Electrocardiogram remote diagnosis scheduling method, terminal equipment and storage medium

Abstract

The invention relates to an electrocardio remote diagnosis scheduling method, terminal equipment and a storage medium, and the method comprises the steps: obtaining a corresponding actual diagnosis disease type and a pre-analysis disease type according to a report of a diagnosis worker on the basis of constructing mapping between an electrocardio disease type and a diagnosis conclusion keyword; and then the diagnosis accuracy and the diagnosis time efficiency of the diagnosis personnel for different disease categories are evaluated, the pre-analyzed disease categories obtained by combining the electrocardiogram analysis model are combined, the matching degree of a case needing to be diagnosed and each diagnosis personnel is calculated, and the case is dispatched to the diagnosis personnel with the highest matching degree for diagnosis. According to the invention, the case needing remote diagnosis can be sent to the diagnosis personnel with the highest matching degree for diagnosis, the accuracy and timeliness of the diagnosis result are improved, and the diagnosis efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of telemedicine, and particularly to a method for electrocardiogram remote diagnosis scheduling, a terminal device and a storage medium. Background Art

[0002] Electrocardiogram (ECG) remote medicine is a medical service method that combines modern electronic technology, communication technology and medical diagnosis technology, and can realize the remote transmission and interpretation of electrocardiogram data. Through information transmission technology, ECG remote medicine transmits the electrocardiogram data of patients to medical institutions in the distance in real time or almost in real time for doctors to diagnose and analyze. This method breaks the geographical restrictions, enabling patients in remote areas or areas with scarce medical resources to enjoy high-quality medical services.

[0003] In ECG remote medicine, due to the uneven level of diagnostic doctors, the time spent on issuing diagnostic reports for electrocardiograms of different complexities varies. When a large number of electrocardiogram diagnosis tasks need to be processed during the peak working period, the entire ECG remote medical diagnosis process will become chaotic and sluggish. For example, complex electrocardiograms may take a long time because they are scheduled to doctors with insufficient experience, affecting the accuracy of the report and even exceeding the agreed diagnostic time limit. When doctors with insufficient experience misdiagnose or are unable to diagnose some complex electrocardiograms, the case needs to be reassigned to other doctors, which will undoubtedly prolong the diagnostic time and reduce the diagnostic efficiency. Summary of the Invention

[0004] In order to solve the above problems, the present invention proposes a method for electrocardiogram remote diagnosis scheduling, a terminal device and a storage medium.

[0005] The specific solutions are as follows:

[0006] An electrocardiogram remote diagnosis scheduling method includes the following steps:

[0007] S1: Construct a mapping table representing the mapping relationship between electrocardiogram disease categories and diagnostic conclusion keywords;

[0008] S2: Receive the historical electrocardiogram diagnostic reports of each remote diagnostician;

[0009] S3: For each report, based on the diagnostic conclusion therein and in combination with the mapping table, obtain the actual diagnosed disease type corresponding to the report; based on the electrocardiogram data therein and in combination with the electrocardiogram analysis model and the mapping table, obtain the pre-analyzed disease type corresponding to the report;

[0010] S4: According to the actual diagnosed disease type and pre-analyzed disease type corresponding to each report, and in combination with the expert diagnosis result of the report, determine whether the report belongs to an accurately diagnosed report, and determine the electrocardiogram disease category to which each report belongs;

[0011] S5: Classify all the reports corresponding to each remote diagnostician according to the types of electrocardiogram diseases they belong to;

[0012] S6: Based on the ratio of the number of accurate diagnosis reports among all the reports corresponding to each remote diagnostician for each type of electrocardiogram disease, calculate the diagnostic accuracy rate of each remote diagnostician for each type of electrocardiogram disease; Based on the diagnostic time and quantity of the accurate diagnosis reports among all the reports corresponding to each remote diagnostician for each type of electrocardiogram disease, calculate the diagnostic efficiency of each remote diagnostician for each type of electrocardiogram disease;

[0013] S7: When remote diagnosis of electrocardiogram data is required, after obtaining the preliminary diagnosis conclusion of the electrocardiogram data through the electrocardiogram analysis model, look up the preliminary analysis disease type corresponding to the electrocardiogram data according to the mapping table;

[0014] S8: Calculate the matching degree of each remote diagnostician according to the diagnostic accuracy rate and diagnostic efficiency of each remote diagnostician corresponding to the preliminary analysis disease type;

[0015] S9: Send the electrocardiogram data to the remote diagnostician with the highest matching degree for diagnosis.

[0016] Furthermore, the method for obtaining the actual diagnosis disease type corresponding to the report based on the diagnostic conclusion therein and in combination with the mapping table is as follows: Search for the diagnostic conclusion keywords included in the mapping table from the diagnostic conclusion, and then obtain the electrocardiogram disease type corresponding to the diagnostic conclusion keywords according to the mapping table, and use the obtained electrocardiogram disease type as the actual diagnosis disease type corresponding to the report.

[0017] Furthermore, the method for obtaining the preliminary analysis disease type corresponding to the report based on the electrocardiogram data therein and in combination with the electrocardiogram analysis model and the mapping table is as follows: Input the electrocardiogram data into the electrocardiogram analysis model, after obtaining the preliminary diagnosis conclusion corresponding to the electrocardiogram data, search for the diagnostic conclusion keywords included in the mapping table from the preliminary diagnosis conclusion, and then obtain the electrocardiogram disease type corresponding to the preliminary diagnosis conclusion according to the mapping table, and use the obtained electrocardiogram disease type as the preliminary analysis disease type corresponding to the report.

[0018] Furthermore, step S4 specifically includes: Judging whether the actual diagnosis disease type and the preliminary analysis disease type corresponding to each report are consistent; Set all the consistent reports as accurate diagnosis reports, and use the corresponding actual diagnosis disease type as the electrocardiogram disease type to which the report belongs; For all the inconsistent reports, obtain the corresponding expert diagnosis results, and after obtaining the electrocardiogram disease type to which the report belongs based on the expert diagnosis results in combination with the mapping table, judge whether the actual diagnosis disease type corresponding to the report is consistent with the electrocardiogram disease type to which the report belongs. If they are consistent, then determine that the report belongs to an accurate diagnosis report; If they are inconsistent, then determine that the report belongs to an inaccurate diagnosis report.

[0019] Further, the calculation formula for the matching degree S of remote diagnosticians is as follows:

[0020]

[0021] Among them, i represents the serial number of the electrocardiogram disease type included in the pre-analyzed disease, n represents the total number of electrocardiogram disease types included in the pre-analyzed disease, and R i represents the diagnostic accuracy rate of the remote diagnostician for the i-th electrocardiogram disease type, and T i represents the diagnostic timeliness of the remote diagnostician for the i-th electrocardiogram disease type. R represents the benchmark diagnostic accuracy rate, T represents the benchmark diagnostic timeliness, λ1 represents the diagnostic accuracy rate weight, and λ2 represents the diagnostic timeliness weight.

[0022] Further, the calculation formula for the diagnostic timeliness is as follows:

[0023]

[0024] Among them, T i represents the diagnostic timeliness of the remote diagnostician for the i-th electrocardiogram disease type, and T ij represents the diagnostic time consumption of the j-th diagnostic accurate report corresponding to the i-th electrocardiogram disease type. j represents the report serial number of the diagnostic accurate report corresponding to the i-th electrocardiogram disease type, and m represents the number of reports of the diagnostic accurate report corresponding to the i-th electrocardiogram disease type.

[0025] Further, the calculation formula for the diagnostic accuracy rate is as follows:

[0026] R i = A / (A + B)

[0027] Among them, R i represents the diagnostic accuracy rate of the remote diagnostician for the i-th electrocardiogram disease type. A represents the number of diagnostic accurate reports in the reports of the remote diagnostician corresponding to the i-th electrocardiogram disease type, and B represents the number of diagnostic inaccurate reports in the reports of the remote diagnostician corresponding to the i-th electrocardiogram disease type.

[0028] An electrocardiogram remote diagnosis scheduling terminal device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method in the above embodiments of the present invention are implemented.

[0029] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method in the above embodiments of the present invention are implemented.

[0030] With the above technical solution, the present invention can send the cases requiring remote diagnosis to the diagnostician with the highest matching degree for diagnosis, improving the accuracy and timeliness of the diagnosis results, and thus improving the diagnosis efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 The flowchart of the method according to the first embodiment of the present invention is shown. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0032] To further illustrate each embodiment, the present invention provides drawings. These drawings are part of the disclosure of the present invention, mainly used to illustrate the embodiments, and can be used to explain the operation principle of the embodiments in conjunction with the relevant descriptions in the specification. With reference to these contents, those of ordinary skill in the art should be able to understand other possible implementation manners and the advantages of the present invention.

[0033] The present invention will be further described below in conjunction with the drawings and specific embodiments.

[0034] Embodiment 1:

[0035] The embodiment of the present invention provides a method for electrocardiogram remote diagnosis scheduling, as Figure 1 shown, the method includes the following steps:

[0036] S1: Construct a mapping table representing the mapping relationship between electrocardiogram disease categories and diagnosis conclusion keywords.

[0037] The mapping table constructed in this embodiment is shown in Table 1. The corresponding categories include 9 types. The first column in Table 1 is the category code, the second column is the category name, and the third column is the diagnosis conclusion keyword. The electrocardiogram disease category to which the diagnosis report belongs can be judged through the diagnosis result keyword.

[0038] Table 1

[0039]

[0040]

[0041] S2: Receive the historical electrocardiogram diagnosis reports of each remote diagnostician (hereinafter simply referred to as reports for convenience).

[0042] The historical electrocardiogram reports can collect the electrocardiogram diagnosis reports of all remote diagnosticians within a certain fixed historical time range. The report information corresponding to the obtained reports includes electrocardiogram data, diagnosticians, acceptance time, diagnosis result submission time, and diagnosis conclusion. Among them, the diagnosis timeliness can be obtained according to the time difference between the acceptance time and the diagnosis result submission time. Table 2 shows the report information of three reports of a diagnostician DR1.

[0043] Table 2

[0044] Report Diagnostician Acceptance Time Diagnosis Result Submission Time Diagnostic Conclusion B1 DR1 09:00:00 09:00:10 Sinus Rhythm, Complete Right Bundle Branch Block B2 DR1 09:01:00 09:01:20 Sinus Rhythm, Incomplete Right Bundle Branch Block B3 DR1 09:02:00 09:02:40 Sinus Rhythm, Normal Electrocardiogram

[0045] S3: For each report, based on the diagnosis conclusion therein and in combination with the mapping table, obtain the actual diagnosed disease type corresponding to the report; based on the electrocardiogram data therein and in combination with the electrocardiogram analysis model and the mapping table, obtain the pre-analyzed disease type corresponding to the report.

[0046] In this embodiment, the method for obtaining the actual diagnosed disease type corresponding to the report based on the diagnosis conclusion therein and in combination with the mapping table is as follows: Search for the diagnosis conclusion keywords included in the mapping table from the diagnosis conclusion, and then obtain the corresponding electrocardiogram disease category according to the mapping table based on the diagnosis conclusion keywords, and use the obtained electrocardiogram disease category as the actual diagnosed disease type corresponding to the report.

[0047] The diagnosis conclusion keywords and the actual diagnosed disease types corresponding to each report obtained based on the diagnosis conclusions of the 3 reports in Table 2 are shown in Table 3.

[0048] Table 3

[0049]

[0050]

[0051] In this embodiment, the method for obtaining the pre-analyzed disease type corresponding to the report based on the electrocardiogram data therein and in combination with the electrocardiogram analysis model and the mapping table is as follows: Input the electrocardiogram data into the electrocardiogram analysis model. After obtaining the pre-diagnosis conclusion corresponding to the electrocardiogram data, search for the diagnosis conclusion keywords included in the mapping table from the pre-diagnosis conclusion, and then obtain the corresponding electrocardiogram disease category according to the mapping table based on the pre-diagnosis conclusion, and use the obtained electrocardiogram disease category as the pre-analyzed disease type corresponding to the report. The electrocardiogram analysis model can adopt an existing model, such as CardioAI.

[0052] The diagnosis conclusion keywords and the pre-analyzed disease types corresponding to each report obtained through the electrocardiogram analysis model based on the electrocardiogram data corresponding to the 3 reports in Table 2 are shown in Table 4.

[0053] Table 4

[0054]

[0055] S4: According to the actual diagnosed disease type and the pre-analyzed disease type corresponding to each report, and in combination with the expert diagnosis result of the report, determine whether the report belongs to an accurately diagnosed report and determine the electrocardiogram disease category to which each report belongs.

[0056] Reports where the actual diagnosed disease type and the pre-analyzed disease type are inconsistent need to be sent to experts for diagnosis. After the expert diagnosis result is to send the corresponding electrocardiogram data of the report to the expert, the expert's detection result for this electrocardiogram data is used to find the diagnostic conclusion keywords included in the mapping table from the expert diagnosis result. Then, according to the mapping table, the electrocardiogram disease type corresponding to the expert diagnosis result can be obtained.

[0057] The above situations include three types, specifically as follows:

[0058] If the actual diagnosed disease type and the pre-analyzed disease type are consistent, it is determined that the diagnosis is accurate.

[0059] If the actual diagnosed disease type and the pre-analyzed disease type are inconsistent but consistent with the expert diagnosis, it is determined that the diagnosis is accurate.

[0060] If the actual diagnosed disease type and the pre-analyzed disease type are inconsistent and inconsistent with the expert diagnosis, it is determined that the diagnosis is inaccurate.

[0061] In this embodiment, the specific implementation manner of step S4 is as follows: Determine whether the actual diagnosed disease type and the pre-analyzed disease type corresponding to each report are consistent; Set all consistent reports as accurately diagnosed reports, and use the corresponding actual diagnosed disease type as the electrocardiogram disease type to which the report belongs; For all inconsistent reports, obtain the corresponding expert diagnosis result, and after obtaining the electrocardiogram disease type to which the report belongs based on the expert diagnosis result in combination with the mapping table, determine whether the actual diagnosed disease type corresponding to the report is consistent with the electrocardiogram disease type to which it belongs. If they are consistent, it is determined that the report belongs to the accurately diagnosed report; If they are inconsistent, it is determined that the report belongs to the inaccurately diagnosed report.

[0062] The situation of whether the actual diagnosed disease type and the pre-analyzed disease type of the 3 reports in Table 2 are consistent is shown in Table 5.

[0063] Table 5

[0064] Report Actual Diagnosed Disease Pre-Analyzed Disease Whether Consistent B1 Right Bundle Branch Block Right Bundle Branch Block Consistent B2 Right Bundle Branch Block Normal Electrocardiogram Inconsistent B3 Normal Electrocardiogram Right Bundle Branch Block Inconsistent

[0065] The result of whether it belongs to the accurately diagnosed report after combining the expert diagnosis result is shown in Table 6.

[0066] Table 6

[0067] Report Actual Diagnosed Disease Pre-Analyzed Disease Expert-Diagnosed Disease Whether the Diagnosis is Accurate B2 Right Bundle Branch Block Normal Electrocardiogram Right Bundle Branch Block Accurate B3 Normal Electrocardiogram Right Bundle Branch Block Right Bundle Branch Block Inaccurate

[0068] S5: Classify all the reports corresponding to each remote diagnostician according to the electrocardiogram disease type to which they belong.

[0069] S6: Calculate the diagnostic accuracy rate of each remote diagnostician for each type of electrocardiogram disease based on the ratio of the number of accurate diagnosis reports among all reports included in the various electrocardiogram disease categories corresponding to each remote diagnostician; calculate the diagnostic timeliness of each remote diagnostician for each type of electrocardiogram disease based on the diagnostic time consumption and quantity of the accurate diagnosis reports among all reports included in the various electrocardiogram disease categories corresponding to each remote diagnostician.

[0070] In this embodiment, the calculation formula for the diagnostic accuracy rate is:

[0071] R i = A / (A + B)

[0072] Wherein, R i represents the diagnostic accuracy rate of the remote diagnostician for the i-th type of electrocardiogram disease, A represents the number of accurate diagnosis reports among the reports corresponding to the i-th type of electrocardiogram disease of the remote diagnostician, and B represents the number of inaccurate diagnosis reports among the reports corresponding to the i-th type of electrocardiogram disease of the remote diagnostician.

[0073] The calculation formula for the diagnostic timeliness (only accurate diagnosis reports are used to calculate the diagnostic timeliness) is:

[0074]

[0075] Wherein, T i represents the diagnostic timeliness of the remote diagnostician for the i-th type of electrocardiogram disease, T ij represents the diagnostic time consumption (in seconds) (diagnosis result submission time - acceptance time) of the j-th accurate diagnosis report corresponding to the i-th type of electrocardiogram disease, j represents the report serial number of the accurate diagnosis report corresponding to the i-th type of electrocardiogram disease, and m represents the number of accurate diagnosis reports corresponding to the i-th type of electrocardiogram disease.

[0076] The diagnostic time consumptions corresponding to the 3 reports in Table 2 are shown in Table 7.

[0077] Table 7

[0078] Report Reported Disease Whether the Diagnosis is Accurate Diagnosis Time Consumption B1 Right Bundle Branch Block Accurate 10s B2 Right Bundle Branch Block Accurate 20s B3 Right Bundle Branch Block Inaccurate

[0079] Through the above formula in this embodiment, it can be calculated that the diagnostic accuracy rate of DR1 for the disease "right bundle branch block" is 2 / (2 + 1) = 67%, and the diagnostic timeliness is (10 + 20) / 2 = 15 s.

[0080] The diagnostic accuracy rates and diagnostic timeliness of each type of electrocardiogram disease calculated for the three diagnosticians DR1, DR2, and DR3 in this embodiment are shown in Tables 8 and 9.

[0081] Table 8

[0082]

[0083] Table 9

[0084]

[0085] S7: When remote diagnosis of electrocardiogram data is required, after obtaining the preliminary diagnosis conclusion of the electrocardiogram data through the electrocardiogram analysis model, look up the preliminary analysis disease types corresponding to the electrocardiogram data according to the mapping table.

[0086] The electrocardiogram analysis model used in step S7 can be the same as or different from the one used in step S3. The finally obtained preliminary analysis disease types can be one or multiple. For example, when the electrocardiogram data L1 is input into the electrocardiogram analysis model, the preliminary diagnosis conclusion is "complete right bundle branch block, acute inferior wall myocardial infarction". According to the mapping relationship between the electrocardiogram disease type category and the diagnosis conclusion keyword in the mapping table, the identified preliminary analysis disease types are: right bundle branch block and acute myocardial infarction.

[0087] S8: Calculate the matching degree of each remote diagnostician according to the diagnosis accuracy rate and diagnosis timeliness of each remote diagnostician corresponding to the preliminary analysis disease types.

[0088] In this embodiment, the calculation formula for the matching degree S of the remote diagnostician is:

[0089]

[0090] where i represents the serial number of the electrocardiogram disease type category included in the preliminary analysis disease types, n represents the total number of electrocardiogram disease type categories included in the preliminary analysis disease types, R i represents the diagnosis accuracy rate of the remote diagnostician for the i-th electrocardiogram disease type category, T i represents the diagnosis timeliness of the remote diagnostician for the i-th electrocardiogram disease type category, R represents the benchmark diagnosis accuracy rate, T represents the benchmark diagnosis timeliness, λ1 represents the diagnosis accuracy rate weight, and λ2 represents the diagnosis timeliness weight.

[0091] Suppose the preliminary analysis disease types corresponding to the electrocardiogram data L1 include two disease types A1 and A2, and the diagnosis accuracy rates of a certain remote diagnostician for the two disease types are A1-r and A2-r respectively, and the diagnosis timeliness are A1-t and A2-t respectively. Then the matching degree S formula of this remote diagnostician = λ1*((A1-r / R)+(A2-t / R)) - λ2*((T / A1-t)+(T / A2-t)).

[0092] In this embodiment, the benchmark diagnosis accuracy rate R = 50%, the benchmark diagnosis timeliness T = 30s, the diagnosis accuracy rate weight λ1 = 1.8, and the diagnosis timeliness weight λ2 = 1. In other embodiments, those skilled in the art can set them according to requirements, which are not limited here.

[0093] The matching degrees of the two pre - analyzed disease types corresponding to the electrocardiogram data L1 calculated by the above formula with doctors DR1, DR2, and DR3 are shown in Table 10.

[0094] Table 10

[0095] Diagnostician A1-r A1-t A2-r A2-t Match Degree D1 67％ 15s 73％ 23s 3.77 D2 79％ 37s 89％ 31s 3.78 D3 78％ 69s 77％ 70s 0.95

[0096] S9: Send the electrocardiogram data to the remote diagnostician with the highest matching degree for diagnosis.

[0097] After sorting in ascending order of the matching degree, it can be concluded that the matching degree of diagnostician D2 is the highest. Therefore, the electrocardiogram data that needs to be remotely diagnosed is sent to diagnostician D2 for diagnosis.

[0098] Based on constructing the mapping between the electrocardiogram disease types and the keywords of the diagnosis conclusion in the embodiment of the present invention, the corresponding actual diagnosis disease types and pre - analyzed disease types are obtained for the reports of the diagnosticians. Furthermore, the diagnostic accuracy rate and diagnostic timeliness of the diagnosticians for different disease types are evaluated, and in combination with the pre - analyzed disease types obtained by the electrocardiogram analysis model, the matching degrees of the cases to be diagnosed with each diagnostician are calculated, and the cases are scheduled to the diagnostician with the highest matching degree for diagnosis.

[0099] Embodiment Two:

[0100] The present invention also provides an electrocardiogram remote diagnosis scheduling terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above - mentioned method embodiment of Embodiment One of the present invention are implemented.

[0101] Furthermore, as an executable solution, the electrocardiogram remote diagnosis scheduling terminal device can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The electrocardiogram remote diagnosis scheduling terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above - described composition structure of the electrocardiogram remote diagnosis scheduling terminal device is only an example of the electrocardiogram remote diagnosis scheduling terminal device, and does not constitute a limitation on the electrocardiogram remote diagnosis scheduling terminal device. It may include more or fewer components than the above, or combine some components, or different components. For example, the electrocardiogram remote diagnosis scheduling terminal device may also include input and output devices, network access devices, a bus, etc. The embodiment of the present invention does not make a limitation on this.

[0102] Further, as an executable solution, the so-called processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the electrocardiogram remote diagnosis scheduling terminal device, and connects various parts of the entire electrocardiogram remote diagnosis scheduling terminal device through various interfaces and lines.

[0103] The memory can be used to store the computer program and / or module. The processor realizes various functions of the electrocardiogram remote diagnosis scheduling terminal device by running or executing the computer program and / or module stored in the memory, and by calling the data stored in the memory. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store the operating system and application programs required for at least one function; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, at least one magnetic disk storage device, flash device, or other volatile solid-state storage devices.

[0104] The present invention also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the method in the above embodiments of the present invention are implemented.

[0105] If the modules / units integrated in the electrocardiogram remote diagnosis scheduling terminal device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), and software distribution medium, etc.

[0106] Although the present invention has been specifically shown and described in conjunction with the preferred embodiments, those skilled in the art should understand that various changes can be made to the present invention in terms of form and details without departing from the spirit and scope of the present invention defined by the appended claims, and all such changes are within the protection scope of the present invention.

Claims

1. A remote ECG diagnosis and scheduling method, characterized in that: The following steps are involved: S1: Construct a mapping table representing the mapping relationship between ECG disease categories and diagnosis conclusion keywords; S2: Receive historical ECG diagnostic reports from each remote diagnostician; S3: For each report, based on the diagnosis conclusion and the mapping table, the actual diagnosed disease type corresponding to the report is obtained; based on the electrocardiogram data, the electrocardiogram analysis model and the mapping table are combined to obtain the pre-analyzed disease type corresponding to the report; S4: Based on the actual diagnosed diseases and pre-analyzed diseases corresponding to each report, combined with the expert diagnosis results of the report, determine whether the report is an accurate diagnosis report, and determine the ECG disease category to which each report belongs; S5: classify all reports corresponding to each remote diagnosis personnel according to the type of electrocardiographic disease they belong to; S6: Based on the ratio of the number of accurate diagnosis reports in all reports included in each category of ECG disease corresponding to each remote diagnostic personnel, the diagnostic accuracy rate of each remote diagnostic personnel for each category of ECG disease is calculated; based on the diagnostic time and number of accurate diagnosis reports in all reports included in each category of ECG disease corresponding to each remote diagnostic personnel, the diagnostic timeliness of each remote diagnostic personnel for each category of ECG disease is calculated; S7: When it is necessary to perform remote diagnosis on the electrocardiogram data, after obtaining the pre-diagnosis conclusion of the electrocardiogram data through the electrocardiogram analysis model, the pre-analysis disease type corresponding to the electrocardiogram data is searched according to the mapping table; S8: Calculate the matching degree of each remote diagnosis personnel according to the diagnosis accuracy and diagnosis time efficiency of each remote diagnosis personnel corresponding to the pre-analyzed disease type; S9: Send the ECG data to the remote diagnostician with the highest matching degree for diagnosis.

2. The ECG remote diagnosis and dispatching method according to claim 1, characterized in that: Based on the diagnostic conclusion and the mapping table, the method for obtaining the actual diagnosed disease type corresponding to the report is as follows: search for the diagnostic conclusion keywords contained in the mapping table from the diagnostic conclusion, and then obtain the corresponding ECG disease type according to the diagnostic conclusion keywords in the mapping table, and use the obtained ECG disease type as the actual diagnosed disease type corresponding to the report.

3. The ECG remote diagnosis and dispatching method according to claim 1, characterized in that: Based on the ECG data, combined with the ECG analysis model and the mapping table, the method for obtaining the pre-analysis disease type corresponding to the report is: input the ECG data into the ECG analysis model, and after obtaining the pre-diagnosis conclusion corresponding to the ECG data, search the pre-diagnosis conclusion keywords contained in the mapping table from the pre-diagnosis conclusion, and then obtain the ECG disease type category corresponding to the pre-diagnosis conclusion according to the mapping table, and use the obtained ECG disease type category as the pre-analysis disease type corresponding to the report.

4. The ECG remote diagnosis and dispatching method according to claim 1, characterized in that: Step S4 specifically includes: determining whether the actual diagnosed disease and pre-analyzed disease corresponding to each report are consistent; setting all consistent reports to be accurately diagnosed reports, and using the corresponding actually diagnosed disease as the ECG disease category to which the report belongs; for all inconsistent reports, obtaining the corresponding expert diagnosis results, and based on the expert diagnosis results combined with the mapping table to obtain the ECG disease category to which the report belongs, determining whether the actual diagnosed disease corresponding to the report is consistent with the ECG disease category to which it belongs, if they are consistent, determining that the report is an accurately diagnosed report; if they are inconsistent, determining that the report is an inaccurately diagnosed report.

5. The ECG remote diagnosis and dispatching method according to claim 1, characterized in that: The calculation formula of the matching degree S of remote diagnosis personnel is: Among them, i represents the serial number of the ECG disease category included in the pre-analysis disease category, n represents the total number of ECG disease categories included in the pre-analysis disease category, R i represents the diagnostic accuracy of the remote diagnostic personnel for the i-th ECG disease category, T i It represents the diagnostic time of the remote diagnostic personnel for the i-th ECG disease category, R represents the benchmark diagnostic accuracy, T represents the benchmark diagnostic time, λ1 represents the diagnostic accuracy weight, and λ2 represents the diagnostic time weight.

6. The ECG remote diagnosis and dispatching method according to claim 1, characterized in that: The calculation formula for diagnostic time is: Among them, T i represents the diagnostic time of the remote diagnostic personnel for the i-th ECG disease category, T ij represents the diagnostic time of the jth report with accurate diagnosis corresponding to the ith ECG disease category, j represents the report serial number of the report with accurate diagnosis corresponding to the ith ECG disease category, and m represents the number of reports with accurate diagnosis corresponding to the ith ECG disease category.

7. The ECG remote diagnosis and dispatching method according to claim 1, characterized in that: The formula for calculating the diagnostic accuracy is: R i =A(A+B) Among them, R i represents the diagnostic accuracy of the remote diagnostic personnel for the i-th ECG disease category, A represents the number of accurate diagnostic reports in the reports of the remote diagnostic personnel for the i-th ECG disease category, and B represents the number of inaccurate diagnostic reports in the reports of the remote diagnostic personnel for the i-th ECG disease category.

8. An ECG remote diagnosis and dispatch terminal device, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 7 when executing the computer program.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images