Specimen delay determination system, clinical examination information system, and specimen delay determination method

Abstract

The present disclosure proposes a technique for suppressing the cost of delay detection and promptly detecting a delay in the movement (transport) of a blood collection tube. The present disclosure proposes a specimen delay determination system that performs a delay determination process for a plurality of specimens using a collection implementation time of a specimen and a conveyance device time of the specimen, wherein the specimen delay determination system performs a process of constituting a group of a plurality of specimens including an object specimen of the delay determination process, a process of calculating an object specimen elapsed time representing an elapsed time from collection to a conveyance device of the object specimen based on the collection implementation time and the conveyance device time of the object specimen, a process of calculating a group constituent specimen elapsed time representing an elapsed time from collection to the conveyance device of a specimen other than the object specimen in the group, and a process of determining whether or not the object specimen is delayed based on the object specimen elapsed time and the group constituent specimen elapsed time (see FIG. 1).

Description

Technical Field

[0001] This disclosure relates to a specimen delay determination system, a clinical examination information system, and a specimen delay determination method. Background Technology

[0002] After blood is drawn at the hospital, and before the blood collection tube is moved into the device, the sample may not arrive at the device before the scheduled time due to loss, forgetting, or incorrect loading. These delays can lead to delayed diagnosis for the patient and require prompt detection. As a solution, for example, Patent Document 1 discloses a method that involves attaching an RFID tag to the blood collection tube to track and manage its movement (movement path, movement time), monitoring the activity of the sample (blood collection tube) within a specific area, thereby determining when the blood collection tube was lost.

[0003] Existing technical documents

[0004] Patent documents

[0005] Patent Document 1: Japanese Patent Application Publication No. 2019-49555 Summary of the Invention

[0006] The problem that the invention aims to solve

[0007] However, according to the aforementioned patent document 1, the implementation of RFID is required for tracking the behavior of blood collection tubes, but due to the cost, the implementation has not progressed.

[0008] Furthermore, the detection of sample delay only considers the travel time of individual blood collection tubes within a specific interval. The travel time of blood collection tubes is not constant daily; on congested days with a large number of samples collected or due to equipment malfunctions, it may take longer than usual to transport all blood collection tubes, which can sometimes be identified as a delay. However, the delay to be detected here is not the overall delay caused by congestion or malfunction, but rather the delay in transporting individual samples (blood collection tubes) caused by factors such as sample loss. Regarding this, in order to quickly detect the delay of individual samples, it is necessary to consider the condition of each blood collection tube for judgment. Thus, a delay detection technique is desired that balances rapid detection of delays for individual samples with cost reduction.

[0009] This disclosure was made in view of the following situation, and proposes a technique for rapidly detecting the movement (delivery) delay of blood collection tubes while suppressing the cost of delayed detection.

[0010] Methods for solving problems

[0011] To address the aforementioned issues, this disclosure provides a specimen delay determination system that is communicatively connected to a clinical examination information system to perform specimen delay determination processing. The clinical examination information system, for multiple specimens, manages at least the specimen collection time and the loading time (indicating the time the collected specimen was loaded into the transport or analysis device) in association with information from each specimen provider.

[0012] The specimen delay determination system has the following features:

[0013] Storage devices, which store various kinds of information;

[0014] The control unit uses at least a portion of various information to determine the delay in testing.

[0015] The control department performs the following processing:

[0016] Processing information on the collection time and the time of placement into the device for multiple specimens obtained from the clinical examination information system;

[0017] The processing that constitutes a group of multiple specimens, including the object specimens for delayed determination processing;

[0018] The processing time of the object sample is calculated based on the collection time and the time of entry into the transfer device, representing the elapsed time from the collection of the object sample to its entry into the transfer device;

[0019] Within a group, the calculation of the time elapsed from the collection of a specimen other than the target specimen to its entry into the transport device constitutes the specimen elapsed time processing.

[0020] Based on the time elapsed between the sample and the time elapsed between the sample composition and the sample processing, it is determined whether there was any delay in the processing of the sample.

[0021] Further features relating to this disclosure will become clear from the description and drawings herein. Furthermore, this disclosure is achieved and implemented by means of elements and combinations thereof, as well as the detailed description below and the appended claims.

[0022] The description in this specification is merely typical and does not limit the claims or application of this disclosure in any way.

[0023] Invention Effects

[0024] According to the technology disclosed herein, it is possible to suppress the cost of delayed detection and to quickly detect delays in the movement (delivery) of blood collection tubes. Attached Figure Description

[0025] Figure 1This is a diagram illustrating an example of the overall structure of the blood collection tube delivery information management system 100 according to the first embodiment.

[0026] Figure 2 This is a diagram illustrating an example of the structure of a setting information input GUI (Graphical User Interface) 200 displayed on the display screen of the user interface 140 when a user inputs setting information into the information system 105, according to the first embodiment.

[0027] Figure 3 This is a flowchart used to explain the details of the delay determination process.

[0028] Figure 4 This is a diagram illustrating an example of the overall structure of the blood collection tube delivery information management system 400 according to the second embodiment.

[0029] Figure 5 This is a diagram illustrating a structural example of the learning model in the second embodiment.

[0030] Figure 6 This is a flowchart explaining the details of the delayed determination process for blood collection tubes (samples) in the second embodiment.

[0031] Figure 7 It is a flowchart used to illustrate the details of the learning model generation and update process. Detailed Implementation

[0032] Hereinafter, embodiments (first and second embodiments) of the present disclosure will be described with reference to the accompanying drawings. In the drawings, functionally identical elements are sometimes shown with the same numbers. Furthermore, the drawings illustrate specific embodiments that conform to the principles of the present disclosure, but these are for the purpose of understanding the present disclosure and are in no way intended to limit the interpretation of the present disclosure.

[0033] Furthermore, while this embodiment has been described in great detail by those skilled in the art for the purpose of implementing this disclosure, other installations and methods are also possible. It should be understood that structural and constructional changes and substitutions of various elements can be made without departing from the scope and spirit of the technical concept of this disclosure. Therefore, the following description is not intended to be limited to this.

[0034] (1) First implementation method

[0035] The first embodiment involves the following: grouping multiple blood collection tubes (usually prepared by one subject) containing blood (samples) collected from multiple subjects, at a predetermined blood collection interval (which can be set by the user) (which may also include blood collection tubes containing samples collected from other subjects) and / or the first X blood collection tubes (which can be set by the user; X is any integer) of the blood collection tubes for delayed detection; statistically processing the loading device time, which represents the time from the end of the blood collection process of each blood collection tube in the same group to the time of loading into the device (transport device, automatic analysis device); and detecting the transport delay of the blood collection tubes based on the statistical processing results. Furthermore, while grouping is done by the first X blood collection tubes of the blood collection tubes for delayed detection, it is also possible to group them by the X blood collection tubes before and after the blood collection tubes for delayed detection. In this case, for example, it can be predetermined what percentage (%) of the overall samples will be delayed in determining the delay before performing delayed detection on the blood collection tubes for the delayed detection (a threshold setting for starting delayed detection).

[0036] <Example of the overall structure of a blood collection tube delivery delay detection system>

[0037] Figure 1 This is a diagram illustrating an example of the overall structure of the blood collection tube delivery information management system 100 according to the first embodiment.

[0038] The blood collection tube delivery information management system 100 includes: a blood collection system 101, a Laboratory Information System (LIS) 102, at least one delivery device 103, at least one automatic analysis device 104, and an information system 105, which are connected to each other via a network 106 in a manner capable of communication. Alternatively, the system can be configured such that the functions of the blood collection system 101 are included in the LIS 102. Furthermore, the system can also be configured such that the functions of the information system 105 are integrated into the LIS 102. Moreover, the system can also be configured such that the blood collection system 101, LIS 102, delivery device 103, and automatic analysis device 104 are connected via a first network (not shown), and the LIS 102 and information system 105 are connected via a second network (not shown) different from the first network.

[0039] The blood collection system 101, for example, is composed of a computer. Based on command information (patient information, ID, and item command information) received from the LIS 102, it determines the number and type of blood collection tubes to be taken, and prepares labels and blood collection tubes on a tray to match the patient's blood collection instructions. The technician then performs blood collection according to the labels. When the blood collection system 101 receives information indicating the end of blood collection input by the technician, it sends information including the blood collection tube ID and a timestamp indicating the end of blood collection for each tube, along with the patient information, to the LIS 102. Furthermore, blood collection-related information can be obtained, for example, by reading the barcode sticker affixed to each blood collection tube using a barcode reader.

[0040] LIS102 receives the aforementioned blood collection information from blood collection system 101, blood collection tube loading information from delivery device 103, and measurement and / or analysis results from automatic analysis device 104, and manages this information according to the subject. In addition, LIS102 sends information about the blood collection execution time (blood collection end time) associated with each blood collection tube and information about the loading time of each blood collection tube into the device to information system 105 at predetermined time intervals (each time it is received (in real time) or at predetermined time intervals).

[0041] For example, the transport device 103 transports blood collection tubes brought in by the user from the receiving location (blood collection site) to the automated analyzer 104. Additionally, as described above, the transport device 103 sends blood collection tube receiving information (including information about the receiving location, receiving date and time, and transport destination) to the LIS 102. Furthermore, the transport device 103 transports blood collection tubes that have been sorted in the blood collection room according to the analytical purpose (the sorting operation is performed by the user) to the target automated analyzer 104.

[0042] The automated analysis device 104 analyzes, for example, the blood contained in blood collection tubes delivered by the delivery device 103 or blood collection tubes inserted by the user, for items set as analysis content for each analysis device. Furthermore, the automated analysis device 104 sends blood collection tube insertion information (e.g., identification information of the automated analysis device 104 as the insertion destination, insertion date and time, etc.) and analysis / measurement results to the LIS 102. Additionally, when the user inserts the blood collection tube into the automated analysis device 104, for example, the blood collection tube may be inserted into the automated analysis device 104 manually by the user in the blood collection room without being transported by the delivery device 103.

[0043] The information system 105 includes, for example, a processing unit 110 composed of a processor, a storage unit 120 composed of a specified storage device, a network interface (e.g., a communication device) 130 that receives information sent via a network 106 and transmits it to the processing unit 110, and a user interface (e.g., an input / output device) 140 for users to input information and give instructions or output processing results.

[0044] The processing unit 110 includes a data acquisition unit 111, a decision unit 112, a user input acceptance unit 113, and a user notification unit 114. These functions can be implemented either in hardware or by the processing unit 110, which acts as a processor, reading various programs (not shown) stored in the storage unit 120 and expanding them in the internal memory (not shown).

[0045] The storage unit 120 includes: a blood collection implementation time information storage unit 121, which associates the blood collection implementation date and time (blood collection end date and time) with the blood collection tube identifier information of each blood collection tube; a loading device time information storage unit 122, which associates the time when the blood collection tube is loaded into (put into) the delivery device 103 or the automatic analysis device 104 (which can be called "system entry time") with the blood collection tube identifier information of each blood collection tube; and a setting information storage unit 123, which stores the definition of the blood collection tube group and the delay determination information set by the user.

[0046] In the processing unit 110, the data acquisition unit 111, for example, when acquiring at least the identifier information of each blood collection tube (the aforementioned blood collection tube identifier information: information assigned to the blood collection tubes according to the blood collection order), the blood collection implementation time (blood collection end time) associated with each blood collection tube (blood collection implementation time information), and the aforementioned loading time information of each blood collection tube (loading device time information) sent from the LIS 102, associates the blood collection tube identifier information with the blood collection tube identifier information, stores the blood collection implementation time information in the blood collection implementation time information storage unit 121, and stores the loading time information in the loading device time information storage unit 122. For example, when blood collection is performed (by the user scanning the barcode of the blood collection tube to perform blood collection), the blood collection tube identifier information and the blood collection implementation time information are transmitted from the blood collection system 101 to the LIS 102. Furthermore, the data acquisition unit 111 acquires the blood collection tube identifier information and the blood collection implementation time information sent sequentially from the LIS 102. In addition, the data acquisition unit 111 acquires the loading device time information (associated with each blood collection tube identifier information) sent from LIS102 at a time different from the blood collection tube identifier information and the blood collection implementation time information (for example, later than these information).

[0047] The determination unit 112 reads user-defined information (group definition information and delay determination formula) from the setting information storage unit 123. Furthermore, the determination unit 112 groups the multiple blood collection tubes of the determination object according to the group definition information. Additionally, the determination unit 112 obtains the blood collection implementation time information of each blood collection tube in the group to which the determination object's blood collection tubes belong from the blood collection implementation time information storage unit 121, and obtains the loading time information of each blood collection tube in the same group from the loading device time information storage unit 122, and substitutes these into the delay determination formula, thereby performing delay determination processing. The determination unit 112 transmits the result of this delay determination processing (delay determination result) to the user notification unit 114.

[0048] User input receiving unit 113 receives setting information (at least the aforementioned group definition information and delay determination information) input by the user from the user interface 140, which is an input / output device, and stores it in setting information storage unit 123. When inputting setting information, the user can use the input device of user interface 140 (keyboard, mouse, touch panel, microphone, etc.).

[0049] The user notification unit 114 notifies the user of the delay determination result received from the determination unit 112 via the output device (display, printer, speaker, etc.) of the user interface 140. Here, the delay determination result can be notified to the user in various ways, such as knowing whether the blood collection tube of the determined object has a delay, knowing whether there are blood collection tubes that cause delay in the object group, and / or information about blood collection tubes that cause delay.

[0050] <Example of the structure of the information input GUI>

[0051] Figure 2 This is a diagram illustrating an example of the structure of a setting information input GUI (Graphical User Interface) 200 displayed on the display screen of the user interface 140 when a user inputs setting information into the information system 105, according to the first embodiment.

[0052] The setting information input GUI200, also known as the delay detection setting screen, includes: a delay determination setting unit 210, a blood collection group definition setting unit 220, an OK button 230, and a cancel button 240.

[0053] The delayed decision setting unit 210 includes, for example, a decision display bar 211 and a scroll button 212 that changes the decision displayed in the decision display bar 211 each time it is pressed. The user can select a desired decision by pressing (operating) the scroll button 212. The user selects a decision from a plurality of pre-prepared decision codes via the delayed decision setting unit 210. The plurality of decision codes are codes that detect deviation values, and may include, for example, codes based on the interquartile range method, the 3-sigma method, the chi-square distribution, the k-nearest neighbor method, the average comparison method, etc.

[0054] The blood collection group definition setting unit 220 includes a tube count setting column 221 for setting the number of blood collection tubes included in the same group and a time setting column 222 for setting the blood collection execution time of the blood collection tubes included in the same group. The tube count setting column 221 is used to set how many blood collection tubes, starting from the delayed determination object and preceding it, will be considered as a group when multiple blood collection tubes are arranged in blood collection execution time order. The time setting column 222 is used to set how many minutes prior to the delayed determination object's blood collection execution will be considered as a group when multiple blood collection tubes are arranged in blood collection execution time order. Multiple blood collection tubes that satisfy both the conditions set in the tube count setting column 221 and the conditions set in the time setting column 222 can be defined as a group, or multiple blood collection tubes that satisfy any condition can be defined as a group. When only one condition is used, the blood collection group definition setting unit 220 can be configured such that NA is displayed in the setting column corresponding to the unused condition.

[0055] When the user has finished entering the settings information, they can close the settings information input GUI by pressing the OK button 230. On the other hand, the system is configured such that when the user presses the Cancel button 240, the temporarily selected and entered information is cleared, and the settings information input GUI returns to a state where it can be set again.

[0056] <Details of Delay Decision Processing>

[0057] Figure 3 This is a flowchart used to explain the details of the delay determination process.

[0058] (i) Step 301

[0059] The determination unit 112 executes (loops) steps 302 to 307 at predetermined time intervals (pre-set time intervals: for example, intervals of a few minutes). Furthermore, the delay determination process for blood collection tubes can be performed at a stage where the information (blood collection time information and device loading time information) of all blood collection tubes constituting the user-defined group is consistent. For example, when the information system 105 obtains information about a blood collection tube containing a sample, it can execute the X root of that blood collection tube (X: defined by grouping information (refer to...). Figure 2 The delayed decision-making process for blood collection tubes is defined as an integer. Therefore, the specified time interval used for the loop only serves as a trigger for the start of the delayed decision-making process. Thus, the delayed decision-making process can also be performed in real time for the trigger, i.e., whenever information about the blood collection tube is obtained.

[0060] (ii) Step 302

[0061] The determination unit 112 obtains information about multiple blood collection tubes (blood collection tube identifier information, blood collection execution time information, and transfer device time information) for multiple blood collection tubes that have been inserted into the automatic analysis device 104 (including insertion via manual operation and insertion / transfer by the transport device 103). It also obtains identifier information for blood collection tubes for which blood collection has been completed but for which specimen (blood collection tube) delay determination has not been performed. Furthermore, since blood collection has been completed when blood collection execution time information has been obtained for the blood collection tubes, step 302 at this point can essentially be considered a process for determining blood collection tubes for which specimen delay determination has not been performed.

[0062] (iii) Step 303

[0063] The determination unit 112 sequentially performs steps 304 to 307 on the blood collection tubes (from the first to the nth) that were not subject to the delayed determination of the specimen obtained in step 302 (the processing is cyclical based on the number of blood collection tubes).

[0064] (iv) Step 304

[0065] The determination unit 112 defines a group for the k-th (k = 1, 2, 3, ..., n) blood collection tube according to the order of the blood collection tube identifier information and based on the grouping definition information stored in the setting information storage unit 123. For example, if the grouping definition information specifies that the first 10 (X = 10) blood collection tubes of the delayed determination object are set to the same group, the blood collection tube with the identifier information k-th (e.g., k = 100) belongs to the group consisting of the (k-10)-th (90)-th (100)-th blood collection tubes. That is, the k-th blood collection tube becomes the last blood collection tube in that group.

[0066] Then, the determination unit 112 determines whether all blood collection tubes except the k-th blood collection tube, which is the target of the delay determination process in this group, have been moved into the device. Whether the device has been moved into the device can be determined, for example, by whether the device moving time information has been obtained. If all blood collection tubes in this group other than the k-th blood collection tube have been moved into the device (if yes in step 304), the process proceeds to step 305. On the other hand, if there are blood collection tubes in this group other than the k-th blood collection tube that have not been moved into the device (if no in step 304), the delay determination process for the k-th blood collection tube ends. Then, the process proceeds to step 303, and the delay determination process for the (k+1)-th blood collection tube is performed.

[0067] Here, if no loading device time information is obtained for all blood collection tubes other than the one subject to delay determination within the same group, no delay determination process is performed. Therefore, for the k-th blood collection tube, delay determination process is performed after it is confirmed that the loading device time information for all blood collection tubes (excluding the k-th) within the group has been obtained.

[0068] (v) Step 305

[0069] The determination unit 112 reads the delayed determination formula from the setting information storage unit 123 and determines whether the kth blood collection tube meets the deviation value within the same group.

[0070] (vi) Step 306

[0071] The determination unit 112 determines whether there is a delay in the k-th blood collection tube based on whether the deviation value is met. If there is a delay (yes in step 306), the process proceeds to step 307. If there is no delay (no in step 306), the delay determination process for the k-th blood collection tube ends. Then, the process proceeds to step 303 to perform the delay determination process for the (k+1)-th blood collection tube.

[0072] (vii) Step 307

[0073] The user notification unit 114 receives the determination result from the determination unit 112 and outputs information indicating a delay in the k-th blood collection tube to the user interface 140 (for example, displaying the information on the display unit of the input / output device). Thus, the user can identify the possibility of the k-th blood collection tube being lost.

[0074] (2) Second implementation method

[0075] The second implementation involves the following: grouping multiple blood collection tubes (typically prepared by one subject) containing blood collected from multiple subjects at a specified blood collection interval (which can be set by the user), and / or the first X roots (which can be set by the user; X is any integer) of the blood collection tubes for delayed detection of the subject; performing delayed determination processing of the subject's blood collection tubes within the group using a learning model; and notifying the results of the delayed determination processing.

[0076] <Example of the overall structure of a blood collection tube delivery delay detection system>

[0077] Figure 4 This is a diagram illustrating an example of the overall structure of the blood collection tube delivery information management system 400 according to the second embodiment. Furthermore, in Figure 4 In the middle, to and Figure 1 The blood collection tube delivery information management system 100 shown has the same structure and the same reference number. Structural elements assigned the same reference number have the same... Figure 1 The structural elements shown have the same function, therefore, detailed descriptions are omitted here.

[0078] The blood collection tube delivery information management system 400 includes: a blood collection system 101, a Laboratory Information System (LIS) 102, at least one delivery device 103, at least one automatic analysis device 104, and an information system 401, which are connected to each other via a network 106 in a manner capable of communication. Alternatively, the system can be configured such that the functions of the blood collection system 101 are included in the LIS 102. Alternatively, the system can be configured such that the functions of the information system 401 are integrated into the LIS 102. Furthermore, the system can also be configured such that the blood collection system 101, LIS 102, delivery device 103, and automatic analysis device 104 are connected via a first network (not shown), and the LIS 102 and information system 401 are connected via a second network (not shown), which is different from the first network.

[0079] Information system 401 includes, for example, a processing unit 410 composed of a processor, a storage unit 420 composed of a specified storage device, a network interface (e.g., a communication device) 130 that receives information sent via network 106 and transmits it to the processing unit 410, and a user interface (e.g., an input / output device) 140 for users to input information, give instructions, or output processing results.

[0080] The processing unit 410 includes: a data acquisition unit 111, a learning unit 411, a judgment unit 412, a user input receiving unit 413, and a user notification unit 414. These functions can be implemented either in hardware or by the processing unit 410, which acts as a processor, reading various programs (not shown) stored in the storage unit 420 and expanding them in the internal memory (not shown).

[0081] The storage unit 420 includes: a blood collection implementation time information storage unit 121, which associates the information of the blood collection implementation date and time (blood collection end date and time) with the blood collection tube identifier information of each blood collection tube; a loading device time information storage unit 122, which associates the time when the blood collection tube is loaded into (put into) the delivery device 103 or the automatic analysis device 104 (which can be called "system entry time") with the blood collection tube identifier information; a learning and judgment setting information storage unit 421; a setting information storage unit 422; and a learning model storage unit 423.

[0082] The learning and judgment setting information storage unit 421 stores, for example, information on the node value settings and weight settings of a learning model containing multiple nodes as learning settings, and information on a threshold for determining whether the latency obtained by the learning model (neural network) is a latency (a threshold used to compare with the latency of the output to determine whether there is a latency) as judgment settings. The learning model can be set, for example, according to the specimen analysis items in the automatic analysis device 104 and by week. Therefore, even for the same specimen analysis item (e.g., LDH value), different learning models can be used if the week is different.

[0083] The information storage unit 422 stores information about the definition of the blood collection tube group set by the user.

[0084] The learning unit 411 first reads the learning model for the week and analysis items of the object being generated or updated from the learning model storage unit 423. Then, the learning unit 411 sets information on the latency level of data determined to have actually caused latency by the object as training data for the neural network. Additionally, it sets the specified data corresponding to this training data as input data for the neural network and adjusts the weighting coefficients of the neural network, thereby generating and updating the learning model. The generation and updating process of the learning model will be described later (see [reference]). Figure 7 ).

[0085] The determination unit 412 reads, for example, a learning model prepared for the corresponding week and the corresponding analysis item from the learning model storage unit 423, applies the input data to the learning data, and obtains information on the degree of delay. Then, the determination unit 412 obtains a delay determination threshold from the learning and determination setting information storage unit 421, and determines whether the specimen (blood collection tube) of the delay determination object has experienced delay by comparing it with the aforementioned delay degree. The determination unit 412 transmits the determination result to the user notification unit 414.

[0086] The user input receiving unit 413 receives the group definition information, the learning setting information, and the judgment setting information input by the user from the user interface 140, which is an input / output device. It stores the group definition information in the setting information storage unit 422 and the learning setting information and judgment setting information in the learning and judgment setting information storage unit 421. When inputting setting information, the user can use the input device of the user interface 140 (keyboard, mouse, touch panel, microphone, etc.).

[0087] The user notification unit 414 notifies the user of the delay determination result received from the determination unit 412 via the output device (display, printer, speaker, etc.) of the user interface 140. Here, the delay determination result can be notified to the user in various ways, such as knowing whether the blood collection tube of the determined object has a delay, knowing whether there are blood collection tubes that cause delay in the object group, and / or information about blood collection tubes that cause delay.

[0088] <Learning Model>

[0089] Figure 5 This is a diagram illustrating a structural example of the learning model in the second embodiment. This learning model can be constructed from neural networks, regression trees, Bayesian recognizers, etc.

[0090] The learning model 500 consists of an input layer 502 (input data 501), an intermediate layer 503, and an output layer 504 with varying output delay. Information input to the input layer 502 (input data 501) propagates to the intermediate layer 503 and then sequentially to the output layer 504, outputting an inference result based on the information input from the output layer 504 to the input layer 502. The input layer 502, intermediate layer 503, and output layer 504 each have multiple input units 5021 to 5023, intermediate units 5031 to 5034, and an output unit 5041, as shown in circles. Furthermore, while neural networks typically have multiple intermediate layers, this diagram uses intermediate layer 503 as a representative example. The input data to each input unit 5021 to 5023 of the input layer 502 is weighted by the coupling coefficient between each input unit 5021 to 5023 and the intermediate units 5031 to 5034, and then input to each intermediate unit 5031 to 5034. The values ​​of intermediate units 5031 to 5034 in intermediate layer 503 are calculated by summing the values ​​from input units 5021 to 5023. Furthermore, the outputs from each intermediate unit 5031 to 5034 in intermediate layer 503 are weighted by the coupling coefficient between intermediate units 5031 to 5034 and output unit 5041, and then input to output unit 5041. The value of output unit 5041 in output layer 504 is calculated by summing the values ​​from intermediate units 5031 to 5034. Thus, the processing in intermediate layer 503 is equivalent to performing a non-linear transformation on the input data input to input layer 502, outputting the delay level 505 as the output data of output layer 504.

[0091] Figure 5 The learning model related to the delay level calculation is represented together with the input and output data as learning model 500. Input layer 502 accepts the elapsed time from the blood collection execution time of the delay determination object specimen (delay determination object blood collection tube) to the determination time, the average time from the blood collection execution of specimens other than the delay object specimen in the blood collection group to the entry into the device, and the number of blood collection specimens (number of blood collection tubes) per predefined specified unit time (e.g., one hour) independent of the blood collection group as input data. Output layer 504 outputs the delay level as the calculation result (inference result) corresponding to the input.

[0092] The determination unit 412 determines whether the delay determination object specimen has experienced delay based on whether the output value of the "delay level" of the output unit 5041 is a probability value and whether the output probability value is above or below the threshold set by the user.

[0093] <Details of Delay Decision Processing>

[0094] Figure 6 This is a flowchart explaining in detail the delayed determination process for the blood collection tube (sample) in the second embodiment.

[0095] (i) Step 601

[0096] The determination unit 412 executes (loops) steps 602 to 609 at predetermined time intervals (pre-set time intervals: for example, intervals of a few minutes). Furthermore, similar to the first embodiment, the delay determination process for blood collection tubes in the second embodiment can also be performed at a stage where the information (blood collection time information and loading device time information) of all blood collection tubes (samples) constituting the user-defined group is consistent. For example, when the information system 105 obtains information about a blood collection tube containing a sample, it can execute the X root of that blood collection tube (X: defined by grouping information (refer to...). Figure 2 The delayed decision-making process is performed on blood collection tubes (samples) before the integer defined in the original text. Therefore, the specified time interval used for the loop only serves as a trigger for the start of the delayed decision-making process. Thus, the delayed decision-making process can also be performed in real-time, i.e., whenever information about the blood collection tube (sample) is obtained, in response to the trigger.

[0097] (ii) Step 602

[0098] The determination unit 412 obtains information about multiple blood collection tubes (blood collection tube identifier information, blood collection implementation time information, and device loading time information) for multiple blood collection tubes that have been inserted into the automatic analysis device 104 (including insertion via manual operation and insertion / loading by the transport device 103). It also obtains identifier information for blood collection tubes for which blood collection has been completed but the specimen (blood collection tube) delay determination has not been implemented. Furthermore, since blood collection has been completed when the blood collection implementation time information has been obtained for the blood collection tubes, step 602 at this point can essentially be considered a process for determining blood collection tubes for which the specimen delay determination has not been implemented.

[0099] (iii) Step 603

[0100] The determination unit 412 sequentially performs steps 604 to 609 on the blood collection tubes (from the first to the nth) that were not subject to the delayed determination of the specimen obtained in step 602 (the processing is cyclical based on the number of blood collection tubes).

[0101] (iv) Step 604

[0102] The determination unit 412 defines a group for the k-th (k = 1, 2, 3, ..., n) blood collection tube according to the order of the blood collection tube identifier information, based on the grouping definition information stored in the setting information storage unit 422. For example, if the grouping definition information specifies that the first 10 (X = 10) blood collection tubes of the delayed determination object are set to the same group, the blood collection tube identifier information indicates that the k-th (e.g., k = 100) blood collection tube belongs to the group consisting of the k-10 (90)-th to the k (100)-th blood collection tubes. That is, the k-th blood collection tube becomes the last blood collection tube in that group.

[0103] Then, the determination unit 412 determines whether all blood collection tubes except the k-th blood collection tube, which is the target of the delay determination process in this group, have been moved into the device. Whether the device has been moved into the device can be determined, for example, by whether the device moving time information has been obtained. If all blood collection tubes in this group other than the k-th blood collection tube have been moved into the device (if yes in step 604), the process proceeds to step 605. On the other hand, if there are blood collection tubes in this group other than the k-th blood collection tube that have not been moved into the device (if no in step 604), the delay determination process for the k-th blood collection tube ends. Then, the process proceeds to step 603, and the delay determination process for the (k+1)-th blood collection tube is performed.

[0104] Here, if no loading device time information is obtained for all blood collection tubes other than the one subject to delay determination within the same group, no delay determination processing is performed. Therefore, for the k-th blood collection tube, delay determination processing is performed after it can be confirmed that the loading device time information of all blood collection tubes (excluding the k-th one) within the group has been obtained.

[0105] (v) Step 605

[0106] The determination unit 412 obtains from the learning model storage unit 423 the learning model corresponding to the analysis item of the blood collection tube (kth blood collection tube) that is the same as the week in which the delayed determination is performed.

[0107] (vi) Step 606

[0108] The determination unit 412 obtains information on the time from the blood collection of the blood collection tube of the delayed determination object to the time of delayed determination, the average time (average time) of the blood collection of blood collection tubes other than the blood collection tube of the delayed determination object in the same group to the time of entry into the transport device, and the information on the number of blood collection tubes (number of specimens) per specified unit time (e.g., 1 hour), and inputs it to the input layer 502 as input data 501 of the learning model.

[0109] (vii) Step 607

[0110] The decision unit 412 obtains information about the delay level 505 as the result of the operation (inference result) from the learning model that has been input data 501.

[0111] (viii) Step 608

[0112] The determination unit 412 obtains the delay determination threshold from the learning and determination setting information storage unit 421, compares it with the delay level 505 obtained in step 607, and thereby determines whether the delay level 505 is above the delay determination threshold.

[0113] If the delay level 505 is above the delay determination threshold (if yes in step 608), the process proceeds to step 609. If the delay level 505 is less than the delay determination threshold (if no in step 608), the delay determination process for the k-th blood collection tube ends. Then, the process proceeds to step 603 to perform the delay determination process for the (k+1)-th blood collection tube.

[0114] (ix) Step 609

[0115] The user notification unit 114 receives the determination result from the determination unit 412 and outputs information indicating a delay in the k-th blood collection tube to the user interface 140 (for example, displaying the information on the display unit of the input / output device). Thus, the user can identify the possibility of the k-th blood collection tube being lost.

[0116] <Learning Model Update Processing>

[0117] Figure 7 This is a flowchart illustrating the detailed processes of learning model generation and update. Figure 7 In this example, the learning model is set to be updated daily, but it can also be set to be updated at regular intervals.

[0118] (i) Step 701

[0119] Learning Unit 411 performs steps 702 to 708 daily to update the learning model in use and adjust the learning model (increase probability).

[0120] (ii) Step 702

[0121] The learning unit 411 retrieves the learning model that corresponds to the week of the week on which the update process was implemented from the learning model storage unit 423. This learning model may contain, for example, multiple learning models corresponding to each analysis item for that week.

[0122] (iii) Step 703

[0123] Learning unit 411 repeatedly performs the processing steps 704 to 708 for each of the learning models used in the delayed determination processing of specimens (blood collection tubes) in multiple analysis items.

[0124] (iv) Step 704

[0125] Learning unit 411 obtains the learning model for updating the object analysis project from the multiple learning models obtained in step 702.

[0126] (v) Step 705

[0127] The learning unit 411, for example, uses data from the day before the day the learning model update process is performed to set information on the degree of delay of blood collection tubes (samples) judged to be delayed as training signal data. The blood collection tubes judged to be delayed can be based on manual input from the user (actually determined to be delayed by the user), or they can be blood collection tubes judged to be delayed based on the degree of delay obtained from using the learning model the previous day and a pre-set delay judgment threshold. However, as training signal data, it is preferable to set it to data that the user actually perceives as experiencing delay (data involving truly bothersome delays) in order to generate an accurate learning model.

[0128] (vi) Step 706

[0129] The learning unit 411 generates (acquires) input data, which consists of information on the time from blood collection to actual placement into the device for blood collection tubes (samples) that are actually determined to be delayed based on the previous day's data (used as training signal data in step 705), the average time from blood collection to placement into the device for multiple blood collection tubes in the group to which the blood collection tube belongs, excluding the blood collection tubes determined to be delayed, and information on the number of blood collection tubes (samples) per specified unit time. The time from blood collection to placement into the device associated with each blood collection tube can be obtained by storing information in the blood collection time information storage unit 121 and the placement device time information storage unit 122, and the average time can also be calculated based on this information. In addition, the number of blood collection tubes (samples) per specified unit time can be provided as a set value, or it can be obtained by actually counting in LIS 102.

[0130] (vii) Step 707

[0131] The learning unit 411 inputs the input data generated (obtained) in step 707 into the input layer 502 of the learning model obtained in step 704, and inputs the training signal data generated (obtained) in step 706 into the output layer 504 of the learning model for learning, adjusting the weight coefficients of the learning model. Thus, the learning model can be optimized through update processing.

[0132] Furthermore, if multiple blood collection tubes were identified as delayed in the previous day's data, multiple sets of training signal data and input data can be generated, allowing for multiple training iterations of the same learning model. By implementing multiple learning model update processes, a more accurate learning model can be generated.

[0133] (viii) Step 708

[0134] The learning unit 411 saves (e.g., overwrites) the updated learning model of the object analysis project in the learning model storage unit 423 of the storage unit 420.

[0135] (3) Summary

[0136] (i) In the first and second embodiments described above, the delay determination of the blood collection tube containing blood collected from the subject as a specimen was explained. However, the specimen is not limited to blood. It can be any specimen collected from the human body, such as urine or saliva.

[0137] In addition, the functions of the information system 105 or 401 in the first and second embodiments (specimen delay determination function) can also be configured to be incorporated into the clinical examination information system 102.

[0138] (ii) According to the first embodiment, the processing unit (control unit) 110 of the information system (sample delay determination system) 105 performs the following processing: obtaining information from the clinical examination information system 102 on the collection implementation time (blood collection date and time) and the transfer device time (date and time when the sample is placed into the transfer device or analysis device) of each of the multiple samples (blood collection tubes); processing to form a group consisting of multiple samples including the sample to be determined for delay, according to a set definition; processing to calculate the elapsed time of the sample, representing the elapsed time from the collection of the sample to the transfer device, based on the collection implementation time and the transfer device time of the sample; processing to calculate the elapsed time of the group consisting of the samples, representing the elapsed time from the collection of the sample other than the sample to the transfer device, within the above group; and processing to determine whether the sample has a delay based on the calculation result obtained by applying the sample elapsed time and the elapsed time of the group consisting of the samples to the delay determination formula. In this way, in the case of delay due to the condition of each sample (blood collection tube), the delay is detected by comparing with other samples in the same sample group. Therefore, since managers will notice the delay as soon as possible, they can perform procedures such as searching for and re-collecting samples (blood sampling), which can shorten the delay in examination and thus shorten the delay in diagnosis and treatment for patients.

[0139] The aforementioned group can be defined as multiple specimens belonging to the same analytical item group as the target specimen, and consisting of multiple specimens collected before a specified time before the target specimen collection (e.g., 10 minutes before the target specimen collection) and / or within a specified number (the first 50 specimens, totaling 51 specimens including the target specimen) from the target specimen. By forming groups in this way, it is possible to detect any delays among multiple specimens collected at approximately the same time (without such a large time difference), thus enabling efficient and rapid determination of specimen delays.

[0140] Specifically, when determining whether there is a delay in the sample, the processing unit (control unit) 110 applies the elapsed time of the sample and the elapsed time of the constituent samples to the formula for calculating the delay characteristic (for example, according to the formula selected by the user: the formula of the interquartile range method: refer to...). Figure 2 The processing unit 110 calculates a delay characteristic (e.g., deviation value) of the sample. Then, it determines whether the sample has a delay by comparing the calculated delay characteristic (deviation value) with a delay determination threshold (e.g., a threshold that can be set by the user to determine whether the delay characteristic (deviation value) represents an outlier). The delay characteristic calculation formula can be appropriately set by the user; therefore, delay characteristics used according to the facility can be used for delay determination, enabling faster and more accurate detection of the sample's delay.

[0141] Furthermore, the information system 105 obtains information on the collection and placement times of at least a plurality of specimens, as well as the analysis items for each specimen, from the clinical examination information system 102, and stores this information in the storage unit 120 in association with the specimen identification information. Thus, the information system 105 can perform delay determination for a specific specimen by obtaining only the minimum information associated with the specimen. The delay determination is performed when it can be confirmed that the elapsed time of the constituent specimens has been obtained for all specimens other than the target specimen included in the aforementioned group. If there is a delayed specimen other than the target specimen, the delay determination for that target specimen can be skipped. After determining that there is a delay in the delay determination for the specimen other than the target specimen, the delayed specimen is removed, and the delay determination for the target specimen is performed again.

[0142] (iii) According to the second embodiment, the processing unit (control unit) 410 of the information system (specimen delay determination system) 401 performs the following processing: processing to obtain information on the collection implementation time of each of the multiple specimens and the information on the time of the transfer device from the clinical examination information system 102; processing to form a group consisting of multiple specimens including the object specimen for delay determination processing (the processing is the same as in the first embodiment); processing to apply the input data, which is the time from the collection of the object specimen to the execution of the delay determination processing, the average of the elapsed time of the group consisting of specimens representing the time elapsed from the collection of all specimens other than the object specimen in the group to the time they are transferred into the transport device or analysis device, and the number of specimens per predetermined unit time (a predetermined time: for example, 1 hour), to a learning model, thereby outputting the degree of delay of the object specimen; and processing to determine whether the object specimen has a delay by comparing the degree of delay with a delay determination threshold (based on a user-defined value). This eliminates the need for users to research past data and pre-register suitable delay determination thresholds and delay characteristic calculation formulas (delay determination formulas) for their facilities, and avoids the need to change these thresholds and formulas based on changes in facility operation. Furthermore, the learning model can be configured to correspond to the analysis items of the target specimens. Additionally, multiple specimens sharing the same analysis item as the target specimens can be grouped together, and the learning model can be applied to each group. This allows for the use of a more suitable learning model to perform delay determination.

[0143] Furthermore, in the second embodiment, the learning model is updated appropriately (daily or periodically). The learning model is updated by generating updated input data and training signal data, and by applying the updated input data and training signal data to the learning model before the update. Here, the data used as update input data includes: the time from the collection of a specimen determined to be delayed (i.e., a learning specimen) to its transfer into the transport or analysis device; the average time elapsed for the group of specimens comprising the group other than the learning specimen; and the number of specimens per specified unit of time. Additionally, the data used as training signal data is information on the degree of delay of the learning specimen. By updating the learning model in this way, optimal judgments can be determined based on the situation without pre-registering them.

[0144] (iv) The functions of this embodiment can also be implemented through software program code. In this case, a storage medium recording the program code is provided to the system or device, and the computer (or CPU, MPU) of the system or device reads the program code stored in the storage medium. In this case, the program code read from the storage medium itself implements the functions of the embodiment described above, and the program code itself and the storage medium storing the program code constitute this disclosure. Examples of storage media for supplying such program code include floppy disks, CD-ROMs, DVD-ROMs, hard disks, optical disks, optical discs, CD-Rs, magnetic tapes, non-volatile memory cards, ROMs, etc.

[0145] Alternatively, the OS (operating system) running on the computer may perform some or all of the actual processing according to the instructions of the program code, thereby achieving the function of the described embodiment. Furthermore, after the program code read from the storage medium is written into the computer's memory, the computer's CPU or other processor may perform some or all of the actual processing according to the instructions of the program code, thereby achieving the function of the described embodiment.

[0146] Furthermore, the program code of the software that implements the functions of each implementation method can also be distributed via the network, and then stored in a storage unit such as a hard disk or memory of the system or device, or a storage medium such as a CD-RW or CD-R. When in use, the computer (or CPU, MPU) of the system or device reads and executes the program code stored in the storage unit or the storage medium.

[0147] The processes and techniques described herein are not inherently associated with any specific device and can be implemented through combinations of components. Furthermore, various types of general-purpose devices can be added. Dedicated devices can also be constructed to perform the functions of this embodiment and its various embodiments. Additionally, various functions can be formed by appropriately combining the multiple structural elements disclosed in this embodiment and its various embodiments. For example, several structural elements can be deleted from all the structural elements shown in the embodiments and their various embodiments, or structural elements from different embodiments can be appropriately combined.

[0148] Specific embodiments are described in this disclosure, but these are for illustrative purposes only and not for limiting the understanding of the technology disclosed herein. Those skilled in the art will recognize that many combinations of hardware, software, and firmware are available to implement the technology disclosed herein. For example, the described software can be implemented using a wide range of programming or scripting languages ​​such as assembler, C / C++, Perl, Shell, PHP, and Java (registered trademark).

[0149] Furthermore, in the above embodiments, control lines and information lines refer to the lines deemed necessary for the description, but may not represent all control lines and information lines on the product. All structures can also be interconnected.

[0150] Furthermore, those skilled in the art will be able to identify other embodiments of this disclosure based on this description and examination of the various embodiments. The description and specific examples are merely typical examples, and the technical scope and spirit of this disclosure will be shown in the following claims.

[0151] Explanation of reference numerals in the attached figures

[0152] 100 and 400 blood collection tube delivery information management system

[0153] 101 Blood Collection System

[0154] 102 Clinical Laboratory Information System (LIS)

[0155] 103 Conveying device

[0156] 104 Automatic Analysis Device

[0157] 105, 401 Information Systems

[0158] 106 Network

[0159] 110 and 410 processing departments

[0160] 111 Data Acquisition Department

[0161] 112, 412 Judgment Department

[0162] 113, 413 User Input Acceptance Department

[0163] 114, 414 User Notification Department

[0164] Storage units 120 and 420

[0165] 121 Blood Collection Implementation Time Information Storage Department

[0166] 122 Time Information Storage Unit for Loading Device

[0167] 123, 422 Set up information storage department

[0168] 130 Network Interface

[0169] 140 User Interface

[0170] 200 Setting Information Input GUI

[0171] 411 Study Department

[0172] 421 Learning and Judgment Setting Information Storage Department

[0173] 423 Learning Model Storage Department.

Claims

1. A specimen delay determination system, communicatively connected to a clinical examination information system, performing specimen delay determination processing, wherein the clinical examination information system, for multiple specimens, manages by associating at least the specimen collection implementation time and the loading device time (indicating the time when the collected specimen is loaded into a transport device or analysis device) with information of each specimen provider, characterized in that... The specimen delay determination system has the following features: Storage devices, which store various kinds of information; The control unit uses at least a portion of the various information to determine the delay of the specimen. The control unit performs the following processing: Processing of obtaining information on the collection time of each of the multiple specimens and the time of entry into the transport device from the clinical examination information system; The processing constitutes a group consisting of multiple specimens including the object specimens for the delayed determination process; The processing of the object sample elapsed time, which is calculated based on the collection time and the loading device time of the object sample; In the group, the calculation of the time elapsed from the collection of a specimen other than the object specimen to its entry into the transport device constitutes the processing of specimen elapsed time; Based on the elapsed time of the object sample and the elapsed time of the constituent samples, it is determined whether there is any delay in the processing of the object sample.

2. The specimen delay determination system according to claim 1, characterized in that, The control unit consists of multiple specimens from the same analysis item group as the target specimen, and multiple specimens collected before or within a specified time before or after the collection implementation time of the target specimen, and / or multiple specimens within a specified number before or after the target specimen.

3. The specimen delay determination system according to claim 2, characterized in that, The control unit maintains the formula for calculating the delay characteristic of the object specimen in the group, and the threshold for delay determination. In the process of determining whether the object sample has a delay, the following steps are performed: applying the elapsed time of the object sample and the elapsed time of the constituent samples to the delay feature calculation formula to calculate the delay feature of the object sample; and comparing the calculated delay feature with the delay determination using a threshold to determine whether the object sample has a delay.

4. The specimen delay determination system according to claim 3, characterized in that, The control unit performs the following processing: The screen displays the time values ​​before or after the collection implementation time of the object specimens of the group and / or the specimen values ​​before or after the collection of the object specimens of the group, as well as the processing of the setting screen for the calculation formulas used according to various delay feature quantity calculation formulas; The process of storing the time value and / or the sample value set via the setting screen, as well as the set delay characteristic calculation formula, in the storage device.

5. The specimen delay determination system according to claim 3, characterized in that, The formula for calculating the delay feature is a calculation formula for calculating the deviation of the object specimen in the group over time. The delay determination threshold is used to determine whether the deviation value indicates an anomaly. If the deviation of the elapsed time of the object sample calculated by the delay feature formula is greater than or equal to the delay determination threshold, the control unit determines that the object sample has a delay.

6. The specimen delay determination system according to claim 5, characterized in that, The control unit performs the process of notifying the user that there is a delay in the object sample.

7. The specimen delay determination system according to claim 4, characterized in that, The control unit performs the process of storing information on the collection time and the loading time of each of the multiple specimens obtained from the clinical examination information system, as well as the analysis items of each specimen, in the storage device.

8. The specimen delay determination system according to claim 1, characterized in that, The control unit performs the following processing: if it can confirm whether the elapsed time of the group constituent specimens has been obtained for all specimens other than the target specimens included in the group, it determines whether there is a delay in the target specimens.

9. A clinical examination information system, characterized in that, It incorporates the functionality of the specimen delay determination system of claim 1.

10. A specimen delay determination system, communicatively connected to a clinical examination information system, performing specimen delay determination processing, wherein the clinical examination information system, for multiple specimens, manages by associating at least the specimen collection implementation time and the loading device time (indicating the time when the collected specimen is loaded into a transport device or analysis device) with information of each specimen provider, characterized in that... The specimen delay determination system has the following features: Storage devices, which store various kinds of information; The control unit applies at least a portion of the various information to a learning model to determine the delay of the specimen. The control unit performs the following processing: Processing of obtaining information on the collection time of each of the multiple specimens and the time of entry into the transport device from the clinical examination information system; The processing constitutes a group consisting of multiple specimens including the object specimens for the delayed determination process; The learning model takes the time from the collection of the object specimen to the execution of the delay determination process, the average time of the group of specimens (representing the elapsed time from the collection of all specimens other than the object specimen in the group to their entry into the conveying device or the analysis device), and the number of specimens per specified unit time as input data. This input data is then applied to the learning model to output delay degree information representing the delay degree of the object specimen. The delay level information is compared with a delay determination threshold to determine whether the object sample has a delay.

11. The specimen delay determination system according to claim 10, characterized in that, The control unit uses the learning model corresponding to the analysis item of the object specimen, and the group consists of multiple specimens with the same analysis item as the object specimen.

12. The specimen delay determination system according to claim 10, characterized in that, The control unit also performs the following processing: The process of generating update input data and training signal data for updating the learning model; The process of updating the learning model by applying the updated input data and the training signal data to the learning model before the update. The updated input data includes: the time from the collection of the specimen determined to be delayed (i.e., the learning specimen) to its transfer into the transport device or the analysis device; the average elapsed time for the group of specimens consisting of the group containing the learning specimen but excluding the learning specimen; and the number of specimens per specified unit of time. The delay information of the learning specimen is used as the training signal data.

13. A clinical examination information system, characterized in that, It incorporates the functionality of the specimen delay determination system of claim 10.

14. A method for determining specimen delay, wherein for multiple specimens, at least the specimen collection implementation time and the loading device time (representing the time when the collected specimen is loaded into a transport device or analysis device) are used to perform the specimen delay determination process, characterized in that, The method for determining sample delay includes the following: The control unit that performs the delay determination process obtains information on the collection time of each of the multiple specimens and the time of the transfer device from the clinical examination information system. The control unit is configured as a group consisting of multiple samples including the object sample for the delayed determination process; The control unit calculates the object sample elapsed time, representing the elapsed time from the collection of the object sample to the entry into the transfer device, based on the collection implementation time and the transfer device time of the object sample; In the group, the calculation of the elapsed time from the collection of a specimen other than the object specimen to its entry into the transport device constitutes the specimen elapsed time; Based on the elapsed time of the subject specimen and the elapsed time of the constituent specimens, it is determined whether there is a delay in the subject specimen.

15. A method for determining specimen delay, wherein for multiple specimens, at least the specimen collection implementation time and the loading device time (representing the time when the collected specimen is loaded into a transport device or analysis device) are used to perform the specimen delay determination process, characterized in that, The method for determining sample delay includes the following: The control unit that performs the delay determination process obtains information on the collection time of each of the multiple specimens and the time of the transfer device from the clinical examination information system. The control unit is configured as a group consisting of multiple samples including the object sample for the delayed determination process; The control unit takes the time from the collection of the target specimen to the execution of the delay determination process, the average time of the group of specimens (which represents the elapsed time from the collection of all specimens except the target specimen in the group to their transfer into the conveying device or the analysis device), and the number of specimens per specified unit time as input data. It applies this input data to a learning model for delay determination, thereby outputting delay degree information representing the delay degree of the target specimen. The presence or absence of delay in the object sample is determined by comparing the delay level information with a delay determination threshold.

Images