Structured generation method and system for medical ultrasonic image report

Abstract

The invention discloses a medical ultrasonic image report structured generation method and system, and relates to the field of data analysis, and the main scheme is as follows: calculating an update index Z according to an update timeliness index Z1, a doctor satisfaction index Z2, an efficiency improvement index Z3, a knowledge coverage index Z4, a diagnosis consistency index Z5, a template compliance index Z6 and a patient population feature change index Z7; the problem that an existing structured report template is low in updating speed and cannot be matched with the rapid change situation, and then diagnosis efficiency is reduced is solved. Whether the structured report template needs to be updated or not is judged according to the updating index Z and the updating threshold value ZH, and when the judgment result is that updating is needed, the structured report template is updated, so that the updating process is optimized, and the working efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a method and system for generating structured medical ultrasound image reports. Background Art

[0002] In the medical field, structured ultrasound reports can help doctors quickly and accurately obtain patients' examination results and improve diagnostic efficiency and accuracy.

[0003] The working principle of the traditional ultrasound image report structured generation method and system is: obtain the patient's ultrasound image data and preprocess it, use computer vision technology to extract key features in the image, and identify specific structures or abnormal areas in the image, and automatically fill the extracted features and measurement results into the structured report template.

[0004] The existing technology still has the following shortcomings: With the continuous development of medical technology and changes in clinical practice, new examination items, diagnostic indicators and treatment recommendations continue to emerge. However, the existing structured report templates are updated slowly and cannot match this rapidly changing situation, which leads to a decrease in diagnostic efficiency. Summary of the invention

[0005] 1. Technical issues to be resolved

[0006] In view of the shortcomings of the prior art, the present invention provides a method and system for generating a structured medical ultrasound image report according to the update timeliness index Z 1 , Doctor satisfaction index Z 2 , efficiency improvement index Z 3 , knowledge coverage index Z 4 , diagnostic consistency index Z 5 , Template compliance indicator Z 6 and patient population characteristics change index Z 7 The calculation update index Z solves the problem that the existing structured report templates are updated slowly and cannot keep up with the rapidly changing situation, thus resulting in reduced diagnostic efficiency.

[0007] (II) Technical solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for generating a structured medical ultrasound image report, comprising the following steps:

[0009] Collect structured report template update data, structured report template disease data, structured report template diagnosis data, physician data, safety data and patient data;

[0010] Calculate the template update timeliness index Z based on the structured report template update data1 ; Calculate the doctor satisfaction index Z based on doctor data and structured report template update data 2 ; Update data calculation efficiency improvement index Z based on structured report template 3 ; Calculate the knowledge coverage index Z based on the disease data of the structured report template 4 ; Calculate the diagnostic consistency index Z based on the structured report template diagnostic data and doctor data 5 ; Calculate template compliance indicator Z based on security data 6 ; Based on the patient data, calculate the age distribution change index M and the gender distribution change index Y, and further calculate the patient population characteristic change index Z 7 ;

[0011] According to the update timeliness index Z 1 , Doctor satisfaction index Z 2 , efficiency improvement index Z 3 , knowledge coverage index Z 4 , diagnostic consistency index Z 5 , Template compliance indicator Z 6 and patient population characteristics change index Z 7 Calculate the update index Z; preset the update threshold ZH; determine whether the structured report template needs to be updated based on the update index Z and the update threshold ZH; when the determination result is that the structured report template needs to be updated, update the structured report template and send the update information to the staff.

[0012] In the preferred embodiment of the structured generation method of medical ultrasound image report, the template update timeliness index Z is calculated. 1 The method is:

[0013] The structured report template updates data including at least the current date T d , Template last updated date T u The date T from the last template update to the current time period for obtaining newly released medical information i ;

[0014] Calculate the template update timeliness index Z based on the structured report template update data 1 , the formula based on is:

[0015]

[0016] Among them, T i is the date of the i-th acquisition of newly released medical information from the last template update to the current time period, i is the serial number corresponding to different acquisition times, and the value is [1, n]; n is the number of times the information is acquired from the last template update date to the current date, and the value of n is a positive integer; in the formula, T i+1The date T of the medical information obtained for the nth time n .

[0017] In the preferred embodiment of the structured generation method of medical ultrasound image report, the doctor satisfaction index Z is calculated. 2 The method is:

[0018] The doctor data at least includes the doctor accuracy score F p Awareness rate of new knowledge among doctors 3 ;

[0019] The structured report template update data also includes the template new knowledge application rate A 4 ;

[0020] New knowledge application rate based on doctor data and templates A 4 , calculate the doctor satisfaction index Z 2 , the formula based on is:

[0021]

[0022] Among them, F p is the accuracy score of the structured report template given by the p-th doctor, p is the serial number corresponding to different doctors, and its value is [1, v]; v is the total number of doctors who have made the score, and its value is a positive integer.

[0023] In the preferred embodiment of the above method for generating a structured medical ultrasound image report: the calculation efficiency improvement index Z 3 The method is:

[0024] The structured report template update data also includes the report generation time before the template update B 1 , Report generation time after template update B 2 , Number of errors in generating reports before template update B 3 The number of errors in generating reports after the template is updated B 4 ;

[0025] Generate report time before template update B 1 , Report generation time after template update B 2 , Number of errors in generating reports before template update B 3 The number of errors in generating reports after the template is updated B 4 Computational efficiency improvement index Z 3 , the formula based on is:

[0026]

[0027] In the preferred embodiment of the structured generation method of medical ultrasound image report, the knowledge coverage index Z is calculated. 4The method is:

[0028] Structured reporting template Disease data including the number of disease types that the template supports diagnosis and reporting C 1 , Rare Disease Support Score D a and disease stage detail score F e ;

[0029] Calculate the knowledge coverage index Z based on the disease data of the structured report template 4 , the formula based on is:

[0030]

[0031] Among them, C 2 is the total number of clinically relevant diseases; D a is the support score of the structured report template for the ath rare disease, a is the serial number corresponding to different rare diseases, and its value is [1, b]; b is the total number of rare diseases, and its value is a positive integer; max{D a} is the maximum value among all rare disease support scores; F e is the stage subdivision score of the structured report template for the e-th disease, where e is the serial number corresponding to different diseases and takes the value [1, C 1 ]; max{F e} is the maximum value of all disease stage subdivision scores; α 1 is the weight coefficient of disease coverage, ranging from 0.3 to 0.5; α 2 is the weight coefficient of the degree of consideration of rare diseases, ranging from 0.2 to 0.5; α 3 is the weight coefficient of the disease stage subdivision, ranging from 0.2 to 0.5; and α 1 +α 2 +α 3 =1.

[0032] In the preferred embodiment of the structured generation method of medical ultrasound image report, the diagnostic consistency index Z is calculated. 5 The method is:

[0033] Structured report template diagnostic data including structured report diagnostic results G h ;

[0034] Doctor data also includes doctor diagnosis results H h ;

[0035] According to the structured report diagnosis results G h and the doctor's diagnosis h Calculate the diagnostic consistency index Z 5 , the formula based on is:

[0036]

[0037]

[0038] Among them, G h is the structured report diagnosis result of the hth case, h is the serial number corresponding to different cases, and its value is [1, g]; g is the total number of cases, and its value is a positive integer; H h is the doctor's diagnosis result of the hth case; I(G h , H h ) is the indicator function.

[0039] In the preferred embodiment of the structured generation method of medical ultrasound image report, the template compliance index Z is calculated. 6 The method is:

[0040] Security data includes the number of data breach incidents K 1 , total number of inspections K 2 、Number of encrypted patient information K 3 , the total number of patient information K 4 and structured reporting format element compliance score L j ;

[0041] Calculate the template compliance indicator Z based on the security data 6 , the formula based on is:

[0042]

[0043] Among them, L j is the compliance score of the jth structured report format element, j is the serial number corresponding to different report format elements, and its value is [1, l]; l is the total number of elements included in the report format, and its value is a positive integer.

[0044] In the preferred embodiment of the structured generation method of medical ultrasound image report, the patient population characteristic change index Z is calculated. 7 The method is:

[0045] Patient data includes current age ratio M x 、Historical age ratio N x 、Current proportion of female patients Y 1 and historical female patient ratio Y 2 ;

[0046] According to the current age ratio of patients M x and historical age ratio N x The calculation of the age distribution change index M is based on the following formula:

[0047]

[0048] Among them, M x is the proportion of patients in the current x-th age group to the total number of patients, x is the serial number corresponding to different age groups, the value is [1,4], x is a positive integer; N x is the proportion of patients in the historical xth age group to the total number of patients;

[0049] According to the current proportion of female patients Y 1 and historical female patient ratio Y 2 The formula for calculating the gender distribution change indicator Y is:

[0050]

[0051] Among them, Y 1 is the current proportion of female patients to the total number of patients; Y 2 is the historical proportion of female patients to the total number of patients;

[0052] Calculate the patient population characteristic change index Z based on the age distribution change index M and the gender distribution change index Y 7 , the formula based on is:

[0053] Z 7 =β 1 ×M+β 2 ×Y

[0054] Among them, β 1 is the weight coefficient of the age distribution change index M, ranging from 0.4 to 0.6; β 2 is the weight coefficient of the gender distribution change index Y, ranging from 0.4 to 0.6; and β 1 +β 2 =1.

[0055] In the preferred embodiment of the above method for generating a structured medical ultrasound image report, the method for determining whether the structured report template needs to be updated is:

[0056] According to the update timeliness index Z 1 , Doctor satisfaction index Z 2 , efficiency improvement index Z 3 , knowledge coverage index Z 4 , diagnostic consistency index Z 5 , Template compliance indicator Z 6 and patient population characteristics change index Z 7 The update index Z is calculated based on the formula:

[0057] Z=Z 1 +Z 2 +Z 3 +Z 4 +Z5 +Z 6 -Z 7

[0058] The formula for determining whether the structured report template needs to be updated is based on the update index Z and the update threshold ZH:

[0059]

[0060] The present invention also discloses a medical ultrasound image report structured generation system, which is used to implement the above-mentioned medical ultrasound image report structured generation method, comprising:

[0061] A data collection module, used for collecting structured report template update data, structured report template disease data, structured report template diagnosis data, doctor data, safety data and patient data;

[0062] Indicator calculation module, which can update the data calculation template based on the structured report template to update the timeliness indicator Z 1 ; Calculate the doctor satisfaction index Z based on doctor data and structured report template update data 2 ; Update data calculation efficiency improvement index Z based on structured report template 3 ; Calculate the knowledge coverage index Z based on the disease data of the structured report template 4 ; Calculate the diagnostic consistency index Z based on the structured report template diagnostic data and doctor data 5 ; Calculate template compliance indicator Z based on security data 6 ; Based on the patient data, calculate the age distribution change index M and the gender distribution change index Y, and further calculate the patient population characteristic change index Z 7 ;

[0063] The judgment module can update the timeliness index Z 1 , Doctor satisfaction index Z 2 , efficiency improvement index Z 3 , knowledge coverage index Z 4 , diagnostic consistency index Z 5 , Template compliance indicator Z 6 and patient population characteristics change index Z 7 Calculate the update index Z; preset the update threshold ZH; determine whether the structured report template needs to be updated based on the update index Z and the update threshold ZH; when the determination result is that the structured report template needs to be updated, update the structured report template and send the update information to the staff.

[0064] (III) Beneficial effects

[0065] The present invention provides a method and system for generating structured medical ultrasound image reports, which have the following beneficial effects:

[0066] (1) By collecting structured report template update data, structured report template disease data, structured report template diagnosis data, doctor data, safety data and patient data, it is helpful to understand whether the structured report template needs to be updated from multiple dimensions and provide effective data for subsequent indicator calculations.

[0067] (2) Calculate the template update timeliness index Z based on the structured report template update data 1 , which can reflect whether the template can keep up with new progress and changes in the medical field and improve the accuracy and timeliness of diagnosis. Calculate the doctor satisfaction index Z based on doctor data and structured report template update data 2 , we can better understand the doctors' acceptance of new technologies and new templates. Update data calculation efficiency improvement index Z based on structured report template 3 , which is conducive to the impact of template updates on doctors' work efficiency. Calculation of knowledge coverage index Z based on structured report template disease data 4 , which helps hospitals understand the role of templates in different disease diagnoses and reports. Calculate the diagnostic consistency index Z based on the structured report template diagnosis data and doctor data 5 , which is helpful to understand the accuracy of the structured report template diagnosis. Calculate the template compliance indicator Z based on safety data 6 , which is helpful to judge the legal risks faced by the template due to security issues such as data leakage. Calculate the patient population characteristic change index Z based on patient data 7 , which is helpful to understand the changes in the age and gender distribution of the patient population. Hospitals can adjust the content and design of the template to make it more in line with the characteristics of different patient groups and improve the pertinence and effectiveness of medical services.

[0068] (3) According to the update timeliness index Z 1 , Doctor satisfaction index Z 2 , efficiency improvement index Z 3 , knowledge coverage index Z 4 , diagnostic consistency index Z 5 , Template compliance indicator Z 6 and patient population characteristics change index Z 7 Calculating the update index Z solves the problem that the existing structured report template is updating slowly and cannot keep up with the rapidly changing situation, which in turn leads to reduced diagnostic efficiency. Judging whether the structured report template needs to be updated is determined based on the update index Z and the update threshold ZH. When the judgment result is that it needs to be updated, the structured report template is updated, which is conducive to optimizing the update process and improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1The present invention is a schematic diagram of the working steps of a method for structured generation of medical ultrasound imaging reports. DETAILED DESCRIPTION

[0070] 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.

[0071] See also Figure 1 The present invention provides a method for generating a structured medical ultrasound image report, comprising the following steps:

[0072] Step 1: Collect structured report template update data, structured report template disease data, structured report template diagnosis data, doctor data, safety data and patient data.

[0073] According to step 1:

[0074] By collecting structured report template update data, structured report template disease data, structured report template diagnosis data, doctor data, safety data and patient data, it is helpful to understand from multiple dimensions whether the structured report template needs to be updated, and provide valid data for subsequent indicator calculations.

[0075] Step 2: Calculate the template update timeliness index Z based on the structured report template update data 1 ; Calculate the doctor satisfaction index Z based on doctor data and structured report template update data 2 ; Update data calculation efficiency improvement index Z based on structured report template 3 ; Calculate the knowledge coverage index Z based on the disease data of the structured report template 4 ; Calculate the diagnostic consistency index Z based on the structured report template diagnostic data and doctor data 5 ; Calculate template compliance indicator Z based on security data 6 ; Based on the patient data, calculate the age distribution change index M and the gender distribution change index Y, and further calculate the patient population characteristic change index Z 7 .

[0076] Step 201: Calculate the template update timeliness index Z 1 The method is:

[0077] The structured report template updates data including at least the current date T d , Template last updated date T uThe date T from the last template update to the current time period for obtaining newly released medical information i .

[0078] It should be noted that the current date T d Represents the current specific year, month and day, which is the benchmark time point for evaluating the timeliness of template updates. It is obtained from the server time of the hospital information system. Template last updated date T u The date when the ultrasound imaging structured report template was last modified in terms of content, format or function, which can be obtained through the historical records of the template management system or version control system. The date when the template was last updated to obtain the newly released medical information within the current time period T i The specific time for obtaining the latest diagnostic standards, treatment guidelines, reporting requirements and other information from medical professional databases or authoritative medical institution websites is determined based on the information acquisition record log.

[0079] Calculate the template update timeliness index Z based on the structured report template update data 1 , the formula based on is:

[0080]

[0081] Among them, T i is the date of the i-th acquisition of newly released medical information from the last template update to the current time period, i is the serial number corresponding to different acquisition times, and the value is [1, n]; n is the number of times the information is acquired from the last template update date to the current date, and the value of n is a positive integer; in the formula, T i+1 The date T of the medical information obtained for the nth time n .

[0082] It should be noted that the operating principle of this formula is to comprehensively measure the timeliness of template updates by calculating the time difference between the current date and the last update date of the template, as well as the sum of the time intervals for obtaining newly released medical information each time during this update cycle. The smaller the time difference and the more regular the time interval for obtaining information, the more timely the template update is. The update timeliness index Z is 1 The higher it is, the less need there is for updates.

[0083] Step 202: Calculate the doctor satisfaction index Z 2 The method is:

[0084] The doctor data at least includes the doctor accuracy score F p Awareness rate of new knowledge among doctors 3 .

[0085] It should be noted that the doctor's accuracy score F pThe accuracy and reliability of the information provided by the structured report template in the auxiliary diagnosis process are quantitatively scored by doctors based on their own professional knowledge and clinical experience, reflecting the degree of fit between the template content and the actual clinical diagnosis situation. The method of obtaining the score is as follows: a questionnaire on the accuracy, information completeness and logical relevance of the template is designed, and the questionnaire is distributed to doctors in various departments who frequently use the ultrasound image structured report template. After the questionnaire is filled out, the answers to each question are counted, and the average score of each question is calculated. Then, weights are assigned to each question according to its importance in the overall accuracy assessment, and finally the doctor accuracy score F is obtained by weighted summation. p . Doctors' awareness of new knowledgeA 3 It refers to the degree of doctors' understanding of new knowledge related to ultrasound imaging structured reports. The method of obtaining it is: design a special test questionnaire that covers all the key points of new knowledge. The questionnaire can include multiple-choice questions, fill-in-the-blank questions, short-answer questions, etc. Doctors are regularly organized to take tests, and the proportion of the number of questions answered correctly by the doctors to the total number of questions is counted, which is the doctor's new knowledge awareness rate A. 3 .

[0086] The structured report template update data also includes the template new knowledge application rate A 4 .

[0087] It should be noted that the template new knowledge application rate A 4 It refers to the degree to which new medical knowledge is actually applied in the ultrasound imaging structured report template. It reflects whether the template can effectively integrate new knowledge into the diagnostic process and help doctors apply this new knowledge in actual work. It is very important for evaluating the practicality and effectiveness of template updates. The acquisition method is to review the medical records of ultrasound imaging structured reports within a certain period of time to check whether the report contains content related to new knowledge, such as new diagnostic terms, new examination method records, new disease characteristics, etc. The proportion of cases that apply new knowledge to the total number of cases is the template new knowledge application rate A. 4 .

[0088] New knowledge application rate based on doctor data and templates A 4 , calculate the doctor satisfaction index Z 2 , the formula based on is:

[0089]

[0090] Among them, F p is the accuracy score of the structured report template given by the p-th doctor, p is the serial number corresponding to different doctors, and its value is [1, v]; v is the total number of doctors who have made the score, and its value is a positive integer.

[0091] It should be noted that the operating principle of this formula is: The average accuracy score of all doctors for the structured report template. The higher the average accuracy score, the higher the doctor satisfaction index Z 2 The higher the value, the better the structured report template will perform and the less likely it will need to be updated. (A 3 -A 4 ) is the doctor's new knowledge awareness rate A 3 And template new knowledge application rate A 4 The smaller the difference, the higher the doctor satisfaction index Z. 2 The higher it is, the better the structured report template will be and the less need there is for updates.

[0092] Step 203: Calculate the efficiency improvement index Z 3 The method is:

[0093] The structured report template update data also includes the report generation time before the template update B 1 , Report generation time after template update B 2 , Number of errors in generating reports before template update B 3 The number of errors in generating reports after the template is updated B 4 .

[0094] It should be noted that the report generation time B before the template is updated 1 It refers to the time it takes for a doctor to generate a complete ultrasound imaging report using the old template before the last update. This time reflects the efficiency of the old template in actual use. It is obtained by: determining the generation time of each report through time recording software, collecting the time data of a large number of doctors using the old template to generate reports and calculating the total time, and dividing it by the number of reports, which is the report generation time before the template update B 1 .

[0095] Time to generate report after template update B 2 It refers to the time it takes for a doctor to generate a complete ultrasound imaging report using the current template. This time reflects the efficiency of the current template in actual use. It is obtained by: determining the generation time of each report through time recording software, collecting the time data of a large number of doctors using the current template to generate reports and calculating the total time, and dividing it by the number of reports, which is the report generation time after the template is updated. 2 .

[0096] Number of errors in generating reports before template update B 3It refers to the number of errors that occurred when doctors used the old template before the last update to generate reports. It reflects the accuracy and reliability of the old template. The method for obtaining it is: perform a quality check on the reports generated using the old template. During the check, count the number of errors found and record them. Through multiple quality checks, we can obtain the number of errors in generating reports before the template update. 3 .

[0097] Number of errors in generating reports after template update B 4 It refers to the number of errors that occur when the doctor generates reports using the current template, reflecting the accuracy and reliability of the current template. The method for obtaining it is to perform a quality check on the reports generated using the current template, and during the check, count the number of errors found and record them. Through multiple quality checks, the number of errors in the report generated after the template is updated is obtained. 4 .

[0098] Generate report time before template update B 1 , Report generation time after template update B 2 , Number of errors in generating reports before template update B 3 The number of errors in generating reports after the template is updated B 4 Computational efficiency improvement index Z 3 , the formula based on is:

[0099]

[0100] It should be noted that this formula measures the efficiency improvement of the last template update by calculating the relative ratio of the report generation time before and after the template update and the relative ratio of the number of errors. The higher the efficiency improvement, the higher the efficiency improvement index, the better the template usage effect, and the less the need for update.

[0101] Step 204: Calculate the knowledge coverage index Z 4 The method is:

[0102] Structured reporting template disease data including the number of disease types that the template supports diagnosis and reporting C 1 , Rare Disease Support Score D a and disease stage detail score F e .

[0103] It should be noted that the template supports the diagnosis and reporting of the number of diseases C 1Indicates the total number of diseases that the structured report template can cover and effectively assist doctors in diagnosing and generating reports. It reflects the disease coverage of the template. The more diseases it covers, the more versatile and applicable the template is. The method to obtain it is: carefully review each part of the structured report template, including disease classification, diagnostic criteria, report format, etc., and count the diseases that can be diagnosed and reported that are clearly listed in the template.

[0104] Rare Disease Support Score D a Used to measure the degree to which the structured reporting template supports the diagnosis and reporting of rare diseases. The specific determination method is: if the template includes three pieces of information: diagnostic processes or prompts specifically for rare diseases, special examination method recommendations for rare diseases, and relevant diagnostic criteria, the score is 1; if it includes two pieces of information, the score is 0.6; if it includes one piece of information, the score is 0.3; if there is no consideration of rare diseases, the score is 0.

[0105] Disease stage detail score F e It is used to evaluate the ability of the structured report template to distinguish and describe different disease stages. The specific determination method is as follows: according to medical expertise and clinical practice, the different stages of common diseases are divided into different standards. The structured report template is compared with the determined disease stage division standards to evaluate the description and distinction ability of each disease stage. Professional doctors or medical experts score each evaluation aspect according to the actual situation of the template, and then add up the scores of each aspect to obtain the disease stage subdivision score F. e .

[0106] Calculate the knowledge coverage index Z based on the disease data of the structured report template 4 , the formula based on is:

[0107]

[0108] Among them, C 2 The total number of clinically relevant diseases is determined by referring to authoritative medical databases, clinical guidelines, and hospital case data. a is the support score of the structured report template for the ath rare disease, a is the serial number corresponding to different rare diseases, and its value is [1, b], b is the total number of rare diseases, and its value is a positive integer; max{D a} is the maximum value among all rare disease support scores. e is the stage subdivision score of the structured report template for the e-th disease, where e is the serial number corresponding to different diseases and takes the value [1, C 1 ],max{F e} is the maximum value among all disease stage subdivision scores. 1is the weight coefficient of disease coverage, ranging from 0.3 to 0.5, and the disease coverage index Z is 4 The degree of influence is determined. 2 is the weight coefficient of the degree of consideration of rare diseases, ranging from 0.2 to 0.5. The knowledge coverage index Z is calculated based on the degree of consideration of rare diseases. 4 The degree of influence is determined. 3 is the weight coefficient of disease stage segmentation, ranging from 0.2 to 0.5. 4 The influence degree of is determined. And α 1 +α 2 +α 3 =1.

[0109] It should be noted that the operating principle of this formula is: The breadth of disease coverage is obtained by calculating the ratio of the number of diseases that the template can support diagnosis and reporting to the total number of clinically relevant diseases. The higher the disease coverage breadth, the more universal the template is, and the knowledge coverage index Z is higher. 4 The higher. The degree of consideration of rare diseases is obtained by calculating the ratio of the total support score of the template for all rare diseases to the number of rare diseases multiplied by the highest support score. The higher the ratio, the more comprehensive the consideration of rare diseases by the template, and the higher the knowledge coverage index Z. 4 The higher. The disease stage segmentation degree is obtained by calculating the ratio of the sum of the template's stage segmentation scores for all diseases to the maximum value of the number of disease types multiplied by the segmentation degree score. The higher the ratio, the more detailed and accurate the template's segmentation of the disease stage is, and the higher the knowledge coverage index Z is. 4 The higher.

[0110] Step 205: Calculate the diagnostic consistency index Z 5 The method is:

[0111] Structured report template diagnostic data including structured report diagnostic results G h , obtained by viewing the ultrasound imaging report system.

[0112] Doctor data also includes doctor diagnosis results H h , obtained through patient medical records.

[0113] According to the structured report diagnosis results G h and the doctor's diagnosis h Calculate the diagnostic consistency index Z 5 , the formula based on is:

[0114]

[0115]

[0116] Among them, G h is the structured report diagnosis result of the hth case, h is the serial number corresponding to different cases, and its value is [1, g]; G is the total number of cases, and its value is a positive integer; H h is the doctor's diagnosis result of the hth case; I(G h , H h ) is an indicator function used to compare the structured report diagnosis results G of each medical record h and the doctor's diagnosis h If the diagnosis results are consistent, I(G h , H h ) is 1. When the diagnosis results are inconsistent, I(G h , H h ) is 0.

[0117] It should be noted that the operating principle of this formula is: by calculating the structured report diagnosis result G in all samples h and the doctor's diagnosis h The consistency between the two is measured by the proportion of the number of consistent cases to the total number of samples. Diagnostic consistency index Z 5 The higher it is, the more accurate the template is and the less need for updates.

[0118] Step 206: Calculate the template compliance index Z 6 The method is:

[0119] Security data includes the number of data breach incidents K 1 , total number of inspections K 2 、Number of encrypted patient information K 3 , the total number of patient information K 4 and structured reporting format element compliance score L j .

[0120] It should be noted that the number of data leakage incidents is K 1 It refers to the total number of incidents involving leakage of ultrasound imaging structured report-related data from the last template update to the current time period. The data here mainly includes patients' personal information, examination results, diagnosis reports, etc. By regularly checking the logs and reports of the security monitoring system, the number of data leakage incidents K is counted. 1 . Total number of inspections K 2 Refers to the total number of ultrasound imaging examinations performed in the hospital from the last template update to the current time period. Obtained from the medical information system.

[0121] Number of encrypted patient information K 3Refers to the number of encrypted patient information in ultrasound image structured reports by the hospital from the last template update to the current period. Obtained through encryption system records. Total number of patient information K 4 Refers to the total amount of patient information involved in the hospital ultrasound imaging structured report from the last template update to the current time period, including all patient-related data such as patient personal information, test results, and diagnostic reports. By querying the ultrasound imaging report system, counting the number of reports in this time period, and multiplying it by the average amount of patient information contained in each report, an estimated value of the total amount of patient information is obtained.

[0122] Structured Report Format Element Compliance Score L j It is used to measure the degree of compliance of different report format elements. Report format elements include report title, patient information, examination date, examination site, image description, diagnosis conclusion, doctor's signature, etc. The specific determination method is: first formulate a set of standards for evaluating the compliance of structured report format elements, and clarify the importance and compliance requirements of each format element. Professionals, such as quality control personnel, medical experts, etc., check the format elements of each report one by one according to the evaluation standards, score each element, and then add up the scores of all elements to obtain the compliance score of the report. The compliance scores of multiple reports evaluated are counted, and the average score is calculated as the compliance score of the structured report format element L. j .

[0123] Calculate the template compliance indicator Z based on the security data 6 , the formula based on is:

[0124]

[0125] Among them, L j is the compliance score of the jth structured report format element, j is the serial number corresponding to different report format elements, and its value is [1, l]; l is the total number of elements included in the report format, and its value is a positive integer.

[0126] It should be noted that the operating principle of this formula is: The security level of the report template is measured by calculating the ratio of the number of data non-leakage incidents to the total number of inspections. By calculating the number of encrypted patient information K 3 The total number of patient information K 4 ratio to measure the degree of protection of patient information by the report template. The overall format compliance of the report template is comprehensively evaluated by taking a weighted sum of the compliance of each report format element. The template compliance index Z is obtained by comprehensively considering the security level of the report template, the degree of protection of patient information and the overall format compliance.6 Template Compliance Indicator Z 6 The higher it is, the less need there is for updates.

[0127] Step 207: Calculate the patient population characteristic change index Z 7 The method is:

[0128] Patient data includes current age ratio M x 、Historical age ratio N x 、Current proportion of female patients Y 1 and historical female patient ratio Y 2 .

[0129] It should be noted that the current age ratio M x Refers to the proportion of patients in different age groups in the total number of patients in the current cycle. Historical age ratio N x Refers to the proportion of patients in different age groups in the total number of patients in the previous cycle. The cycle time is determined according to medical management needs and disease seasonality, usually in months, quarters, or years. Current age ratio M x and historical age ratio N x The method of obtaining the data is as follows: by querying the hospital's patient information management system, the number of patients who underwent ultrasound imaging examinations in different periods is counted, and they are classified according to age ranges. Then the proportion of the number of patients in each age group to the total number of patients is calculated to obtain the age ratio. The specific division criteria for age groups are: 0-14 years old is the children group, 15-44 years old is the youth group, 45-64 years old is the middle-aged group, and 65 years old and above is the elderly group.

[0130] Current proportion of female patients Y 1 Refers to the proportion of female patients in the total number of patients in the current cycle. Historical proportion of female patients Y 2 Refers to the proportion of female patients in the total number of patients in the previous cycle. Current proportion of female patients Y 1 and historical female patient ratio Y 2 The method of obtaining is: using the hospital's medical records, querying the patient records of ultrasound imaging examinations in different periods, and determining the number of female patients. Then calculate the ratio of the number of female patients to the total number of patients to obtain the proportion of female patients.

[0131] According to the current age ratio of patients M x and historical age ratio N x The calculation of the age distribution change index m is based on the formula:

[0132]

[0133] Among them, M xis the proportion of patients in the current x-th age group to the total number of patients, x is the serial number corresponding to different age groups, the value is [1,4], x is a positive integer; N x It is the proportion of patients in the xth age group in history to the total number of patients.

[0134] It should be noted that this formula obtains the age distribution change index M by calculating the difference in age ratios.

[0135] According to the current proportion of female patients Y 1 and historical female patient ratio Y 2 The formula for calculating the gender distribution change indicator Y is:

[0136]

[0137] Among them, Y 1 is the current proportion of female patients to the total number of patients; Y 2 is the historical ratio of female patients to the total number of patients.

[0138] It should be noted that the operating principle of this formula is: |Y 1 -Y 2 | is the difference in the proportion of female patients, |(1-Y 1 )-(1-Y 2 )|| is the difference in the proportion of male patients. By calculating the difference in the age ratio of female patients and male patients, the age distribution change index M is obtained.

[0139] Calculate the patient population characteristic change index Z based on the age distribution change index M and the gender distribution change index Y 7 , the formula based on is:

[0140] Z 7 =β 1 ×M+β 2 ×Y

[0141] Among them, β 1 is the weight coefficient of the age distribution change index M, which ranges from 0.4 to 0.6. 7 The degree of influence is determined. 2 is the weight coefficient of the gender distribution change index Y, with a value of 0.4 to 0.6. 7 The degree of influence is determined. And β 1 +β 2 =1.

[0142] It should be noted that this formula comprehensively considers the influence of age distribution and gender distribution to obtain the patient population characteristic change index Z 7Patient population characteristics change indicator Z 7 The higher it is, the more variable the patient population characteristics are and the greater the need for template updates.

[0143] Combined with the contents of step 201 to step 207:

[0144] Calculate the template update timeliness index Z based on the structured report template update data 1 , which can reflect whether the template can keep up with new progress and changes in the medical field and improve the accuracy and timeliness of diagnosis. Calculate the doctor satisfaction index Z based on doctor data and structured report template update data 2 , we can better understand the doctors' acceptance of new technologies and new templates. Update data calculation efficiency improvement index Z based on structured report template 3 , which is helpful to understand the impact of template updates on doctors’ work efficiency. Calculation of knowledge coverage index Z based on disease data of structured report template 4 , which helps hospitals understand the role of templates in different disease diagnoses and reports. Calculate the diagnostic consistency index Z based on the structured report template diagnosis data and doctor data 5 , which is helpful to understand the accuracy of the structured report template diagnosis. Calculate the template compliance indicator Z based on safety data 6 , which is helpful to judge the legal risks faced by the template due to security issues such as data leakage. Calculate the patient population characteristic change index Z based on patient data 7 , which is helpful to understand the changes in the age and gender distribution of the patient population. Hospitals can adjust the content and design of the template to make it more in line with the characteristics of different patient groups and improve the pertinence and effectiveness of medical services.

[0145] Step 3: Update the timeliness indicator Z 1 , Doctor satisfaction index Z 2 , efficiency improvement index Z 3 , knowledge coverage index Z 4 , diagnostic consistency index Z 5 , Template compliance indicator Z 6 and patient population characteristics change index Z 7 Calculate the update index Z; preset the update threshold ZH; determine whether the structured report template needs to be updated based on the update index Z and the update threshold ZH; when the determination result is that the structured report template needs to be updated, update the structured report template and send the update information to the staff.

[0146] Step 301: The method for determining whether the structured report template needs to be updated is:

[0147] According to the update timeliness index Z 1 , Doctor satisfaction index Z 2 , efficiency improvement index Z3 , knowledge coverage index Z 4 , diagnostic consistency index Z 5 , Template compliance indicator Z 6 and patient population characteristics change index Z 7 The update index Z is calculated based on the formula:

[0148] Z=Z 1 +Z 2 +Z 3 +Z 4 +Z 5 +Z 6 -Z 7

[0149] It should be noted that the formula comprehensively considers the impact of multiple factors on the update of the structured report template to obtain the update index Z.

[0150] The formula for determining whether the structured report template needs to be updated is based on the update index Z and the update threshold ZH:

[0151]

[0152] It should be noted that the method for determining the update threshold ZH is: presetting different initial update thresholds, counting the error rates of the structured report templates under different update thresholds, screening out the initial update thresholds corresponding to 20% of the data with lower error rates as a reference data set, and calculating the average value of the reference data set as a reference value for the update threshold ZH.

[0153] Combined with the content of step 301:

[0154] According to the update timeliness index Z 1 , Doctor satisfaction index Z 2 , efficiency improvement index Z 3 , knowledge coverage index Z 4 , diagnostic consistency index Z 5 , Template compliance indicator Z 6 and patient population characteristics change index Z 7 Calculating the update index Z solves the problem that the existing structured report template is slow to update and cannot keep up with the rapidly changing situation, which leads to reduced diagnostic efficiency. The structured report template is updated based on the update index Z and the update threshold ZH. If it is necessary to update, the structured report template is updated, which is conducive to optimizing the update process and improving work efficiency.

[0155] On the other hand, the present invention also discloses a structured generation system for medical ultrasound image reports, comprising:

[0156] The data collection module is used to collect structured report template update data, structured report template disease data, structured report template diagnosis data, doctor data, safety data and patient data.

[0157] Indicator calculation module, which can update the data calculation template based on the structured report template to update the timeliness indicator Z 1 ; Calculate the doctor satisfaction index Z based on doctor data and structured report template update data 2 ; Update data calculation efficiency improvement index Z based on structured report template 3 ; Calculate the knowledge coverage index Z based on the disease data of the structured report template 4 ; Calculate the diagnostic consistency index Z based on the structured report template diagnostic data and doctor data 5 ; Calculate template compliance indicator Z based on security data 6 ; Based on the patient data, calculate the age distribution change index M and the gender distribution change index Y, and further calculate the patient population characteristic change index Z 7 .

[0158] The judgment module can update the timeliness index Z 1 , Doctor satisfaction index Z 2 , efficiency improvement index Z 3 , knowledge coverage index Z 4 , diagnostic consistency index Z 5 , Template compliance indicator Z 6 and patient population characteristics change index Z 7 Calculate the update index Z; preset the update threshold ZH; determine whether the structured report template needs to be updated based on the update index Z and the update threshold ZH; when the determination result is that the structured report template needs to be updated, update the structured report template and send the update information to the staff.

[0159] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware or in combination with computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0160] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0161] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for generating a structured medical ultrasound image report, characterized in that: The following steps are involved: Collect structured report template update data, structured report template disease data, structured report template diagnosis data, physician data, safety data and patient data; The template update timeliness index Z1 is calculated based on the structured report template update data; the doctor satisfaction index z2 is calculated based on the doctor data and the structured report template update data; Update data based on structured report templates to calculate efficiency improvement index Z3; calculate knowledge coverage index z4 based on structured report template disease data; Calculate the diagnostic consistency index Z5 based on the structured report template diagnostic data and doctor data; calculate the template compliance index Z6 based on the safety data; calculate the age distribution change index M and gender distribution change index Y based on the patient data, and further calculate the patient population characteristic change index z7; Calculate the update index Z according to the update timeliness index z1, the doctor satisfaction index Z2, the efficiency improvement index z3, the knowledge coverage index z4, the diagnosis consistency index Z5, the template compliance index Z6 and the patient population characteristic change index Z7; preset the update threshold ZH; determine whether the structured report template needs to be updated according to the update index Z and the update threshold ZH; when the judgment result is that updating is required, update the structured report template and send the update information to the staff.

2. A method for generating a structured medical ultrasound image report according to claim 1, characterized in that: The method for calculating the template update timeliness index Z1 is: The structured report template updates data including at least the current date T d , Template last updated date T u The date T from the last template update to the current time period for obtaining newly released medical information i ; The template update timeliness indicator Z1 is calculated based on the structured report template update data, based on the formula: Among them, T i is the date of the i-th acquisition of newly released medical information from the last template update to the current time period, i is the serial number corresponding to different acquisition times, and the value is [1, n]; n is the total number of times the information is acquired from the last template update date to the current date, and the value of n is a positive integer; in the formula, T i+1 Corresponding to the date T of the nth acquisition of newly released medical information n .

3. A method for generating a structured medical ultrasound image report according to claim 2, characterized in that: The method for calculating the doctor satisfaction index Z2 is: The doctor data at least includes the doctor accuracy score F p and doctors’ new knowledge awareness rate A3; The structured report template update data also includes the template new knowledge application rate A4; Based on the doctor data and the application rate of new knowledge in the template A4, the doctor satisfaction index Z2 is calculated based on the following formula: Among them, E p is the accuracy score of the structured report template given by the p-th doctor, p is the serial number corresponding to different doctors, and its value is [1, v]; v is the total number of doctors who have made the score, and its value is a positive integer.

4. A method for generating a structured medical ultrasound image report according to claim 3, characterized in that: The method for calculating the efficiency improvement index Z3 is: The structured report template update data also includes the report generation time B1 before the template update, the report generation time B2 after the template update, the number of errors in the report generation before the template update B3, and the number of errors in the report generation after the template update B4; The efficiency improvement index Z3 is calculated based on the report generation time B1 before template update, the report generation time B2 after template update, the number of errors in report generation before template update B3, and the number of errors in report generation after template update B4. The formula used is:

5. A method for generating a structured medical ultrasound image report according to claim 4, characterized in that: The method for calculating the knowledge coverage index Z4 is: The disease data of the structured reporting template includes the number of diseases that the template supports diagnosis and reporting C1, and the rare disease support score D a and disease stage detail score F e ; The knowledge coverage indicator Z4 is calculated based on the disease data of the structured reporting template, based on the formula: Among them, C2 is the total number of clinically relevant diseases; D a is the support score of the structured report template for the ath rare disease, a is the serial number corresponding to different rare diseases, and its value is [1, b]; b is the total number of rare diseases, and its value is a positive integer; max{D a } is the maximum value among all rare disease support scores; F e is the stage subdivision score of the structured report template for the e-th disease, where e is the serial number corresponding to different diseases and takes the value [1, C1]; max{F e } is the maximum value of all disease stage segmentation scores; α1 is the weight coefficient of disease coverage, ranging from 0.3 to 0.5; α2 is the weight coefficient of the degree of consideration of rare diseases, ranging from 0.2 to 0.5; α3 is the weight coefficient of disease stage segmentation, ranging from 0.2 to 0.5; and α1+α2+α3=1.

6. A method for generating a structured medical ultrasound image report according to claim 5, characterized in that: The method for calculating the diagnostic consistency index Z5 is: Structured report template diagnostic data including structured report diagnostic results G h ; Doctor data also includes doctor diagnosis results H h ; According to the structured report diagnosis results G h and the doctor's diagnosis h The diagnostic consistency index Z5 is calculated based on the formula: Among them, G h is the structured report diagnosis result of the hth case, h is the serial number corresponding to different cases, and its value is [1, g]; g is the total number of cases, and its value is a positive integer; H h is the doctor's diagnosis result of the hth case; I(G h , H h ) is the indicator function.

7. A method for generating a structured medical ultrasound image report according to claim 6, characterized in that: The method for calculating the template compliance indicator Z6 is: Security data includes the number of data breach incidents (K1), the total number of inspections (K2), the number of encrypted patient information (K3), the total number of patient information (K4), and the compliance score of the structured report format element (L). j ; The template compliance indicator Z6 is calculated based on the safety data according to the formula: Among them, L j is the compliance score of the jth structured report format element, j is the serial number corresponding to different report format elements, and its value is [1, l]; l is the total number of elements included in the report format, and its value is a positive integer.

8. A method for generating a structured medical ultrasound image report according to claim 7, characterized in that: The method for calculating the patient population characteristic change index Z7 is: Patient data includes current age ratio M x 、Historical age ratio N x , the current proportion of female patients Y1 and the historical proportion of female patients Y2; According to the current age ratio of patients M x and historical age ratio N x The calculation of the age distribution change index M is based on the following formula: Among them, M x is the proportion of patients in the current x-th age group to the total number of patients, x is the serial number corresponding to different age groups, the value is [1,4], x is a positive integer; N x is the proportion of patients in the historical xth age group to the total number of patients; The gender distribution change index Y is calculated based on the current female patient ratio Y1 and the historical female patient ratio Y2, and the formula is: Among them, Y1 is the current proportion of female patients to the total number of patients; Y2 is the historical proportion of female patients to the total number of patients; The patient population characteristic change index Z7 is calculated based on the age distribution change index M and the gender distribution change index Y, and the formula is: Z7=β1×M+β2×Y Among them, β1 is the weight coefficient of the age distribution change index M, and its value is 0.4~0.6; β2 is the weight coefficient of the gender distribution change index Y, and its value is 0.4~0.6; and β1+β2=1.

9. A method for generating a structured medical ultrasound image report according to claim 8, characterized in that: The method to determine whether the structured report template needs to be updated is: The update index Z is calculated based on the update timeliness index Z1, the doctor satisfaction index Z2, the efficiency improvement index Z3, the knowledge coverage index Z4, the diagnosis consistency index Z5, the template compliance index Z6 and the patient population characteristic change index Z7. The formula is: Z=Z1+Z2+Z3+Z4+Z5+Z6-Z7 The formula for determining whether the structured report template needs to be updated is as follows:

10. A medical ultrasound image report structured generation system, characterized in that: include: A data collection module, used for collecting structured report template update data, structured report template disease data, structured report template diagnosis data, doctor data, safety data and patient data; The indicator calculation module can calculate the template update timeliness indicator Z1 based on the structured report template update data; calculate the doctor satisfaction indicator Z2 based on the doctor data and the structured report template update data; Update data based on structured report templates to calculate efficiency improvement index Z3; calculate knowledge coverage index Z4 based on structured report template disease data; Calculate the diagnostic consistency index Z5 based on the structured report template diagnostic data and doctor data; calculate the template compliance index Z6 based on the safety data; calculate the age distribution change index M and gender distribution change index Y based on the patient data, and further calculate the patient population characteristic change index Z7; The judgment module can calculate the update index Z according to the update timeliness index Z1, the doctor satisfaction index Z2, the efficiency improvement index Z3, the knowledge coverage index Z4, the diagnosis consistency index Z5, the template compliance index Z6 and the patient population characteristic change index Z7; preset the update threshold ZH; judge whether the structured report template needs to be updated according to the update index Z and the update threshold ZH; when the judgment result is that it needs to be updated, update the structured report template and send the update information to the staff.

Images