Rare disease follow-up visit data processing system

Abstract

The invention relates to the technical field of medical data processing, in particular to a rare disease follow-up visit data processing system which is used for improving the acquisition efficiency of rare disease follow-up visit data. According to the main scheme, the method comprises the steps of determining a follow-up visit data change curve and an expected data change curve according to patient follow-up visit data of each period transmitted by a patient client and expected medical data corresponding to each treatment period in a rare disease database; according to the follow-up data change curve, the expected data change curve and a follow-up data period prediction model, determining the acquisition time of follow-up data of the next period; according to the acquisition time of the follow-up visit data of the next period and the patient follow-up visit data of each treatment period transmitted by the patient client, revising the follow-up visit demand item of the current period to obtain a final follow-up visit demand item; and sending the final follow-up visit demand item to a patient client of the target patient, so that the target patient fills in patient follow-up visit data according to the final follow-up visit demand item.

Description

Technical Field

[0001] The present application relates to the technical field of medical data processing, and in particular to a rare disease follow-up data processing system. Background Art

[0002] Rare diseases refer to diseases with extremely low prevalence, usually less than 5 people per 100,000. Since there are relatively few patients with rare diseases, it is more difficult to study and treat them. There are currently more than 7,000 known rare diseases, most of which are hereditary diseases caused by gene mutations.

[0003] Due to the low incidence of rare diseases, many patients and doctors lack knowledge and understanding of them, which also leads to great difficulties for patients with rare diseases in diagnosis, treatment and rehabilitation. At present, patients are required to upload rare disease follow-up data regularly so that doctors can diagnose and treat based on the uploaded rare disease follow-up data. The uploaded rare disease follow-up data is only uploaded within a certain period of time, which may delay the upload time, and the uploaded rare disease follow-up data may not be the data currently needed by the doctor. Summary of the invention

[0004] In view of this, the present application provides a rare disease follow-up data processing system for improving the efficiency of obtaining rare disease follow-up data.

[0005] In a first aspect, an embodiment of the present application provides a rare disease follow-up data processing system, the system comprising: a patient client, a doctor client, and a follow-up data processing server, the follow-up data processing server comprising: a memory and at least one processor, the memory storing a computer program, the at least one processor being configured to implement the following steps when executing the computer program:

[0006] Obtaining a corresponding rare disease database according to the type of rare disease suffered by the target patient, wherein the rare disease database includes a follow-up requirement template and expected medical data corresponding to each treatment cycle;

[0007] Transmitting the follow-up requirement template corresponding to the current treatment cycle of the target patient to the doctor client of the attending physician corresponding to the target patient, so that the doctor client selects the follow-up requirement items of the current cycle according to the follow-up requirement template;

[0008] Determine a follow-up data change curve and an expected data change curve according to the patient follow-up data of each cycle transmitted by the patient client and the expected medical data corresponding to each treatment cycle in the rare disease database;

[0009] Determining the acquisition time of the next cycle of follow-up data according to the follow-up data change curve, the expected data change curve and the follow-up data cycle prediction model;

[0010] According to the acquisition time of the follow-up data of the next cycle and the patient follow-up data of each treatment cycle transmitted by the patient client, the follow-up requirement items of the current cycle are revised to obtain the final follow-up requirement items;

[0011] When the acquisition time of the next cycle follow-up data arrives, the final follow-up requirement items are sent to the patient client of the target patient, so that the target patient fills in the patient follow-up data according to the final follow-up requirement items.

[0012] Optionally, determining the follow-up data change curve and the expected data change curve according to the patient follow-up data of each cycle transmitted by the patient client and the expected medical data corresponding to each treatment cycle in the rare disease database includes:

[0013] Obtaining the follow-up data change curve according to the data change of the patient follow-up data of each period transmitted by the patient client;

[0014] The expected data change curve is obtained by performing linear fitting based on the expected medical data corresponding to each treatment cycle in the rare disease database.

[0015] Optionally, determining the acquisition time of the follow-up data of the next cycle according to the follow-up data change curve, the expected data change curve and the follow-up data cycle prediction model includes:

[0016] Calculate the data difference of the most recent cycle through the follow-up data change curve and the expected data change curve;

[0017] The follow-up data change curve, the expected data change curve and the data difference of the most recent cycle are input into the first follow-up data cycle prediction model to obtain the acquisition time of the next cycle follow-up data.

[0018] Optionally, determining the acquisition time of the follow-up data of the next cycle according to the follow-up data change curve, the expected data change curve and the follow-up data cycle prediction model includes:

[0019] Inputting the follow-up data change curve into the second follow-up data cycle prediction model to predict the follow-up data of the next cycle;

[0020] Calculate the data difference of the next cycle according to the predicted follow-up data of the next cycle and the expected data of the next cycle corresponding to the expected data change curve;

[0021] The acquisition time of the follow-up data of the next cycle is determined according to the data difference of the next cycle.

[0022] Optionally, inputting the follow-up data change curve, the expected data change curve, and the data difference of the most recent cycle into a first follow-up data cycle prediction model to obtain the acquisition time of the follow-up data of the next cycle includes:

[0023] Inputting the follow-up data change curve, the expected data change curve and the data difference of the most recent period into the input layer of the first follow-up data period prediction model;

[0024] The input layer inputs the follow-up data change curve and the data difference of the most recent period into the first neural network structure to obtain a first prediction value;

[0025] The input layer inputs the expected data change curve and the data difference of the most recent period into the second neural network structure to obtain a second prediction value;

[0026] The acquisition time of the next cycle follow-up data is obtained according to the first prediction value and the second prediction value.

[0027] Optionally, obtaining the acquisition time of the next cycle follow-up data according to the first prediction value and the second prediction value includes:

[0028] The first predicted value and the second predicted value are weighted calculated or averaged to obtain the acquisition time of the next cycle follow-up data.

[0029] Optionally, the training process of the first follow-up data period prediction model is:

[0030] Acquire sample data and corresponding sample labels, wherein the sample data includes a sample follow-up data change curve and a sample expected data change curve;

[0031] Calculate the sample data difference of the most recent period according to the sample follow-up data change curve and the sample expected data change curve;

[0032] Inputting the sample follow-up data change curve, the sample expected data change curve, and the sample data difference of the most recent period into the first follow-up data period prediction model to obtain a first prediction value and a second prediction value;

[0033] Calculate a loss value according to the first predicted value, the second predicted value, and the sample label;

[0034] When the loss value is less than a preset value, the training of the first follow-up data period prediction model is stopped.

[0035] Optionally, the following steps are performed to revise the follow-up requirements of the current cycle according to the acquisition time of the follow-up data of the next cycle and the patient follow-up data of each treatment cycle transmitted by the patient client to obtain the final follow-up requirements, including:

[0036] Calculate the time difference according to the acquisition time of the next cycle follow-up data and the acquisition time of the previous cycle follow-up data;

[0037] If the time difference is less than a preset value, the follow-up requirement items of the current cycle are revised according to the follow-up requirement items of the previous cycle to obtain the final follow-up requirement items;

[0038] If the time difference is greater than or equal to the preset value, determining the need for data change exceeding the preset range through the patient follow-up data of each treatment cycle transmitted by the patient client;

[0039] According to the demand items whose change range exceeds the preset range, the follow-up demand items of the current cycle are revised to obtain the final follow-up demand items.

[0040] Optionally, the step of revising the follow-up requirement items of the current cycle according to the requirement items whose change range exceeds a preset range to obtain final follow-up requirement items includes:

[0041] The demand items whose change amplitude exceeds the preset amplitude are added to the follow-up demand items of the current cycle to obtain the final follow-up demand items.

[0042] In a second aspect, an embodiment of the present application further provides a follow-up data processing server, the follow-up data processing server comprising:

[0043] An acquisition module, used to acquire a corresponding rare disease database according to the type of rare disease suffered by the target patient, wherein the rare disease database includes a follow-up requirement template and expected medical data corresponding to each treatment cycle;

[0044] A transmission module, used for transmitting the follow-up requirement template corresponding to the current treatment cycle of the target patient to the doctor client of the attending physician corresponding to the target patient, so that the doctor client selects the follow-up requirement items of the current cycle according to the follow-up requirement template;

[0045] A determination module, configured to determine a follow-up data change curve and an expected data change curve according to the patient follow-up data of each cycle transmitted by the patient client and the expected medical data corresponding to each treatment cycle in the rare disease database;

[0046] A prediction module, used to determine the acquisition time of the follow-up data of the next cycle according to the follow-up data change curve, the expected data change curve and the follow-up data cycle prediction model;

[0047] A revision module, configured to revise the follow-up requirement items of the current cycle to obtain final follow-up requirement items according to the acquisition time of the follow-up data of the next cycle and the patient follow-up data of each treatment cycle transmitted by the patient client;

[0048] The sending module is used to send the final follow-up requirement items to the patient client of the target patient when the acquisition time of the next cycle follow-up data arrives, so that the target patient fills in the patient follow-up data according to the final follow-up requirement items.

[0049] An embodiment of the present application provides a rare disease follow-up data processing system, which includes: a patient client, a doctor client, and a follow-up data processing server. The follow-up data processing server first obtains the corresponding rare disease database according to the type of rare disease suffered by the target patient, and the rare disease database includes the follow-up demand template and expected medical data corresponding to each treatment cycle. Then, the follow-up demand template corresponding to the current treatment cycle of the target patient is transmitted to the doctor client of the attending physician corresponding to the target patient, so that the doctor client selects the follow-up demand items of the current cycle according to the follow-up demand template. Then, according to the patient follow-up data of each cycle transmitted by the patient client and the expected medical data corresponding to each treatment cycle in the rare disease database, the follow-up data change curve and the expected data change curve are determined, and the acquisition time of the follow-up data of the next cycle is determined according to the follow-up data change curve, the expected data change curve and the follow-up data cycle prediction model. Finally, according to the acquisition time of the follow-up data of the next cycle and the patient follow-up data of each treatment cycle transmitted by the patient client, the follow-up demand items of the current cycle are revised to obtain the final follow-up demand items, and when the acquisition time of the follow-up data of the next cycle is reached, the final follow-up demand items are sent to the patient client of the target patient, so that the target patient fills in the patient follow-up data according to the final follow-up demand items. Compared with the prior art in which patients upload fixed follow-up data at a certain period, the present application determines the time for obtaining the follow-up data of the next period and the follow-up requirements based on the patient follow-up data of the target patient's current treatment period and historical periods, so that the patient follow-up data obtained by the present application meets the data requirements of the current period, thereby improving the efficiency of obtaining follow-up data for rare diseases through the present application.

[0050] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 A flow chart of a method for processing follow-up data of a rare disease provided in an embodiment of the present application is shown;

[0053] Figure 2 A training flow chart of a first follow-up data cycle prediction model provided in an embodiment of the present application is shown;

[0054] Figure 3 A structural block diagram of a follow-up data processing server provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0055] The terms "first", "second", "third", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects rather than to limit a specific order.

[0056] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way for easy understanding.

[0057] In the description of this application, unless otherwise specified, " / " indicates that the objects associated before and after are in an "or" relationship, for example, A / B can represent A or B; "and / or" in this application is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. In addition, in the description of this application, unless otherwise specified, "multiple" refers to two or more than two. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0058] In the embodiments of the present application, at least one can also be described as one or more, and multiple can be two, three, four or more, which is not limited in the present application.

[0059] The embodiment of the present application provides a rare disease follow-up data processing system, the system comprising: a patient client, a doctor client, and a follow-up data processing server. The follow-up data processing server comprises a memory and at least one processor, the memory stores a computer program, and the at least one processor is configured to implement a rare disease follow-up data processing method when executing the computer program, such as Figure 1 The method shown includes the following steps S101-S106:

[0060] S101. Obtain a corresponding rare disease database according to the type of rare disease suffered by the target patient.

[0061] Among them, different types of rare diseases correspond to different rare disease databases. The rare disease database includes follow-up demand templates and expected medical data corresponding to each treatment cycle. The treatment cycle in the rare disease database can be set according to actual needs, such as one month as a treatment cycle or one week as a treatment cycle. The treatment cycle can be of fixed length or dynamically adjusted; the follow-up demand template is set according to the treatment cycle of the corresponding rare disease type. The follow-up demand template includes pre-set follow-up demand items corresponding to different treatment cycles for the attending physician to choose. The follow-up demand items are the follow-up data that the patient needs to upload, and the follow-up data is various physical test data that need to be monitored for the corresponding rare disease type.

[0062] The rare disease type in this embodiment refers to a disease with a relatively low incidence rate, which may specifically be albinism, acromegaly, spinal muscular atrophy, etc. This embodiment does not make any specific limitations on this.

[0063] S102: Transmit the follow-up requirement template corresponding to the current treatment cycle of the target patient to the doctor client of the attending physician corresponding to the target patient, so that the doctor client selects the follow-up requirement items of the current cycle according to the follow-up requirement template.

[0064] Specifically, the doctor client can be installed on a mobile device or a computer, and the doctor client can display the follow-up requirement template corresponding to the current treatment cycle of the target patient, and the attending physician selects the follow-up requirement items required for the current cycle in the follow-up requirement template. Among them, the follow-up requirement items are follow-up data that the target patient needs to provide, which can specifically be heart rate, blood pressure, weight change, pain status, etc., which are not specifically limited in this embodiment.

[0065] S103. Determine a follow-up data change curve and an expected data change curve according to the patient follow-up data of each cycle transmitted by the patient client and the expected medical data corresponding to each treatment cycle in the rare disease database.

[0066] The follow-up data change curve can be determined based on the data changes of the follow-up data of the patients in each cycle, and the expected data change curve can be obtained by fitting the expected medical data of each treatment cycle. It should be noted that the expected medical data of each treatment cycle can be the medical data of multiple patients with the same rare disease in each treatment cycle, that is, the expected medical data is determined by fitting the medical data of multiple patients in each treatment cycle.

[0067] In an optional embodiment provided in the present application, the follow-up data change curve and the expected data change curve are determined based on the patient follow-up data of each cycle transmitted by the patient client and the expected medical data corresponding to each treatment cycle in the rare disease database, including: obtaining the follow-up data change curve based on the data changes of the patient follow-up data of each cycle transmitted by the patient client; and obtaining the expected data change curve by performing linear fitting based on the expected medical data corresponding to each treatment cycle in the rare disease database.

[0068] Specifically, this embodiment mainly determines the data change curve of the corresponding data item based on the data change of each data item in the patient follow-up data. For example, if the patient follow-up data includes blood pressure and blood lipids, it is necessary to generate a blood pressure data change curve and a blood lipid data change curve; similarly, the expected data change curve is also generated for each data in the medical data. For example, the expected blood pressure data change curve is obtained by linearly fitting the blood pressure data of all patients in each cycle. The expected blood pressure data change curve can represent the blood pressure changes corresponding to most patients in each treatment cycle. This embodiment can determine whether the treatment effect of the target patient in each treatment cycle meets expectations by comparing the follow-up data change curve and the expected change data curve.

[0069] S104: Determine the time for obtaining the follow-up data of the next cycle according to the follow-up data change curve, the expected data change curve and the follow-up data cycle prediction model.

[0070] In an optional embodiment provided in the present application, determining the acquisition time of the next cycle of follow-up data according to the follow-up data change curve, the expected data change curve and the follow-up data cycle prediction model includes:

[0071] S1041. Calculate the data difference of the most recent cycle through the follow-up data change curve and the expected data change curve.

[0072] For example, if the most recent cycle is the third treatment cycle, the data of all time points in the third treatment cycle are first obtained, and then the data of all time points are calculated to obtain the average value, and then the data difference of the most recent cycle in the follow-up data change curve and the expected data change curve is calculated based on the average value.

[0073] S1042: Input the follow-up data change curve, the expected data change curve, and the data difference of the most recent cycle into the first follow-up data cycle prediction model to obtain the acquisition time of the next cycle follow-up data.

[0074] Wherein, the step of inputting the follow-up data change curve, the expected data change curve and the data difference of the most recent cycle into the first follow-up data cycle prediction model to obtain the acquisition time of the follow-up data of the next cycle includes: inputting the follow-up data change curve, the expected data change curve and the data difference of the most recent cycle into the input layer of the first follow-up data cycle prediction model; the input layer inputs the follow-up data change curve and the data difference of the most recent cycle into the first neural network structure to obtain the first prediction value; the input layer inputs the expected data change curve and the data difference of the most recent cycle into the second neural network structure to obtain the second prediction value; and obtaining the acquisition time of the follow-up data of the next cycle according to the first prediction value and the second prediction value. Specifically, obtaining the acquisition time of the follow-up data of the next cycle according to the first prediction value and the second prediction value includes: performing weighted calculation or averaging on the first prediction value and the second prediction value to obtain the acquisition time of the follow-up data of the next cycle.

[0075] It should be noted that, since the follow-up data change curve and the expected data change curve include change curves of various data items, this embodiment requires that the change curves of all data items be input into the first follow-up data period prediction model, and the first prediction value and the second prediction value are obtained through the first neural network structure and the second neural network structure. The first prediction value and the second prediction value include the acquisition time of the next period corresponding to each data item. The final acquisition time is determined for the acquisition time of all data items in the first prediction value, such as taking the average value to obtain the final acquisition time. Finally, the acquisition time of the follow-up data of the next period is calculated according to the final acquisition time in the first prediction value and the final acquisition time in the second prediction value.

[0076] like Figure 2 As shown, this embodiment provides a training method for a first follow-up data period prediction model, and the training process is:

[0077] S201. Obtain sample data and corresponding sample labels, where the sample data includes a sample follow-up data change curve and a sample expected data change curve.

[0078] The sample label is the actual time when the follow-up data of the next cycle is obtained.

[0079] It should be noted that the sample follow-up data change curve and the sample expected data change curve in this embodiment are Figure 1 The determination method of the corresponding steps is the same as that of the embodiment, and will not be repeated here.

[0080] S202: Calculate the sample data difference of the most recent period according to the sample follow-up data change curve and the sample expected data change curve.

[0081] The calculation method of the sample data difference in this embodiment is the same as the calculation method of the above step S1041.

[0082] S203, inputting the sample follow-up data change curve, the sample expected data change curve, and the sample data difference of the most recent period into the first follow-up data period prediction model to obtain a first prediction value and a second prediction value.

[0083] In this embodiment, the sample follow-up data change curve and the sample data difference of the most recent period are input into the first neural network structure to obtain a first prediction value; the sample expected data change curve and the sample data difference of the most recent period are input into the second neural network structure to obtain a second prediction value.

[0084] Among them, the first prediction value and the second prediction value include the acquisition time of the follow-up data of each data item in the next cycle. The first prediction value and the second prediction value can be used to obtain the final acquisition time of the follow-up data of the next cycle according to the average of the acquisition time of the corresponding data items.

[0085] S204: Calculate a loss value according to the first prediction value, the second prediction value, and the sample label.

[0086] In this embodiment, the loss value may be calculated based on the average acquisition time of the first prediction value and the second prediction value, or the loss value may be calculated based on the acquisition time of all data items.

[0087] Specifically, in this embodiment, the loss value can be calculated by the following formula:

[0088]

[0089] Among them, n is the number of sample data, a i is the first predicted value corresponding to the i-th sample data, b i is the second predicted value corresponding to the i-th sample data, y i is the sample label of the i-th sample data.

[0090] S205. When the loss value is less than a preset value, stop training the first follow-up data period prediction model.

[0091] The preset values ​​are data values ​​set according to actual needs.

[0092] In another optional embodiment provided by the present application, determining the acquisition time of the follow-up data of the next cycle according to the follow-up data change curve, the expected data change curve and the follow-up data cycle prediction model includes: inputting the follow-up data change curve into a second follow-up data cycle prediction model to predict the follow-up data of the next cycle; calculating the data difference of the next cycle according to the predicted follow-up data of the next cycle and the expected data of the next cycle corresponding to the expected data change curve; and determining the acquisition time of the follow-up data of the next cycle according to the data difference of the next cycle.

[0093] Among them, the second follow-up data cycle prediction model is a trained neural network model, that is, it is obtained by training according to sample data and sample labels. The sample data is a sample follow-up data change curve, and the sample label is the follow-up data of the next cycle; the second follow-up data cycle prediction model can also be a trained time prediction model, that is, the follow-up data of a period of history is input into the second follow-up data cycle prediction model, and the follow-up data of the next cycle is predicted. After the follow-up data of the next cycle is predicted, the data difference of the next cycle is calculated according to the predicted follow-up data of the next cycle and the expected data change curve corresponding to the expected data The expected data of the next cycle, and then the acquisition time of the follow-up data of the next cycle is determined according to the data difference of the next cycle. Specifically, this embodiment can determine the acquisition time of the follow-up data of the next cycle according to the size of the data difference. The larger the numerical difference, the closer the acquisition time of the western medicine cycle follow-up data is to the current date. The numerical difference is less than or equal to a predetermined value, and the acquisition time of the follow-up data of the next cycle can be determined according to the original time interval.

[0094] S105 , according to the acquisition time of the follow-up data of the next cycle and the patient follow-up data of each treatment cycle transmitted by the patient client, revise the follow-up requirements of the current cycle to obtain the final follow-up requirements.

[0095] In an optional embodiment provided by the present application, the follow-up requirement items of the current cycle are revised to obtain the final follow-up requirement items according to the acquisition time of the follow-up data of the next cycle and the patient follow-up data of each treatment cycle transmitted by the patient client, including:

[0096] S1051. Calculate a time difference according to the acquisition time of the next cycle follow-up data and the acquisition time of the previous cycle follow-up data.

[0097] S1052: If the time difference is less than a preset value, the follow-up requirement items of the current cycle are revised according to the follow-up requirement items of the previous cycle to obtain final follow-up requirement items.

[0098] S1053: If the time difference is greater than or equal to the preset value, determine the requirement items whose data change amplitude exceeds the preset amplitude through the patient follow-up data of each treatment cycle transmitted by the patient client.

[0099] S1054. According to the demand items whose change range exceeds the preset range, revise the follow-up demand items of the current cycle to obtain final follow-up demand items.

[0100] Specifically, according to the requirement items whose change amplitude exceeds the preset amplitude, the follow-up requirement items of the current cycle are revised to obtain the final follow-up requirement items, including: adding the requirement items whose change amplitude exceeds the preset amplitude to the follow-up requirement items of the current cycle to obtain the final follow-up requirement items.

[0101] S106. When the time for obtaining the follow-up data of the next cycle is reached, the final follow-up requirement items are sent to the patient client of the target patient, so that the target patient fills in the patient follow-up data according to the final follow-up requirement items.

[0102] The present embodiment provides a method for processing follow-up data of a rare disease. The follow-up data processing server first obtains a corresponding rare disease database according to the type of rare disease suffered by a target patient, the rare disease database including follow-up requirement templates and expected medical data corresponding to each treatment cycle, and then transmits the follow-up requirement template corresponding to the current treatment cycle of the target patient to the doctor client of the attending physician corresponding to the target patient, so that the doctor client selects the follow-up requirement items of the current cycle according to the follow-up requirement template, and then determines the follow-up data change curve and the expected data change curve according to the patient follow-up data of each cycle transmitted by the patient client and the expected medical data corresponding to each treatment cycle in the rare disease database, and determines the acquisition time of the follow-up data of the next cycle according to the follow-up data change curve, the expected data change curve and the follow-up data cycle prediction model, and finally, according to the acquisition time of the follow-up data of the next cycle and the patient follow-up data of each treatment cycle transmitted by the patient client, the follow-up requirement items of the current cycle are revised to obtain the final follow-up requirement items, and when the acquisition time of the follow-up data of the next cycle is reached, the final follow-up requirement items are sent to the patient client of the target patient, so that the target patient fills in the patient follow-up data according to the final follow-up requirement items. Compared with the prior art in which patients upload fixed follow-up data at a certain period, the present application determines the time for obtaining the follow-up data of the next period and the follow-up requirements based on the patient follow-up data of the target patient's current treatment period and historical periods, so that the patient follow-up data obtained by the present application meets the data requirements of the current period, thereby improving the efficiency of obtaining follow-up data for rare diseases through the present application.

[0103] The present application also provides a follow-up data processing server, such as Figure 3 As shown, the follow-up data processing server may include:

[0104] An acquisition module 31 is used to acquire a corresponding rare disease database according to the type of rare disease suffered by the target patient, wherein the rare disease database includes a follow-up requirement template and expected medical data corresponding to each treatment cycle;

[0105] A transmission module 32, configured to transmit the follow-up requirement template corresponding to the current treatment cycle of the target patient to the doctor client of the attending physician corresponding to the target patient, so that the doctor client selects the follow-up requirement items of the current cycle according to the follow-up requirement template;

[0106] A determination module 33, configured to determine a follow-up data change curve and an expected data change curve according to the patient follow-up data of each cycle transmitted by the patient client and the expected medical data corresponding to each treatment cycle in the rare disease database;

[0107] A prediction module 34, configured to determine the acquisition time of the next cycle of follow-up data according to the follow-up data change curve, the expected data change curve and the follow-up data cycle prediction model;

[0108] A revision module 35 is used to revise the follow-up requirement items of the current cycle to obtain final follow-up requirement items according to the acquisition time of the follow-up data of the next cycle and the patient follow-up data of each treatment cycle transmitted by the patient client;

[0109] The sending module 36 is used to send the final follow-up requirement items to the patient client of the target patient when the acquisition time of the next cycle follow-up data arrives, so that the target patient fills in the patient follow-up data according to the final follow-up requirement items.

[0110] Optionally, the determination module 33 is specifically configured to:

[0111] Obtaining the follow-up data change curve according to the data change of the patient follow-up data of each period transmitted by the patient client;

[0112] The expected data change curve is obtained by performing linear fitting based on the expected medical data corresponding to each treatment cycle in the rare disease database.

[0113] Optionally, the determination module 33 is specifically configured to:

[0114] Calculate the data difference of the most recent cycle through the follow-up data change curve and the expected data change curve;

[0115] The follow-up data change curve, the expected data change curve and the data difference of the most recent cycle are input into the first follow-up data cycle prediction model to obtain the acquisition time of the next cycle follow-up data.

[0116] Optionally, the determination module 33 is specifically configured to:

[0117] Inputting the follow-up data change curve into the second follow-up data cycle prediction model to predict the follow-up data of the next cycle;

[0118] Calculate the data difference of the next cycle according to the predicted follow-up data of the next cycle and the expected data of the next cycle corresponding to the expected data change curve;

[0119] The acquisition time of the follow-up data of the next cycle is determined according to the data difference of the next cycle.

[0120] Optionally, the determination module 33 is specifically configured to:

[0121] Inputting the follow-up data change curve, the expected data change curve and the data difference of the most recent period into the input layer of the first follow-up data period prediction model;

[0122] The input layer inputs the follow-up data change curve and the data difference of the most recent period into the first neural network structure to obtain a first prediction value;

[0123] The input layer inputs the expected data change curve and the data difference of the most recent period into the second neural network structure to obtain a second prediction value;

[0124] The acquisition time of the next cycle follow-up data is obtained according to the first prediction value and the second prediction value.

[0125] Optionally, the determination module 33 is specifically configured to:

[0126] The first predicted value and the second predicted value are weighted calculated or averaged to obtain the acquisition time of the next cycle follow-up data.

[0127] Optionally, the training process of the first follow-up data period prediction model is:

[0128] Acquire sample data and corresponding sample labels, wherein the sample data includes a sample follow-up data change curve and a sample expected data change curve;

[0129] Calculate the sample data difference of the most recent period according to the sample follow-up data change curve and the sample expected data change curve

[0130] Inputting the sample follow-up data change curve, the sample expected data change curve, and the sample data difference of the most recent period into the first follow-up data period prediction model to obtain a first prediction value and a second prediction value;

[0131] Calculate a loss value according to the first predicted value, the second predicted value, and the sample label;

[0132] When the loss value is less than a preset value, the training of the first follow-up data period prediction model is stopped.

[0133] Optionally, Module 35 is revised to specifically:

[0134] Calculate the time difference according to the acquisition time of the next cycle follow-up data and the acquisition time of the previous cycle follow-up data;

[0135] If the time difference is less than a preset value, the follow-up requirement items of the current cycle are revised according to the follow-up requirement items of the previous cycle to obtain the final follow-up requirement items;

[0136] If the time difference is greater than or equal to the preset value, determining the need for data change exceeding the preset range through the patient follow-up data of each treatment cycle transmitted by the patient client;

[0137] According to the demand items whose change range exceeds the preset range, the follow-up demand items of the current cycle are revised to obtain the final follow-up demand items.

[0138] Optionally, Module 35 is revised to specifically:

[0139] The demand items whose change amplitude exceeds the preset amplitude are added to the follow-up demand items of the current cycle to obtain the final follow-up demand items.

[0140] Based on the same application concept, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the rare disease follow-up data processing method provided in the above embodiment are executed.

[0141] Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, etc. When the computer program on the storage medium is run, the above-mentioned rare disease follow-up data processing method can be executed. First, the corresponding rare disease database is obtained according to the type of rare disease suffered by the target patient, and the rare disease database includes follow-up requirement templates and expected medical data corresponding to each treatment cycle. Then, the follow-up requirement template corresponding to the current treatment cycle of the target patient is transmitted to the doctor client of the attending physician of the target patient, so that the doctor client selects the follow-up requirement items of the current cycle according to the follow-up requirement template. Then, according to the patient follow-up data of each cycle and the rare disease data transmitted by the patient client, the doctor client selects the follow-up requirement items of the current cycle. See the expected medical data corresponding to each treatment cycle in the disease database, determine the follow-up data change curve and the expected data change curve, and determine the acquisition time of the follow-up data of the next cycle based on the follow-up data change curve, the expected data change curve and the follow-up data cycle prediction model, and finally revise the follow-up requirements of the current cycle according to the acquisition time of the follow-up data of the next cycle and the patient follow-up data of each treatment cycle transmitted by the patient client to obtain the final follow-up requirements, and send the final follow-up requirements to the patient client of the target patient when the acquisition time of the follow-up data of the next cycle is reached, so that the target patient fills in the patient follow-up data according to the final follow-up requirements. Compared with the prior art in which patients upload fixed follow-up data according to a certain cycle, this application determines the acquisition time and follow-up requirements of the follow-up data of the next cycle based on the patient follow-up data of the current treatment cycle and the historical cycle of the target patient, so that the patient follow-up data obtained by this application meets the data requirements required for the current cycle, and thus the acquisition efficiency of follow-up data of rare diseases can be improved through this application.

[0142] In the embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0143] 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.

[0144] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0145] If the functions 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 this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0146] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0147] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A rare disease follow-up data processing system, characterized in that: The system comprises: a patient client, a doctor client, and a follow-up data processing server, wherein the follow-up data processing server comprises: a memory and at least one processor, wherein the memory stores a computer program, and the at least one processor is configured to implement the following steps when executing the computer program: Obtaining a corresponding rare disease database according to the type of rare disease suffered by the target patient, wherein the rare disease database includes a follow-up requirement template and expected medical data corresponding to each treatment cycle; Transmitting the follow-up requirement template corresponding to the current treatment cycle of the target patient to the doctor client of the attending physician corresponding to the target patient, so that the doctor client selects the follow-up requirement items of the current cycle according to the follow-up requirement template; Determine a follow-up data change curve and an expected data change curve according to the patient follow-up data of each cycle transmitted by the patient client and the expected medical data corresponding to each treatment cycle in the rare disease database; Determining the acquisition time of the next cycle of follow-up data according to the follow-up data change curve, the expected data change curve and the follow-up data cycle prediction model; According to the acquisition time of the follow-up data of the next cycle and the patient follow-up data of each treatment cycle transmitted by the patient client, the follow-up requirement items of the current cycle are revised to obtain the final follow-up requirement items; When the acquisition time of the next cycle follow-up data arrives, the final follow-up requirement items are sent to the patient client of the target patient, so that the target patient fills in the patient follow-up data according to the final follow-up requirement items.

2. The system according to claim 1, characterized in that The determining of the follow-up data change curve and the expected data change curve according to the patient follow-up data of each cycle transmitted by the patient client and the expected medical data corresponding to each treatment cycle in the rare disease database includes: Obtaining the follow-up data change curve according to the data change of the patient follow-up data of each period transmitted by the patient client; The expected data change curve is obtained by performing linear fitting based on the expected medical data corresponding to each treatment cycle in the rare disease database.

3. The system according to claim 2, characterized in that The determining the acquisition time of the next cycle of follow-up data according to the follow-up data change curve, the expected data change curve and the follow-up data cycle prediction model includes: Calculate the data difference of the most recent cycle through the follow-up data change curve and the expected data change curve; The follow-up data change curve, the expected data change curve and the data difference of the most recent cycle are input into the first follow-up data cycle prediction model to obtain the acquisition time of the next cycle follow-up data.

4. The system according to claim 2, characterized in that The determining the acquisition time of the next cycle of follow-up data according to the follow-up data change curve, the expected data change curve and the follow-up data cycle prediction model includes: Inputting the follow-up data change curve into the second follow-up data cycle prediction model to predict the follow-up data of the next cycle; Calculate the data difference of the next cycle according to the predicted follow-up data of the next cycle and the expected data of the next cycle corresponding to the expected data change curve; The acquisition time of the follow-up data of the next cycle is determined according to the data difference of the next cycle.

5. The system according to claim 3, characterized in that The step of inputting the follow-up data change curve, the expected data change curve, and the data difference of the most recent cycle into a first follow-up data cycle prediction model to obtain the acquisition time of the follow-up data of the next cycle includes: Inputting the follow-up data change curve, the expected data change curve and the data difference of the most recent period into the input layer of the first follow-up data period prediction model; The input layer inputs the follow-up data change curve and the data difference of the most recent period into the first neural network structure to obtain a first prediction value; The input layer inputs the expected data change curve and the data difference of the most recent period into the second neural network structure to obtain a second prediction value; The acquisition time of the next cycle follow-up data is obtained according to the first prediction value and the second prediction value.

6. The system according to claim 5, characterized in that The obtaining time of the next cycle follow-up data according to the first prediction value and the second prediction value includes: The first predicted value and the second predicted value are weighted calculated or averaged to obtain the acquisition time of the next cycle follow-up data.

7. The system according to claim 5, characterized in that The training process of the first follow-up data cycle prediction model is: Acquire sample data and corresponding sample labels, wherein the sample data includes a sample follow-up data change curve and a sample expected data change curve; Calculate the sample data difference of the most recent period according to the sample follow-up data change curve and the sample expected data change curve; Inputting the sample follow-up data change curve, the sample expected data change curve, and the sample data difference of the most recent period into the first follow-up data period prediction model to obtain a first prediction value and a second prediction value; Calculate a loss value according to the first predicted value, the second predicted value, and the sample label; When the loss value is less than a preset value, the training of the first follow-up data period prediction model is stopped.

8. The system according to claim 1, characterized in that The step of revising the follow-up requirement items of the current cycle according to the acquisition time of the follow-up data of the next cycle and the patient follow-up data of each treatment cycle transmitted by the patient client to obtain the final follow-up requirement items includes: Calculate the time difference according to the acquisition time of the next cycle follow-up data and the acquisition time of the previous cycle follow-up data; If the time difference is less than a preset value, the follow-up requirement items of the current cycle are revised according to the follow-up requirement items of the previous cycle to obtain the final follow-up requirement items; If the time difference is greater than or equal to the preset value, determining the need for data change exceeding the preset range through the patient follow-up data of each treatment cycle transmitted by the patient client; According to the demand items whose change range exceeds the preset range, the follow-up demand items of the current cycle are revised to obtain the final follow-up demand items.

9. The system according to claim 8, characterized in that The following steps of revising the follow-up requirement items of the current cycle according to the requirement items whose change range exceeds the preset range to obtain the final follow-up requirement items include: The demand items whose change amplitude exceeds the preset amplitude are added to the follow-up demand items of the current cycle to obtain the final follow-up demand items.

10. A follow-up data processing server, characterized in that: The follow-up data processing server comprises: An acquisition module, used to acquire a corresponding rare disease database according to the type of rare disease suffered by the target patient, wherein the rare disease database includes a follow-up requirement template and expected medical data corresponding to each treatment cycle; A transmission module, used for transmitting the follow-up requirement template corresponding to the current treatment cycle of the target patient to the doctor client of the attending physician corresponding to the target patient, so that the doctor client selects the follow-up requirement items of the current cycle according to the follow-up requirement template; A determination module, configured to determine a follow-up data change curve and an expected data change curve according to the patient follow-up data of each cycle transmitted by the patient client and the expected medical data corresponding to each treatment cycle in the rare disease database; A prediction module, used to determine the acquisition time of the follow-up data of the next cycle according to the follow-up data change curve, the expected data change curve and the follow-up data cycle prediction model; A revision module, configured to revise the follow-up requirement items of the current cycle to obtain final follow-up requirement items according to the acquisition time of the follow-up data of the next cycle and the patient follow-up data of each treatment cycle transmitted by the patient client; The sending module is used to send the final follow-up requirement items to the patient client of the target patient when the acquisition time of the next cycle follow-up data arrives, so that the target patient fills in the patient follow-up data according to the final follow-up requirement items.

Images