Treatment time prediction system and treatment time prediction method

Abstract

The present invention provides a doctor-seeing time prediction system for predicting a doctor-seeing call time of a subject patient, comprising: a storage device for storing and storing progress of a plurality of steps from reception of a call and actual performance data relating to a sample for each doctor-seeing; a processing device that, on the basis of the actual performance data, calculates an implementation prediction time for each process in which the subject patient sees a doctor, and predicts a doctor-seeing call time; and a database that records the predicted treatment call timing calculated by the processing device and that can be accessed from a terminal carried by the subject patient, the processing device being configured to process the treatment call of the subject patient after a portion of the process relating to the treatment of the subject patient has been completed, and the database being configured to store the predicted treatment call timing calculated by the processing device. On the basis of the actual performance data, an implementation prediction time is recalculated for an uncompleted process, and a doctor-seeing call prediction time of the subject patient recorded in the database is updated.

Description

Technical Field

[0001] This invention relates to a system and method for predicting appointment times. Background Technology

[0002] A system is known to predict the waiting time from the time a sample is accepted until a sample is called for (e.g., blood collection) (Patent Documents 1, 2).

[0003] Existing technical documents

[0004] Patent documents

[0005] Patent Document 1: International Publication No. 2022 / 185810

[0006] Patent Document 2: Japanese Patent No. 4156813 Summary of the Invention

[0007] The technical problem that the invention aims to solve

[0008] Patients may have to wait in the hospital after sampling but before being called for their appointment. For example, patients unfamiliar with hospital procedures, such as first-time patients, may be unsure of the specifics and the length of the wait before being called can cause psychological stress. Therefore, it is worth considering, for example, applying Patent Document 1 to predict the time from acceptance to appointment.

[0009] However, the situation differs significantly between acceptance and being called for sampling versus being called for a doctor's appointment. For example, between acceptance and being called for blood collection, simple transactional or mechanical tasks can be performed, but not complex human operations or time-consuming procedures requiring judgment. Therefore, the time from acceptance to being called for blood collection can be predicted for each patient using the same approach. In contrast, from acceptance to being called for a doctor's appointment, time-consuming procedures such as sample analysis and pretreatment like centrifugation, and more complex human operations such as determining whether further testing is needed based on the sample analysis results, are involved. The number of such human interventions and whether further testing is required varies for each patient, making it difficult to predict the appointment time for each patient using the same approach as at the acceptance stage, such as at the blood collection time. For patients waiting based on the indicated time, if they do not receive a call within the indicated time and remain unaware of their situation, they may experience anxiety such as whether there was an error in not being called or whether they are in the wrong waiting area.

[0010] The purpose of this invention is to provide a system and method for predicting appointment times, which can provide the time until the patient is called for an appointment each time, according to the patient's needs.

[0011] Technical solutions to solve technical problems

[0012] To achieve the above objectives, the present invention provides a consultation time prediction system that predicts the consultation call time of a target patient. The system includes: a storage device that stores and accumulates progress data and sample-related performance data for multiple procedures from acceptance to call for each consultation; a processing device that calculates the predicted execution time for each procedure of the patient's consultation based on the performance data, and predicts the consultation call time; and a database that records the consultation call prediction times calculated by the processing device and can be accessed from a terminal carried by the target patient. After completing a portion of the procedures related to the patient's consultation, the processing device recalculates the predicted execution time for the unfinished procedures based on the performance data and updates the consultation call prediction times of the target patient recorded in the database.

[0013] Invention Effects

[0014] According to the present invention, the time until the patient is called for medical attention can be determined according to the patient's needs each time. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating an example of the procedures within a hospital up to the point of treatment.

[0016] Figure 2 This is a schematic diagram of a medical appointment time prediction system according to one embodiment of the present invention.

[0017] Figure 3 This is a schematic diagram of the appointment time prediction process in an appointment time prediction system according to one embodiment of the present invention.

[0018] Figure 4 This is a schematic diagram illustrating the calculation of the appointment time prediction system during blood collection, according to one embodiment of the present invention.

[0019] Figure 5 This is a schematic diagram illustrating the calculation of the predicted time of medical visit in a system for predicting the time of medical visit during blood collection, according to one embodiment of the present invention.

[0020] Figure 6 This is a schematic diagram illustrating the calculation of the appointment time prediction system performed when accepting samples from the examination room, according to one embodiment of the present invention.

[0021] Figure 7 This is a schematic diagram illustrating the calculation of the predicted time of medical visit in a system for predicting the time of medical visit upon completion of an examination, according to one embodiment of the present invention.

[0022] Figure 8 This is an example diagram of an application form that notifies the patient of the predicted time of their medical visit upon acceptance of the application.

[0023] Figure 9 This is an example image showing a portable terminal displaying a predicted time. Detailed Implementation

[0024] In the following description, embodiments of the invention are illustrated with reference to the accompanying drawings.

[0025] The appointment time prediction system and method of this embodiment predict the appointment time for each patient coming to the hospital and provide each patient whose case has been processed with an approximate waiting time until their appointment. The approximate waiting time provided to each patient is updated as the hospital procedures progress until their appointment, thus improving accuracy. For ease of explanation, the system and procedures will be described focusing on one patient, and this patient will be distinguished as the "target patient," while other patients will be distinguished as "other patients." Furthermore, in this embodiment, blood will be used as an example of a sample from the target patient.

[0026] - Procedures up to the point of medical consultation -

[0027] Figure 1 This is a flowchart illustrating an example of the procedures within a hospital, from initial blood collection (sample taking) to being called by a doctor. Within a hospital, the process from a patient's initial blood collection to their appointment generally includes blood collection and sample testing, each involving multiple steps.

[0028] according to Figure 1 To illustrate, a patient arriving at the hospital first undergoes an initial screening (Arrival Screening), then follows a guide to the blood collection room (Blood Collection Room Movement). After completing their blood collection request in the blood collection room (Blood Collection Request), the patient waits to be called and, after receiving their blood sample (Blood Collection Implementation), moves to the examination room (Waiting at the Location Example) (Example of Waiting at the Examination Room Movement), waiting for the doctor to call them for their appointment. Finally, the patient waits to be called to enter the examination room (Example of Moving Inside the Examination Room), where they receive their medical consultation.

[0029] On the other hand, in the blood collection room, the application for blood collection is processed based on the request of the target patient (blood collection acceptance). Then, the target patient is called for blood collection and the blood collection is performed (blood collection call / blood collection completed). The blood collected from the target patient is transported to the examination room along with the blood from other patients.

[0030] Additionally, while patients wait for their doctor's appointment after blood collection, their samples are received in the examination room (sample reception) and fed into a pre-processing unit (sample pre-processing). In this pre-processing, centrifugation is performed according to the required testing items, which may take time. Afterward, the pre-processed sample is fed into an automated analysis unit to determine the required testing items (sample testing / test completion). The test results are verified as needed (result verification) and recorded in a database, which the doctor can view at a terminal in the consultation room (result viewing). If the result requires verification or viewing, or if an error occurred in the automated analysis unit during sample testing, the sample test can be repeated. In the consultation room, the patient is called (consultation call), and the doctor conducts the patient's consultation based on the sample test results (consultation completion).

[0031] In the appointment time prediction system of this embodiment, the time from when a patient's blood collection is initiated to when they are called by a doctor for their appointment is predicted. Figure 1 In the example, the approximate time of movement within the consultation room is predicted, and the prediction is updated each time based on the progress of the procedure, so that the target patient can appropriately confirm the timing of being called for consultation.

[0032] -Medical appointment time prediction system-

[0033] Figure 2 This is a schematic diagram of a medical appointment time prediction system according to one embodiment of the present invention. Figure 3 This is a conceptual diagram of the appointment time prediction process in an appointment time prediction system according to one embodiment of the present invention. Figure 2 The appointment time prediction system 1 shown is configured, for example, to include a computer 100 located on a local network of the hospital and a database 200 located in the cloud. The appointment time prediction system of the present invention is narrowly equivalent to appointment time prediction system 1, but broadly refers to a system that includes the supervising system X described later and appointment time prediction system 1.

[0034] The prediction of the appointment time is performed by the processing unit 120 of the computer 200, and the predicted appointment call time calculated by the computer 100 is recorded in the database 200. The database 200 is stored in a server (not shown) set up in the cloud, and unlike the case set up in the hospital's local network, it can be accessed from the patient's portable terminal M, such as a smartphone.

[0035] but, Figure 2 The system structure shown is an example; it could also be a system structure where database 200 is set up on the hospital's local network, allowing access from patients. Alternatively, a server located outside the hospital's local network could also function as computer 100.

[0036] The functions of the computer 100 will now be described. The computer 100 is configured to include a storage device 110 that stores various databases required for predicting appointment times and a processing device 120 that performs appointment time prediction processing based on the data stored in the storage device 110.

[0037] Storage device 110

[0038] In storage device 110, from receiving (e.g.) Figure 1 Blood collection acceptance) to call (e.g. Figure 1 The progress of multiple procedures (up to the point of moving within the consultation room) and the performance data related to the sample are stored and accumulated for each consultation. For example, the storage device 110 records examination information DB111, timestamp information DB112, and learning model storage unit 113.

[0039] Specifically, the examination information DB111 includes patient sample information such as the examination items, sample type, and whether there is a need for re-examination, according to the acceptance number of each patient sample. Figure 3 This data is recorded as performance data. This data is input from the upper-level system X, which manages multiple systems in a unified manner in the hospital, or from the so-called blood collection service auxiliary system Y, which improves the efficiency of blood collection operations in the blood collection room, via the external system communication processing unit 121.

[0040] The timestamp information DB112 contains information related to the patient's medical history up to the present, including the number of people waiting when blood collection is accepted, the number of people waiting when sample collection is accepted in the examination room, the number of people waiting when the examination is completed, the time of blood collection acceptance, the time of blood collection call (the time of blood collection implementation), the time of blood collection completion (the time of sample collection completion), the time of sample acceptance in the examination room, the time of sample preprocessing input, the time of sample analysis device input, the time of sample examination completion when the test results are reported, and the time of patient call. Figure 3 The data is recorded according to the acceptance number of each patient sample. In the data related to the progress of the procedure, i.e., the examination progress information, in addition to data input from the upper-level system X or the blood collection business support system Y, such as the blood collection call time, it also includes the current waiting number (e.g., the number of people waiting for treatment at the time of blood collection acceptance) calculated by the processing device 120 (prediction processing unit 123) based on the progress of other patients' medical procedures. This waiting number becomes one of the basic pieces of information used by the prediction processing unit 123 to calculate the predicted time of the patient's medical call.

[0041] The learning model 130, which predicts the time of medical visit and is constructed by the processing device 120, is stored in the learning model storage unit 113. Figure 3 ).

[0042] Processing unit 120

[0043] The processing device 120 is configured to include an external system communication processing unit 121, a learning model construction unit 122, a prediction processing unit 123, and a screen display processing unit 124. The functions of these processing units can be implemented as hardware elements such as circuits or software elements such as programs that execute each process.

[0044] The external system communication processing unit 121 receives patient sample information and examination progress information from the host system X and the blood collection business auxiliary system Y, saves the patient sample information in the examination information DB111, and saves the examination progress information in the timestamp information DB112.

[0045] The learning model construction unit 122 performs machine learning on the patient sample information stored in the examination information DB111 and the examination progress information stored in the timestamp information DB112 to construct a learning model 130. Figure 3 The constructed learning model 130 is stored in the learning model storage unit 113. The learning model 130 is a prediction unit that takes into account data related to the target patient, such as the test items, and outputs the doctor's appointment call time. The learning model construction unit 122 constructs and updates the learning model 130 periodically (e.g., once a day) based on the actual data (patient sample information and examination progress information) up to the previous day. The patient sample information used in the construction of the learning model 130 includes the acceptance number, test items, sample type, whether there is a re-examination, and whether centrifugation is performed. In addition, the examination progress information includes the number of people waiting when blood collection is accepted, the number of people waiting when the examination room sample is accepted, the number of people waiting when the examination is completed, the time of blood collection acceptance, the time of blood collection call, the time of blood collection completion, the time of examination room sample acceptance, the time of preprocessing input, the time of analysis device input, the time of sample examination completion, and the time of appointment call.

[0046] The prediction processing unit 123 calculates the predicted time of each medical procedure for the target patient based on the performance data recorded in the storage device 110, and predicts the time of the patient's medical call. For example, for the target patient, the prediction processing unit 123 calculates the number of people waiting at various time points such as when blood is collected, when the examination room sample is collected, and when the examination is completed, based on the examination progress information of other patients recorded in the timestamp information DB112, and stores the examination progress information of the target patient in the timestamp information DB112. Specifically, in this embodiment, the prediction processing unit 123 reads the learning model 130 that has learned the performance data from the learning model storage unit 113, inputs the patient sample information and examination progress information of the target patient stored in the examination information DB111 and the timestamp information DB112, and calculates the predicted time for the incomplete procedures as the output of the learning model 130. If the prediction processing unit 123 calculates each predicted time, it stores the calculated predicted time in the timestamp information DB112, sends it to the upper system X via the external system communication processing unit 121, and records it in the cloud database 200.

[0047] At this time, the calculation of the predicted time of the patient's medical visit may include uncertainties that greatly affect the calculation result. For example, the time required until the medical visit call varies depending on whether sample re-examination and centrifugation are required in the pre-processing. Therefore, in the prediction processing unit 123, the predicted time of the patient's medical visit is calculated based on actual data regarding the presence or absence of centrifugation and re-examination of the patient's sample. That is, when classified according to whether centrifugation and re-examination are required, the predicted time is calculated for the following four cases: cases where neither centrifugation nor re-examination is required, cases where both centrifugation and re-examination are required, cases where centrifugation is required but re-examination is not required, and cases where re-examination is required but centrifugation is not required. The predicted times of the medical visit calls registered in the database 200, that is, the predicted times of the medical visit calls that the patient can view, can be configured as the latest or earliest time to be displayed, for example, the time when each case can be confirmed from the patient's portable terminal M.

[0048] Furthermore, in this embodiment, the processing device 120 illustrates a structure that uses machine learning to calculate the predicted time of a patient's appointment call, but the method for calculating the appointment call time is not limited to machine learning. For example, an algorithm that calculates the predicted execution time of each procedure including the appointment call time based on actual data can be pre-built, and the appointment call time can be calculated based on the actual data using this algorithm.

[0049] Here, after a part of the process related to the patient's visit is completed, the processing device 120 (prediction processing unit 123) recalculates the predicted time of the implementation of the incomplete process (including the predicted time of the visit call) based on the actual data, and updates the predicted time of the patient's visit call recorded in the database 200. The predicted time of the incomplete process calculated by the prediction processing unit 123 varies depending on the progress of the process. In addition, when a process for which the implementation time for the patient has been predicted is completed, the actual implementation time is recorded as actual data in the timestamp information DB112. For example, in the case of blood collection, in this embodiment, the prediction processing unit 123 calculates the predicted time of blood collection call, the predicted time of sample examination completion, and the predicted time of visit call. Then, when the patient's blood is collected, the actual time when the patient is called for blood collection is recorded in the timestamp information DB112 and used as the basis information for the construction of the subsequent learning model 130. Furthermore, when the process progresses and blood collection is completed, the predicted time involved in the implemented blood collection call is removed from the calculation object, and the implementation prediction time of the uncompleted process is calculated, such as the prediction time of sample examination completion and the prediction time of medical visit call.

[0050] In addition, performance data related to the implementation time, including the blood collection call time, is sent to the host system X via the relevant system through manual operation or automatic processing, and then input from the host system X to the consultation time prediction system 1 via the external system communication processing unit 121.

[0051] The display processing unit 124 outputs examination information DB111 and timestamp information DB112 to an output device Z, such as a monitor or printer, based on operations from terminals in the consultation room. By outputting the examination information DB111 and timestamp information DB112 to the output device Z, the examination status for each day and each time period can be confirmed. The patient's appointment call time, calculated by the prediction processing unit 123, can also be output to the output device Z, for example, printed on paper and provided to the patient.

[0052] -action-

[0053] • Blood collection application

[0054] When accepting blood collection requests, the processing device 120 calculates the blood collection call time, the sample examination completion time, and the consultation call time based on the test items related to the target patient, the sample type, the number of people waiting at the time of sample collection acceptance as the current waiting number, and the sample collection acceptance time.

[0055] Specifically, when a patient's blood collection is accepted, the appointment time prediction system 1 receives the patient sample information (acceptance number, test items, and sample type) from the upper-level system X and the blood collection service support system Y via the external system communication processing unit 121. It also receives the blood collection acceptance time as the examination progress information for the patient. The external system communication processing unit 121 stores the received patient sample information in the examination information DB111 and the examination progress information in the timestamp information DB112. When the patient sample information and examination progress information received along with the blood collection acceptance are stored, the appointment time prediction system 1 transfers the processing to the prediction processing unit 123.

[0056] Figure 4 This is a conceptual diagram of the calculation of the predicted time of medical visit during blood collection. The prediction processing unit 123 calculates the number of patients waiting at the time of blood collection for the target patient based on the examination progress information of other patients in the timestamp information DB112, and saves this information to the timestamp information DB112. Additionally, as... Figure 4 As shown, the prediction processing unit 123 reads the patient's admission number, examination items, sample type, number of people waiting at the time of blood collection, and blood collection time from the examination information DB111 and the timestamp information DB112, and inputs this information into the learning model 130 stored in the learning model storage unit 113 to calculate the prescribed prediction times. In this example, the predicted times calculated are the blood collection call prediction time, the sample examination completion prediction time, and the consultation call prediction time. The prediction processing unit 123 saves these calculated prediction times in the timestamp information DB112, sends them to the upper-level system X via the external system communication processing unit 121, and stores the patient's consultation record in the cloud database 200.

[0057] When the higher-level system X accepts blood collection applications, it outputs the following information to the target patient: Figure 8 The form 300 shown is provided. The information printed on the form 300 includes the acceptance time, patient name, patient number, acceptance number, predicted blood draw call time, probability of being called around the predicted blood draw call time, predicted appointment call time, probability of being called around the predicted appointment call time, and a QR code 400 for viewing the predicted time URL. The QR code 400 is a URL issued for accessing the database 200.

[0058] Figure 9This is an example of a display when a QR code 400, used to view the URL for the predicted time, is read and accessed on a portable terminal M. The information displayed on the portable terminal M includes the service number, the predicted time for a blood collection call, the probability of a call being made around the predicted time for a blood collection call, the predicted time for a medical appointment call, the probability of a medical appointment call being made around the predicted time for a medical appointment, the time from the current moment until the next call, and the number of people who were called before the target patient. (This is in contrast to printed materials.) Figure 8 The acceptance slip 300 is different. Figure 9 The display updates to the latest content based on the progress of the procedure during the patient's visit. Furthermore, in this embodiment, a QR code 400 is printed on a paper receipt 300, but the URL can also be provided via an electromagnetic method without paper.

[0059] At the time of blood collection acceptance, there are many unfinished procedures before the call for medical attention. In addition, it is unclear whether there will be any further examinations. Therefore, it is difficult to predict the time of the call for medical attention. However, it is important to inform the target patients of the approximate time before the call for medical attention at the time of acceptance.

[0060] • When blood collection is complete

[0061] When blood collection is completed (when sample collection is completed), the processing device 120 calculates the sample examination completion time and the consultation call time again based on the test items involved in the patient, sample type, blood collection acceptance time, blood collection call time, and blood collection completion time.

[0062] When blood collection for the target patient is completed, the appointment time prediction system 1 inputs the acceptance number from the blood collection service support system Y via the external system communication processing unit 121 as the target patient's sample information. Additionally, as examination progress information related to the target patient, the newly input blood collection call time and blood collection completion time are also input. Based on the acceptance number, the external system communication processing unit 121 stores the newly received examination progress information, i.e., the blood collection call time and blood collection completion time, in the timestamp information DB112 for the target patient. When the blood collection call time and blood collection completion time input along with the target patient's blood collection completion are stored, the appointment time prediction system 1 transfers the processing to the prediction processing unit 123.

[0063] Figure 5 This is a conceptual diagram of the calculations performed to predict the time of medical visit after blood collection is completed. For example... Figure 5As shown, the prediction processing unit 123 reads the patient's acceptance number, test items, sample type, number of people waiting at the time of blood collection acceptance (the number of people waiting at the time of blood collection completion can be recalculated), blood collection acceptance time, blood collection call time, and blood collection completion time from the examination information DB111 and timestamp information DB112, and inputs them into the learning model 130 stored in the learning model storage unit 113 to calculate the prescribed prediction time. Regarding blood collection calls or blood collection completions that were not completed at the time of blood collection acceptance or were included in the time prediction, since they are completed at that time and thus become actual results, the blood collection call time and blood collection completion time are added as input items to the learning model 130 at the time of blood collection acceptance and at the time of blood collection completion. The prediction time calculated at the end of blood collection is the sample examination completion prediction time and the consultation call prediction time, excluding the time predictions of completed blood collection calls. The prediction processing unit 123 saves the calculated prediction times in the timestamp information DB112, sends them to the host system X via the external system communication processing unit 121, and records the patient's medical visit in the cloud database 200.

[0064] Therefore, the predicted time of sample examination completion and the predicted time of medical call in the updated database 200 can be confirmed by the target patient via a portable terminal M with the latest predicted time updated as blood collection is completed.

[0065] -When the test room accepts samples-

[0066] When the processing device 120 accepts samples in the examination room, it calculates the sample examination completion time and the consultation call time again based on the test items involved in the patient, the sample type, the number of people waiting in the examination room when accepting samples as the current number of people waiting, the blood collection acceptance time, the blood collection call time, the blood collection completion time, and the examination room sample acceptance time.

[0067] When a patient's sample is received in the examination room, the appointment time prediction system 1 inputs the acceptance number from the host system X via the external system communication processing unit 121 as the patient's sample information. Additionally, the examination room sample acceptance time is newly input as information on the progress of the patient's examination. Based on the acceptance number, the external system communication processing unit 121 stores the newly received examination progress information, i.e., the examination room sample acceptance time, in the timestamp information DB112 for the patient. When the examination room sample acceptance time is saved, the appointment time prediction system 1 transfers the processing to the prediction processing unit 123.

[0068] Figure 6This is a conceptual diagram of the calculation of the predicted time of visit during sample acceptance in the examination room. The prediction processing unit 123 calculates the number of patients waiting in the examination room for the target patient based on the examination progress information of other patients in the timestamp information DB112, and saves this information to the timestamp information DB112. Additionally, as... Figure 6 As shown, the prediction processing unit 123 reads the patient's admission number, examination items, sample type, number of people waiting in the examination room when the sample is admitted, blood collection admission time, blood collection call time, blood collection completion time, and examination room sample admission time from the examination information DB111 and timestamp information DB112, and inputs them into the learning model 130 stored in the learning model storage unit 113 to calculate the prescribed prediction time. Regarding examination room sample admissions that were not completed when blood collection was completed, since they have been completed and become a record at that time, the examination room sample admission time is added as an input item to the learning model 130 relative to the blood collection completion time. Furthermore, the number of people waiting in the examination room is used instead of the number of people waiting when blood collection was admitted. The prediction time calculated at the examination room sample admission time is the sample examination completion prediction time and the consultation call prediction time. The prediction processing unit 123 saves the calculated prediction times in the timestamp information DB112, sends them to the host system X via the external system communication processing unit 121, and records the patient's medical visit in the cloud database 200.

[0069] Therefore, the predicted time of sample examination completion and the predicted time of patient call are updated in database 200. Patients can then confirm the latest predicted time updated as samples are processed in the examination room via their portable terminal M. At the time of sample processing in the examination room, compared to when blood collection is completed, there are fewer incomplete procedures, and the predicted time is updated to include the current number of people waiting in the examination room, based on the information in the prediction calculation. Therefore, the predicted time becomes a more accurate value.

[0070] Furthermore, in large hospitals, samples are not transported one by one from the blood collection room to the examination room in real time. Sometimes, samples of a certain number are transported in batches, and the time from completion of blood collection to delivery varies depending on the timing of the blood collection completion. Therefore, it is very important to recalculate the number of people waiting and the predicted time of patient calls when the sample processing time in the examination room is set.

[0071] -When sample inspection is completed-

[0072] When a sample examination is completed, the processing device 120 calculates the number of people waiting at the end of the examination based on the following information: the test items involved for the patient, the sample type, the number of people currently waiting, the time of blood collection acceptance, the time of blood collection call, the time of blood collection completion, the time of sample acceptance in the examination room, and the time of sample preprocessing start. Figure 1The start time of sample preprocessing and the time when the sample is fed into the automated analysis device. Figure 1 The start time of sample measurement and the completion time of sample examination are used to calculate the doctor's consultation call time again.

[0073] When the sample examination is completed, the appointment time prediction system 1 receives patient sample information, including an acceptance number, from the host system X via the external system communication processing unit 121. Additionally, as examination progress information related to the patient, the newly input information includes the pre-processing start time, the analysis device start time, and the sample examination completion time. Based on the acceptance number, the external system communication processing unit 121 stores the newly received examination progress information—namely, the pre-processing start time, the analysis device start time, and the sample examination completion time—in timestamp information DB112 for the patient. When the examination progress information input along with the completion of the patient's sample examination is stored, the appointment time prediction system 1 transfers the processing to the prediction processing unit 123.

[0074] Figure 7 This is a conceptual diagram of the calculation of the predicted time of medical visit upon completion of the examination. The prediction processing unit 123 calculates the number of patients waiting upon completion of the examination for the target patient sample based on the examination progress information of other patients in the timestamp information DB112, and saves this information to the timestamp information DB112. Additionally, as... Figure 7 As shown, the prediction processing unit 123 reads the patient's acceptance number, the test items, the sample type, the number of people waiting when the test is completed, the blood collection acceptance time, the blood collection call time, the blood collection completion time, the test room sample acceptance time, the pre-processing input time, the analysis device input time, and the sample test completion time from the examination information DB111 and the timestamp information DB112. This information is then input into the learning model 130 stored in the learning model storage unit 113, and the predicted time is calculated. Regarding the examination and pre-processing of samples that were not completed when accepted in the test room, since they have been completed and become actual results at that time, the pre-processing input time, the analysis device input time, and the sample test completion time are added as input items to the learning model 130 at the time of sample test completion, relative to the time of test room sample acceptance. Furthermore, the number of people waiting when the test is completed is used instead of the number of people waiting when the test is accepted. The predicted time calculated at the time of test completion is the patient call prediction time. The prediction processing unit 123 saves the calculated prediction time in the timestamp information DB112, sends it to the host system X via the external system communication processing unit 121, and records the patient's medical visit in the cloud database 200.

[0075] Therefore, the predicted appointment call time in database 200 is updated, and the target patient can check the latest predicted appointment call time updated as the sample examination is completed via portable terminal M. At the time of examination completion, compared with when the sample was received in the examination room, there are fewer incomplete procedures, and the prediction is updated to include the current number of people waiting in the examination room at the time of examination completion, which is also included in the basic information of the prediction calculation. Therefore, the predicted appointment call time becomes a more accurate value.

[0076] Furthermore, sometimes re-examinations are required based on the results of sample testing, and sometimes time-consuming procedures such as centrifugation are added depending on the test items. Therefore, the completion time of sample testing may sometimes deviate from the initial prediction. Thus, it is important to recalculate the waiting number and the predicted appointment call time at the time sample testing is completed, in order to provide patients with a more accurate predicted appointment call time.

[0077] Furthermore, the examination information DB111 and timestamp information DB112 can be output to the output device Z at any time via the screen display processing unit 124, allowing doctors and others to confirm the examination status daily or at different times. Additionally, the predicted waiting time for each patient can also be output to the output device Z for confirmation.

[0078] -Effect-

[0079] (1) According to this embodiment, after a portion of the procedures related to the patient's visit is completed, for the incomplete procedures, the predicted time of implementation is recalculated based on the actual data, and the predicted time of the patient's visit call recorded in the database 200 is updated in stages. Thus, according to the progress of the procedures, the latest information on the time until the patient is called for a visit can be provided each time, as needed by the patient. Furthermore, since the implementation time of procedures that become actual as the procedures progress is added to the basic information of the prediction calculation, the prediction accuracy of the visit call time improves as the procedures progress.

[0080] For example, during blood collection, the basic information for time prediction does not include the completion time of blood collection. However, upon completion of blood collection, the actual completion time can be added to the basic information for predicting the patient call time. Similarly, during sample collection in the examination room, the current time of sample collection or the number of people waiting (after recalculation) can be added to the basic information. Furthermore, upon completion of sample examination, the time of sample preprocessing or input into the automated analysis device during the examination, the completion time of the sample examination, and the number of people waiting (at the current recalculation time) can be added to the basic information. Through this successive calculation, the accuracy of the patient call time calculation can be improved as the process progresses.

[0081] (2) When machine learning is used to calculate the predicted time of the patient’s medical call as in this embodiment, the reliability of the time prediction of the learning model 130 can be expected to improve with the accumulation of actual data.

[0082] (3) When calculating the predicted time of medical call based on whether the patient’s sample has been centrifuged or re-examined, the system can flexibly indicate the time of medical call according to the test items or whether re-examination is required.

[0083] (4) Even if access from the patient’s general portable terminal M is restricted in the hospital’s local network, the patient can access the database 200 set in the cloud to confirm the latest predicted time of medical appointment by recording the time of medical appointment call in the database 200 set in the cloud as in this embodiment.

[0084] (5) By outputting the URL used to access the database 200 as a QR code 400 printed in the form of a receipt 300, the target patient can easily access the database 200 and confirm the latest appointment call prediction time.

[0085] - Variation Example -

[0086] This invention is not limited to the embodiments described above and may include various modifications. For example, the embodiments described above have been given in detail for ease of understanding, but are not necessarily limited to including all the structures described. For example, a part of the structure may be replaced with another structure. In addition, a part of the structure in each embodiment may be deleted or other structures may be added.

[0087] For example, the appointment time prediction system 1 can also be integrated into the computer of the automatic analysis device. Furthermore, the storage device 110 can be composed of multiple storage devices, or multiple storage devices can share the storage of examination information DB111, timestamp information DB112, and learning model storage unit 113. In this case, each storage device only needs to be connected via a network and does not necessarily need to be on the same computer or connected to it. Similarly, the processing device 120 can be configured such that multiple processing devices share the functions of the learning model construction unit 122, the prediction processing unit 123, etc.

[0088] Furthermore, the basic information used for calculating the timing of patient calls is not limited to the method described in the above embodiments and can be appropriately modified. For example, in predicting the timing of patient calls upon completion of blood collection, the completion time of blood collection is known as the latest progress time, so it is also possible to remove the blood collection call times preceding it from the basic information to reduce the computational load. Similarly, in predicting the timing of patient calls upon acceptance of samples in the examination room, the blood collection acceptance time, blood collection call time, and blood collection completion time can be removed from the basic information. In predicting the timing of patient calls upon completion of sample examination, the blood collection acceptance time, blood collection call time, blood collection completion time, examination room sample acceptance time, preprocessing start time, and analysis device input time can also be removed from the basic information.

[0089] Label Explanation

[0090] 1. Medical Appointment Time Prediction System

[0091] 110 Storage device

[0092] 11. Check the information database (performance data).

[0093] 112 Timestamp Information DB (Actual Performance Data)

[0094] 113 Learning Model Storage Department

[0095] 120 processing device

[0096] 121 External System Communication Processing Department

[0097] 122 Learning Model Construction Department

[0098] 123 Predictive Processing Department

[0099] 124 Screen Display Processing Unit

[0100] 130 Learning Model

[0101] 200 databases

[0102] 300 Service Request Form

[0103] 400 QR code (URL).

Claims

1. A system for predicting appointment times, The system for predicting patient appointment times predicts the time a patient will call for medical attention. Its key feature is that it predicts the time a patient will call for medical attention. include: A storage device that stores and accumulates progress data and sample-related performance data for each visit, from admission to call. The processing device calculates the predicted implementation time of each procedure in the patient's medical visit based on the actual performance data, and predicts the time of the medical visit call. as well as A database that records predicted appointment times calculated by the processing device, accessible from a terminal carried by the target patient. The processing device, After completing a portion of the procedures related to the patient's visit, the predicted time for the unfinished procedures is recalculated based on the actual performance data, and the predicted time for the patient's visit call recorded in the database is updated.

2. The appointment time prediction system as described in claim 1, characterized in that, The performance data related to the progress of the procedure includes the current number of people waiting, calculated based on the progress of other patients' medical procedures. The processing device calculates the predicted time of the patient's medical call based on the number of people waiting.

3. The appointment time prediction system as described in claim 1, characterized in that, The performance data associated with the sample includes the measured test items and sample category.

4. The appointment time prediction system as described in claim 1, characterized in that, The processing device uses machine learning to calculate the predicted time of the patient's medical call.

5. The appointment time prediction system as described in claim 1, characterized in that, The processing device calculates the predicted time of the patient's medical visit based on the actual data, according to whether the patient's sample has been centrifuged or re-examined.

6. The appointment time prediction system as described in claim 1, characterized in that, The database is located in the cloud.

7. The appointment time prediction system as described in claim 4, characterized in that, The process includes sample collection and sample inspection. When accepting the sample collection, the processing device calculates the blood collection call time, the sample examination completion time, and the consultation call time based on the test items involved in the patient, the sample category, the number of people waiting at the time of sample collection acceptance as the current waiting number, and the sample collection acceptance time.

8. The appointment time prediction system as described in claim 7, characterized in that, When the sample collection is completed, the processing device calculates the sample examination completion time and the medical call time based on the measurement and examination items involved in the patient, the sample category, and the sample collection completion time.

9. The appointment time prediction system as described in claim 8, characterized in that, When the sample is accepted in the examination room, the processing device calculates the sample examination completion time and the consultation call time based on the measurement and examination items involved in the patient, the sample category, the number of people waiting in the examination room as the current number of people waiting, and the time of sample acceptance in the examination room.

10. The appointment time prediction system as described in claim 9, characterized in that, When the sample examination completed in the examination room, the processing device calculates the time of the medical call based on the measurement examination items involved in the patient, the sample category, the number of people waiting when the examination is completed (as the current number of people waiting), and the time when the sample examination is completed.

11. The appointment time prediction system as described in claim 1, characterized in that, Issue a URL for accessing the database.

12. The appointment time prediction system as described in claim 11, characterized in that, The output printed the receipt containing the URL.

13. A method for predicting the time of medical visit. This method for predicting appointment times stores and accumulates progress data and sample-related performance data for each appointment, covering multiple steps from initial acceptance to call. Based on the aforementioned performance data, the system predicts the timing of each step in the patient's medical process. The method for predicting the time of a patient's medical appointment is characterized by the following features: After completing a portion of the procedures related to the patient's visit, the predicted time for the unfinished procedures is recalculated based on the performance data, and the predicted time for the patient's visit call, which is recorded in the database accessible from the terminal carried by the patient, is updated.

Images