Medical examination time prediction system, medical examination time prediction method for same, and display device

Abstract

This medical examination time prediction system comprises: a storage device that stores, for each reception number, specimen attribute information of a subject patient, the progression of a plurality of steps from reception in a facility to calling in a medical examination, and result information relating to the specimen; and a processing device that calculates, using the specimen attribute information and a learning model constructed from the result information, a predicted time for each medical examination step including a medical examination calling time of the subject patient for whom a prediction is to be made. The result information for constructing the learning model includes urgency information indicating whether examination of the specimen is urgent, and the specimen attribute information includes the urgency information of the subject patient. When calculating the predicted time of the subject patient after receiving the specimen of the subject patient, the processing device inputs information including the subject patient urgency information to the learning model to calculate the predicted time, and stores the predicted time in the storage device.

Description

Examination Time Prediction System, Its Examination Time Prediction Method, and Display Device

[0001] The present disclosure relates to an examination time prediction system, its examination time prediction method, and a display device.

[0002] After receiving an outpatient patient, a technique for generating an examination flow including at least one examination item, generating examination time information regarding the examination flow, and notifying is known (Patent Document 1).

[0003] Japanese Patent Application Laid-Open No. 2024-65567

[0004] When an examination is performed at a facility such as a hospital, after the patient has been received at the facility, an examination of a specimen collected from the patient is often performed, and based on the examination results of the specimen, the doctor examines the patient in many cases. In this case, the patient is examined after the time from reception until being called for the examination of the specimen, the time for analyzing the specimen, and the waiting time until being examined by the doctor after the analysis of the specimen has ended have elapsed. Since it takes time from reception to examination in this way, the patient may become anxious and feel stressed. To prevent such a situation, a system for predicting and notifying the examination time as described above has been proposed.

[0005] However, for example, when examining a specimen collected from a patient in an examination room, the time required for analyzing the specimen varies depending on the examination items of the specimen, the degree of urgency, and the congestion status of the specimen. These are not considered in Patent Document 1 mentioned above. Therefore, it has been difficult to accurately predict the patient's waiting time for examination.

[0006] An object of the present disclosure is to provide a prediction technique capable of more accurately predicting the waiting time for examination.

[0007] A representative embodiment of this disclosure has the following configuration. The consultation time prediction system of one embodiment predicts the consultation call time for a patient in a facility that includes a testing facility having a testing device for testing a patient's specimen and a transport device for transporting the specimen to the testing device. The consultation time prediction system includes a storage device that stores specimen attribute information indicating the attributes of the specimen of the target patient, as well as progress of multiple processes from reception to consultation call at the facility and actual information regarding the specimen for each reception number, and a processing device that calculates the predicted time for each process of the consultation, including the consultation call time for the target patient, using a learning model constructed from the actual information and the specimen attribute information. The actual information used to construct the learning model includes urgency information indicating whether or not there is urgency in testing the specimen. The specimen attribute information includes the urgency information of the target patient. When the processing device calculates the predicted time for the target patient after receiving the specimen of the target patient, it inputs information including the urgency information of the target patient into the learning model to calculate the predicted time and stores the calculated predicted time in the storage device.

[0008] Furthermore, the consultation time prediction method of one embodiment of the consultation time prediction system predicts the consultation call time of a patient in a facility including a testing facility having a testing device for testing a patient's specimen and a transport device for transporting the specimen to the testing device. The consultation time prediction system includes a storage device that stores specimen attribute information indicating the attributes of the target patient's specimen, as well as progress of multiple processes from reception to consultation call at the facility and actual information regarding the specimen for each reception number, and a processing device that calculates the predicted time for each process of the consultation, including the consultation call time of the target patient to be predicted, using a learning model constructed from the actual information and the specimen attribute information. The actual information used to construct the learning model includes urgency information indicating whether or not there is urgency in testing the specimen. The specimen attribute information includes the urgency information of the target patient. The method for predicting the time of consultation includes the steps of: receiving the sample from the target patient;, after receiving the sample, calculating the predicted time for the target patient by inputting information including the urgency information of the target patient into the learning model; and storing the calculated predicted time in the storage device.

[0009] One embodiment of the display device displays information stored in a consultation time prediction system that predicts the consultation call time for a patient in a facility including a testing facility having a testing device for testing a patient's specimen and a transport device for transporting the specimen to the testing device. The consultation time prediction system includes a storage device that stores specimen attribute information indicating the attributes of the specimen of the target patient, as well as progress information for multiple processes from reception to consultation at the facility and actual information regarding the specimen, for each reception number, and a processing device that calculates the predicted time for each consultation process, including the consultation call time for the target patient, using a learning model constructed from the actual information and the specimen attribute information. The actual information used to construct the learning model includes urgency information indicating whether or not there is urgency in testing the specimen. The specimen attribute information includes the urgency information of the target patient. When the processing device calculates the predicted time for the target patient after receiving the specimen from the target patient, it inputs information including the urgency information of the target patient into the learning model to calculate the predicted time and stores the calculated predicted time in the storage device. The display device displays the calculated predicted time stored in the storage device.

[0010] According to a representative embodiment of this disclosure, a prediction technology can be provided that can more accurately predict waiting times for medical consultations. Other issues, configurations, and effects will be shown in the embodiments for carrying out the invention.

[0011] This is a schematic diagram showing an example of the process within the hospital from the arrival of a target patient of the embodiment until examination. This is a schematic diagram showing an example of the process within the laboratory of the embodiment. This is a diagram showing an example of the configuration of the information processing system including the examination time prediction system of the embodiment. This is a diagram showing an example of specimen attribute information of the embodiment. This is a diagram showing an example of timestamp information of the embodiment. This is a diagram showing an example of analyzer setting information of the embodiment. This is a diagram showing an example of transport device setting information of the embodiment. This is a diagram showing an example of information used to construct a learning model of the embodiment. This is a diagram showing an example of sample number calculation setting information of the embodiment. This is a flowchart showing an example of the processing of the examination time prediction system of the embodiment. This is a diagram showing the concept of the calculation of the predicted time performed at the time of blood collection reception of the embodiment. This is a diagram showing the concept of the calculation of the predicted time performed at the time of blood collection completion of the embodiment. This is a diagram showing the concept of the calculation of the predicted time performed at the time of laboratory reception of the embodiment. This is a diagram showing the concept of the calculation of the predicted time performed when the transport device is brought in of the embodiment. This is a diagram showing the concept of the calculation of the predicted time performed when the analyzer is brought in of the embodiment. This is a diagram showing the concept of the calculation of the predicted time performed at the time of examination completion of the embodiment. This is a diagram showing the concept of the calculation of the predicted time performed at the time of blood collection reception when there are multiple specimen IDs in the embodiment. This is a diagram showing an example of the display screen of the graphical user interface device of the embodiment. This figure shows an example of the display screen of a mobile terminal device according to the embodiment. This figure shows an example of the display screen of a graphical user interface device according to the embodiment.

[0012] The embodiments of this disclosure will be described in detail below with reference to the drawings. In the drawings, the same parts are generally denoted by the same reference numerals, and repeated descriptions are omitted. In the drawings, the representation of components may not show their actual location, size, shape, extent, etc., in order to facilitate understanding of the invention.

[0013] In explanations, when describing program-based processing, the focus may be on the program, functions, or processing units. However, the main hardware component is the processor, or a controller, device, computer system, or other system composed of such a processor. A computer system, using resources such as memory and communication interfaces as appropriate, executes processing according to the program read into memory. This realizes the specified functions and processing units. A processor is composed of semiconductor devices such as a CPU / MPU or GPU. Processing is not limited to software program processing; it can also be implemented using dedicated circuits. Applicable dedicated circuits include FPGAs, ASICs, CPLDs, etc.

[0014] The program may be pre-installed as data on the target computer system, or it may be distributed as data from the program source to the target computer system. The program source may be a program distribution server on a communication network, or a non-transient computer-readable storage medium, such as a memory card or disk. The program may consist of multiple modules. The computer system may consist of multiple devices. The computer system may consist of a client-server system, a cloud computing system, an IoT system, etc. Various types of data and information are composed of structures such as tables and lists, but are not limited to these. Representations such as identification information, identifiers, IDs, names, and numbers are interchangeable.

[0015] [Embodiment] <Process from arrival at the hospital to examination> Figure 1 is a schematic diagram showing an example of the process within the hospital from the time a target patient arrives at the hospital until they are called in for an examination by a doctor. In a hospital, the process from when a target patient arrives at the hospital and registers at the reception desk until they are called in for an examination by a doctor broadly includes the processes of blood collection (collection of specimen) in the blood collection room (laboratory) and specimen testing in the laboratory. Furthermore, both blood collection and specimen testing involve multiple processes. In the following explanation, we will use the case where the specimen is blood as an example, but the specimen is not limited to blood.

[0016] As shown in Figure 1, patients arriving at the hospital first register (check-in) and then move to the blood collection room according to the instructions given by the receptionist (movement to blood collection room). In the blood collection room, the patient requests to have blood drawn (blood collection request). Next, the patient waits to be called and has blood drawn (blood collection performed), then moves to the area in front of the examination room (movement to in front of the examination room) and waits until they are called in for a consultation with a doctor. After that, the patient waits to be called in and enters the examination room (movement to inside the examination room) and receives a consultation with a doctor.

[0017] Meanwhile, in the blood collection room, blood collection is registered (blood collection registration) in response to the patient's application. After that, the patient is called in for blood collection and the blood is collected (blood collection call / blood collection completed). Once the required number of patients' blood samples have been collected, or once a predetermined amount of time has elapsed, the blood collected from the patient is transported to the laboratory along with blood collected from other patients.

[0018] In the laboratory, while the patient who has finished blood collection waits outside the examination room for a doctor's consultation, the patient's sample is received (laboratory sample reception) and, if necessary, placed in a sample preprocessing device (sample preprocessing). During this preprocessing, depending on the measurement items of the sample, centrifugation may be performed, which may take time. Subsequently, the testing of samples that do not require preprocessing and samples that have undergone preprocessing is automatically performed by the testing device (sample analysis). In this embodiment, the testing device is described as an analytical device that performs sample analysis, but it may be a device that performs other tests. In the sample analysis process, the sample is set in a transport device (transport device loading), and the sample transported from the transport device, or the sample transported directly without going through the transport device, is loaded into the analytical device (analytical device loading). Once the analysis by the analytical device is completed (sample test completion), the analysis results are verified as necessary (result validation) and stored in the clinical laboratory information system (described later).

[0019] In the examination room, the physician can view the analysis results stored in the clinical laboratory information system on a terminal device located in the room (results viewing). If deemed necessary based on result validation or results viewing, or if an error occurred in the analyzer during sample measurement, the sample measurement may be repeated. After the analysis results are obtained, the patient is called in (consultation call), and the physician examines the patient based on the analysis results of the sample (consultation completed).

[0020] <Sample Analysis Process> Next, we will explain the process within the laboratory. Figure 2 is a schematic diagram showing an example of the process within the laboratory.

[0021] As shown in Figure 2, within the laboratory, laboratory technicians and other laboratory personnel receive specimens transported from the blood collection room (laboratory reception). The laboratory personnel input specimen attribute information (reception number, specimen ID, measurement test items, specimen type, emergency designation, and referring clinical department, etc.) into the clinical laboratory information system. After inputting the information, the laboratory personnel perform pre-processing, such as centrifugation, on the received specimens using a pre-processing device (specimen pre-processing).

[0022] In the laboratory, a transport system is installed to transport samples, allowing samples to be delivered from the transport system to analyzers A and B via a transport route. On the other hand, samples cannot be delivered from the transport system to analyzer C, and are instead transported manually by the laboratory staff. Analyst C is, for example, an analyzer that performs tests infrequently and for which connecting to the transport route is not beneficial, or an analyzer that analyzes samples that are difficult to transport via the transport route due to the need for temperature control, size, etc.

[0023] If the sample has been pre-processed and there is no urgency for testing, the inspector will place the sample into the transport device (transport device placement). The transport device will then transport the placed sample via a transport path to the analyzer corresponding to the measurement item. In this way, the sample is placed into the analyzer (analyzer placement). Alternatively, if the sample has been pre-processed and there is an urgency for testing, the inspector may transport the sample to the analyzer themselves. In this case, the sample may be placed into the analyzer (analyzer placement). Once the sample is placed into the analyzer, the sample is analyzed. When the analysis of the sample is completed in the analyzer, the sample test is completed (sample test completion). After this, result validation is performed, and the analysis results of the sample are made available for viewing, as described above.

[0024] In Figure 2, samples A1 to A8 represent samples to be analyzed using analyzer A. Samples B1 to B4 represent samples to be analyzed using analyzer B. Sample C1 represents a sample to be analyzed using analyzer C. Samples A1, B1, and B2 represent samples that have been received but are not yet loaded into the transport device. Samples A2, A3, and A4 represent samples that have been loaded into the transport device but are not yet loaded into analyzer A. Samples B3 and B4 represent samples that have been loaded into the transport device but are not yet loaded into analyzer B. Samples A4 and B4 are shown in transit on the transport path. Samples A5 to A8 represent samples that have been loaded into analyzer A. Sample C1 represents a sample that has been received but is not yet loaded into analyzer C.

[0025] <Configuration of the Consultation Time Prediction System> Figure 3 shows an example of the configuration of the information processing system 1, which includes the consultation time prediction system 10. The information processing system 1 is an information system that manages information such as information about hospital facilities, patient information, examination information, and medical fee information installed within the hospital. In this embodiment, the information processing system 1 includes the consultation time prediction system 10, the clinical laboratory information system 20, the blood collection support system 30, and the graphical user interface device 40.

[0026] The consultation time prediction system 10 predicts the patient's consultation call time in a facility such as a hospital, which includes a laboratory having an analyzer for analyzing patient samples and a transporter for transporting samples to the analyzer. The consultation time prediction system 10 is configured, for example, by a computer system installed on the hospital's local network. The consultation time prediction system 10 includes a storage device 110 and a processing device 120. The consultation time prediction system 10 may also be installed, for example, on a server located outside the hospital's local network.

[0027] The storage device 110 stores specimen attribute information indicating the attributes of the target patient's specimen, as well as progress information on multiple processes from reception at a facility such as a hospital to being called for examination, and performance information regarding the specimen, for each reception number.

[0028] The processing unit 120 calculates the predicted time for each step of the examination process, including the time of the patient's consultation call, using a learning model constructed from actual data and specimen attribute information. The actual data includes urgency information indicating whether or not the analysis of the specimen is urgent. The specimen attribute information includes patient urgency information indicating the urgency of the analysis of the patient's specimen. After receiving the patient's specimen, the processing unit 120 calculates the predicted time for the patient by inputting information including the patient urgency information into the learning model and storing the calculated predicted time in the storage device 110.

[0029] The performance information includes, in more detail, information indicating at least one of the following times: the time the sample was received in the laboratory, the time the sample was brought into the transport device, and the time the sample was brought into the analyzer. In this case, when the processing device 120 calculates the predicted time when the analysis of a sample is accepted, when the sample is brought into the transport device, and when the sample is brought into the analyzer, it reflects the transport congestion information, which indicates the transport status of samples within the testing facility calculated from at least one of the times the sample was received in the laboratory, when the sample was brought into the transport device, and when the sample was brought into the analyzer, in the calculation of the predicted time.

[0030] More specifically, the sample transport congestion information includes at least one of the following: the number of samples after acceptance for testing but before being transported to the transport device; the number of samples transported to the transport device but before being transported to the analyzer; and the number of samples transported to the analyzer.

[0031] Furthermore, if the sample attribute information includes patient urgency information, the processing device 120 calculates the predicted time when the sample is delivered to the analyzer using a learned model, without calculating the predicted time when the sample is delivered to the transport device.

[0032] Furthermore, urgency information includes information indicating emergency designation within the specimen attribute information, or information indicating that the requesting department that submitted the specimen is an emergency department.

[0033] Furthermore, within the laboratory, the analytical apparatus includes a first analyzer for analyzing the first measurement test item and a second analyzer for analyzing the second measurement test item. The first analyzer may be connected to the transport path of the transport device, while the second analyzer may not be connected to the transport path of the transport device. In this case, the storage device 110 stores connection information indicating the connection relationship between the transport device and the first and second analyzers. If the measurement test item included in the sample attribute information of the target patient is the second measurement test item, the processing device 120 calculates the predicted time when the sample is delivered to the second analyzer using a learned model, without calculating the predicted time when the sample is delivered to the transport device. Details of the processing performed by the storage device 110 and the processing device 120 will be described later.

[0034] The clinical laboratory information system 20 is a system that manages test results, such as the analysis results of specimens, when a specimen has been tested. Test results are entered into the clinical laboratory information system 20, for example, by the laboratory technician. The blood collection support system 30 manages information about specimens collected by blood collectors. Information about collected specimens is entered into the blood collection support system 30, for example, by the blood collector.

[0035] The graphical user interface device 40 includes a display device, an input device, and a printing device. The graphical user interface device 40 is installed in a hospital, such as in a clinical department or an examination room. For example, a doctor can use the graphical user interface device 40 installed in the examination room to check the analysis results of a patient.

[0036] The mobile terminal device 50 is, for example, a smartphone or tablet device owned by the patient. In this embodiment, the mobile terminal device 50 is able to communicate with the consultation time prediction system 10 via the external communication processing unit 25.

[0037] Next, the consultation time prediction system 10 will be described in more detail. The consultation time prediction system 10 includes, as functions, a specimen attribute information DB (database) 11, a timestamp information DB (database) 12, a setting information DB (database) 13, a learning model storage unit 14, an external system communication processing unit 21, a prediction processing unit 22, a screen display processing unit 23, a learning model construction unit 24, and an external communication processing unit 25. The external system communication processing unit 21 is connected to the clinical laboratory information system 20 and the blood collection support system 30, respectively, in a communicative manner. The screen display processing unit 23 is connected to the graphical user interface device 40 in a communicative manner, for example, by wired or wireless connection. The external communication processing unit 25 is connected to the mobile terminal device 50 in a communicative manner, for example, by wireless connection.

[0038] The functions of the specimen attribute information DB11, timestamp information DB12, setting information DB13, learning model storage unit 14, external system communication processing unit 21, prediction processing unit 22, screen display processing unit 23, learning model construction unit 24, and external communication processing unit 25 are realized by the processor included in the processing unit 120 controlling hardware such as the memory included in the storage device 110 and the memory included in the processing unit 120, the storage unit that stores information such as programs, the communication control unit that controls communication, and the input / output control unit that controls the input and output of information.

[0039] For example, the functions of the specimen attribute information DB 11, timestamp information DB 12, setting information DB 13, and learning model storage unit 14 are realized by the processor controlling the storage device 110, etc. The functions of the prediction processing unit 22 and the learning model construction unit 24 are realized by the processor reading the program stored in the storage unit into memory and executing it. The functions of the external system communication processing unit 21 and the external communication processing unit 25 are realized by the processor controlling the communication control unit and memory, etc. The functions of the screen display processing unit 23 are realized by the processor controlling the input / output control unit and memory, etc.

[0040] The specimen attribute information DB 11 stores specimen attribute information obtained from the clinical laboratory information system 20. In this embodiment, the specimen attribute information is information about the attributes of the blood specimen. Figure 4 shows an example of specimen attribute information 11a. As shown in Figure 4, in the specimen attribute information 11a, information such as specimen ID, measurement test items, specimen type, emergency designation, and referring clinical department is associated with each reception number.

[0041] The reception number indicates, for example, the number received at the reception desk upon arrival. The specimen ID indicates a number that identifies the specimen. Note that multiple tests may be performed on a single specimen. In this embodiment, specimens are distinguished by assigning different reception numbers. The measurement test items indicate the test items to be measured on the specimen. Depending on the specimen and the type of test, there may be multiple measurement test items. In this embodiment, the measurement test items are items X1 to X5. The specimen type indicates the type of specimen. In this embodiment, since the specimen is blood, the specimen types are serum, whole blood, and plasma. The emergency designation indicates whether or not the specimen needs to be tested urgently. If the emergency designation is YES, it indicates urgency; if it is NO, it indicates that it is not urgent. The requesting department indicates the source that requested the specimen testing. Requesting departments include, for example, internal medicine, surgery, emergency medicine, orthopedics, and cardiology. Specimens requested by the emergency department have an urgent need for testing.

[0042] As shown in FIG. 4, for example, for the reception number "xxxx1", the specimen ID "1", the measurement test item "Item X1", the specimen type "serum", the emergency designation "NO", and the requested medical department "Internal Medicine" are associated with each other.

[0043] The timestamp information DB 12 stores the timestamp information acquired by the examination time prediction system 10 from the clinical examination information system 20 through communication. The timestamp information includes information indicating the time of each process until the target patient shown in FIG. 1 is called for examination. FIG. 5 is a diagram showing an example of the timestamp information 12a. As shown in FIG. 5, in the timestamp information 12a, information indicating the reception number, specimen ID, measurement test item, blood collection reception time, blood collection call time, laboratory reception time, pretreatment input time, conveyance device loading time, analyzer A loading time to analyzer C loading time, test completion time, and examination call time is associated. Also, in the timestamp information 12a, initially "NULL" is stored in each information, and each information is overwritten and stored in this way.

[0044] Regarding the reception number, specimen ID, and measurement test item, it is the same as in the case of FIG. 4. The blood collection reception time indicates the time when the request for blood collection of the target patient is received in the examination room. The blood collection call time indicates the time when the target patient is called for blood collection in the blood collection room. The laboratory reception time indicates the time when the specimen is received for examination in the laboratory. The pretreatment input time indicates the time when the specimen is input into the pretreatment device. The conveyance device loading time indicates the time when the specimen is loaded into the conveyance device. The analyzer A loading time to analyzer C loading time indicate the time when the specimen is loaded into analyzers A to C. The test completion time indicates the time when the examination of the specimen is completed. The examination call time indicates the time when the target patient is called for examination.

[0045] As shown in FIG. 5, for example, for the reception number "xxx11", the specimen ID "10", the measurement test item "Item X1", the blood collection reception time "8:30", the blood collection call time "8:45", the laboratory reception time "8:47", the pretreatment input time "8:50", the conveyance device loading time "8:55", the analyzer A loading time "9:00", the analyzer B loading time "NULL", the analyzer C loading time "NULL", the inspection end time "9:05", and the examination call time "9:40" are associated.

[0046] Also, for the reception number "xxx11", the specimen ID "10" and the measurement test item "Item X1" are associated, for the reception number "xxx12", the specimen ID "10" and the measurement test item "Item X2" are associated, and for the reception number "xxx13", the specimen ID "10" and the measurement test item "Item X4" are associated. This indicates that the specimen with the specimen ID "10" has been examined for three measurement test items.

[0047] Using the timestamp information 12a stored in this timestamp information DB12, the processing device 120 can also calculate the number of people waiting at the time of blood collection reception, the number of people waiting at the time of laboratory specimen reception, the number of people waiting at the time of inspection completion, the number of specimens between the received and the conveyance device, the number of specimens between the conveyance device and analyzer A, the number of specimens between the conveyance device and analyzer B, the number of specimens between the received and analyzer A, the number of specimens between the received and analyzer B, and the number of specimens between the received and analyzer C.

[0048] For example, for the number of people waiting at the time of blood collection reception, if there is a specimen ID for which the blood collection reception time is stored but the examination call time is NULL, the processing device 120 determines that it is waiting for blood collection. The processing device 120 can calculate the number of people waiting at the time of blood collection reception by counting the number of specimen IDs in such a state.

[0049] Furthermore, for example, as shown in Figure 2 above, the processing device 120 can calculate the number of samples between the received sample and the transport device by counting the number of samples that have been accepted for testing but have not been transported to the transport device. The same applies when the processing device 120 calculates the number of samples between the received sample and the transport device, the number of samples between the transport device and analyzer A, the number of samples between the transport device and analyzer B, the number of samples between the received sample and analyzer A, the number of samples between the received sample and analyzer B, and the number of samples between the received sample and analyzer C. These sample counts indicate the congestion level of samples in the laboratory.

[0050] The configuration information DB13 stores configuration information. The configuration information includes analysis device configuration information 13a related to the analysis device and transport device connection information 13b indicating whether or not the analysis device is connected to the transport device.

[0051] Figure 6 shows an example of the analytical instrument setting information 13a. In the analytical instrument setting information 13a, the analytical instrument that performs the measurement is associated with the measurement and inspection items. The information indicating the measurement and inspection items is items X1 to X5 as described above. The analytical instruments set in the analytical instrument setting information 13a are analytical instruments A to analytical instruments C.

[0052] As shown in Figure 6, for example, "Analyzer A" is associated with the measurement test item "Item X1". Similarly, "Analyzer A" is also associated with "Item X4". This indicates that Analyzer A is used for both the measurement of Item X1 and Item X4. In this way, it is possible to perform multiple tests (for example, tests at different times) with a single analyzer.

[0053] Figure 7 shows an example of the transport device connection information 13b. In the transport device connection information 13b, transport device connection information indicating whether or not an analyzer A to C is connected to the transport device is associated with each analyzer A to C. In this configuration, "YES" is displayed if the device is connected to the transport device, and "NO" is displayed if it is not connected to the transport device.

[0054] As shown in Figure 7, analyzers A and B are associated with "YES," and analyzer C is associated with "NO." In other words, the setting shown in Figure 7 is the case where analyzers A and B are connected to the transport device, as shown in Figure 2 above, and analyzer C is not connected to the transport device.

[0055] The learning model memory unit 14 stores the learning model for predicting consultation times, which is constructed by the learning model construction unit 24. Details of the learning model will be described later.

[0056] The external system communication processing unit 21 receives specimen attribute information 11a and test progress information from the clinical laboratory information system 20 and the blood collection support system 30, and stores the specimen attribute information 11a in the specimen attribute information DB 11, and the test progress information and laboratory congestion information in the timestamp information DB 12. The test progress information is information that indicates the progress of the test, such as the time of blood collection acceptance and the time of test acceptance. The laboratory congestion information is information that indicates the number of specimens in the laboratory, such as the number of specimens between the accepted-transport device as described above.

[0057] The learning model construction unit 24 uses machine learning to construct a learning model 240 (see Figure 8 described later) based on the sample attribute information stored in the sample attribute information DB 11, the examination progress information stored in the timestamp information DB 12, and the congestion information in the examination room. The constructed learning model 240 is then stored in the learning model storage unit 14.

[0058] The learning model 240 is a prediction means that takes information about the target patient, such as measurement and examination items, as input and outputs the time when the doctor will call the patient for an examination. The learning model construction unit 24 periodically (for example, once a day) constructs and updates the learning model 240 based on performance information up to the previous day (specimen attribute information, examination progress information, and information on congestion in the examination room).

[0059] Figure 8 shows an example of the information used to construct the learning model 240. As shown in Figure 8, the learning model 240 is constructed using performance data. The performance data includes sample attribute information, test progress information, and laboratory congestion information.

[0060] Specimen attribute information includes reception number, measurement test items, specimen type, whether or not a retest is required (optional), centrifugation treatment, whether or not it is designated as an emergency, and information indicating the clinical department. In addition, test progress information includes the number of people waiting at blood collection reception, the number of people waiting at laboratory specimen reception, the number of people waiting at test completion, blood collection reception time, blood collection call time, blood collection completion time, laboratory specimen reception time, pre-processing input time, transport device arrival time, analyzer A-C arrival time, test completion time, and consultation call time. Furthermore, laboratory congestion information includes the number of specimens between reception and transport device, transport device and analyzer A, transport device and analyzer B, reception and analyzer A, reception and analyzer B, and reception and analyzer C.

[0061] We will now explain the laboratory congestion information in more detail. Figure 9 shows an example of the sample count calculation setting information 13c. The sample count calculation setting information 13c is an example of a setting for calculating the number of samples between received samples and the transport device, the number of samples between the transport device and analyzer A, the number of samples between the transport device and analyzer B, the number of samples between received samples and analyzer A, the number of samples between received samples and analyzer B, and the number of samples between received samples and analyzer C.

[0062] For example, the setting information for the number of samples received and transferred to the transport device is set as follows: Testing facility reception time ≠ NULL, transport device entry route = YES, and transport device entry time = NULL.

[0063] The setting information for the number of samples between the transport device and analyzer A is that the sample transport device arrival time ≠ NULL, and the analyzer A arrival time = NULL. The setting information for the number of samples between the transport device and analyzer B is that the transport device arrival time ≠ NULL, and the analyzer B arrival time = NULL. The setting information for the number of samples between the received sample and analyzer A is that the testing facility reception time ≠ NULL, the transport device arrival route = NO, the analyzer A arrival time = NULL, and the analyzer = analyzer A. The setting information for the number of samples between the received sample and analyzer B is that the testing facility reception time ≠ NULL, the transport device arrival route = NO, the analyzer B arrival time = NULL, and the analyzer = analyzer B. The setting information for the number of samples received and analyzed by analyzer C is as follows: Test facility reception time ≠ NULL, analyzer C arrival time = NULL, and analyzer = analyzer C.

[0064] The prediction processing unit 22 predicts the consultation call time by calculating the estimated execution time for each step of the patient's examination based on the actual information stored in the storage device 110. For example, for the patient, the prediction processing unit 22 calculates the number of people waiting and the number of samples based on the examination progress information of other patients stored in the timestamp information DB 12 at each point in time, such as when blood collection is accepted, when the sample is accepted in the laboratory, when the sample is brought into the transport device, when the sample is brought into analyzers A to C, and when the examination is completed, and stores this information in the timestamp information DB 12 as the examination progress information for the patient.

[0065] Specifically, in this embodiment, the prediction processing unit 22 reads the learning model 240, which has been learned based on actual performance information, from the learning model storage unit 14, inputs the patient's specimen attribute information, examination progress information, and laboratory congestion information stored in the specimen attribute information DB 11 and timestamp information DB 12, and calculates the predicted execution time for the incomplete steps as the output of the learning model 240. Once the prediction processing unit 22 has calculated each predicted time, it stores the calculated predicted time in the timestamp information DB 12.

[0066] In this embodiment, the processing unit 120 is shown as having a configuration that uses machine learning to calculate the predicted time of the patient's consultation call. However, the method for calculating the consultation call time is not limited to machine learning. For example, an algorithm may be pre-built to calculate the predicted execution time of each process, including the consultation call time, based on actual data, and the consultation call time may be calculated based on actual data according to this algorithm.

[0067] Here, the processing unit 120 (prediction processing unit 22) recalculates the predicted execution time (including the consultation call time) for the incomplete processes after some processes related to the examination of the target patient have been completed, based on actual data, and updates the consultation call times of the target patient stored in the storage device 110. The predicted times for the incomplete processes calculated by the prediction processing unit 22 vary depending on the progress of the processes.

[0068] Furthermore, when a process for which the implementation time has been predicted for a target patient is completed, the actual implementation time is stored in the timestamp information DB12 as sequential performance information. For example, at the time of blood collection reception, in this embodiment, the prediction processing unit 22 calculates the blood collection call time, the examination completion time, and the consultation call time. Subsequently, when the patient's blood collection is performed, the time when the target patient was actually called for blood collection is stored in the timestamp information DB12 and used as basic information for the subsequent construction of the learning model 240. Furthermore, when the process progresses and blood collection is completed, the predicted time related to the completed blood collection call is excluded from the calculation, and the predicted implementation times for incomplete processes, such as the examination completion time and the consultation call time, are calculated.

[0069] The screen display processing unit 23 displays information stored in the specimen attribute information DB 11 and the timestamp information DB 12 on the graphical user interface device 40, for example, in response to the operation of the graphical user interface device 40 installed in the hospital. By displaying the information stored in the specimen attribute information DB 11 and the timestamp information DB 12 on the graphical user interface device 40, laboratory technicians and doctors can check the examination status in real time. The graphical user interface device 40 can be installed, for example, in the reception area, blood collection room, laboratory, and examination room of a hospital. The time of the patient's appointment may be printed on paper from the printer device of the graphical user interface device 40, and the printed paper may be provided to the patient.

[0070] The external communication processing unit 25, when accessed based on an operation of a mobile terminal device 50 such as a smartphone held by a target patient, displays information stored in the specimen attribute information DB 11 and the timestamp information DB 12 regarding the target person on the mobile terminal device 50. For example, when the external communication processing unit 25 receives an operation from the mobile terminal device 50 to request the display of the consultation call time, it causes the mobile terminal device 50 to display information regarding the consultation call time of the target patient.

[0071] <Operation of the Consultation Time Prediction System> Next, the operation of the consultation time prediction system 10 will be explained. Figure 10 is a flowchart showing an example of the processing of the consultation time prediction system 10.

[0072] <<At the time of blood collection registration>> First, the operation at the time of blood collection registration will be explained (ST101). At the time of blood collection registration, the processing device 120 predicts the time of blood collection call, the time of test completion, and the time of consultation call based on the registration number of the target patient, the measurement test items, the type of specimen, whether it is urgent or not, the requesting medical department, the time of blood collection registration, the number of people waiting at the time of specimen collection registration (number of people waiting for blood collection), and the current congestion status of specimens in the laboratory.

[0073] When a patient's blood collection is registered in the blood collection room, for example, the registration staff in the blood collection room inputs the blood collection registration time, registration number, measurement test items, specimen type, whether it is urgent or not, and the requesting medical department into the blood collection support system 30. As a result, the consultation time prediction system 10 receives the registration number, measurement test items, specimen type, whether it is urgent or not, and the requesting medical department as specimen attribute information for the target patient, and the blood collection registration time as examination progress information for the target patient.

[0074] The external system communication processing unit 21 stores specimen attribute information for the target patient in the specimen attribute information DB 11, and the examination progress information, i.e., the blood collection reception time, in the timestamp information DB 12. Then, the consultation time prediction system 10 moves on to processing by the prediction processing unit 22.

[0075] Figure 11 shows the concept of calculating the predicted time at the time of blood collection registration. The prediction processing unit 22 calculates the number of people waiting and the number of samples in the laboratory at the time of blood collection registration for the target patient from the examination progress information of other patients in the timestamp information DB 12, and stores it in the timestamp information DB 12. Also, as shown in Figure 11, the prediction processing unit 22 reads the target patient's registration number, measurement test items, sample type, whether it is urgent or not, the requesting medical department, blood collection registration time, the number of people waiting at the time of blood collection registration, and the number of samples in the laboratory (laboratory congestion information) from the sample attribute information DB 11 and the timestamp information DB 12, inputs it into the learning model 240 stored in the learning model storage unit 14, and calculates the predicted time. In this embodiment, the predicted times to be calculated are the blood collection call time, the examination completion time, and the consultation call time. The prediction processing unit 22 stores the calculated predicted time in the timestamp information DB 12.

[0076] In this way, the consultation time prediction system 10 can predict the consultation time for the target patient at the time of blood collection registration.

[0077] Furthermore, the consultation time prediction system 10 can reflect the congestion status of specimen testing in the laboratory in its prediction time. More specifically, it can predict the completion time of testing and the consultation call time by reflecting factors such as whether or not there is an emergency, whether or not the analyzer is connected to the transport device, the time required for transporting specimens within the laboratory, and the time required for specimen analysis. This allows for further improvement in the accuracy of the predictions made by the consultation time prediction system 10.

[0078] <<Upon completion of blood collection>> Next, the operation upon completion of blood collection will be explained (ST102). Upon completion of blood collection (completion of specimen collection), the processing device 120 predicts the completion time of the test and the time for consultation based on the measurement test items, specimen type, whether or not it is urgent, the requesting medical department, the time of blood collection reception, the time of blood collection call, the time of blood collection completion, the number of people waiting at the time of specimen collection reception (number of people waiting for consultation), and the congestion status of specimens in the laboratory.

[0079] Once blood collection from the target patient is complete, for example, the blood collector in the blood collection room enters the reception number, the blood collection call time, and the blood collection completion time into the blood collection support system 30. As a result, the consultation time prediction system 10 receives the reception number as the target patient's specimen attribute information, and the blood collection call time and blood collection completion time as examination progress information.

[0080] The external system communication processing unit 21 stores the newly received examination progress information, namely the blood collection call time and blood collection completion time, for the target patient based on the reception number in the timestamp information DB 12. Then, the consultation time prediction system 10 proceeds to processing by the prediction processing unit 22.

[0081] Figure 12 shows the concept of calculating the predicted time when blood collection is completed. As shown in Figure 12, the prediction processing unit 22 reads the target patient's reception number, measurement test items, specimen type, whether it is urgent or not, the requesting clinical department, blood collection reception time, blood collection call time, blood collection completion time, number of people waiting at the time of blood collection completion, and laboratory congestion information (the number of specimens at the time of blood collection completion may be recalculated) from the specimen attribute information DB 11 and the timestamp information DB 12, and inputs this information into the learning model 240 stored in the learning model storage unit 14 to calculate the predicted time. Blood collection calls and blood collection completions that were incomplete or subject to time prediction at the time of blood collection reception are considered completed and recorded at this point, so at the time of blood collection completion, the blood collection call time and blood collection completion time are added as input items to the learning model 240 compared to the time of blood collection reception. The predicted time calculated at the time of blood collection completion is the test completion time and the consultation call time. Time predictions for completed blood collection calls are excluded from the calculation. The prediction processing unit 22 stores the calculated predicted time in the timestamp information DB 12.

[0082] Since the blood collection reception time, as well as the blood collection call time and blood collection completion time, are included in the actual data, the consultation time prediction system 10 can improve the accuracy of predicting the examination completion time and consultation call time for the target patient.

[0083] Furthermore, the consultation time prediction system 10 can improve its prediction accuracy by recalculating the number of people waiting at the time of blood collection registration and the number of samples collected at the time of blood collection completion, thereby determining a predicted consultation time that corresponds to the number of people waiting for consultation and the congestion of samples in the laboratory at the time of blood collection completion.

[0084] <<When receiving a specimen in the laboratory>> Next, the operation when receiving a specimen in the laboratory will be explained (ST103). When receiving a specimen in the laboratory, the processing device 120 predicts the time of completion of the test and the time of calling for consultation based on the measurement test items, specimen type, whether or not it is urgent, the requesting medical department, the time of blood collection reception, the time of blood collection call, the time of blood collection completion, the time of laboratory specimen reception, the number of people waiting at the time of specimen collection reception (number of people waiting for consultation), and the congestion status of specimens in the laboratory.

[0085] Once the patient's registration at the laboratory is complete, the laboratory technician, for example, enters the registration number and the time of registration into the clinical laboratory information system 20. As a result, the consultation time prediction system 10 receives the registration number as the patient's specimen attribute information and the time of registration as the examination progress information.

[0086] The external system communication processing unit 21 stores the newly received examination progress information, i.e., the examination room reception time, for the target patient in the timestamp information DB 12, based on the reception number. Then, the consultation time prediction system 10 proceeds to processing by the prediction processing unit 22.

[0087] Figure 13 shows the concept of calculating the predicted time at the time of laboratory reception. The prediction processing unit 22 calculates the number of people waiting and the number of samples in the laboratory at the time of blood collection reception for the target patient from the examination progress information of other patients in the timestamp information DB 12 and stores it in the timestamp information DB 12. Also, as shown in Figure 13, the prediction processing unit 22 reads the target patient's reception number, measurement test items, sample type, whether it is urgent or not, requesting clinical department, blood collection reception time, blood collection call time, blood collection completion time, laboratory reception time, number of people waiting at the time of examination reception, and laboratory congestion information (which may be calculated again) from the sample attribute information DB 11 and the timestamp information DB 12, inputs it into the learning model 240 stored in the learning model storage unit 14, and calculates the predicted time. The laboratory sample reception time, which was incomplete at the time of blood collection completion, is now completed and recorded as actual at this point. Therefore, the laboratory sample reception time is added as an input item to the learning model 240 at the time of laboratory sample reception, compared to the time of blood collection completion. The estimated time calculated at the time of check-in at the examination room is the time of examination completion and the time of call for consultation.

[0088] The prediction processing unit 22 stores these calculated predicted times in the timestamp information DB 12. This updates the examination completion time and the consultation call time. At the time of sample reception in the laboratory, there are fewer incomplete processes compared to when blood collection is completed, and the current number of people waiting, which is included in the basic information for the prediction calculation, is updated to reflect the number of people waiting at the time of laboratory reception. Furthermore, the current congestion status of samples in the laboratory is also reflected, so the predicted time of the consultation time prediction system 10 becomes a more accurate value.

[0089] Furthermore, in facilities that handle specimens, such as large hospitals, collected specimens are not transported one by one from the blood collection room to the laboratory as they are collected. Instead, a certain number of specimens may be transported in batches. In this case, the time from blood collection completion to transport will vary depending on when the blood collection is completed. Therefore, by recalculating the test completion time and the consultation call time at the time the specimen is received in the laboratory, the accuracy of the consultation time prediction system 10 can be further improved.

[0090] <<After receiving the sample>> Upon receiving the sample, the prediction processing unit 22 predicts the test completion time and the consultation call time when the sample is brought into the transport device and when the sample is brought into the analyzer, respectively. However, in this embodiment, in the following two cases, the sample is not brought into the transport device, so the prediction processing unit 22 does not perform prediction processing of the predicted time using the learning model 240 when the sample is brought into the transport device.

[0091] (1) In cases of urgency, when a sample from the patient is received in the laboratory, the sample is marked as received. Once the sample is marked as received, the consultation time prediction system 10 determines whether or not there is an urgency in the analysis of the sample (ST104). The prediction processing unit 22 makes this determination based on the information indicating urgency and the information indicating the requesting department contained in the sample attribute information 11a identified by the reception number. For example, the prediction processing unit 22 reads the urgency setting and the requesting department from the sample attribute information 11a of the sample indicated by the reception number, and determines whether the emergency designation is "YES" and whether the requesting department is "emergency". In these cases, since it is necessary to analyze the sample urgently, the sample is not transported by a transport device, and for example, the sample is directly transported to the analyzer by the examiner. For this reason, samples that need to be analyzed urgently are not brought into the transport device.

[0092] In this embodiment, the prediction processing unit 22 was described as using two pieces of information—information indicating urgency and information indicating the requesting medical department—to determine urgency. However, at least one of the pieces of information indicating urgency and information indicating the requesting medical department may be used as the information for this determination.

[0093] (2) If the sample is not connected to a transport device, or if it is determined that there is no urgency (ST104: NO), the examination time prediction system 10 determines whether or not the analyzer for analyzing the sample is connected to the transport device (ST105). The prediction processing unit 22 makes this determination based on the analyzer identified by the measurement sample item of the sample to be analyzed and the connection status of the analyzer to the transport device set in the analyzer setting information 13a. For example, when the prediction processing unit 22 refers to the analyzer setting information 13a, it can be seen that the measurement test item of the sample to be analyzed is "item X3", and the analysis of "item X3" is performed by "analyzer C". Here, when the transport device connection information 13b is referred to, analyzer C is set to "NO". In other words, analyzer C is not connected to a transport device. For this reason, for example, the sample is transported directly to analyzer C by the examiner. In this way, the sample to be analyzed by analyzer C is not brought into the transport device.

[0094] In the two cases described above, the prediction processing unit 22 predicts the examination completion time and the consultation call time only when the items are brought into the analysis device, without making predictions when the items are brought into the transport device. Note that the order of the determination in step ST104 and the determination in step ST105 may be reversed.

[0095] <<When transporting to the transport device>> Next, we will explain what happens when the patient's specimen is transported to and brought into the transport device (ST106).

[0096] When the transport device is brought in, the processing device 120 recalculates the test completion time and the consultation call time based on the patient's measurement test items, specimen type, whether it is urgent or not, the requesting medical department, blood collection reception time, blood collection call time, blood collection completion time, specimen reception time, transport device arrival time, and the number of people waiting (number of people waiting for consultation) at the time of transport device arrival, as well as the congestion status of specimens in the laboratory.

[0097] When a specimen is transported and placed into the transport device, the clinical laboratory information system 20 obtains the specimen's reception number and the time of arrival at the transport device. For example, the reception number and the time of arrival at the transport device are entered by the laboratory staff. The transport device may be configured to automatically detect the reception number and the time of arrival at the transport device when the specimen is set in the transport device.

[0098] The consultation time prediction system 10 receives the reception number as specimen attribute information for the target patient and the arrival time of the transport device as examination progress information. The external system communication processing unit 21 stores the newly received examination progress information, i.e., the arrival time of the transport device, for the target patient based on the reception number in the timestamp information DB 12. Then, the consultation time prediction system 10 proceeds to processing by the prediction processing unit 22.

[0099] Figure 14 shows the concept of calculating the predicted time when the transport device is brought in. As shown in Figure 14, the prediction processing unit 22 reads the target patient's reception number, measurement test items, specimen type, whether or not it is designated as an emergency, the requesting clinical department, blood collection reception time, blood collection call time, blood collection completion time, laboratory specimen reception time, transport device arrival time, number of people waiting when the transport device is brought in, and laboratory congestion information (which may be calculated again) from the specimen attribute information DB 11 and the timestamp information DB 12, inputs this information into the learning model 240 stored in the learning model storage unit 14, and calculates the predicted time. When the transport device is brought in, the transport device arrival time is added as input information. The predicted times calculated when the transport device is brought in are the test completion time and the consultation call time.

[0100] The prediction processing unit 22 stores these calculated predicted times in the timestamp information DB 12. This updates the examination completion time and the consultation call time. When the transport device is brought in, there are fewer incomplete processes compared to when the patient is checked into the examination room. Furthermore, the current number of people waiting, which is included in the basic information for the prediction calculation, is updated to reflect the number of people waiting at the time of check-in. In addition, the current congestion status of specimens in the examination room is also reflected, so the predicted time of the consultation time prediction system 10 becomes a more accurate value.

[0101] In this way, when the sample is brought into the transport device, the examination time prediction system 10 uses the time the sample is brought into the transport device to predict the examination completion time and the consultation call time, thereby calculating the predicted time while taking into account the congestion situation in the examination room in real time.

[0102] Furthermore, if a specimen is brought into the transport device and the specimen's attributes indicate an emergency, or if the requesting clinical department is an emergency, the clinical laboratory information system 20 may be configured to notify the laboratory technician of the error from the transport device. This prevents specimens that should not be brought into the transport device from being brought into the transport device, and also prevents the error information from being included in the basic information of the learning model 240 constructed by the learning model construction unit 24.

[0103] <<When transporting samples to the analyzer>> Next, we will explain what happens when the patient's sample is transported to the analyzer (ST107). As described above, samples are transported to the analyzer via a transport route from a transport device (analyzer A and analyzer B), or they are transported by an inspector (analyzer C).

[0104] When the analyzer is brought in, the processing unit 120 recalculates the test completion time and the consultation call time based on the patient's measurement test items, sample type, blood collection reception time, blood collection call time, blood collection completion time, laboratory sample reception time, transport device arrival time, analyzer arrival time, number of people waiting (number of people waiting for consultation) at the time of analyzer arrival, and the congestion status of samples in the laboratory.

[0105] When a sample is brought from the transport device to analyzer A or analyzer B, or transported to analyzer C, the clinical laboratory information system 20 obtains the sample's reception number and the time of arrival at the analyzer. For example, in the case of analyzer A and analyzer B, the reception number and the time of arrival at the analyzer to which the sample was brought are automatically detected. For example, in the case of analyzer C, the reception number and the time of arrival at analyzer C are entered by the laboratory worker transporting the sample.

[0106] The consultation time prediction system 10 receives the reception number as specimen attribute information for the target patient and the time the analyzer was brought in as examination progress information. The external system communication processing unit 21 stores the newly received examination progress information, i.e., the time the analyzer was brought in, for the target patient based on the reception number in the timestamp information DB 12. Then, the consultation time prediction system 10 proceeds to processing by the prediction processing unit 22.

[0107] Figure 15 shows the concept of calculating the predicted time when the analyzer is brought in. As shown in Figure 15, the prediction processing unit 22 reads the target patient's reception number, measurement test items, specimen type, whether it is urgent or not, the requesting clinical department, blood collection reception time, blood collection call time, blood collection completion time, laboratory specimen reception time, transport device arrival time, analyzer arrival time, number of people waiting at the time of analyzer arrival, and the congestion status in the laboratory (which may be calculated again) from the specimen attribute information DB 11 and the timestamp information DB 12, and inputs this information into the learning model 240 stored in the learning model storage unit 14 to calculate the predicted time. The predicted time calculated when the analyzer is brought in is the test completion time and the consultation call time.

[0108] The prediction processing unit 22 stores these calculated predicted times in the timestamp information DB 12. This updates the examination completion time and the consultation call time. When an analytical device is brought in, there are fewer incomplete processes compared to when a transport device is brought in, and the current number of people waiting, which is included in the basic information for the prediction calculation, is updated to reflect the number of people waiting at the time of reception in the examination room. Furthermore, the current congestion status of samples in the examination room is also reflected, so the predicted time of the consultation time prediction system 10 becomes a more accurate value.

[0109] In this way, when the analyzer is brought in, the consultation time prediction system 10 can calculate the predicted time by using the time the sample is brought into the analyzer to predict the time the test is completed and the time the patient is called for consultation. Therefore, the consultation time prediction system 10 can improve the accuracy of the predicted time.

[0110] <<When specimen testing is complete>> Next, we will explain what happens when specimen testing for the target patient is completed (ST108).

[0111] The processing unit 120, upon completion of the specimen testing, recalculates the consultation call time based on the patient's measurement test items, specimen type, urgency status, requesting department, blood collection reception time, blood collection call time, blood collection completion time, laboratory specimen reception time, transport device arrival time, analyzer arrival time, test completion time, number of people waiting (number of people waiting for consultation) at the time of test completion, and the specimen congestion status in the laboratory. Note that the specimen congestion status in the laboratory does not need to be included in the prediction process since the laboratory testing has already been completed.

[0112] Once the analysis of the sample is completed by the analyzer, the clinical laboratory information system 20 obtains the sample's reception number and the time of test completion. For example, the reception number and the time of test completion are entered by the laboratory staff.

[0113] The consultation time prediction system 10 receives the reception number as specimen attribute information for the target patient and the examination completion time as examination progress information. The external system communication processing unit 21 stores the newly received examination progress information, i.e., the examination completion time, for the target patient based on the reception number in the timestamp information DB 12. Then, the consultation time prediction system 10 proceeds to processing by the prediction processing unit 22.

[0114] Figure 16 shows the concept of calculating the predicted time when the examination is completed. As shown in Figure 16, the prediction processing unit 22 reads the patient's reception number, measurement test items, specimen type, urgency status, requesting department, blood collection reception time, blood collection call time, blood collection completion time, laboratory reception time, transport device arrival time, analyzer arrival time, examination completion time, number of people waiting at the time of examination completion, and laboratory congestion information (which may be calculated again) from the specimen attribute information DB 11 and timestamp information DB 12, and inputs this information into the learning model 240 stored in the learning model storage unit 14 to calculate the predicted time. For specimens that were incomplete or subject to time prediction when the analyzer was brought in, the analysis is completed at this point and has become a record, so the examination completion time is added as an input item to the learning model 240. The predicted time calculated when the examination is completed is the time of the patient's call.

[0115] The prediction processing unit 22 stores these calculated predicted times in the timestamp information DB 12. This updates the consultation call time. When the examination is completed, there are fewer incomplete processes compared to when the analysis equipment is brought in, and the number of people waiting included in the basic information for the prediction calculation is updated to the current number of people waiting when the examination is completed, so the predicted time of the consultation time prediction system 10 becomes a more accurate value.

[0116] As more information is entered as actual results upon completion of the inspection, the prediction processing unit 22 can calculate a more accurate predicted time.

[0117] <<When there are multiple identical specimen IDs>> As shown in Figure 5, there are cases where specimens have different reception numbers but the same specimen ID. In Figure 5, the specimen IDs for reception numbers "xxx11", "xxx12", and "xxx13" are all the same, "10". When there are multiple identical specimen IDs in this way, the consultation time prediction system 10 may perform the following processing. The following explanation will use the case of blood collection reception as an example, but the same applies when blood collection is completed, when the laboratory is checked in, when the transport device is brought in, when the analyzer is brought in, and when the test is completed.

[0118] The consultation time prediction system 10 receives the reception number as specimen attribute information for the target patient and, for example, the blood collection reception time as examination progress information. The external system communication processing unit 21 stores the newly received examination progress information, i.e., the blood collection reception time, for the target patient in the timestamp information DB 12 based on the reception number. Then, the consultation time prediction system 10 proceeds to processing by the prediction processing unit 22. The above processing is the same as in the case described above.

[0119] When the prediction processing unit 22 reads information from the timestamp information DB 12, it determines whether there are multiple specimen IDs in the timestamp information DB 12 that match the specimen ID of the target patient. If it is determined that there are no multiple specimen IDs, the predicted blood collection call time, test completion time, and consultation call time for the target patient's specimen become the predicted times, as described above. On the other hand, if it is determined that there are multiple specimen IDs, the latest predicted time among the blood collection call time, test completion time, and consultation call time predicted for each of the multiple specimens with the same specimen ID becomes the predicted time.

[0120] Figure 17 illustrates the concept of calculating the predicted time at the time of blood collection when there are multiple samples with the same ID.

[0121] In cases where there are multiple identical specimen IDs, the prediction processing unit 22 selects the latest predicted time from the predicted times for all of the specimen IDs. For example, in Figure 5, for the three reception numbers "xxx11", "xxx12", and "xxx13", which all share the same specimen ID "10", the test completion times differ at "9:05", "9:23", and "9:30". However, the latest time, "9:30", is used to calculate the consultation call time for each reception number, resulting in "9:40". In this way, the consultation time prediction system 10 can always calculate the latest predicted time, thus preventing situations where patients become frustrated because their predicted time is delayed.

[0122] In other words, when the processing unit 120 calculates the predicted time, it stores sample attribute information of the target patient in the storage device 110. For example, if there are multiple sample IDs, it calculates the predicted time for each sample ID, and the latest predicted time among the calculated predicted times is used as the predicted time for each sample.

[0123] In the above embodiment, when performing tests on a target patient, the explanation described a case where the reception numbers were different but the sample IDs were the same. However, similar effects can be achieved even if the reception numbers are the same but the sample IDs are different.

[0124] <Display on the graphical user interface device> The information stored in the timestamp information DB12 can be displayed on the graphical user interface device 40 and can also be printed.

[0125] <<Display screen for physicians and laboratory technicians>> Figure 18 shows an example of the display screen 41 of the graphical user interface device 40. The display screen 41 displays information 41a for physicians and laboratory technicians from the contents stored in the specimen attribute information DB 11 and the timestamp information DB 12. As shown in Figure 18, the specimen type, emergency designation, requesting department, blood collection call time, test completion time, and consultation call time are displayed in association with the reception number and specimen ID. How to display information other than the blood collection call time, test completion time, and consultation call time can be appropriately decided by the operator, such as a physician or laboratory technician. Physicians and laboratory technicians may print out the display screen 41 and give it to the patient if necessary.

[0126] In this way, the graphical user interface device 40 can display the sample attribute information 11a, performance information, and predicted time stored in the storage device 110. Doctors, laboratory technicians, etc. can check the progress of blood sampling tests for all patients by looking at the display screen 41 shown in Figure 18.

[0127] <<Display screen for patients>> The consultation time prediction system 10 is further equipped with an external communication processing unit 25 that can communicate with the mobile terminal device 50. Furthermore, when an access is received from the mobile terminal device 50 held by the target patient, the processing unit 120 can read the consultation call time of the target patient from the storage device 110 and display the read consultation call time on the mobile terminal device 50.

[0128] Figure 19 shows an example of the display screen 42 of the mobile terminal device 50. The display screen 42 shows patient-oriented information 42a from the contents stored in the specimen attribute information DB 11 and the timestamp information DB 12. As shown in Figure 19, the measurement test items, specimen type, emergency designation, requesting clinical department, blood collection call time, test completion time, and consultation call time are displayed in association with the reception number and specimen ID. How information other than the blood collection call time, test completion time, and consultation call time is displayed can be appropriately set by the hospital while ensuring security by allowing viewing by multiple patients.

[0129] For example, when a patient checks in or registers for blood collection, the receptionist hands the patient a sheet of paper with a QR code printed on it. The patient can then scan the QR code using their mobile terminal device 50 to access the address indicated by the QR code and display the screen 42 shown in Figure 19 on the mobile terminal device 50. This allows the patient to easily check their blood collection call time, test completion time, and consultation call time. The consultation time prediction system 10 can update the predicted consultation call time at each stage leading up to the consultation, so it can provide the patient with an appropriate consultation call time depending on when they scan the QR code.

[0130] More specifically, the consultation time prediction system 10 can update the blood collection call time until blood collection is completed, the test completion time and consultation call time until the test is completed, and at the time of blood collection reception, blood collection completion, laboratory reception, transport device arrival, analyzer arrival, and test completion, respectively. Therefore, the target patient can check the latest predicted time each time they check using the mobile terminal device 50.

[0131] Furthermore, predicting the time required for analysis within the laboratory is difficult because it varies greatly depending on the number of samples transported to the laboratory, the items to be measured, and the analysis time of the analyzer. In this embodiment, the consultation time prediction system 10 can predict the blood collection call time, the test completion time, and the consultation call time, taking into account the congestion of samples in the laboratory at the time of blood collection reception, blood collection completion, and test reception. Therefore, the consultation time prediction system 10 can improve its prediction accuracy.

[0132] <<Setting Information Settings Screen>> Figure 20 shows an example of the display screen 43 of the graphical user interface device 40. The display screen 43 shows the setting screen 43a for the analyzer setting information 13a and the setting screen 43b for the transport device connection information 13b, which are stored in the setting information DB 13. On the setting screen 43a, it is possible to set one of the analyzers A to analyzers C for each of the measurement and inspection items X1 to X5. Pull-down menus 43a1 to 43a5 are provided corresponding to items X1 to X5. Each of the pull-down menus 43a1 to 43a5 displays the option to set analyzers A to analyzers C. On the setting screen 43b, it is possible to set the connection status of the transport device for each of the analyzers A to analyzers C. Pull-down menus 43b1 to 43b3 are provided corresponding to analyzers A to analyzers C. Each of the pull-down menus 43b1 to 43b3 displays the option to set either "YES" or "NO".

[0133] For example, the administrator of the information processing system 1 can access the settings screens 43a and 43b. The administrator can change the settings for measurement and testing items and analytical devices by using the pull-down menus 43a1 to 43a5 on the settings screen 43a. The administrator can also change the connection relationship between the transport device and the analytical device by using the pull-down menus 43b1 to 43b3 on the settings screen 43b. As a result, the consultation time prediction system 10 can calculate the predicted time in accordance with the change in the arrangement of the analytical devices for analyzing specimens in the laboratory.

[0134] <Modification> In the above embodiment, the consultation time prediction system 10 does not predict the test completion time and the consultation call time when the sample preprocessing is completed by the preprocessing device. However, the consultation time prediction system 10 may also predict the test completion time and the consultation call time during the sample preprocessing. With this configuration in which the test completion time and the consultation call time are predicted during the sample preprocessing, for example, if there is a long time between the sample preprocessing and the time the sample is loaded into the transport device or into the analyzer C, the consultation time prediction system 10 can provide the patient with a more accurate predicted time if the patient refers to the test completion time and the consultation call time after the sample preprocessing is completed and before the sample is loaded into the transport device or analyzer C.

[0135] Furthermore, for example, in a laboratory, an analytical instrument connected to the transport path of a transport device may not be used for a certain period of time. This situation can be confirmed by the examination time prediction system 10 by referring to the timestamp information DB 12. Therefore, based on the actual information stored in the timestamp information DB 12, if an analytical instrument connected to the transport path is not used for testing specimens even after a certain period of time, the processing device 120 may output to the graphical user interface device 40 a message suggesting that the analytical instrument connected to the transport path be disconnected from the transport path. The timing of this output may be, for example, when the administrator of the information processing system 1 accesses the system. At this time, a message including the suggestion to disconnect the analytical instrument from the transport path is displayed in a pop-up format on the display screen of the graphical user interface device 40. By viewing this display, the administrator can change the arrangement of analytical instruments in the laboratory to an appropriate arrangement.

[0136] Although embodiments of this disclosure have been described in detail above, the present invention is not limited to the embodiments described above and can be modified in various ways without departing from the gist of the invention. Each embodiment can be modified by adding, deleting, or replacing components, except for essential components. Unless otherwise specified, each component may be singular or plural. Combinations of each embodiment and its variations are also possible. Each of the above-described configurations, functions, and processing units may be implemented in part or in whole by hardware, such as by designing an integrated circuit, or by software, such as by a processor interpreting and executing a program. Data and information such as programs, tables, and files that realize each function can be stored in a recording device such as memory, a hard disk, or an SSD, or on a recording medium such as an IC card, an SD card, or a DVD.

[0137] 1... Information processing system, 10... Examination time prediction system, 11... Specimen attribute information DB, 11a... Specimen attribute information, 12... Timestamp information DB, 12a... Timestamp information, 13... Setting information DB, 13a... Analytical device setting information, 13b... Transport device connection information, 13c... Specimen count calculation setting information, 14... Learning model storage unit, 20... Clinical laboratory information system, 21... External system communication processing unit, 22... Prediction processing unit, 23... Screen display processing unit, 24... Learning model construction unit, 25... External communication processing unit, 40... Graphical user interface device, 41-43... Display screen, 50... Mobile terminal device, 110... Storage device, 120... Processing unit, 240... Learning model

Claims

1. A medical consultation time prediction system for a facility including a testing facility having a testing device for testing patient specimens and a transport device for transporting the specimens to the testing device, the system comprising: a storage device that stores specimen attribute information indicating the attributes of the specimen of the target patient, and progress information of multiple processes from reception to calling for consultation at the facility and actual information regarding the specimen for each reception number; and a processing device that calculates the predicted time for each process of the consultation, including the medical consultation time of the target patient to be predicted, using a learning model constructed from the actual information and the specimen attribute information, wherein the actual information used to construct the learning model includes urgency information indicating whether or not there is urgency in testing the specimen, the specimen attribute information includes the urgency information of the target patient, and when the processing device receives the specimen of the target patient and calculates the predicted time for the target patient, it inputs information including the urgency information of the target patient into the learning model to calculate the predicted time and stores the calculated predicted time in the storage device.

2. A consultation time prediction system according to claim 1, wherein the plurality of steps include the step of transporting the specimen into the transport device and the step of testing the specimen with the testing device, the actual information includes information indicating at least one of the following times: the time of laboratory reception when the specimen was received at the testing facility, the time of transport device arrival when the specimen was transported into the transport device, and the time of testing device arrival when the specimen was transported into the testing device, and the processing device, when calculating the predicted time, reflects congestion information indicating the transport status of the specimen within the testing facility, calculated from at least one of the times of laboratory reception, transport device arrival, and testing device arrival, in the calculation of the predicted time.

3. A consultation time prediction system according to claim 2, wherein the specimen congestion information includes at least one of the following: the number of specimens after acceptance of the test but before being transported to the transport device; the number of specimens transported to the transport device but before being transported to the testing device; and the number of specimens transported to the testing device.

4. A medical consultation time prediction system according to claim 2, wherein the processing device, when the specimen attribute information includes the urgency information of the target patient, performs the calculation of the predicted time using the learning model when the specimen is brought into the testing device without performing the calculation of the predicted time when the specimen is brought into the transport device.

5. A consultation time prediction system according to claim 2, wherein the urgency information is information indicating an emergency designation included in the specimen attribute information, or information indicating that the requesting medical department that requested the specimen is an emergency.

6. A medical consultation time prediction system according to claim 1, wherein the testing apparatus includes a first testing apparatus for testing a first measurement test item and a second testing apparatus for testing a second measurement test item, the first testing apparatus is connected to the transport path of the transport device, the second testing apparatus is not connected to the transport path of the transport device, the storage device stores connection information indicating the connection relationship between the transport device and the first and second testing apparatuses, and the processing device, when the measurement test item included in the sample attribute information of the target patient is the second measurement test item, calculates the predicted time using the learning model when the sample is brought into the second testing apparatus without calculating the predicted time when the sample is brought into the transport device.

7. A consultation time prediction system according to claim 6, wherein the processing device outputs a statement suggesting that the first testing device connected to the transport path be disconnected from the transport path if the first testing device connected to the transport path is not used to test the specimen after a certain period of time based on the actual performance information.

8. A medical examination time prediction system according to claim 1, wherein, when the processing device calculates the predicted time, if there are multiple specimen attribute information for the target patient in the storage device, it calculates the predicted time for each of the specimen attribute information, and the latest of the calculated predicted times is set as the predicted time for each specimen.

9. A consultation time prediction system according to claim 1, further comprising a user interface device for displaying information, wherein the user interface device displays the specimen attribute information, the actual information, and the predicted time stored in the storage device.

10. A medical consultation time prediction system according to claim 1, further comprising a communication processing unit capable of communicating with a mobile terminal device, wherein when accessed from the mobile terminal device held by the target patient, the processing unit reads the target patient's medical consultation call time from the storage device and displays the read medical consultation call time on the mobile terminal device.

11. A method for predicting the time a patient is called for consultation in a facility including a testing facility having a testing device for testing a patient's specimen and a transport device for transporting the specimen to the testing device, wherein the consultation time prediction system comprises: a storage device that stores specimen attribute information indicating the attributes of the specimen of a target patient, and progress of multiple processes from reception to consultation at the facility and actual information regarding the specimen for each reception number; a processing device that calculates the predicted time for each consultation process, including the consultation call time of the target patient to be predicted, using a learning model constructed from the actual information and the specimen attribute information, wherein the actual information used to construct the learning model includes urgency information indicating whether or not there is urgency in testing the specimen, the specimen attribute information includes the urgency information of the target patient, and the consultation time prediction method comprises: a step of receiving the specimen of the target patient; and, after receiving the specimen, when calculating the predicted time for the target patient, inputting information including the urgency information of the target patient into the learning model to calculate the predicted time. A method for predicting the time of a medical examination, comprising the steps of: storing the calculated predicted time in the storage device; 12. A display device for displaying information stored in a consultation time prediction system for predicting the consultation call time of a patient in a facility including a testing facility having a testing device for testing a patient's specimen and a transport device for transporting the specimen to the testing device, wherein the consultation time prediction system comprises: a storage device that stores specimen attribute information indicating the attributes of the specimen of a target patient, and progress information of multiple processes from reception to consultation at the facility and actual information regarding the specimen for each reception number; a processing device that calculates the predicted time for each process of the consultation, including the consultation call time of the target patient to be predicted, using a learning model constructed from the actual information and the specimen attribute information, wherein the actual information used to construct the learning model includes urgency information indicating whether or not there is urgency in testing the specimen, the specimen attribute information includes the urgency information of the target patient, and when the processing device calculates the predicted time of the target patient after receiving the specimen of the target patient, it inputs information including the urgency information of the target patient into the learning model to calculate the predicted time, and stores the calculated predicted time in the storage device, and the display device displays A display device that displays the calculated predicted time stored in the memory device.

Images