A real-time early warning method in pathological specimen delivery process

Abstract

The application discloses a real-time early warning method in pathological specimen delivery process, relates to the medical informatization technical field, and constructs a specimen parameter-stability mapping relation by extracting historical patient data in the specimen collection link, carries out surgical collection and verification after determining the optimal parameters of the patient specimen, and ensures that the specimen collection quality adapts to the personalized needs of the patient; in the specimen delivery link, a transportation road condition-state mapping relation is generated to screen the best delivery route, transportation data and position are monitored in real time through embedded sensors and labels during transportation, the path is dynamically adjusted when the transportation is not in compliance, and the safety, stability and controllability of the transportation process are ensured; in the specimen receiving link, the information and receiving state are automatically checked by scanning the bar code, the pre-prevention, intervention and accurate treatment of the whole process of specimen delivery are realized, and the specimen quality, delivery efficiency and medical safety are effectively improved.

Description

Technical Field

[0001] This invention relates to the field of medical information technology, specifically to a real-time early warning method during the delivery of pathological specimens. Background Technology

[0002] Pathological specimens are the standard basis for disease diagnosis. The submission process involves multiple stages, including collection, fixation, verification, transportation, and receipt. Oversights in any stage can lead to specimen invalidation or information mismatch, ultimately affecting the diagnostic results. Real-time early warning can ensure specimen quality and lay the foundation for accurate diagnosis.

[0003] Existing technology, such as the blood test sample storage and management method and system disclosed in patent application CN118571443A, includes the following steps: Step 1, blood test sample registration: RFID tags are affixed to the blood test samples, and then patient information is written into the RFID tags using a reader / writer. After writing, the information inside the RFID tags is read and verified using a reader / writer to prevent information errors. Once the information is verified correctly, it is immediately uploaded to the cloud-based LIS system to complete the initial registration. This invention has the advantage of high efficiency, solving the problems of low automation in existing blood test sample storage and management, increased sample storage and management time, and potential for sample misreading, misplacement, confusion, and information recording errors, thereby affecting the accuracy of test results.

[0004] Existing technologies, such as the intelligent scheduling method, system, medium, and equipment for hospital laboratory specimens disclosed in patent application CN119252405A, belong to the field of medical auxiliary technology. The method includes acquiring patient information and laboratory department information; processing scheduling demand information using a clustering algorithm to obtain a clustered demand set; combining the clustered demand set with scheduling device information to obtain a scheduling task list; verifying unique RFID tags using RFID technology; obtaining the optimal path based on the current location coordinates of the laboratory specimens using a path planning model to process scene path node information and scheduling demand information; generating path navigation information based on the optimal path; obtaining obstacle warning information through feature extraction based on road image sequences; and verifying the unique RFID tag when the scheduling device reaches the location coordinates of the sending department using RFID technology to obtain the verification result. This achieves unmanned scheduling of hospital laboratory specimens, improves the efficiency of specimen scheduling, and ensures the timely delivery of specimens.

[0005] The above-mentioned solutions have at least the following shortcomings: 1. In the specimen collection process, the existing technology does not have personalized standard requirements for specimen collection quality, making it impossible to achieve precise pathological specimen collection. Without personalized standards, uniform collection requirements cannot be adapted to the special circumstances of different patients, which can easily lead to specimens that do not meet the testing requirements, resulting in poor specimen quality stability, an increase in invalid specimens, and affecting the reference value of test results.

[0006] 2. In most existing technologies, the quality of specimens is verified only during acceptance. There is a lack of verification during specimen collection. As a result, if a specimen does not meet the requirements of the test, it will only be known upon receipt. There is no timely and intelligent warning in advance, which greatly reduces the efficiency, safety and accuracy of specimen testing, easily increases doctor-patient conflicts, and leads to the circulation of invalid specimens, which greatly increases the waste of medical resources.

[0007] 3. During the specimen delivery process, different specimens have different requirements for environmental parameters and transportation stability. However, the existing technology lacks the ability to select a suitable route based on the individualized delivery needs of the specimens, as well as real-time monitoring during the delivery process. Furthermore, there is no corresponding adjustment when transportation is non-compliant, resulting in a high risk of specimen quality loss of control, low delivery efficiency, and impact on the accuracy of testing. Summary of the Invention

[0008] To address the aforementioned technical shortcomings, the present invention aims to provide a real-time early warning method during the pathological specimen delivery process.

[0009] To solve the above technical problems, the present invention adopts the following technical solution: The present invention provides a real-time early warning method in the process of submitting pathological specimens for examination, including the following steps: S1, specimen collection: extract specimen collection records within a specified period, then perform virtual specimen collection, construct a mapping relationship between specimen parameters and stability, extract the patient's pathological specimen examination request form during specimen collection, generate a specimen collection barcode, and confirm the optimal parameters of the patient's specimen based on the mapping relationship between specimen parameters and stability, then collect the patient's pathological tissue through surgery, perform specimen collection and verification, and after successful verification, place it in a collection container, and at the same time affix the specimen collection barcode to the surface of the collection container.

[0010] S2. Specimen delivery: Construct virtual models of each delivery route, simulate specimen transportation, establish a transportation road condition-state mapping relationship, select the optimal delivery route for transportation, monitor specimen transportation data and movement trajectory during transportation, determine the compliance of specimen delivery, and make transportation adjustments if non-compliant.

[0011] S3. Specimen Receiving: After the specimen arrives, the specimen collection barcode on the surface of the collection container is scanned for automatic verification, and the specimen ex-body time and receiving status data are extracted. The specimen receiving status is analyzed. If the receiving status is normal, the specimen status is updated and the receiving is completed. If the receiving status is abnormal, manual verification is initiated.

[0012] The beneficial effects of this invention are as follows: 1. This invention provides a real-time early warning method for the process of sending pathological specimens for examination. In the specimen collection stage, this method extracts historical patient data to construct a specimen parameter-stability mapping relationship. After determining the optimal parameters for the patient's specimen, surgical collection and verification are carried out to ensure that the specimen collection quality is adapted to the patient's personalized needs. In the specimen delivery stage, a transportation route-state mapping relationship is generated to screen the best delivery route. During transportation, embedded sensors and tags monitor transportation data and location in real time. When transportation is non-compliant, the route is dynamically adjusted to ensure the safety, stability, and controllability of the transportation process. In the specimen receiving stage, scanning the barcode automatically verifies the information and determines the receiving status, realizing pre-delivery prevention, in-process intervention, and precise post-delivery processing of the entire specimen delivery process, effectively improving specimen quality, delivery efficiency, and medical safety.

[0013] 2. The specimen collection quality of this invention is based on the individualized standard requirements of patients, which effectively achieves precise pathological specimen collection. The personalized standards can be adapted to the special circumstances of different patients, greatly improving the testing requirements of the specimen itself, increasing the stability of specimen quality, reducing invalid specimens, and improving the reference value of test results.

[0014] 3. This invention verifies the specimen during collection, thereby enabling timely detection and early warning when the specimen does not meet the requirements of the examination items, greatly improving the efficiency and accuracy of specimen testing, reducing doctor-patient conflicts, reducing the circulation of invalid specimens, and effectively reducing the waste of medical resources.

[0015] 4. This invention selects a suitable route and conducts real-time monitoring during the delivery process based on the individualized delivery requirements of the specimen. It also makes corresponding adjustments when transportation is non-compliant, thereby reducing the risk of specimen quality loss of control, ensuring the safety and stability of the specimen, improving delivery efficiency, and ensuring the accuracy of subsequent specimen testing. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of the implementation steps of the method of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Please see Figure 1 As shown, a real-time early warning method for the process of submitting pathological specimens includes the following steps: S1, specimen collection: extract specimen collection records within a specified period, then perform virtual specimen collection, construct a mapping relationship between specimen parameters and stability, extract the patient's pathological specimen examination request form during specimen collection, generate a specimen collection barcode, and confirm the optimal parameters of the patient's specimen based on the mapping relationship between specimen parameters and stability, then collect the patient's pathological tissue through surgery, perform specimen collection and verification, and after successful verification, place it in a collection container and affix the specimen collection barcode to the surface of the collection container.

[0020] In a specific embodiment, the specific process of S1 is as follows: S1.1, extract the basic parameters, specimen parameters and specimen collection feature values ​​of each historical patient from the specimen collection records within the specified period, then perform data processing, set the test specimen parameter set for each patient with basic parameters, and then collect the test data of each patient with basic parameters through specimen virtual test collection.

[0021] It should be noted that the specimen collection records within a specified period are retrieved from the database.

[0022] Basic parameters include age, gender, weight, height, smoking history, marital and reproductive history, alcohol consumption history, allergy history, surgical history, lesion location and size, among which size includes major diameter, minor diameter, thickness, height or volume.

[0023] Specimen parameters include the location, volume, quantity, and cutting edge distance of the collection site.

[0024] Preferably, the specific process of setting the test specimen parameter set for patients with each basic parameter is as follows: integrating historical patients with the same basic parameters to obtain the specimen parameters and specimen collection feature values ​​corresponding to each historical patient in each basic parameter; then integrating historical patients with the same specimen parameters to obtain the specimen collection feature values ​​corresponding to each specimen parameter used by each patient with each basic parameter; and calculating the stability assessment value corresponding to each specimen parameter used by each patient with each basic parameter.

[0025] The stability assessment value calculation process described above is as follows: The differences between the characteristic values ​​collected from each specimen are calculated, and the largest difference is selected as the maximum specimen collection characteristic value difference. Simultaneously, the differences between each specimen collection characteristic value and its average are calculated, and then the average difference is obtained. The stability assessment value is calculated as: (Average specimen collection characteristic value difference - Maximum specimen collection characteristic value difference) ÷ Average specimen collection characteristic value difference. This method is used to calculate the stability assessment value corresponding to each specimen parameter for each patient with each baseline parameter.

[0026] When the average difference in characteristic values ​​of specimen collection is 0, the stability evaluation value is assigned as 1.

[0027] Each specimen parameter with a stable assessment value greater than a preset stable assessment value threshold was selected as the target specimen parameter for each patient with each baseline parameter, while each specimen parameter with a stable assessment value less than a preset stable assessment value threshold was selected as the marker specimen parameter for each patient with each baseline parameter.

[0028] It should be noted that the stability assessment threshold is a critical value for assessing whether a specimen is stable after collection. The specific value is set and adjusted by professional medical staff according to the specimen stability requirements, and no specific numerical limit is set here.

[0029] The target specimen parameters of each patient with each baseline parameter are set according to the preset specimen parameter difference to form the test specimen parameter set for each patient with each baseline parameter.

[0030] Preferably, the specific process of the virtual specimen testing and acquisition is as follows: a virtual model of the patient with each basic parameter is constructed in the virtual simulation software, and the acquisition control data of the patient with each basic parameter using each labeled specimen parameter is extracted from the database as each interference data.

[0031] It should be noted that the data collected includes environmental change data, equipment change data, operational data, and patient vital sign change data. Among them, environmental change data reflects the changes in the collection environment, such as fluctuations in ambient temperature and humidity. Equipment change data is data on abnormal operation of the collection equipment, such as the frequency of equipment downtime and the deviation in equipment accuracy. Operational data consists of behavioral parameters of medical staff that may lead to collection errors, such as the collection angle and the interval between each collection step. Patient vital sign change data represents parameters that increase the difficulty of collection or cause fluctuations in specimen status due to individual patient differences, such as heart rate and blood pressure.

[0032] The collection steps for pathological specimens from different sites are different; specific details can be found online and will not be listed here.

[0033] Each test specimen parameter is input into the virtual model of the patient with each baseline parameter. Specimens are collected according to each test specimen parameter. During specimen collection, each interference data is set to interfere with the collection. After the specimen collection is completed, the specimen state data of each patient with each baseline parameter under the interference of each interference data is collected and used as the test data of each patient with each baseline parameter.

[0034] Among them, specimen status data represents the integrity and characteristics of the specimen after collection, including color parameters and morphological integrity.

[0035] Color parameters include RGB values; Morphological integrity: Obtain the specimen morphological image after the test, obtain the specimen size from the specimen morphological image, obtain the color parameters from the image attributes, and then compare it with the standard morphological image of the specimen in the database. Obtain the size of the area with the same morphology in the specimen morphological image and the standard morphological image of the specimen, and then divide it by the size of the specimen to obtain the morphological integrity.

[0036] It should be noted that the standard morphological image of the specimen represents a standard image of the specimen under normal morphology, which is uploaded to the database by professional medical personnel.

[0037] S1.2 Analyze the test data of patients with each baseline parameter, obtain the stable characteristic values ​​of patients with each baseline parameter when collecting specimens using each test specimen parameter, and then construct the mapping relationship between specimen parameter and stability.

[0038] Preferably, the process of obtaining stable characteristic values ​​of patients with each baseline parameter when collecting specimens using each test specimen parameter is as follows: extract specimen state data under interference from various interfering data when patients with each baseline parameter collect specimens using each test specimen parameter from the test data of patients with each baseline parameter, then perform normalization processing, subtract the specimen state data under interference from various interfering data when patients with each baseline parameter collect specimens using each test specimen parameter, and select the maximum difference as the specimen state difference when patients with each baseline parameter collect specimens using each test specimen parameter.

[0039] Simultaneously, the mean difference of specimens collected by patients using each test specimen parameter for each baseline parameter is calculated, and then input into the stable characteristic value assessment model, which outputs the stable characteristic value of patients using each test specimen parameter for each baseline parameter.

[0040] The average difference of specimens is obtained by subtracting the average value of the specimen status data under each interference data from the specimen status data under each interference data, and then performing mean processing.

[0041] The specimen status data are divided into two categories: Category I data and Category II data. Category I data, such as morphological integrity, indicates that the specimen status is closer to normal as the value is higher. Category II data, such as color parameters, indicates that the specimen status is closer to normal as the value is close to the standard value.

[0042] The standard values ​​for each type II data point are retrieved from the database. The absolute value of the difference between each type II data point and its standard value is divided by the standard value to obtain the difference rate for each type II data point. The reciprocal of the difference rate is then used as the normal value for each type II tissue. The normal values ​​for each type II tissue and each type I data point are normalized, and then mean-averaged to obtain the specimen status value. When the difference rate for the type II data point is 0, the normalized value is directly assigned the value 1.

[0043] Among them, the standard values ​​of each type of data represent the values ​​of each type of data under normal conditions of the specimen, which are uploaded to the database by professional medical staff.

[0044] Stable eigenvalue evaluation model: Stable eigenvalue = 0.5 × (sample mean difference - sample state difference) ÷ sample mean difference + 0.5 × sample state value.

[0045] S1.3. Extract the patient's pathological specimen examination request form from the patient management center, obtain the patient's basic parameters from the patient's pathological specimen examination request form, generate a specimen collection barcode, compare the patient's basic parameters with the mapping relationship of specimen parameters-stability, confirm the optimal parameters of the patient's specimen, and then use the optimal parameters of the patient's specimen to collect the patient's pathological tissue through surgery for specimen collection and verification. After successful verification, place it in the collection container and affix the specimen collection barcode to the surface of the collection container.

[0046] In the above, the specimen verification process is as follows: After the specimen is collected, a high-definition camera is used to take high-definition images of the specimen, and then the actual state data of the specimen is extracted to determine the state of the specimen. When the state of the specimen is normal, the verification is successful; otherwise, when the state of the specimen is abnormal, the verification fails, and an abnormal specimen state signal is sent to the collection personnel for manual verification.

[0047] The actual state data of the specimen includes actual color parameters and actual morphological integrity. The actual color parameters are obtained from the high-resolution image of the specimen, and the actual morphological integrity is obtained in the same way as the morphological integrity. Then, the actual state value of the specimen is calculated according to the specimen state value calculation process. When the actual state value of the specimen is greater than the preset state value threshold, the specimen is determined to be in a normal state; otherwise, the specimen is determined to be in an abnormal state.

[0048] It should be noted that the status threshold is a critical value for judging whether the specimen status is normal, and it is set by professional medical staff according to the specimen collection requirements.

[0049] S2. Specimen delivery: Construct virtual models of each delivery route, simulate specimen transportation, establish a transportation road condition-state mapping relationship, select the optimal delivery route for transportation, monitor specimen transportation data and movement trajectory during transportation, determine the compliance of specimen delivery, and make transportation adjustments if non-compliant.

[0050] In a specific embodiment, the specific process of S2 is as follows: S2.1, access the map system, obtain the current road condition data of each inspection route, construct a virtual model of each inspection route in the virtual simulation software, obtain historical inspection records from the database, extract the delay data of each inspection route from the historical inspection records, and set the delay impact factor of each inspection route.

[0051] Preferably, the delay data is data that reflects transportation delays, such as congestion duration and congestion frequency.

[0052] The delay data for each inspection route is normalized, and then the delay data for each inspection route is divided by the sum of the delay data for all inspection routes to obtain the delay impact factor for each inspection route.

[0053] S2.2 Simultaneously, a virtual model of the specimen is constructed in the virtual simulation software according to the optimal parameters of the specimen. The virtual model of the specimen is dynamically simulated for transportation in the virtual models of each delivery route. The simulated transportation data and movement trajectory in each delivery route are obtained, and the virtual state data of the specimen before and after transportation in each delivery route are obtained.

[0054] It should be noted that the simulated transportation data and movement trajectory are the transportation data and movement trajectory during the simulation process. The transportation data includes environmental data at each time point during transportation, including temperature and humidity, etc.

[0055] S2.3. Based on the delay impact factors of each delivery route, simulated transportation data, movement trajectory, and virtual state data of the specimens before and after transportation, construct the transportation road condition-state mapping relationship, and then select the optimal delivery route for transportation.

[0056] Preferably, the process of constructing the transportation condition-state mapping relationship is as follows: normalize the simulated transportation data of each delivery route and the virtual state data of the specimens before and after transportation, and use the normalized simulated transportation data of each delivery route to calculate the first transportation characteristic value of each delivery route; compare the movement trajectories between each delivery route to obtain the second transportation characteristic value of each delivery route; and calculate the third transportation characteristic value of each delivery route based on the normalized virtual state data of the specimens before and after transportation.

[0057] In the above process, environmental data at each time point is extracted from the simulated transportation data of each inspection route. Then, the duration of each environmental data is calculated, and the safe range and duration threshold of the environmental data are obtained from the database. When an environmental data is not within the safe range and the duration of the environmental data is greater than or equal to the duration threshold, the first transportation feature value is 0; otherwise, it is 1.

[0058] Among them, the environmental data safety range and duration threshold are environmental requirements for the safe transportation of specimens, which are set by professional medical personnel.

[0059] The transport time, number of transit nodes, and average speed are obtained from the movement trajectories of each delivery route. These are then normalized. The transport time and number of transit nodes are subtracted from the normalized average speed to obtain the second transport characteristic value. The virtual state data of the specimens before and after transport on each delivery route are then used to calculate the third transport characteristic value according to the same process as calculating the specimen state value.

[0060] The first, second, and third transport characteristic values ​​of each inspection route are added together, and then the delay impact factor of the corresponding inspection route is subtracted to obtain the transport status value of each inspection route, which serves as the transport condition-status mapping relationship.

[0061] S2.4 When transporting specimens along the optimal delivery route, monitor the specimens, obtain the specimens' transportation data and movement trajectory, determine the compliance of the specimens' delivery, and if non-compliance occurs, obtain the type of non-compliance and then make corresponding transportation adjustments.

[0062] Preferably, the specific process of S2.4 is as follows: S2.4-1, embed several sensors in the collection container and equip them with unique electronic tags to collect transportation data and location at preset time intervals and transmit them to the control center through the Internet of Things.

[0063] S2.4-2. The control center generates the actual movement trajectory based on the timestamps corresponding to each location received, and then determines the compliance of the specimen submission.

[0064] In the above, determining the compliance of specimen submission: obtaining the time of specimen removal from the collection monitoring center ( ) and current time ( The difference ,if If the preset timeout threshold is exceeded, a real-time timeout warning will be triggered.

[0065] Based on transportation data, the duration of each environmental data point is calculated. When an environmental data point is outside the safe range and its duration is greater than or equal to the duration threshold, the temperature compensation mechanism is activated.

[0066] For example: safe temperature range With a duration threshold of 5 minutes and an ambient temperature of 9°C for 10 minutes, the temperature compensation mechanism is activated.

[0067] Temperature compensation mechanism: A technical means to actively intervene and offset the negative impact of temperature fluctuations on the target object, ensuring that its characteristics, performance, or measurement results remain stable within a preset range. For example, when the temperature is too high, the cooling module is activated to ensure that the temperature inside the chamber is within the safe temperature range.

[0068] Location: The electronic tag communicates with several beacons via Bluetooth, Wi-Fi, or GPS, and calculates the tag's coordinates using the received signal strength. ,in: : Signal strength at reference distance : Actual received signal strength of the i-th beacon, n: Path loss indicator, i represents the beacon number (i is a positive integer), N is the number of beacons. This represents the weight of the i-th beacon.

[0069] It should be noted that weight Dynamic adjustments are made by professionals based on beacon signal quality and historical positioning errors.

[0070] The value of n is environment-dependent, and varies significantly across different scenarios. There are clearly defined typical ranges for reference within the industry, which can be found online. The signal strength at the reference distance is the signal strength at 1 meter, obtained through actual measurement. This measurement is based on existing technology and will not be elaborated upon here.

[0071] Motion state prediction, combining accelerometer data to predict the tag's motion trajectory: , Wherein, the state vector The state of motion of the tag at time k is represented by four components, where x and y represent the position coordinates in the two-dimensional plane. This represents the velocity components in the x and y directions, and k represents the time number, where k is a positive integer.

[0072] By using state vectors, the label's position and motion trend (velocity) can be estimated simultaneously, thus enabling trajectory prediction and correction. For example, if rapid movement begins, the velocity component... This change will be reflected in a timely manner.

[0073] The transition matrix F is the mathematical representation of the state transition model, used to determine the state transition from time k to k. Predict the state at time k The main function of the transition matrix is ​​to predict position and maintain velocity. It predicts the position increment by multiplying the velocity component by the time step, assuming that the velocity remains constant in a short time (uniform velocity model), and directly transfers the velocity from the previous moment to the current moment.

[0074] The observation matrix H is the mathematical representation of the observation model, used to represent the state vector. Mapped to the observation space, if the sensor can only measure position, H will extract... The position component in the state vector; the observation matrix connects the state and observations, extracting the position component from the state vector into observed values; it can also correct prediction errors by comparing predicted positions. Compared with the actual observation location Kalman filtering can correct state estimation and reduce positioning errors.

[0075] To measure the accelerometer data of the tag, and For process noise and observation noise, The observed value represents the raw data actually measured by the sensor at time k, used in the measurement update step of Kalman filtering; by fusing positioning data and motion prediction, the optimized trajectory is obtained. .

[0076] Electronic fence detection: An electronic fence is defined as a polygonal area. Current location The shortest distance to the fence is: Where j represents the vertex number of the polygon region, j is a positive integer, M represents the total number of edges of the vertices, and P is the vertex coordinates of the polygon. and Let represent the coordinates of the j-th vertex and the (j+1)-th vertex, respectively.

[0077] If D > c (threshold), it is considered an out-of-bounds error. Here, c is the threshold set by professionals to determine whether an out-of-bounds error has occurred.

[0078] Combining positioning error and motion status, a composite alarm index is defined: The parameters are explained below: These represent the first weight, the second weight, and the third weight, respectively. , Predicted location based on historical trajectory; Standard deviation of positioning error; : Continuous boundary crossing time.

[0079] in, It can be obtained through linear prediction, sliding window weighted prediction, or Kalman filter prediction.

[0080] Used to measure the degree of dispersion between the actual location of a tag and its true location. The smaller the size, the more stable the positioning. The larger the value, the more drastic the fluctuations in positioning data.

[0081] The single positioning error e = |PQ|, where P represents the actual positioning position of the tag and Q represents the reference real position. Then, the standard deviation of multiple positioning errors is calculated to obtain... .

[0082] It should be noted that the reference real location needs to be obtained through high-precision means. For example, in static scenes, a total station is used to mark fixed points, and in dynamic scenes, a higher-precision positioning device, such as RTK-GPS, is used as the reference.

[0083] Continuous out-of-bounds time refers to the duration from when a tag is first determined to be out of bounds to the current moment.

[0084] Professionals will set and adjust the parameters according to the calculation requirements; no specific numerical limits will be imposed here.

[0085] when And continue If the sample is within a certain number of seconds, an alarm is triggered, and the specimen submission is determined to be non-compliant; otherwise, the specimen submission is determined to be compliant.

[0086] in and These are the composite alarm indicator thresholds and duration thresholds set by professionals, which are used to determine the critical values ​​for whether to trigger an alarm.

[0087] Alarm derivation example: Assume the tag enters the area outside the electronic fence: and The times were 1.5 seconds and 8 seconds, respectively.

[0088] A. Positioning stage: The calculation yields D=1.2c, satisfying D>c.

[0089] B. Prediction Phase: Motion Model Predicts Position Deviation from actual position is .

[0090] C. Alarm Calculation: .

[0091] D. Continuous confirmation: If The alarm will be triggered after 10 seconds.

[0092] S2.4-3 If the specimen test is compliant, transportation shall continue; otherwise, if the specimen test is non-compliant, alternative routes shall be obtained from the map system, the best alternative route shall be selected from the alternative routes, and sent to the driver for route change.

[0093] Preferably, the process of selecting the best alternative route is as follows: using a positioning device to obtain the location when the specimen is not submitted for testing as the starting point, then obtaining each route from the starting point to the destination from the map system as each alternative route, and obtaining the transportation status value of each route from the transportation road condition-status mapping relationship.

[0094] Each alternative route is compared with each delivery route. If an alternative route overlaps with a delivery route, the overlap ratio is extracted, and the delivery route is marked as a marked route. The overlap ratio between each alternative route and each marked route and the transportation status value of each marked route are obtained. The alternative feature value of each alternative route is calculated, and the alternative route corresponding to the largest alternative feature value is selected as the best alternative route.

[0095] In the above process, the overlap ratio of each candidate path with each marked route and the transportation status value of the corresponding marked route are multiplied to obtain the transportation status value of each candidate path corresponding to each marked route. Then, these values ​​are accumulated to obtain the candidate feature value of each candidate path.

[0096] S3. Specimen Receiving: After the specimen arrives, the specimen collection barcode on the surface of the collection container is scanned for automatic verification, and the specimen ex-body time and receiving status data are extracted. The specimen receiving status is analyzed. If the receiving status is normal, the specimen status is updated and the receiving is completed. If the receiving status is abnormal, manual verification is initiated.

[0097] In a specific embodiment, the analysis of the specimen reception status specifically involves: reading the time of scanning the specimen collection barcode on the surface of the collection container as the specimen reception time; the duration between the specimen reception time and the specimen removal time as the specimen removal duration; obtaining the removal duration threshold from the control center; calculating the received specimen status value based on the reception status data; and then comparing the specimen removal duration and the received specimen status value with the specimen removal duration threshold and a preset specimen status value threshold. If the specimen removal duration is greater than or equal to the removal duration threshold, or the received specimen status value is less than the specimen status value threshold, the reception status is determined to be abnormal; otherwise, the reception status is determined to be normal.

[0098] It should be noted that the calculation method for the received specimen status value is the same as that for the specimen status value, and will not be repeated here. The preset specimen status value threshold is a critical value for judging whether the specimen status is normal. It is set by professional medical staff according to the specimen status testing needs, and no specific numerical limit is given here.

[0099] The database is used to store the acquisition control data of each patient using each labeled specimen parameter, historical test records, specimen acquisition records within a specified period, standard morphological images of specimens, standard values ​​of each type II data, environmental data safety ranges, and duration thresholds.

[0100] It should be noted that the models and methods involved in this invention, such as state transition models, observation models, linear prediction methods, sliding window weighted prediction, and Kalman filter prediction, have parameter settings and operation details that are common knowledge in the prior art. Those skilled in the art can set them themselves according to the actual scenario, or flexibly configure them based on conventional experience and specific scenarios, without affecting the implementation and reproduction of the technical solution of this invention.

[0101] The formulas described above all utilize the principle of dimensional consistency and mathematical standardization methods, such as normalization, dimensionless parameter conversion, or unit system unification, to translate physical quantities with different properties into unitless standard values ​​or superimposed parameters of the same dimension. This eliminates the interference of different dimensions on the computational logic, ensuring that the formulas retain the original data distribution characteristics while possessing mathematical rationality and adaptability to objective laws. These descriptions are merely exemplary embodiments of the present invention and should not be construed as limiting the scope of the invention.

[0102] The examples described in this invention are not limited to the specific embodiments listed above. The examples are merely illustrative to facilitate understanding of the invention and do not constitute a limitation on the scope of protection of this invention. Any modifications, equivalent substitutions, etc., made within the spirit and principles of this invention should be included within the scope of protection.

[0103] The above description is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined in this specification, they should all fall within the protection scope of the present invention.

Claims

1. A real-time early warning method during the delivery of pathological specimens, characterized in that, Includes the following steps: S1. Specimen Collection: Extract specimen collection records within a specified period, then perform virtual specimen collection, and construct a mapping relationship between specimen parameters and stability. During specimen collection, extract the patient's pathological specimen examination request form, generate a specimen collection barcode, and confirm the optimal parameters of the patient's specimen based on the mapping relationship between specimen parameters and stability. Then, collect the patient's pathological tissue through surgery for specimen collection and verification. After successful verification, place the specimen in the collection container and affix the specimen collection barcode to the surface of the collection container. S2. Specimen delivery: Construct virtual models of each delivery route, simulate the transportation of specimens, establish a transportation road condition-state mapping relationship, select the optimal delivery route for transportation, and monitor the transportation data and movement trajectory of specimens during transportation to determine the compliance of specimen delivery and make transportation adjustments if non-compliant. S3. Specimen Receiving: After the specimen arrives, the specimen collection barcode on the surface of the collection container is scanned for automatic verification, and the specimen ex-body time and receiving status data are extracted. The specimen receiving status is analyzed. If the receiving status is normal, the specimen status is updated and the receiving is completed. If the receiving status is abnormal, manual verification is initiated.

2. The real-time early warning method for pathological specimen delivery according to claim 1, characterized in that, The specific process of S1 is as follows: S1.1 Extract the baseline parameters, specimen parameters, and specimen collection characteristic values ​​of each historical patient from the specimen collection records within the specified period, then perform data processing, set the test specimen parameter set for each patient with baseline parameters, and then collect the test data of each patient with baseline parameters through virtual specimen testing. S1.2 Analyze the test data of patients with each baseline parameter, obtain the stable characteristic values ​​of patients with each baseline parameter when collecting specimens using each test specimen parameter, and then construct the mapping relationship between specimen parameter and stability; S1.

3. Extract the patient's pathological specimen examination request form from the patient management center, obtain the patient's basic parameters from the patient's pathological specimen examination request form, generate a specimen collection barcode, compare the patient's basic parameters with the mapping relationship of specimen parameters-stability, confirm the optimal parameters of the patient's specimen, and then use the optimal parameters of the patient's specimen to collect the patient's pathological tissue through surgery for specimen collection and verification. After successful verification, place it in the collection container and affix the specimen collection barcode to the surface of the collection container.

3. The real-time early warning method for pathological specimen delivery according to claim 2, characterized in that, The specific process for setting the test specimen parameter set for each patient's basic parameters is as follows: By integrating historical patients with the same baseline parameters, the specimen parameters and specimen collection characteristic values ​​corresponding to each historical patient in each baseline parameter are obtained. Then, by integrating historical patients with the same specimen parameters, the specimen collection characteristic values ​​corresponding to each specimen parameter are obtained for each patient with each baseline parameter. Finally, the stability assessment value corresponding to each patient with each specimen parameter is calculated. Each specimen parameter with a stable assessment value greater than a preset stable assessment value threshold was selected as the target specimen parameter for each patient with each baseline parameter, while each specimen parameter with a stable assessment value less than a preset stable assessment value threshold was selected as the marker specimen parameter for each patient with each baseline parameter. The target specimen parameters of each patient with each baseline parameter are set according to the preset specimen parameter difference to form the test specimen parameter set for each patient with each baseline parameter.

4. The real-time early warning method for pathological specimen delivery according to claim 3, characterized in that, The specific process for collecting the virtual specimen test is as follows: In virtual simulation software, virtual models of patients with various basic parameters are constructed, and the acquisition control data of patients with various basic parameters using various labeled specimen parameters are extracted from the database as various interference data. Each test specimen parameter is input into the virtual model of the patient with each baseline parameter. Specimens are collected according to each test specimen parameter. During specimen collection, each interference data is set to interfere with the collection. After the specimen collection is completed, the specimen state data of each patient with each baseline parameter under the interference of each interference data is collected and used as the test data of each patient with each baseline parameter.

5. The real-time early warning method for pathological specimen delivery according to claim 2, characterized in that, The specific process for obtaining stable characteristic values ​​of each baseline parameter when patients collect specimens using each test specimen parameter is as follows: Extract specimen status data from patients with each baseline parameter under the interference of various data when collecting specimens using each test specimen parameter. Then, perform normalization processing. Subtract the specimen status data of patients with each baseline parameter under the interference of various data when collecting specimens using each test specimen parameter, and select the maximum difference as the specimen status difference of patients with each baseline parameter when collecting specimens using each test specimen parameter. Simultaneously, the mean difference of specimens collected by patients using each test specimen parameter for each baseline parameter is calculated, and then input into the stable characteristic value assessment model, which outputs the stable characteristic value of patients using each test specimen parameter for each baseline parameter.

6. The real-time early warning method for pathological specimen delivery according to claim 1, characterized in that, The specific process of S2 is as follows: S2.

1. Connect to the map system, obtain the current road condition data of each inspection route, and build a virtual model of each inspection route in the virtual simulation software. At the same time, obtain historical inspection records from the database, extract the delay data of each inspection route from the historical inspection records, and set the delay impact factor of each inspection route. S2.2 Simultaneously, construct a virtual model of the specimen in the virtual simulation software according to the optimal parameters of the specimen, and dynamically simulate the transportation of the specimen virtual model in the virtual models of each delivery route, obtain the simulated transportation data and movement trajectory in each delivery route, and obtain the virtual state data of the specimen before and after transportation in each delivery route. S2.3 Based on the delay impact factors of each delivery route, simulated transportation data, movement trajectory and virtual state data of specimens before and after transportation, construct the transportation road condition-state mapping relationship, and then select the best delivery route for transportation; S2.4 When transporting specimens along the optimal delivery route, monitor the specimens, obtain the specimens' transportation data and movement trajectory, determine the compliance of the specimens' delivery, and if non-compliance occurs, obtain the type of non-compliance and then make corresponding transportation adjustments.

7. The real-time early warning method for pathological specimen delivery according to claim 6, characterized in that, The process of constructing the transportation condition-state mapping relationship is as follows: The simulated transportation data of each delivery route and the virtual state data of the specimens before and after transportation are normalized, and the first transportation characteristic value of each delivery route is calculated using the normalized simulated transportation data of each delivery route. The movement trajectories of each delivery route are compared to obtain the second transport characteristic value of each delivery route; the third transport characteristic value of each delivery route is calculated based on the normalized virtual state data of the specimens before and after transport. The first, second, and third transport characteristic values ​​of each inspection route are added together, and then the delay impact factor of the corresponding inspection route is subtracted to obtain the transport status value of each inspection route, which serves as the transport condition-status mapping relationship.

8. A real-time early warning method for the process of submitting pathological specimens according to claim 6, characterized in that, The specific process of S2.4 is as follows: S2.4-1. Several sensors are embedded in the collection container and equipped with a unique electronic tag to collect transportation data and location at preset time intervals and transmit them to the control center via the Internet of Things. S2.4-2. The control center generates the actual movement trajectory based on the timestamps corresponding to each location received, and then determines the compliance of the specimen submission. S2.4-3 If the specimen test is compliant, transportation shall continue; otherwise, if the specimen test is non-compliant, alternative routes shall be obtained from the map system, the best alternative route shall be selected from the alternative routes, and sent to the driver for route change.

9. A real-time early warning method for the process of submitting pathological specimens for examination according to claim 8, characterized in that, The specific process for selecting the best alternative path is as follows: The location of the specimen submission is obtained using a positioning device as the starting point. Then, the routes from the starting point to the submission endpoint are obtained from the map system as alternative routes. Finally, the transportation status value of each submission route is obtained from the transportation road condition-status mapping relationship. Each alternative route is compared with each delivery route. If an alternative route overlaps with a delivery route, the overlap ratio is extracted, and the delivery route is marked as a marked route. The overlap ratio between each alternative route and each marked route and the transportation status value of each marked route are obtained. The alternative feature value of each alternative route is calculated, and the alternative route corresponding to the largest alternative feature value is selected as the best alternative route.

10. A real-time early warning method for the process of submitting pathological specimens for examination according to claim 1, characterized in that, The specific process for the sample reception status is as follows: The time it takes to read the specimen collection barcode on the surface of the scanning collection container is taken as the specimen reception time. The duration between the specimen reception time and the specimen removal time is taken as the specimen removal duration. The removal duration threshold is obtained from the control center. Based on the reception status data, the received specimen status value is calculated. Then, the specimen removal duration and the received specimen status value are compared with the specimen removal duration threshold and the preset specimen status value threshold. If the specimen removal duration is greater than or equal to the removal duration threshold, or the received specimen status value is less than the specimen status value threshold, the reception status is determined to be abnormal; otherwise, the reception status is determined to be normal.

Images