a list of susceptible diseases;

[0064] Information processing module: Based on medical record information, it acquires the external manifestations and diagnostic information of patients, analyzes diseases in conjunction with a list of susceptible diseases; it statistically analyzes the external manifestations of patients to obtain a list of external manifestations of diseases; it judges the diagnostic information of patients to obtain the diagnostic items of diseases; and it obtains a list of disease diagnoses based on the diagnostic information of patients and the diagnostic items of diseases.

[0065] Detection and Analysis Module: Acquires the user's personal information, obtains the user's test items based on the user's personal information, statistically analyzes the test results of the test items to obtain a test list; analyzes the test list with the disease diagnosis list to obtain the user's disease prediction value;

[0066] Risk assessment module: Based on the user's disease prediction values, conduct a health risk assessment for the user, generate a risk assessment report, and store the risk assessment report in encrypted form.

[0067] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0068] 1. This invention analyzes existing medical data, categorizing patient information into external manifestations and specific diagnoses; it statistically analyzes the manifestations of different diseases based on external manifestations; it integrates disease diagnostic data based on specific diagnoses; it digitizes the manifestations and diagnoses of different diseases, reducing the impact of human factors in the risk assessment process; and it enhances the accuracy of the assessment.

[0069] 2. Compare the user's external performance with the digitized disease data to reduce the scope of assessment and lower assessment costs; arrange testing items for the user based on the comparison results; calculate the similarity between the test results and the diseases in the comparison results, and make a judgment based on the similarity; clarify the target of the test results to facilitate accurate judgment of the user.

[0070] 3. Encrypt user evaluation results by encrypting each character of the evaluation result using the user's unique identifier. Differentiate encryption based on character order to enhance encryption strength and ensure security. Store the encrypted text in binary format according to the length of the user's unique identifier and obfuscate the text characters to protect the user's personal information security. Attached Figure Description

[0071] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0072] Figure 1 This is a schematic diagram of the method of the present invention;

[0073] Figure 2 This is a schematic diagram of data analysis in this invention;

[0074] Figure 3 This is a schematic diagram of the system of the present invention; Detailed Implementation

[0075] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0076] Example 1

[0077] Please see Figure 1 This invention relates to the field of risk assessment and provides a technical solution for a health risk assessment method based on medical data, comprising:

[0078] Step S1: Obtain the medical record information of patients in the hospital, obtain the frequency of disease occurrence based on the medical record information, sort the frequency of disease occurrence in descending order, and obtain a list of susceptible diseases.

[0079] Step S11: Obtain the number of patients in the hospital and record the number as 'as'; based on the number of patients, obtain their medical record information and record the medical record information as 'blx'. a Among them: blx z Let a represent the medical record information of the a-th patient, where a∈[1, as];

[0080] Step S12: Obtain the diseases of the patients based on their medical records, classify the diseases of as patients, and obtain the number of disease types bs; count the number of patients for each disease type to obtain the number of patients hrs. b Among them: hrs b This represents the number of patients with the b-th disease, where b∈[1, bs];

[0081] The frequency of disease occurrence is calculated based on the number of patients and the number of people seeking medical treatment, resulting in the frequency fpl. b ;

[0082] ;

[0083] Sort the diseases in descending order according to their frequency of occurrence to obtain a list of susceptible diseases. The list of susceptible diseases is denoted as yhj, and the list element in the list of susceptible diseases is denoted as yhj[b]; yhj[b] represents the b-th element in the list of susceptible diseases.

[0084] Step S2: Obtain the external manifestations and diagnostic information of patients based on medical record information, and analyze the diseases in conjunction with the list of susceptible diseases; statistically analyze the external manifestations of patients to obtain a list of external manifestations of diseases; judge the diagnostic information of patients to obtain the diagnostic items of diseases; obtain a list of disease diagnoses based on the diagnostic information of patients and the diagnostic items of diseases.

[0085] It should be noted that: external manifestations refer to the patient's symptoms, such as dizziness, vomiting, and tongue discoloration; diagnostic information refers to the patient's blood pressure, complete blood count, urinalysis, liver function, kidney function, blood lipids, and electrocardiogram.

[0086] Step S21: Based on the external manifestation information of patients and the list of susceptible diseases, statistical analysis is conducted on patients with the same disease. The external manifestations of the disease are integrated based on the external manifestations of the patients to obtain the external manifestation text of the disease. The external manifestation text of the disease is then processed to obtain the external manifestation list of the disease.

[0087] Step S211: Based on the list of susceptible diseases, obtain information on patients with the same disease; based on the number of patients with the same disease, statistically analyze the external manifestation information of each patient to obtain the text of the external manifestation of the disease.

[0088] Step S212: Obtain the external manifestation type of the disease based on the external manifestation text of the disease; process the external manifestation text of the disease based on the external manifestation type of the disease, count the frequency of occurrence of the external manifestation type of the disease in the external manifestation text, sort the external manifestation types of the disease in descending order according to the frequency of occurrence, and obtain a list of external manifestations of the disease.

[0089] It should be noted that by statistically analyzing the external manifestations of all patients with the same disease, the external manifestations of the disease are comprehensively recorded, thus enhancing the accuracy of disease diagnosis. Based on the recorded results, each different manifestation type is ranked, and the external manifestations of the disease are classified into primary and secondary categories. Different diseases with similar external manifestations are recorded differently to prevent confusion between diseases with similar manifestations.

[0090] Step S22: Obtain standard and fluctuating data of various human body indicators; screen the diagnostic information of patients based on the standard and fluctuating data to obtain disease-related detection indicators; and determine the diagnostic items of the disease based on the disease-related detection indicators.

[0091] It should be noted that: fluctuation data refers to the range of fluctuation of various indicators of the human body under normal physiological conditions. For example, the average normal human body temperature is between 36 and 37°C, so the standard value of body temperature is set to 36.5°C, and the fluctuation data is set to 0.5°C.

[0092] Step S221: Record the standard data of various human body indicators as bzs and the floating data as fds; based on the standard data and floating data of various human body indicators, obtain the value range of various human body indicators.

[0093] Step S222: Based on the patient's diagnostic information, obtain the diagnostic data of various indicators of the patient, and record it as zds; calculate the diagnostic data of various indicators of the patient and the value range of various human body indicators to obtain the judgment value pdz.

[0094] ;

[0095] Where: bzs is the standard data of the indicator, and fds is the floating data;

[0096] Determine the disease-related test indicators based on the judgment values:

[0097] If pds > 1, it indicates that this indicator is a detection indicator;

[0098] If pds≤1, it indicates that this indicator is not a detection indicator;

[0099] Please see Figure 2 ; Obtain the number of each indicator for testing, denoted as sl; Judge each indicator of the patient to obtain the list of test indicators jzl for the patient; jzl = [zb(1), zb(2), ..., zb(sl)]; where zb(sl) represents the determined value of the sl-th test indicator. When the sl-th test indicator is a non-test indicator, zb(sl) is assigned the value of 0, and when it is a test indicator, zb(sl) is assigned the value of 1; Obtain the list of test indicators for multiple patients with the same disease, denoted as jzl1 to jzl rs According to the list of detection indicators jzl1 to jzl rs The number of times a detection indicator appears in different patients is calculated. If more than half of all patients with the same disease have the same detection indicator, then that indicator is considered a detection indicator for the disease. The determination of a disease detection indicator is as follows:

[0100] ;

[0101] Where: jjc(s) represents the judgment of the s-th indicator, and jjc(s) > 0 indicates that it is a disease detection indicator; zb r (s) represents the determined value of s test indicators for the r-th patient.

[0102] By statistically analyzing the detection indicators of the disease, a list of diagnostic items for the disease can be obtained;

[0103] Step S23: Combine the diagnostic items of the disease with the diagnostic information of the patient, calculate the specific range of the disease in each diagnostic item, and construct a diagnostic list of the disease based on the specific range of each diagnostic item.

[0104] Step S231: Based on the list of diagnostic items for the disease, obtain the number of diagnostic items for the disease and record the number of diagnostic items as zs; record each diagnostic item in the list of diagnostic items as zdx(1) to zdx(zs) based on the number of diagnostic items.

[0105] Step S232: Obtain the data of patients with the corresponding disease, denoted as xs; combine the diagnostic items to obtain the diagnostic data of patients with the corresponding disease, denoted as hxy(x, z); hxy(x, z) represents the diagnostic data of the z-th diagnostic item of the x-th patient with the corresponding disease;

[0106] It should be noted that: having the corresponding disease refers to the disease corresponding to the disease in step S231 above; based on the disease diagnosis items determined in step S231, the actual patients with the disease are analyzed to enhance the reliability of the data.

[0107] The mean of the disease is calculated based on the diagnostic data to obtain the diagnostic mean zjz(z).

[0108] ;

[0109] The difference between the diagnostic mean and the diagnostic data is calculated, and the diagnostic mean and the difference between the diagnostic data are integrated to obtain the fluctuation value bdz(z) of the diagnostic data.

[0110] ;

[0111] It should be noted that by calculating the overall difference, the impact of special values ​​on the data is reduced, and the diagnostic data is statistically analyzed as a whole based on the diagnostic mean, simplifying the calculation process.

[0112] Based on the diagnostic mean zjz(z) and the fluctuation value bdz(z), the diagnostic range of the z-th diagnostic item of the disease is zjz(z) ± bdz(z); the diagnostic items zs are statistically analyzed to obtain the diagnostic list jzd of the disease; jzd = [zjz(1) ± bdz(1), zjz(2) ± bdz(2), ..., zjz(zs) ± bdz(zs)].

[0113] Step S3: Obtain the user's personal information, obtain the user's test items based on the user's personal information, statistically analyze the test results of the test items to obtain a test list; analyze the test list with the disease diagnosis list to obtain the user's disease prediction value;

[0114] Step S31: Obtain a list of external manifestations of diseases; perform text matching on the user's personal information based on the list of external manifestations of diseases to obtain the diseases corresponding to the user's personal information; and statistically analyze the diseases corresponding to the user's personal information to obtain a list of detected diseases.

[0115] Step S311: Process the user's personal information, extract the user's medical history and family hereditary diseases, and use the user's medical history and family hereditary diseases as the detection diseases; perform text matching between the user's personal information and the list of external manifestations of diseases; when the user's personal information matches the list of external manifestations of diseases, the disease is used as the user's detection disease; count the user's detection diseases to obtain the user's detection disease list.

[0116] Step S32: Based on the disease test list, obtain the diagnostic item list for each disease to get the user's test items; perform tests on the user based on the user's test items to get the test results, and statistically analyze the test results to get the test list;

[0117] Step S321: Obtain the number of diseases in the disease detection list, denoted as js; obtain the list of diagnostic items for each disease, denoted as ydx. j The quantity in the diagnostic item list is denoted as ms; the diagnostic items in the diagnostic item list are denoted as ydx. j (1) to ydx j (ms);

[0118] Step S322: Based on the diagnostic item ydx j (1) to ydx j (ms) Perform detection on the user, obtain the detection result, and record the detection result as jcg. j (1) to jcg j (ms); Statistical analysis of the detection results yields the detection list jcl;

[0119] .

[0120] Step S33: Obtain the disease diagnosis list; extract the corresponding test results from the test list according to the disease diagnosis items, calculate the test results in combination with the disease diagnosis list, and obtain the user's disease prediction value; calculate the disease prediction value for each disease from the user's test disease list to obtain a disease prediction value list.

[0121] Step S331: Obtain the user's list of detected diseases, and obtain the diagnosis list of diseases based on the user's list of detected diseases, denoted as jzd. j jzd jThis represents the diagnosis list of the j-th disease in the user's disease detection list;

[0122] Step S332: Obtain the test list, calculate the similarity between the test list and the disease diagnosis list, and obtain the similarity value xsz;

[0123] ;

[0124] Among them: xsz j This refers to the similarity value between the j-th disease in the user's detection list and the disease's diagnosis list; zjz j (m) represents the mean diagnostic value of the m-th diagnostic item in the diagnostic list for the j-th disease, bdz j (m) represents the diagnostic fluctuation value of the m-th diagnostic item in the diagnostic list for the j-th disease; jcg j (m) represents the test result of the m-th diagnostic item for the j-th disease in the test list.

[0125] It should be noted that: by comparing the test results with the diagnostic mean, a similarity calculation is performed on the test results. The result is divided by the fluctuation value, and values ​​with a similarity value less than 1 are considered similar. The difference between the similarity value and 1 is calculated, and the larger the similarity value, the more similar the results are. At the same time, the absolute values ​​are summed, and values ​​less than 0 are represented as 0 in the formula. Through the similarity value calculation, the association between users and diseases is intuitively reflected.

[0126] Step S333: Obtain the ranking b of the disease in the list of susceptible diseases; calculate the predicted value ycz of the disease by combining the similarity value xsz;

[0127] ;

[0128] Where: bs represents the number of disease types;

[0129] The predicted values ​​of js diseases are statistically analyzed to obtain a list of predicted values ​​for the diseases;

[0130] It should be noted that the higher a disease appears on the list of susceptible diseases, the more frequent it is, and the more comprehensive the patient data for that disease. This leads to a more accurate assessment of the relevance of the disease to a user's individual circumstances. Conversely, for diseases further down the list, the accuracy of patient data is insufficient. Therefore, diseases for this category are given higher weight in prediction to reduce errors in disease prediction.

[0131] Step S4: Conduct a health risk assessment on the user based on the user's disease prediction value, obtain a risk assessment report, and encrypt and store the risk assessment report;

[0132] Step S41: Obtain the disease prediction value list, analyze the disease prediction value for each disease based on the list; extract the prediction value ycz for each disease, and evaluate the prediction value:

[0133] If ycz ≥ 1 / 2, the user is considered to be at high risk of having the disease.

[0134] If ycz < 1 / 2, the user is considered to have a low risk of having the disease.

[0135] Based on the analysis results, a health risk assessment is conducted on the user. For high-risk diseases, the user is reminded to undergo more detailed testing to ensure good health. For low-risk diseases, the user is provided with corresponding preventive measures. A risk assessment report is provided to the user based on the risk assessment of all diseases.

[0136] Step S42: Based on the user's personal information, obtain the user's unique identifier value, denoted as wbs, and use the user's unique identifier value as the key to encrypt the risk assessment report; the specific encryption process is as follows:

[0137] The character code of each character in the risk assessment report is obtained and denoted as pzf(1) to pzf(fs), where pzf(fs) represents the character code of the fs-th character in the risk assessment report;

[0138] Each character is encrypted based on the user's unique identifier, resulting in the encrypted character "jmz".

[0139] ;

[0140] Where: mod represents the modulo operation; (wbs)mod(f) means taking the modulo of wbs, such as wbs is 10 and f is 3; then (wbs)mod(f) = 1; f represents the encoding of the f-th character; jmz(f) is the encrypted character of the f-th character, pzf(f) represents the character encoding of the f-th character, f∈[1, fs];

[0141] It should be noted that: using modulo operation enhances the distinctiveness between encrypted characters, thereby improving their security; at the same time, using numerical division reduces the length of the encrypted characters, lowering storage costs; and performing modulo operation and addition on the divided data prevents loss of precision.

[0142] The encrypted text is obtained by counting the encrypted characters, and the length of the unique identifier value (bcd) is obtained. The characters of the encrypted text are converted into binary according to the length of the unique identifier value, and the binary file is stored. The encryption strength of the encrypted text is enhanced to ensure the security of the file.

[0143] When a user retrieves a risk assessment report, the user provides their unique identifier. The binary file is extracted based on the length of the unique identifier, and the text is decrypted using the unique identifier to obtain the risk assessment report.

[0144] It should be noted that a user's unique identifier refers to information that uniquely represents the user, such as an ID card number.

[0145] Example 2

[0146] Please see Figure 3 A health risk assessment system based on medical data relates to the field of risk assessment. The system includes: an information acquisition module, an information processing module, a detection and analysis module, a risk assessment module, and a server. The server controls the information acquisition module, information processing module, detection and analysis module, and risk assessment module.

[0147] Information collection module: Acquires medical record information of patients in the hospital, obtains the frequency of disease occurrence based on the patient's medical record information, sorts the frequency of disease occurrence in descending order, and obtains a list of susceptible diseases;

[0148] Information processing module: Based on medical record information, it acquires the external manifestations and diagnostic information of patients, analyzes diseases in conjunction with a list of susceptible diseases; it statistically analyzes the external manifestations of patients to obtain a list of external manifestations of diseases; it judges the diagnostic information of patients to obtain the diagnostic items of diseases; and it obtains a list of disease diagnoses based on the diagnostic information of patients and the diagnostic items of diseases.

[0149] Detection and Analysis Module: Acquires the user's personal information, obtains the user's test items based on the user's personal information, statistically analyzes the test results of the test items to obtain a test list; analyzes the test list with the disease diagnosis list to obtain the user's disease prediction value;

[0150] Risk assessment module: Based on the user's disease prediction values, conduct a health risk assessment for the user, generate a risk assessment report, and store the risk assessment report in encrypted form;

[0151] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A health risk assessment system based on medical data, characterized in that, It includes an information acquisition module, an information processing module, a detection and analysis module, and a risk assessment module; The information acquisition module is used to execute step S1: Step S1: Obtain the medical record information of patients in the hospital, obtain the frequency of disease occurrence based on the medical record information, sort the frequency of disease occurrence in descending order, and obtain a list of susceptible diseases. The information processing module is used to execute step S2: Step S2: Obtain the external manifestations and diagnostic information of the patients based on medical record information, and analyze the diseases in conjunction with the list of susceptible diseases; statistically analyze the external manifestations of the patients to obtain a list of external manifestations of the diseases; determine the diagnostic information of the patients to obtain the diagnostic items of the diseases; obtain the diagnostic list of the diseases based on the diagnostic information of the patients and the diagnostic items of the diseases; external manifestations refer to the symptoms of the patients' illness; diagnostic information refers to the patients' blood pressure, complete blood count, urinalysis, liver function, kidney function, blood lipids, and electrocardiogram tests. The detection and analysis module is used to execute step S3: Step S3: Obtain the user's personal information, obtain the user's test items based on the user's personal information, statistically analyze the test results of the test items to obtain a test list; analyze the test list with the disease diagnosis list to obtain the user's disease prediction value; The specific steps of step S3 are as follows: Step S31: Obtain a list of external manifestations of diseases; perform text matching on the user's personal information based on the list of external manifestations of diseases to obtain the diseases corresponding to the user's personal information; and statistically analyze the diseases corresponding to the user's personal information to obtain a list of detected diseases. Step S32: Based on the disease test list, obtain the list of diagnostic items for each disease, record the number of diagnostic items in the list as ms, and obtain the user's test items; perform tests on the user based on the user's test items, obtain the test results, and statistically analyze the test results to obtain the test list; Step S33: Obtain the list of disease diagnoses; Based on the disease's diagnostic items, the corresponding test results in the test list are extracted, and the test results are calculated in combination with the disease's diagnostic list to obtain the user's disease prediction value; the disease prediction value for each disease is calculated from the user's list of detected diseases to obtain a list of disease prediction values. The specific steps of step S33 are as follows: Step S331: Obtain the user's list of detected diseases, and obtain the diagnosis list of diseases based on the user's list of detected diseases, denoted as jzd. j jzd j This represents the diagnosis list of the j-th disease in the user's disease detection list; Step S332: Obtain the test list, calculate the similarity between the test list and the disease diagnosis list, and obtain the similarity value, denoted as xsz; ； Among them: xsz j This refers to the similarity value between the j-th disease in the user's detection list and the disease's diagnosis list; zjz j (m) represents the mean diagnostic value of the m-th diagnostic item in the diagnostic list for the j-th disease, bdz j (m) represents the diagnostic fluctuation value of the m-th diagnostic item in the diagnostic list for the j-th disease; jcg j (m) represents the test result of the m-th diagnostic item for the j-th disease in the test list; Step S333: Obtain the ranking of the disease in the list of susceptible diseases; calculate the predicted value of the disease by combining the similarity value xsz, denoted as ycz; The predicted values ​​of js diseases are statistically analyzed to obtain a list of predicted values ​​for the diseases; The risk assessment module is used to perform step S4: Step S4: Conduct a health risk assessment on the user based on the user's disease prediction value, obtain a risk assessment report, and encrypt and store the risk assessment report.

2. The health risk assessment system based on medical data according to claim 1, characterized in that, The specific steps of step S1 are as follows: Step S11: Obtain the number of patients in the hospital and record the number as 'as'; based on the number of patients, obtain their medical record information and record the medical record information as 'blx'. a ; Step S12: Based on the medical records of the patients, obtain the diseases they suffer from, classify the diseases of the *as* patients, and obtain the number of disease types, denoted as *bs*; count the number of patients for each disease type, and obtain the total number of patients, denoted as *hrs*. b ; The frequency of disease occurrence is calculated based on the number of patients and the number of people seeking medical treatment, and is denoted as fpl. b ; Sort the diseases in descending order according to their frequency of occurrence to obtain a list of susceptible diseases. The list of susceptible diseases is denoted as yhj, and the list elements in the list of susceptible diseases are denoted as yhj[b].

3. The health risk assessment system based on medical data according to claim 1, characterized in that, The specific steps of step S2 are as follows: Step S21: Based on the external manifestation information of patients and the list of susceptible diseases, statistical analysis is conducted on patients with the same disease. The external manifestations of the disease are integrated based on the external manifestations of the patients to obtain the external manifestation text of the disease. The external manifestation text of the disease is then processed to obtain the external manifestation list of the disease. Step S22: Obtain standard and fluctuating data of various human body indicators; screen the diagnostic information of patients based on the standard and fluctuating data to obtain disease-related detection indicators; and determine the diagnostic items of the disease based on the disease-related detection indicators. Step S23: Combine the diagnostic items of the disease with the diagnostic information of the patient, calculate the specific range of the disease in each diagnostic item, and construct a diagnostic list of the disease based on the specific range of each diagnostic item.

4. A health risk assessment system based on medical data according to claim 3, characterized in that, The specific steps of step S22 are as follows: Step S221: Record the standard data of various human body indicators as bzs and the floating data as fds; based on the standard data and floating data of various human body indicators, obtain the value range of various human body indicators. Step S222: Based on the patient's diagnostic information, obtain the diagnostic data of various indicators of the patient, denoted as zds; calculate the diagnostic data of various indicators of the patient with the value range of various human body indicators to obtain the judgment value, denoted as pdz; Determine the disease-related test indicators based on the judgment values: If pds > 1, it indicates that this indicator is a detection indicator; If pds≤1, it indicates that this indicator is not a detection indicator; The number of each indicator to be tested is denoted as sl; the indicators of each patient are judged to obtain the list of test indicators jzl for the patient; jzl = [zb(1), zb(2), ..., zb(sl)]; where zb(sl) represents the determined value of the sl-th test indicator. When the sl-th test indicator is a non-test indicator, zb(sl) is assigned the value of 0, and when it is a test indicator, zb(sl) is assigned the value of 1; the list of test indicators of multiple patients with the same disease is obtained and denoted as jzl1 to jzl. rs According to the list of detection indicators jzl1 to jzl rs The number of times a detection indicator appears in different patients is calculated. If more than half of all patients with the same disease have the same detection indicator, then that indicator is the detection indicator for the disease. The detection indicators for the disease are statistically analyzed to obtain a list of diagnostic items for the disease.

5. A health risk assessment system based on medical data according to claim 3, characterized in that, The specific steps of step S23 are as follows: Step S231: Based on the list of disease diagnosis items, obtain the number of disease diagnosis items and record the number of diagnosis items as zs; record each diagnosis item in the list of diagnosis items as zdx(1) to zdx(zs) based on the number of diagnosis items. Step S232: Obtain the data of patients with the corresponding disease, denoted as xs; combine the diagnostic items to obtain the diagnostic data of patients with the corresponding disease, denoted as hxy(x, z); hxy(x, z) represents the diagnostic data of the z-th diagnostic item of the x-th patient with the corresponding disease; The mean of the disease is calculated based on the diagnostic data, and the diagnostic mean is denoted as zjz(z). The difference between the diagnostic mean and the diagnostic data is calculated, and the fluctuation value of the diagnostic data is obtained by integrating the diagnostic mean and the difference of the diagnostic data, denoted as bdz(z). Based on the diagnostic mean zjz(z) and the fluctuation value bdz(z), the diagnostic range of the z-th diagnostic item of the disease is zjz(z) ± bdz(z); the diagnostic items zs are statistically analyzed to obtain the diagnostic list jzd of the disease; jzd = [zjz(1) ± bdz(1), zjz(2) ± bdz(2), ..., zjz(zs) ± bdz(zs)].

6. A health risk assessment system based on medical data according to claim 1, characterized in that, The specific steps of step S32 are as follows: Step S321: Obtain the number of diseases in the disease detection list, denoted as js; obtain the list of diagnostic items for each disease, denoted as ydx. j Diagnostic items in the diagnostic item list are denoted as ydx j (1) to ydx j (ms); Step S322: Based on the diagnostic item ydx j (1) to ydx j (ms) Perform detection on the user, obtain the detection result, and record the detection result as jcg. j (1) to jcg j (ms); The detection results are statistically analyzed to obtain a detection list, denoted as jcl.

7. A health risk assessment system based on medical data according to claim 1, characterized in that, The specific steps of step S4 are as follows: Step S41: Obtain the disease prediction value list, analyze the disease prediction value for each disease based on the list; extract the prediction value ycz for each disease, and evaluate the prediction value: If ycz ≥ 1 / 2, the user is considered to be at high risk of having the disease. If ycz < 1 / 2, the user is considered to have a low risk of having the disease. Based on the analysis results, a health risk assessment is conducted on the user. For high-risk diseases, the user is reminded to undergo more detailed testing. For low-risk diseases, a risk assessment report is provided to the user based on the risk assessment of all diseases. Step S42: Based on the user's personal information, obtain the user's unique identifier value, denoted as wbs, and use the user's unique identifier value as a key to encrypt the risk assessment report; The specific encryption process is as follows: The character code of each character in the risk assessment report is obtained and denoted as pzf(1) to pzf(fs), where pzf(fs) represents the character code of the fs-th character in the risk assessment report; Each character is encrypted based on the user's unique identifier to obtain the encrypted character, denoted as jmz; ； Where: mod represents the modulo operation; (wbs)mod(f) represents the modulo operation on wbs, where f represents the encoding of the f-th character; jmz(f) is the encrypted character of the f-th character, pzf(f) represents the character encoding of the f-th character, and f∈[1, fs]; The encrypted text is obtained by counting the encrypted characters, and the length of the unique identifier value is obtained and denoted as bcd; the characters of the encrypted text are converted into binary according to the length of the unique identifier value, and the binary file is stored. When a user retrieves a risk assessment report, the user provides their unique identifier. The binary file is extracted based on the length of the unique identifier, and the text is decrypted using the unique identifier to obtain the risk assessment report.

Images