Health risk assessment method and system based on medical data

Abstract

The invention discloses a health risk assessment method and system based on medical data, relates to the field of risk assessment, and solves the problem of insufficient accuracy of existing health risk assessment, and the method comprises the steps: S1, obtaining the medical record information of a doctor in a hospital; s2, acquiring external performance information and diagnosis information of the patient, and analyzing diseases in combination with a susceptible disease list; obtaining an external expression list of the diseases and diagnosis items of the diseases; according to the diagnosis information of the patient and the diagnosis items of the diseases, a diagnosis list of the diseases is obtained; s3, obtaining personal information of the user, and analyzing the detection list and the disease diagnosis list according to the personal information of the user to obtain a disease prediction value of the user; s4, performing health risk assessment on the user, and performing encrypted storage on a risk assessment report; according to the invention, the accuracy of health risk assessment can be effectively improved, and risk early warning is provided for users.

Description

Technical Field

[0001] The present invention belongs to the field of medical health, and more specifically to the field of risk assessment, and specifically provides a health risk assessment method and system based on medical data. Background Art

[0002] Existing health risk assessment methods and systems based on medical data have the following specific defects when conducting risk assessment: 1. The health risk assessment of users mainly involves medical staff making a preliminary diagnosis of the user's external manifestations (such as shortness of breath and pale complexion) 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 is limited.

[0003] 2. Existing health risk assessment methods and systems based on medical data mainly focus on analyzing user test data to evaluate the user's body. The assessment direction is not specific and the assessment cost is high.

[0004] 3. When conducting health risk assessments on users, a large amount of personal privacy data of users is involved. The health risk assessment results of users should be encrypted and stored to ensure the security of their personal information.

[0005] To this end, we propose a health risk assessment method and system based on medical data. Summary of the Invention

[0006] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide a health risk assessment method and system based on medical data, and the present invention aims to improve the accuracy of health risk assessment.

[0007] To achieve the above objectives, the present invention adopts the following technical solution: a health risk assessment method based on medical data, characterized by comprising: Step S1: Obtain the medical records of patients in the hospital, obtain the frequency of disease occurrence based on the medical records of the patients, sort the frequency of disease occurrence in descending order, and obtain a list of susceptible diseases; Step S2: Obtain the patient's external manifestation information and diagnosis information based on the medical record information, and analyze the disease in combination with the list of susceptible diseases; collect the patient's external manifestation information to obtain a list of external manifestations of the disease; judge the patient's diagnosis information to obtain the diagnosis items of the disease; obtain the diagnosis list of the disease based on the patient's diagnosis information and the diagnosis items of the disease; Step S3: Obtain the personal information of the user, obtain the detection items of the user according to the personal information of the user, and obtain the detection list by counting the detection results of the detection items; analyze the detection list and the diagnosis list of the disease to obtain the disease prediction value of the user; Step S4: According to the disease prediction value of the user, the health risk of the user is evaluated, and the risk assessment report is obtained. The risk assessment report is stored after encryption.

[0008] Further, the specific steps of step S1 are as follows: Step S11: Obtain the number of personnel in the hospital, and record the number of personnel as as; according to the number of personnel, obtain the medical record information of the personnel, and record the medical record information as blx a ; Step S12: Obtain the disease of the personnel according to the medical record information of the personnel, classify the diseases of the as personnel, and obtain the number of disease types bs; count the number of patients with each disease type to obtain the number of patients hrs b ; According to the number of patients and the number of personnel, the occurrence frequency of the disease is calculated, and the occurrence frequency fpl b ; According to the occurrence frequency of the disease, the diseases are sorted in descending order to obtain the list of susceptible diseases, and the list of susceptible diseases is recorded as yhj. The list elements in the list of susceptible diseases are recorded as yhj[b].

[0009] Further, the specific steps of step S2 are as follows: Step S21: According to the external performance information of the personnel and the list of susceptible diseases, the personnel with the same disease are counted, the external performance of the disease is integrated according to the external performance of the personnel, the external performance text of the disease is obtained, and the external performance file of the disease is processed to obtain the external performance list of the disease; Step S22: Obtain the standard data and floating data of each index of the human body; filter the diagnosis information of the personnel according to the standard data and the floating data to obtain the detection index associated with the disease, and determine the diagnosis project of the disease from the detection index associated with the disease; Step S23: Combine the diagnosis project of the disease with the diagnosis information of the personnel, count the specific range of the disease in each diagnosis project, and construct the diagnosis list of the disease from the specific range of each diagnosis project.

[0010] Further, the specific steps of step S22 are as follows: Step S221: record the standard data of each index of the human body as bzs, and the floating data as fds; obtain the value range of each index of the human body according to the standard data and the floating data of each index of the human body; Step S222: obtain the diagnosis data of each index of the patient according to the diagnosis information of the patient, and record it as zds; calculate the diagnosis data of each index of the patient and the value range of each index of the human body to obtain a judgment value pdz; According to the judgment value, the detection index associated with the disease is determined: If pds>1, it indicates that the index is a detection index; If pds≤1, it indicates that the index is not a detection index; Obtain the number of each detection index, and record it as sl; judge each index of the patient to obtain the detection index list jzl of the patient; jzl=[zb(1), zb(2), …, zb(sl)]; where zb(sl) represents the determination value of the slth detection index, and when the slth detection index is not a detection index, zb(sl) is assigned a value of 0, and when it is a detection index, zb(sl) is assigned a value of 1; obtain the detection index list of multiple patients with the same disease, and record it as jzl1 to jzl rs ; according to the detection index list jzl1 to jzl rs Calculate the number of detection indexes in different patients, if there are more than half of the same detection indexes in all patients with the same disease, then the index is a detection index of the disease, and the detection index of the disease is counted to obtain the diagnosis item list of the disease.

[0011] Further, the specific steps of step S23 are as follows: Step S231: obtain the number of diagnosis items of the disease according to the diagnosis item list of the disease, and record the number of diagnosis items as zs; record each diagnosis item in the diagnosis item list as zdx(1) to zdx(zs) according to the number of diagnosis items; Step S232: obtain the patient data of the corresponding disease, and record it as xs; obtain the diagnosis data of the patient with the corresponding disease in combination with the diagnosis items, and record it as hxy(x, z); hxy(x, z) represents the diagnosis data of the zth diagnosis item of the xth patient with the corresponding disease; According to the diagnosis data, the mean value of the disease is calculated to obtain the diagnosis mean value zjz(z); Calculate the difference between the diagnosis mean value and the diagnosis data, and integrate the difference between the diagnosis mean value and the diagnosis data to obtain the fluctuation value bdz(z) of the diagnosis data; According to the diagnosis mean zjz(z) and the fluctuation value bdz(z), a diagnosis range of the zth diagnosis item of the disease is zjz(z)±bdz(z); the zs diagnosis items are counted to obtain a diagnosis list jzd of the disease; jzd=[zjz(1)±bdz(1), zjz(2)±bdz(2), …, zjz(zs)±bdz(zs)].

[0012] Further, the specific steps of the step S3 are as follows: Step S31: obtaining a list of external manifestations of the disease, performing text matching on the personal information of the user according to the list of external manifestations of the disease to obtain a disease corresponding to the personal information of the user; and counting the disease corresponding to the personal information of the user to obtain a list of detected diseases; Step S32: obtaining a diagnosis item list of each disease according to the list of detected diseases, obtaining a detection item of the user, detecting the user according to the detection item of the user, counting a detection result, and obtaining a detection list; Step S33: obtaining a diagnosis list of the disease; extracting a corresponding detection result in the detection list according to the diagnosis item of the disease, calculating the detection result in combination with the diagnosis list of the disease, obtaining a disease prediction value of the user; and calculating the disease prediction value of each disease by the list of detected diseases of the user to obtain a disease prediction value list.

[0013] Further, the specific steps of the step S32 are as follows: Step S321: obtaining a number of diseases in the list of detected diseases, denoted as js; obtaining a diagnosis item list of each disease, denoted as ydx j ; the number of the diagnosis item list is denoted as ms; and the diagnosis items in the diagnosis item list are denoted as ydx j (1) to ydx j (ms); Step S322: detecting the user according to the diagnosis items ydx j (1) to ydx j (ms) to obtain a detection result, denoted as jcg j (1) to jcg j (ms); and counting the detection result to obtain a detection list jcl.

[0014] Further, the specific steps of the step S33 are as follows: Step S331: obtaining a list of detected diseases of the user, obtaining a diagnosis list of the disease according to the list of detected diseases of the user, denoted as jzd j ; jzd jA diagnosis list representing the jth disease in the detection disease list of the user; Step S332: Obtain the detection list, and perform similarity calculation on the detection list and the diagnosis list of the disease to obtain a similarity value xsz. xsz = ∑ zjz / ∑ zjz j zjz represents the similarity value of the jth disease in the detection list of the user and the diagnosis list of the disease; zjz = ∑ (m) (m) / ∑ (m) (m) j (m) represents the diagnosis average value of the mth diagnosis item in the diagnosis list of the jth disease; bdz = ∑ (m) (m) / ∑ (m) (m) j (m) represents the diagnosis fluctuation value of the mth diagnosis item in the diagnosis list of the jth disease; jcg = ∑ (m) (m) / ∑ (m) (m) j (m) represents the detection result of the mth diagnosis item of the jth disease in the detection list; Step S333: Obtain the ranking position b of the disease in the susceptible disease list; and perform calculation on the disease in combination with the similarity value xsz to obtain a prediction value ycz of the disease. The prediction values of the js diseases are counted to obtain a prediction value list of the diseases.

[0015] Further, the specific steps of the step S4 are as follows: Step S41: Obtain a disease prediction value list, analyze the disease prediction value of each disease according to the disease prediction value list, and extract the prediction value ycz of each disease to judge the prediction value. If ycz≥1 / 2, it is determined that the user has a high risk of suffering from the disease. If ycz<1 / 2, it is determined that the user has a low risk of suffering from the disease. According to the analysis result, the health risk of the user is evaluated, the user is reminded to perform more detailed detection for the high-risk disease, and the user is provided with a risk assessment report according to the risk assessment of all diseases for the low-risk disease. Step S42: Obtain a unique identifier value of the user according to the personal information of the user, denoted as wbs, and encrypt the risk assessment report by taking the unique identifier value of the user as a key. The specific encryption process is as follows: Obtain the character encoding of each character in the risk assessment report, denoted as pzf(1) to pzf(fs), wherein pzf(fs) represents the character encoding of the fs th character in the risk assessment report. Each character is encrypted according to the unique identifier of the user to obtain an encrypted character jmz. ​​Wherein: mod represents the modulo operation; (wbs) mod (f) represents the modulo operation on wbs, f represents the fth character code; jmz (f) is the encrypted character of the fth character, pzf (f) represents the character code of the fth character, f [1, fs] ; The encrypted text is obtained by counting the encrypted characters, and the length bcd of the unique identification value is obtained; the characters of the encrypted text are converted into binary according to the length of the unique identification value, and the binary file is stored; When the user extracts the risk assessment report, the user provides the unique identification value; the binary file is extracted according to the length of the unique identification value, the text is decrypted in combination with the unique identification value, and the risk assessment report is obtained.

[0016] A health risk assessment system based on medical data, the assessment system comprising: An information collection module: obtaining medical record information of a person in a hospital, obtaining the frequency of occurrence of diseases according to the medical record information of the person in the hospital, and obtaining a list of susceptible diseases in descending order of the frequency of occurrence of diseases; An information processing module: obtaining external manifestation information and diagnosis information of the person in the hospital according to the medical record information, analyzing the diseases in combination with the list of susceptible diseases; obtaining a list of external manifestations of diseases by counting the external manifestation information of the person in the hospital; obtaining a diagnosis item of the disease by judging the diagnosis information of the person in the hospital; and obtaining a diagnosis list of the disease from the diagnosis information of the person in the hospital and the diagnosis item of the disease; A detection analysis module: obtaining personal information of a user, obtaining a detection item of the user according to the personal information of the user, counting detection results of the detection item to obtain a detection list; and analyzing the detection list and the diagnosis list of the disease to obtain a disease prediction value of the user; A risk assessment module: performing health risk assessment on the user according to the disease prediction value of the user to obtain a risk assessment report, and encrypting and storing the risk assessment report.

[0017] As described above, due to the adoption of the above technical solutions, the present application has the following beneficial effects: 1. The present application analyzes the existing medical data, and divides the information of the person in the hospital into external manifestations and specific diagnoses; according to the external manifestations, the manifestations of different diseases are counted; according to the specific diagnoses, the diagnosis data of the diseases are integrated; the manifestations and diagnoses of different diseases are dataized, reducing the influence of human factors in the risk assessment process; and the accuracy of the assessment is enhanced.

[0018] 2. Compare the external manifestations of the user being evaluated with the digitized disease to reduce the scope of evaluation and lower the evaluation cost; arrange testing items for the user based on the comparison results; calculate the similarity between the test results and the disease in the comparison results, and make judgments based on the similarity; clarify the goals of the test results to facilitate accurate judgment of the user.

[0019] 3. Encrypt the user's evaluation results. Use the user's unique identifier to encrypt each character of the evaluation result. Differentiate the characters based on their order to enhance encryption strength and ensure encryption security. Store the encrypted text in binary format according to the length of the user's unique identifier, and obfuscate the text characters to ensure the security of the user's personal information. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] To facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0021] Figure 1 Schematic diagram of the method of the present invention; Figure 2 Schematic diagram of data analysis of the present invention; Figure 3 A schematic diagram of the system of the present invention; DETAILED DESCRIPTION The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0022] Example 1 See also Figure 1 A health risk assessment method based on medical data relates to the field of risk assessment. The present invention provides a technical solution: A health risk assessment method based on medical data includes: Step S1: Obtain the medical records of patients in the hospital, obtain the frequency of disease occurrence based on the medical records of the patients, sort the frequency of disease occurrence in descending order, and obtain a list of susceptible diseases; Step S11: Obtain the number of patients in the hospital, and record the number of patients as; according to the number of patients, obtain the medical records of the patients, and record the medical records as blx a ; Among them: blx z represents the medical record information of the a-th patient, a∈[1,as]; Step S12: acquiring the disease of the clinic personnel according to the medical record information of the clinic personnel, classifying the disease of the as clinic personnel, obtaining the number bs of disease types; counting the number of patients with each disease type to obtain the number of patients hrs b ; wherein: hrs b represents the number of patients with the bth disease, b ∈ [1, bs]; According to the number of patients and the number of clinic personnel, the occurrence frequency of the disease is calculated, and the occurrence frequency fpl b is obtained. ; According to the occurrence frequency of the disease, the disease is sorted in descending order to obtain a list of susceptible diseases, and 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 bth element in the list of susceptible diseases.

[0023] Step S2: acquiring the external manifestation information and diagnosis information of the clinic personnel according to the medical record information, analyzing the disease in combination with the list of susceptible diseases; counting the external manifestation information of the clinic personnel to obtain the external manifestation list of the disease; judging the diagnosis information of the clinic personnel to obtain the diagnosis project of the disease; obtaining the diagnosis list of the disease from the diagnosis information of the clinic personnel and the diagnosis project of the disease; It should be noted that the external manifestation information refers to the manifestation of the clinic personnel, such as dizziness, vomiting, and tongue discoloration; the diagnosis information refers to the detection and diagnosis of the clinic personnel in terms of blood pressure, blood routine, urine routine, liver function, kidney function, blood lipid, and electrocardiogram.

[0024] Step S21: according to the external manifestation information of the clinic personnel and the list of susceptible diseases, the clinic personnel with the same disease are counted, the external manifestations of the disease are integrated according to the external manifestations of the clinic personnel, the external manifestation text of the disease is obtained, and the external manifestation file of the disease is processed to obtain the external manifestation list of the disease; Step S211: according to the list of susceptible diseases, the clinic personnel with the same disease are obtained; the external manifestation information of each clinic personnel is counted according to the number of clinic personnel with the same disease to obtain the external manifestation text of the disease; Step S212: acquiring the external manifestation type of the disease according to the external manifestation text of the disease; processing the external manifestation text of the disease according to the external manifestation type of the disease, counting the occurrence frequency of the external manifestation type in the external manifestation text, and sorting the external manifestation type of the disease in descending order according to the occurrence frequency to obtain the external manifestation list of the disease; It should be noted that: by counting the external manifestation information of all patients with the same disease, the external manifestations of the disease are recorded comprehensively, and the accuracy of disease judgment is enhanced; according to the record results, different types of manifestations are sorted, the primary and secondary of the external manifestations of the disease are divided, and the different diseases with similar external manifestations are differentiated to prevent the confusion of similar manifestations.

[0025] Step S22: obtaining standard data and floating data of each index of the human body; screening the diagnosis information of the patient according to the standard data and the floating data to obtain the detection index associated with the disease, and determining the diagnosis item of the disease according to the detection index associated with the disease; It should be noted that: the floating data refers to the fluctuation range of each index of the human body under normal physiological state, for example, the normal body temperature of the human body is between 36-37℃, then the standard value of the body temperature is set to 36.5℃, and the floating data is set to 0.5℃; Step S221: recording the standard data of each index of the human body as bzs, and recording the floating data as fds; obtaining the value range of each index of the human body according to the standard data and the floating data of each index of the human body; Step S222: obtaining the diagnosis data of each index of the patient according to the diagnosis information of the patient, and recording it as zds; calculating the diagnosis data of each index of the patient and the value range of each index of the human body to obtain a judgment value pdz; ; Wherein: bzs is the standard data of the index, and fds is the floating data; According to the judgment value, the detection index associated with the disease is determined: If pds>1, it indicates that the index is a detection index; If pds≤1, it indicates that the index is not a detection index; Please refer to Figure 2 ; obtaining the number of each index of the detection, recording it as sl; judging each index of the patient to obtain the detection index list jzl of the patient; jzl=[zb(1), zb(2), …, zb(sl)]; wherein zb(sl) represents the determination value of the slth detection index, when the slth detection index is not a detection index, zb(sl) is assigned a value of 0, and when it is a detection index, zb(sl) is assigned a value of 1; obtaining the detection index list of multiple patients with the same disease, recording it as jzl1 to jzl rs ; according to the detection index list jzl1 to jzl rsThe number of detection indicators in different personnel is calculated, and if more than half of the same disease personnel have the same detection indicator, the indicator is the detection indicator of the disease. The detection indicators of the disease are determined as follows: ; Wherein: jjc(s) represents the judgment of the s-th indicator, jjc(s)>0 represents the detection indicator of the disease; zb r (s) represents the determination value of the s-th detection indicator of the r-th personnel.

[0026] The detection indicators of the disease are counted to obtain the diagnosis item list of the disease; Step S23: Combine the diagnosis items of the disease with the diagnosis information of the personnel, and count the specific range of the disease in each diagnosis item. The diagnosis list of the disease is constructed from the specific range of each diagnosis item; Step S231: According to the diagnosis item list of the disease, the number of diagnosis items is obtained, which is recorded as zs; According to the number of diagnosis items, each diagnosis item in the diagnosis item list is recorded as zdx(1) to zdx(zs); Step S232: The data of the personnel with the corresponding disease is obtained, which is recorded as xs; The diagnosis data of the personnel with the corresponding disease is obtained by combining the diagnosis items, which is recorded as hxy(x,z); hxy(x,z) represents the diagnosis data of the z-th diagnosis item of the x-th personnel with the corresponding disease; It should be noted that: the corresponding disease refers to the disease corresponding to the disease in the above step S231; According to the disease diagnosis item determined in step S231, the patients actually suffering from the disease are analyzed to enhance the reliability of the data; According to the diagnosis data, the mean value of the disease is calculated to obtain the diagnosis mean value zjz(z); ; The difference between the diagnosis mean value and the diagnosis data is calculated, and the difference between the diagnosis mean value and the diagnosis data is integrated to obtain the fluctuation value bdz(z) of the diagnosis data; ; It should be noted that: by calculating the overall difference, the influence of special values on data is reduced, and the overall statistics of diagnosis data is simplified according to the diagnosis mean value.

[0027] According to the diagnosis mean zjz(z) and the fluctuation value bdz(z), a diagnosis range of the zth diagnosis item of the disease is zjz(z)±bdz(z); the zs diagnosis items are counted to obtain a diagnosis list jzd of the disease; jzd=[zjz(1)±bdz(1), zjz(2)±bdz(2), …, zjz(zs)±bdz(zs)].

[0028] Step S3: obtaining personal information of the user, obtaining detection items of the user according to the personal information of the user, counting detection results of the detection items to obtain a detection list; analyzing the detection list and the diagnosis list of the disease to obtain a disease prediction value of the user; Step S31: obtaining a list of external manifestations of the disease, performing text matching on the personal information of the user according to the list of external manifestations of the disease to obtain a disease corresponding to the personal information of the user; counting the disease corresponding to the personal information of the user to obtain a detection disease list; Step S311: processing the personal information of the user, extracting a disease history and a family genetic disease of the user, taking the disease history and the family genetic disease of the user as detection diseases; performing text matching on the personal information of the user and the list of external manifestations of the disease; when the personal information of the user matches the list of external manifestations of the disease, taking the disease as a detection disease of the user; counting the detection diseases of the user to obtain a detection disease list of the user; Step S32: obtaining a diagnosis item list of each disease according to the disease detection list to obtain detection items of the user; detecting the user according to the detection items of the user to obtain detection results, and counting the detection results to obtain a detection list; Step S321: obtaining a number of diseases in the disease detection list, denoted as js; obtaining a diagnosis item list of each disease, denoted as ydx j ; the number of diagnosis items in the diagnosis item list is denoted as ms; the diagnosis items in the diagnosis item list are denoted as ydx j (1) to ydx j (ms); Step S322: detecting the user according to the diagnosis items ydx j (1) to ydx j (ms) to obtain detection results, denoted as jcg j (1) to jcg j (ms); counting the detection results to obtain a detection list jcl; .

[0029] Step S33: Obtain the diagnosis list of the disease; extract the corresponding detection result in the detection list according to the diagnosis item of the disease, calculate the detection result combined with the diagnosis list of the disease, and obtain the disease prediction value of the user; calculate the disease prediction value of each disease in the detection disease list of the user to obtain the disease prediction value list; Step S331: Obtain the detection disease list of the user, and obtain the diagnosis list of the disease according to the detection disease list of the user, denoted as jzd j ; jzd j , which represents the diagnosis list of the jth disease in the detection disease list of the user. Step S332: Obtain the detection list, and calculate the similarity value xsz by calculating the similarity between the detection list and the diagnosis list of the disease. ; Wherein: xsz j , which represents the similarity value of the jth disease in the user detection list and the diagnosis list of the disease; zjz j (m) represents the diagnosis mean value of the mth diagnosis item in the diagnosis list of the jth disease, bdz j (m) represents the diagnosis fluctuation value of the mth diagnosis item in the diagnosis list of the jth disease; jcg j (m) represents the detection result of the mth diagnosis item of the jth disease in the detection list.

[0030] It should be noted that: by calculating the similarity of the detection result and the diagnosis mean value, dividing the detection result by the fluctuation value, the similarity value less than 1 is represented as similarity, and the difference from 1 is obtained, so that the greater the similarity value, the more similar the result; At the same time, the absolute value is summed, so that the value less than 0 is represented as 0 in the formula; Through similarity value calculation, the association between the user and the disease is intuitively reflected.

[0031] Step S333: Obtain the sorting position b of the disease in the susceptible disease list; calculate the disease by combining the similarity value xsz to obtain the prediction value ycz of the disease. ; Wherein: bs is the number of disease types. The prediction values of js diseases are counted to obtain the prediction value list of the disease. It should be noted that: the disease in the susceptible disease list is higher, the occurrence frequency is higher, and the patient data about the disease is more comprehensive, so the judgment of the user's personal situation on the disease is more accurate, and the disease in the list is less accurate, so the judgment of the disease is given higher weight to predict and reduce the error of disease prediction.

[0032] Step S4: According to the user's disease prediction value, the user is evaluated for health risk, and a risk assessment report is obtained, which is stored after encryption; Step S41: Obtain a list of disease prediction values, analyze the disease prediction values of each disease according to the list of disease prediction values; extract the prediction value ycz of each disease, and judge the prediction value: If ycz is greater than or equal to 1 / 2, it is determined that the user has a high risk of having the disease; If ycz is less than 1 / 2, it is determined that the user has a low risk of having the disease; According to the analysis result, the user is evaluated for health risk, the user is reminded to perform more detailed detection for high-risk diseases, and the user is ensured to be healthy, the user is provided with corresponding preventive measures for low-risk diseases, and the user is provided with a risk assessment report according to the risk assessment of all diseases.

[0033] Step S42: According to the user's personal information, obtain the user's unique identifier value, denoted as wbs, and encrypt the risk assessment report using the user's unique identifier value as the key; the specific encryption process is as follows: Obtain the character encoding of each character in the risk assessment report, denoted as pzf(1) to pzf(fs), where pzf(fs) represents the character encoding of the fs-th character in the risk assessment report; According to the user's unique identifier, each character is encrypted to obtain an encrypted character jmz; ; Wherein: mod represents the modulo operation; (wbs) mod (f) represents taking the modulus of wbs, such as wbs is 10 and f is 3; then (wbs) mod (f) = 1; f represents the f-th character encoding; jmz(f) is the encrypted character of the f-th character, and pzf(f) represents the character encoding of the f-th character, f∈[1, fs]; It should be noted that: the difference between the encrypted characters is enhanced by the modulo operation, and the security of the encrypted characters is improved; at the same time, the length of the encrypted characters is reduced by dividing the data, and the storage cost is reduced; the modulo addition of the divided data prevents precision loss; The encrypted characters are counted to obtain an encrypted text, and the length bcd of the unique identifier value is obtained; the characters of the encrypted text are converted to 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, and the security of the file is ensured; When the user extracts the risk assessment report, the user provides his unique identifier value; according to the length of the unique identifier value, the binary file is extracted, and the text is decrypted in combination with the unique identifier value to obtain the risk assessment report.

[0034] ​It should be noted that the user's unique identification value refers to information that can uniquely represent the user, such as an ID number; Example 2 See also Figure 3 A health risk assessment system based on medical data relates to the field of risk assessment. A health risk assessment system based on medical data comprises: an information acquisition module, an information processing module, a detection and analysis module, a risk assessment module, and a server. The information acquisition module, the information processing module, the detection and analysis module, and the risk assessment module are controlled by the server. Information collection module: obtains the medical records of patients in the hospital, obtains the frequency of disease occurrence based on the medical records of the patients, sorts the frequency of disease occurrence in descending order, and obtains a list of susceptible diseases; Information processing module: Obtain the patient's external manifestation information and diagnosis information based on medical records, and analyze the disease in combination with the list of susceptible diseases; collect statistics on the patient's external manifestation information to obtain a list of external manifestations of the disease; judge the patient's diagnosis information to obtain the diagnosis items of the disease; obtain the diagnosis list of the disease based on the patient's diagnosis information and the diagnosis items of the disease; Detection and analysis module: obtains the user's personal information, obtains the user's test items based on the user's personal information, compiles statistics on the test results of the test items, and obtains a test list; analyzes the test list with the disease diagnosis list to obtain the user's disease prediction value; Risk assessment module: conducts health risk assessment on users based on their disease prediction values, obtains risk assessment reports, and encrypts and stores the risk assessment reports; The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A health risk assessment method based on medical data, characterized in that: include: Step S1: Obtain the medical records of patients in the hospital, obtain the frequency of disease occurrence based on the medical records of the patients, sort the frequency of disease occurrence in descending order, and obtain a list of susceptible diseases; Step S2: Obtain the patient's external manifestation information and diagnosis information based on the medical record information, and analyze the disease in combination with the list of susceptible diseases; collect the patient's external manifestation information to obtain a list of external manifestations of the disease; judge the patient's diagnosis information to obtain the diagnosis items of the disease; obtain the diagnosis list of the disease based on the patient's diagnosis information and the diagnosis items of the disease; Step S3: Obtain the user's personal information, obtain the user's test items based on the user's personal information, collect statistics on the test results of the test items, and obtain a test list; analyze the test list with the disease diagnosis list to obtain the user's disease prediction value; Step S4: Perform 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. A health risk assessment method 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 of patients as; according to the number of patients, obtain the medical records of the patients, and record the medical records as blx a ; Step S12: Obtain the diseases suffered by the patients according to their medical records, classify the diseases suffered by as patients, and obtain the number of disease types bs; count the number of patients of each disease type to obtain the number of patients hrs b ; The frequency of disease occurrence is calculated based on the number of patients and the number of patients seeking medical treatment, and the frequency of disease occurrence fpl is obtained. b ; Sort the diseases in descending order according to their frequency of occurrence to obtain a list of susceptible diseases. The susceptible disease list is denoted as yhj, and the list elements in the susceptible disease list are denoted as yhj[b].

3. The health risk assessment method 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 the patients and the list of susceptible diseases, the patients with the same disease are counted, the external manifestations of the disease are integrated according to the external manifestations of the patients to obtain a text of the external manifestation of the disease, and the external manifestation file of the disease is processed to obtain a list of the external manifestations of the disease; Step S22: Obtaining standard data and floating data of various human body indicators; screening the patient's diagnostic information based on the standard data and floating data to obtain detection indicators associated with the disease, and determining the diagnosis items of the disease based on the detection indicators associated with the disease; Step S23: combining the diagnosis items of the disease with the diagnosis information of the patient, counting the specific range of the disease in each diagnosis item, and constructing a diagnosis list of the disease based on the specific range of each diagnosis item.

4. A health risk assessment method 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; obtain the value range of various human body indicators based on the standard data and floating data of various human body indicators; Step S222: Based on the patient's diagnostic information, the diagnostic data of each indicator of the patient is obtained, which is recorded as zds; the diagnostic data of each indicator of the patient is calculated with the value range of each indicator of the human body to obtain the judgment value pdz; Determine the detection indicators associated with the disease based on the judgment value: If pds>1, it indicates that the indicator is a detection indicator; If pds≤1, it means that the indicator is not a detection indicator; Obtain the number of various indicators to be tested, denoted as sl; judge the various indicators of the patients and obtain the patient's test indicator list jzl; jzl = [zb (1), zb (2), ..., zb (sl)]; where zb (sl) represents the determined value of the slth test indicator. When the slth test indicator is a non-test indicator, zb (sl) is assigned a value of 0, and when it is a test indicator, zb (sl) is assigned a value of 1; obtain the test indicator lists of multiple patients with the same disease, denoted as jzl1 to jzl rs ; According to the detection index list jzl1 to jzl rs The number of detection indicators in different patients is calculated. If more than half of all patients with the same disease have the same detection indicator, then the indicator is the detection indicator of the disease. The detection indicators of the disease are counted to obtain a list of diagnostic items for the disease.

5. The health risk assessment method based on medical data according to claim 3, characterized in that: The specific steps of step S23 are as follows: Step S231: according to the diagnosis item list of the disease, obtain the number of diagnosis items of the disease, and record the number of diagnosis items as zs; according to the number of diagnosis items, record each diagnosis item in the diagnosis item list as zdx(1) to zdx(zs); Step S232: Acquire the data of patients with the corresponding disease, denoted as xs; acquire the diagnostic data of patients with the corresponding disease in combination with the diagnostic items, denoted as hxy(x, z); hxy(x, z) represents the diagnostic data of the zth diagnostic item of the xth patient with the corresponding disease; Calculate the mean of the disease according to the diagnosis data to obtain the diagnosis mean zjz (z); The difference of the diagnostic data is calculated by the diagnostic mean, and the diagnostic mean and the difference of the diagnostic data are integrated to obtain the fluctuation value bdz (z) of the diagnostic data; According to the diagnostic mean zjz(z) and the fluctuation value bdz(z), the diagnostic range of the zth diagnostic item of the disease is zjz(z)±bdz(z); the zs diagnostic items are counted to obtain the diagnostic list jzd of the disease; jzd=[zjz(1)±bdz(1), zjz(2)±bdz(2),…,zjz(zs)±bdz(zs)].

6. The health risk assessment method based on medical data according to claim 1, characterized in that: 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, and obtain the diseases corresponding to the user's personal information; perform statistics on the diseases corresponding to the user's personal information to obtain a list of detected diseases; Step S32: According to the disease detection list, a list of diagnostic items for each disease is obtained to obtain the user's detection items; the user is tested according to the user's detection items to obtain the detection results, and the detection results are counted to obtain a detection list; Step S33: Obtain a diagnosis list of diseases; The corresponding test results in the test list are extracted according to the diagnostic items of the disease, and the test results are calculated in combination with the diagnostic list of the disease to obtain the user's disease prediction value; the disease prediction value of each disease is calculated from the user's detected disease list to obtain a disease prediction value list.

7. A health risk assessment method based on medical data according to claim 6, characterized in that: The specific steps of step S32 are as follows: Step S321: Get the number of diseases in the disease detection list, recorded as js; get the list of diagnostic items for each disease, recorded as ydx j ;Record the number of diagnostic items in the diagnostic item list as ms;Record the diagnostic items in the diagnostic item list as ydx j (1) to ydx j (ms); Step S322: According to the diagnostic item ydx j (1) to ydx j (ms) to detect the user and obtain the detection result, which is recorded as jcg j (1) to jcg j (ms); perform statistics on the detection results to obtain the detection list jcl.

8. The health risk assessment method based on medical data according to claim 6, characterized in that: The specific steps of step S33 are as follows: Step S331: Obtain the user's detected disease list, and obtain the disease diagnosis list based on the user's detected disease list, denoted as jzd j ;jzd j A diagnosis list representing the jth disease in the user's list of detected diseases; Step S332: Obtain a test list, calculate the similarity between the test list and the disease diagnosis list, and obtain a similarity value xsz; ； Among them: xsz j Refers to the similarity value between the jth disease in the user's detection list and the diagnosis list of the disease; zjz j (m) represents the diagnostic mean of the mth diagnostic item in the diagnosis list of the jth disease, bdz j (m) represents the diagnostic fluctuation value of the mth diagnostic item in the diagnosis list of the jth disease; jcg j (m) represents the test result of the mth diagnostic item of the jth disease in the test list; Step S333: Obtain the ranking b of the disease in the list of susceptible diseases; calculate the disease in combination with the similarity value xsz to obtain the predicted value ycz of the disease; The predicted values ​​of js diseases are counted to obtain a list of predicted values ​​of the diseases.

9. The health risk assessment method based on medical data according to claim 1, characterized in that: The specific steps of step S4 are as follows: Step S41: Obtain a disease prediction value list, analyze the disease prediction value of each disease according to the disease prediction value list; extract the prediction value ycz of each disease, and judge the prediction value: If ycz≥1 / 2, the user is judged to be at high risk of contracting the disease; If ycz < 1 / 2, the user is judged to have a low risk of contracting the disease; Conduct health risk assessments for users based on the analysis results, prompt users to undergo more detailed tests for high-risk diseases, and provide users with risk assessment reports based on the risk assessment of all diseases for low-risk diseases; Step S42: Based on the user's personal information, obtain the user's unique identification value, denoted as wbs, and use the user's unique identification 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 recorded as pzf(1) to pzf(fs), where pzf(fs) represents the character code of the fs-th character in the risk assessment report; Encrypt each character according to the user's unique identifier to obtain the encrypted character jmz; ； Where: mod represents the modulo operation; (wbs) mod (f) represents the modulo operation on wbs, f represents the code of the fth character; jmz (f) is the encrypted character of the fth character, pzf (f) represents the character code of the fth character, f∈[1, fs]; Count the encrypted characters to obtain the encrypted text, and obtain the length bcd of the unique identification value; convert the characters of the encrypted text into binary according to the length of the unique identification value, and store the binary file; When a user extracts a risk assessment report, the user provides a unique identification value; the binary file is extracted according to the length of the unique identification value, and the text is decrypted in combination with the unique identification value to obtain the risk assessment report.

10. A health risk assessment system based on medical data, applicable to a health risk assessment method based on medical data according to any one of claims 1 to 9, characterized in that: The assessment system includes: Information collection module: obtains the medical records of patients in the hospital, obtains the frequency of disease occurrence based on the medical records of the patients, sorts the frequency of disease occurrence in descending order, and obtains a list of susceptible diseases; Information processing module: Obtain the patient's external manifestation information and diagnosis information based on medical records, and analyze the disease in combination with the list of susceptible diseases; collect statistics on the patient's external manifestation information to obtain a list of external manifestations of the disease; judge the patient's diagnosis information to obtain the diagnosis items of the disease; obtain the diagnosis list of the disease based on the patient's diagnosis information and the diagnosis items of the disease; Detection and analysis module: obtains the user's personal information, obtains the user's test items based on the user's personal information, compiles statistics on the test results of the test items, and obtains a test list; analyzes the test list with the disease diagnosis list to obtain the user's disease prediction value; Risk assessment module: conducts health risk assessment on users based on their disease prediction values, obtains risk assessment reports, and encrypts and stores the risk assessment reports.

Images