Medical diagnosis data management system based on big data

Abstract

The invention discloses a medical diagnosis data management system based on big data, and relates to the technical field of medical diagnosis data management, and the system specifically comprises a medical diagnosis data cloud platform which collects complete medical diagnosis data of patients in a hospital through an information system of the hospital, divides the levels of the medical diagnosis data of the patients according to the medical diagnosis process, and stores the levels of the medical diagnosis data; classifying and storing medical diagnosis data of different patients based on the levels of the medical diagnosis data; the medical diagnosis data matching module quantifies the relevance of the medical diagnosis data of different patients, and provides complete medical diagnosis data with reference value for the real-time medical diagnosis data of the to-be-matched patient based on the medical diagnosis data of all patients in the medical diagnosis cloud platform; a doctor is helped to quickly perfect real-time medical diagnosis data of the patient to be matched; and the medical diagnosis data updating module formulates a patient historical medical diagnosis data updating method according to the medical diagnosis data level, and relieves the memory pressure of the medical diagnosis data cloud platform by releasing the medical diagnosis data.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical diagnosis data management, and in particular relates to a medical diagnosis data management system based on big data. Background Art

[0002] In today's era of rapid development of information technology, the medical field has also ushered in an era of data explosion. With the continuous advancement and popularization of medical technology, medical institutions generate massive amounts of medical data every day. These data cover electronic medical records, handwritten case records, imaging data, test results, medical treatment costs, etc. However, despite the amazing accumulation speed of these data, their effective utilization lags far behind the growth rate of data, forming an embarrassing situation of "rich data, poor information".

[0003] For patients, every time they see a doctor, they need to explain their condition and medical history to the doctor again. However, due to the long time span and vague memory, it is often difficult for patients to accurately describe their condition. This not only increases the difficulty for doctors to understand the condition, but also prolongs the diagnosis time. If medical data can be effectively used, doctors can quickly and accurately understand the evolution of patients' conditions by consulting patients' historical medical records and test results, so as to make more accurate diagnoses and treatment plans. Summary of the invention

[0004] The purpose of the present invention is to provide a medical diagnosis data management system based on big data, which is used to solve the technical problem that the prior art cannot effectively utilize patient historical data.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: The medical diagnosis data cloud platform uses the hospital's information system to collect complete medical diagnosis data of hospital patients. The complete medical diagnosis data includes the patient's basic information, diagnosis results, treatment plans, and examination and test results. The collected and organized medical diagnosis data will be checked to establish a medical diagnosis data cloud platform, and the checked and accurate medical diagnosis data will be entered into the medical diagnosis data cloud platform. The above-mentioned basic patient information includes the patient's name, age, height, weight, and gender. The diagnosis results include: the patient's cause of disease, clinical symptoms and signs data, and doctor's advice. The treatment plan includes: drug treatment, non-drug treatment, surgical treatment, and rehabilitation treatment. The examination and test results include: laboratory tests, imaging examinations, and pathological examinations. The patient's medical diagnosis data level is divided according to the medical diagnosis process, and the medical diagnosis data of different patients is saved based on the medical diagnosis data level classification. The specific division method is as follows: The diagnosis result is determined by combining the patient's symptoms, physical sign data and the doctor's experience. The medical diagnosis data obtained in the diagnosis process is divided into the first level. All the first-level medical diagnosis data are combined to obtain the first-level data set. Physical sign data refers to the patient's body data affected by the patient's symptoms. For example, the severity of the patient's headache symptoms will affect the patient's body temperature data, and the patient's dizziness symptoms will affect the patient's blood pressure data. Based on the first-level diagnostic process, according to the doctor's request, the patient undergoes a specific non-pathological examination to determine the diagnosis result. The medical diagnostic data obtained by the diagnostic process is divided into the second level, and all the second-level medical diagnostic data are combined to obtain the second-level data set; Based on the first-level diagnostic process, according to the doctor's request, the patient determines the diagnosis result through pathological examination of specific cells or body tissues. The medical diagnostic data obtained in this diagnostic process is divided into the third level, and all third-level medical diagnostic data are combined to obtain a third-level data set.

[0006] The medical diagnosis data matching module, for patients whose historical medical diagnosis data have not been entered into the medical diagnosis data cloud platform, creates the patient's medical diagnosis data in real time by inputting the patient's basic information into the medical diagnosis data cloud platform, and records it as real-time medical diagnosis data. The real-time medical diagnosis data does not contain treatment plan content. By determining the patient's medical data level, the medical data of other patients with a high degree of correlation with the patient's medical data are matched. The doctor refers to the medical diagnosis data of other patients and the patient's historical medical diagnosis data to improve the treatment plan; For patients whose historical medical diagnosis data has been entered into the medical diagnosis data cloud platform, the basic information of the patient is input, the patient's medical diagnosis data is created in real time, and the patient's historical medical diagnosis data is automatically matched. By comparing with the patient's real-time medical diagnosis data, it is determined whether the patient's historical treatment plan is effective for the patient's related symptoms. Then, by determining the patient's medical data level, the medical data of other patients with a high degree of correlation with the patient's medical data is matched. The doctor refers to the medical diagnosis data of other patients and the patient's historical medical diagnosis data to improve the treatment plan; In order to quantify the correlation between the medical diagnosis data of different patients, the medical diagnosis correlation degree is set based on the medical diagnosis data of all patients in the medical diagnosis cloud platform. By determining the size of the medical diagnosis correlation between different patients, the medical diagnosis data with close correlation is screened and matched. The specific method is as follows: Determine the medical diagnosis data of the patient to be matched, denoted as the data to be matched. Based on the patient's age and gender information, the doctor determines the matching range through the diagnosis result. According to the matching range and the level of the medical diagnosis data of the patient to be matched, match the medical diagnosis data of the patients within the corresponding level of the data set, denoted as the matching data. Set the medical diagnosis correlation degree. By comparing the medical diagnosis data of different patients, screen out the medical diagnosis data with a high medical diagnosis correlation degree. The medical diagnosis correlation degree formula is specifically as follows: ; where represents the medical diagnosis correlation degree between the patient x to be matched and the matching patient , k represents the k-th matching patient, a(x) represents the height and weight index data of the patient x to be matched, represents the height and weight index of the matching patient , u(x, i) represents the patient physical sign data of the patient x to be matched affected by the i-th symptom, n represents the total number of symptoms exhibited by the patient x to be matched, represents the physical sign data of the same type as u(x, i) of the matching patient , e represents the base of the natural logarithm, The larger the value, the higher the medical diagnosis correlation degree between the patient x to be matched and the matching patient .

[0007] By calculating the medical diagnosis correlation degrees between the patient to be matched and different matching patients, set the medical diagnosis correlation degree threshold M. Compare all medical diagnosis correlation degrees with M. When the medical diagnosis correlation degree is greater than or equal to M, retain to obtain the matching patient sequence. Sort the matching patient sequence according to the size of the medical diagnosis correlation degree, and select the top m medical diagnosis data with the largest medical diagnosis correlation degree as the reference data, m < k. The doctor further improves the treatment plan part of the real-time medical diagnosis data of the patient through the reference data.

[0008] The patient to be matched obtains medical diagnosis data and physical sign data about himself after performing relevant medical diagnosis, and inputs the medical diagnosis data and physical sign data into the medical diagnosis data matching module, matches the input data of the patient to be matched with the medical diagnosis data of the matching patients within the matching range, determines the medical diagnosis correlation between the patient to be matched and different matching patients within the matching range, compares the medical diagnosis correlation data with a preset medical diagnosis correlation threshold M, retains matching patients whose medical diagnosis correlation with the patient to be matched is greater than or equal to M, screens out a group of matching patients within the matching range that have passed the threshold judgment, and the size relationship between their medical diagnosis correlation with the patient to be matched, sets the number of retention to be m, retains m matching patients with the largest medical diagnosis correlation, obtains a group of matching patients that meets the conditions, and records them as a reference group, obtains the medical diagnosis data of the reference group by querying in the medical diagnosis data cloud platform according to the personal information of each matching patient in the reference group, and uses the medical diagnosis data of the reference group as the reference data of the patient to be matched.

[0009] The medical diagnosis data update module formulates a method for updating the patient's historical medical diagnosis data according to the medical diagnosis data level; sets a time period t, and for the first-level medical diagnosis data, only retains the patient's latest first-level medical diagnosis data within a time period, and deletes all the patient's first-level medical diagnosis data that are not within a time period; For the second-level medical diagnosis data, within one time period, all the second-level medical diagnosis data of the patient shall be completely retained. If the time period exceeds one time period and is within N time periods, only the latest second-level medical diagnosis data of the patient shall be completely retained. For the other second-level medical diagnosis data of the patient, only the key parts shall be retained, such as the cause of the patient's disease and treatment plan, and all medical diagnosis data of the patient within N time periods shall be deleted; For the third-level medical diagnosis data, within N time periods, all the third-level medical diagnosis data of the patient are completely retained, and for the other third-level medical diagnosis data of the patient, only the key parts are retained.

[0010] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: 1. The present invention quantifies the correlation of medical diagnosis data of different patients by setting a medical diagnosis correlation formula. Considering that the patient's physique, age, and gender factors may affect the development of the disease and the treatment effect, the medical diagnosis data of other patients with similar symptoms as the patient are matched through the medical diagnosis correlation formula, thereby realizing effective mining and utilization of medical diagnosis data management; 2. The present invention calculates the medical diagnosis correlation between different patients, sets a medical diagnosis correlation threshold, compares the medical diagnosis correlation between different patients with the medical diagnosis correlation threshold, accurately identifies and screens out matching patient groups that meet specific correlation conditions, locks in medical diagnosis data with a high degree of correlation, and achieves a horizontal comparison of the clinical manifestations, course of disease and treatment effects of patients' diseases, which helps to identify neglected symptoms or signs. Through the medical diagnosis data management method, the medical diagnosis data of historical patients can be effectively utilized to improve the accuracy and precision of diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0012] Figure 1 A structural diagram of a medical diagnosis data management system based on big data is shown; Figure 2 A step diagram of the matching method of the medical diagnosis data matching module of the present invention is shown. DETAILED DESCRIPTION

[0013] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0014] like Figure 1 , Figure 2 As shown, this embodiment provides a medical diagnosis data management system based on big data, which specifically includes: The medical diagnosis data cloud platform uses the hospital's information system to collect complete medical diagnosis data of hospital patients. The complete medical diagnosis data includes the patient's basic information, diagnosis results, treatment plans, and examination and test results. The collected and organized medical diagnosis data will be checked to establish a medical diagnosis data cloud platform, and the checked and accurate medical diagnosis data will be entered into the medical diagnosis data cloud platform. The above-mentioned basic patient information includes the patient's name, age, height, weight, and gender. The diagnosis results include: the patient's cause of disease, clinical symptoms and signs data, and doctor's advice. The treatment plan includes: drug treatment, non-drug treatment, surgical treatment, and rehabilitation treatment. The examination and test results include: laboratory tests, imaging examinations, and pathological examinations. The patient's medical diagnosis data level is divided according to the medical diagnosis process, and the medical diagnosis data of different patients is saved based on the medical diagnosis data level classification. The specific division method is as follows: The diagnosis result is determined by combining the patient's symptoms, physical sign data and the doctor's experience. The medical diagnosis data obtained in the diagnosis process is divided into the first level. All the first-level medical diagnosis data are combined to obtain the first-level data set. Physical sign data refers to the patient's body data affected by the patient's symptoms. For example, the severity of the patient's headache symptoms will affect the patient's body temperature data, and the patient's dizziness symptoms will affect the patient's blood pressure data. Based on the first-level diagnostic process, according to the doctor's request, the patient undergoes a specific non-pathological examination to determine the diagnosis result. The medical diagnostic data obtained by the diagnostic process is divided into the second level, and all the second-level medical diagnostic data are combined to obtain the second-level data set; Based on the first-level diagnostic process, according to the doctor's request, the patient determines the diagnosis result through pathological examination of specific cells or body tissues. The medical diagnostic data obtained in this diagnostic process is divided into the third level, and all third-level medical diagnostic data are combined to obtain a third-level data set.

[0015] The medical diagnosis data matching module, for patients whose historical medical diagnosis data have not been entered into the medical diagnosis data cloud platform, creates the patient's medical diagnosis data in real time by inputting the patient's basic information into the medical diagnosis data cloud platform, and records it as real-time medical diagnosis data. The real-time medical diagnosis data does not contain treatment plan content. By determining the patient's medical data level, the medical data of other patients with a high degree of correlation with the patient's medical data are matched. The doctor refers to the medical diagnosis data of other patients and the patient's historical medical diagnosis data to improve the treatment plan; For patients whose historical medical diagnosis data has been entered into the medical diagnosis data cloud platform, the basic information of the patient is input, the patient's medical diagnosis data is created in real time, and the patient's historical medical diagnosis data is automatically matched. By comparing with the patient's real-time medical diagnosis data, it is determined whether the patient's historical treatment plan is effective for the patient's related symptoms. Then, by determining the patient's medical data level, the medical data of other patients with a high degree of correlation with the patient's medical data is matched. The doctor refers to the medical diagnosis data of other patients and the patient's historical medical diagnosis data to improve the treatment plan; In order to quantify the correlation between the medical diagnosis data of different patients, the medical diagnosis correlation degree is set based on the medical diagnosis data of all patients in the medical diagnosis cloud platform. By determining the size of the medical diagnosis correlation between different patients, the medical diagnosis data with close correlation is screened and matched. The specific method is as follows: Determine the medical diagnosis data of the patient to be matched, recorded as the data to be matched, and based on the patient's age and gender information, the doctor determines the matching range through the diagnosis results. For example, a patient is male and 33 years old. Based on the patient's diagnosis results, the doctor determines that the medical diagnosis data of male patients aged 25 to 40 years old has reference value. According to the matching range and the level of the medical diagnosis data of the patient to be matched, match the medical diagnosis data of patients in the data set of the corresponding level, recorded as matching data, set the medical diagnosis correlation, and screen out medical diagnosis data with a high degree of medical diagnosis correlation by comparing the medical diagnosis data of different patients. The medical diagnosis correlation formula is as follows: ; in Represents the patient to be matched x and the matching patient The medical diagnosis correlation degree, k represents the kth matching patient, a(x) represents the height and weight index data of the patient x to be matched, Indicates matching patients The height and weight index, u(x, i) represents the patient's physical sign data affected by the i-th symptom of the matching patient x, n represents the total number of symptoms exhibited by the matching patient x, Indicates matching patients The same type of physical sign data as u(x, i), for example: u(x, 1) represents the body temperature data of the patient x to be matched affected by the first symptom, then represents the temperature data matching patient y, e represents the base of the natural number logarithm, The larger the value, the closer the matching patient x is to the matching patient. The higher the relevance of the medical diagnosis.

[0016] By calculating the medical diagnosis correlation degree between the patient to be matched and different matched patients, setting a medical diagnosis correlation degree threshold M, and comparing all medical diagnosis correlation degrees with M. When the medical diagnosis correlation degree is greater than or equal to M, retain to obtain a sequence of matched patients, sort the sequence of matched patients according to the magnitude of the medical diagnosis correlation degree, and select the top m medical diagnosis data as reference data, where m < k. The doctor further improves the treatment plan part of the patient's real-time medical diagnosis data through the reference data. In this embodiment, set , .

[0017] After the patient to be matched undergoes relevant medical diagnoses, medical diagnosis data and physical sign data about himself / herself are obtained. The medical diagnosis data and physical sign data are input into the medical diagnosis data matching module. The input data of the patient to be matched is matched with the medical diagnosis data of the matched patients within the matching range to determine the medical diagnosis correlation degree between the patient to be matched and different matched patients within the matching range. Compare the medical diagnosis correlation degree data with the pre-set medical diagnosis correlation degree threshold M, retain the matched patients whose medical diagnosis correlation degree with the patient to be matched is greater than or equal to M, screen out the group of matched patients that have passed the threshold judgment within the matching range, and the magnitude relationship between their medical diagnosis correlation degree and the patient to be matched. Set the retention number as m, retain the m matched patients with the largest medical diagnosis correlation degree, obtain a group of matched patients that meet the conditions, denoted as the reference group. According to the personal information of each matched patient in the reference group, query the medical diagnosis data of the reference group in the medical diagnosis data cloud platform, and use the medical diagnosis data of the reference group as the reference data for the patient to be matched.

[0018] The medical diagnosis data update module formulates a method for updating the patient's historical medical diagnosis data according to the medical diagnosis data level; sets a time period t. For the first-level medical diagnosis data, within one time period, only retain the latest first-level medical diagnosis data of the patient, and delete all first-level medical diagnosis data of the patient that are not within one time period; For the second-level medical diagnosis data, within one time period, completely retain all the second-level medical diagnosis data of the patient. When it exceeds one time period and is within N time periods, only completely retain the latest second-level medical diagnosis data of the patient. For other second-level medical diagnosis data of the patient, only retain the key parts, such as: the cause of the patient's illness, the treatment plan, and delete all medical diagnosis data of the patient that exceed N time periods; For the third-level medical diagnosis data, within N time periods, completely retain all the third-level medical diagnosis data of the patient, and only retain the key parts for other third-level medical diagnosis data of the patient.

[0019] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

[0020] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A medical diagnosis data management system based on big data, characterized in that: include: The medical diagnosis data cloud platform uses the hospital's information system to collect complete medical diagnosis data of hospital patients, classifies the medical diagnosis data of patients according to the medical diagnosis process, and saves the medical diagnosis data of different patients based on the classification of medical diagnosis data levels; The medical diagnosis data matching module provides complete medical diagnosis data that meets the correlation requirements for the real-time medical diagnosis data of the patient to be matched based on the correlation degree of the medical diagnosis data of different patients and the medical diagnosis data of all patients in the medical diagnosis cloud platform; The medical diagnosis data update module formulates a method for updating the patient's historical medical diagnosis data according to the medical diagnosis data level.

2. A medical diagnosis data management system based on big data according to claim 1, characterized in that: Complete medical diagnostic data, including the following: Complete medical diagnosis data includes the patient's basic information, diagnosis results, treatment plan, and examination and test results. The collected and organized medical diagnosis data will be verified, and a medical diagnosis data cloud platform will be established. The verified and accurate medical diagnosis data will be entered into the medical diagnosis data cloud platform.

3. A medical diagnosis data management system based on big data according to claim 1, characterized in that: The patient medical diagnosis data level is divided according to the medical diagnosis process. The specific method is as follows: The diagnosis result is determined by combining the patient's symptoms, physical sign data and the doctor's experience. The medical diagnosis data obtained in the diagnosis process is divided into the first level. All the first-level medical diagnosis data are combined to obtain the first-level data set. Physical sign data refers to the patient's body data affected by the patient's symptoms. Based on the first-level diagnostic process, according to the doctor's request, the patient undergoes a specific non-pathological examination to determine the diagnosis result. The medical diagnostic data obtained by the diagnostic process is divided into the second level, and all the second-level medical diagnostic data are combined to obtain the second-level data set; Based on the first-level diagnostic process, according to the doctor's request, the patient determines the diagnosis result through pathological examination of specific cells or body tissues. The medical diagnostic data obtained in this diagnostic process is divided into the third level, and all third-level medical diagnostic data are combined to obtain a third-level data set.

4. A medical diagnosis data management system based on big data according to claim 1, characterized in that: According to the correlation between the medical diagnosis data of different patients, based on the medical diagnosis data of all patients in the medical diagnosis cloud platform, provide complete medical diagnosis data with reference value for the real-time medical diagnosis data of the patients to be matched. The specific method is as follows: For patients whose historical medical diagnosis data has not been entered into the medical diagnosis data cloud platform, by entering the patient's basic information into the medical diagnosis data cloud platform, the patient's medical diagnosis data is created in real time and recorded as real-time medical diagnosis data. The real-time medical diagnosis data does not include treatment plan content. By determining the patient's medical data level, the medical data of other patients with a high degree of correlation with the patient's medical data is matched; For patients whose historical medical diagnosis data has been entered into the medical diagnosis data cloud platform, the patient's basic information is input, the patient's medical diagnosis data is created in real time, and the patient's historical medical diagnosis data is automatically matched. By comparing with the patient's real-time medical diagnosis data, the effect of the patient's historical treatment plan on the patient's related symptoms is judged, and then the patient's medical data level is determined to match the medical data of other patients with a high degree of correlation with the patient's medical data.

5. A medical diagnosis data management system based on big data according to claim 4, characterized in that: By determining the level of the patient's medical data, the medical data of other patients with a high degree of correlation with the patient's medical data are matched, and the specific method is as follows: Determine the medical diagnosis data of the patient to be matched, recorded as the data to be matched. Based on the patient's age and gender information, the doctor determines the matching range through the diagnosis result. According to the matching range and the level of the medical diagnosis data of the patient to be matched, match the medical diagnosis data of patients in the data set of the corresponding level, recorded as the matching data, set the medical diagnosis correlation, and screen out other medical diagnosis data with a high degree of correlation with the medical diagnosis of the patient to be matched by comparing the medical diagnosis data of different patients.

6. A medical diagnosis data management system based on big data according to claim 5, characterized in that: Set the medical diagnosis relevance. The specific method is: Using the formula represents the medical diagnosis relevance, where Represents the patient to be matched x and the matching patient The medical diagnosis correlation degree, k represents the kth matching patient, a(x) represents the height and weight index data of the patient x to be matched, Indicates matching patients The height and weight index, u(x, i) represents the patient's physical sign data affected by the i-th symptom of the matching patient x, n represents the total number of symptoms exhibited by the matching patient x, Indicates matching patients The same type of physical data as u(x, i), e represents the base of the natural number logarithm, The larger the value, the closer the matching patient x is to the matching patient. The higher the degree of correlation with the medical diagnosis of the patient to be matched, the more other medical diagnosis data with a high degree of correlation with the medical diagnosis of the patient to be matched are screened out.

7. A medical diagnosis data management system based on big data according to claim 1, characterized in that: Screening to obtain other medical diagnosis data that is highly correlated with the medical diagnosis of the patient to be matched, the specific method is: Set a medical diagnosis relevance threshold M, compare the medical diagnosis relevance of all patients to be matched with M, and determine the patients whose medical diagnosis relevance is greater than or equal to M. The number of matched patients is obtained, and the matched patient sequences are sorted according to the medical diagnosis correlation, and the first m with the largest medical diagnosis correlation are selected. Medical diagnosis data of m <k。 8. The medical diagnosis data management system based on big data according to claim 1, characterized in that: According to the level of medical diagnosis data, formulate the method of updating the patient's historical medical diagnosis data. The specific method is as follows: Set a time period t. For the first-level medical diagnosis data, only the latest first-level medical diagnosis data of the patient is retained within a time period, and all the first-level medical diagnosis data of the patient that are not within a time period are deleted; For the second-level medical diagnosis data, within one time period, all the second-level medical diagnosis data of the patient shall be completely retained. If the time period exceeds one time period and is within N time periods, only the latest second-level medical diagnosis data of the patient shall be completely retained. For the other second-level medical diagnosis data of the patient, only the key parts shall be retained. The key parts refer to the key data content in the medical diagnosis data. All medical diagnosis data of the patient within N time periods shall be deleted. For the third-level medical diagnosis data, within N time periods, all the third-level medical diagnosis data of the patient are completely retained, and for the other third-level medical diagnosis data of the patient, only the key parts are retained.

Images