Nuclear magnetic resonance reservation late prediction method and device

Abstract

The invention relates to the technical field of medical information management, in particular to a nuclear magnetic resonance reservation late prediction method and device. The method comprises the following steps: acquiring nuclear magnetic resonance reservation data, extracting historical feature data, and converting the historical feature data into historical identifiers; obtaining timeliness data, extracting timeliness characteristic data, and converting the timeliness characteristic data into timeliness identifiers; appointment registration time periods are divided, registration conditions of the patients in the appointment registration time periods are inquired, and registration identifiers are output; setting a judgment threshold value, obtaining a current calculation threshold value according to the historical identifier, the aging identifier and the registration identifier, comparing the judgment threshold value with the current calculation threshold value, and outputting late prediction information of the patient; the device comprises a historical data acquisition module, a timeliness data acquisition module, a registration data acquisition module and a judgment output module. The late condition of the patient is predicted by combining the patient information data, the timeliness data and the patient registration condition, and the prediction accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical information management, and in particular to a method and device for predicting lateness of a nuclear magnetic resonance imaging appointment. Background Art

[0002] In medical institutions, MRI examinations are generally performed by appointment due to their long duration and high clinical demand. However, patient lateness and no-shows are common, leading to conflicts between doctors and patients and wasted medical resources.

[0003] The existing method of predicting patient lateness is to make inferences based on the patient's historical data. For example, if a patient is often late for treatment and examinations for a long time, it can be predicted that the patient is likely to be late for this MRI examination.

[0004] Predicting a patient's lateness relies solely on the patient's historical data, resulting in low accuracy. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and device for predicting lateness for nuclear magnetic resonance imaging appointments, aiming to solve the technical problem in the prior art that the prediction of patient lateness relies solely on the patient's historical data, resulting in low accuracy of the prediction results.

[0006] To achieve the above object, the present invention adopts a method for predicting lateness of nuclear magnetic resonance appointments, comprising the following steps: Obtain MRI appointment data, extract the patient's unique identifier, query the patient's information data through the identifier, extract historical feature data, and convert it into a historical identifier; Obtain timeliness data, extract timeliness feature data, and convert it into timeliness identifier; Divide the appointment registration time period, query the patient's registration status in the appointment registration time period, and output the registration identifier; Set the judgment threshold, obtain the current calculation threshold based on the historical identifier, time identifier and registration identifier, compare the judgment threshold and the current calculation threshold, and output the patient's lateness prediction information.

[0007] Among them, in the steps of obtaining MRI appointment data, extracting the patient's unique identifier, querying the patient's information data through the identifier, extracting historical feature data, and converting it into a historical identifier: Connect to the database, query the patient's information data based on the patient's unique identifier extracted from the MRI appointment data, and output it; Process the data, extract historical feature data and create the first late arrival feature; Convert the first late feature to a history identifier.

[0008] Among them, in the step of processing data, extracting historical feature data and creating the first late arrival feature: According to the historical feature data, the lateness time is calculated for each appointment and arrival data, the difference between the patient's actual arrival time and the appointment time is calculated, and the first lateness feature is output.

[0009] Among them, in the step of calculating the lateness time for each appointment and arrival data based on the historical feature data, calculating the difference between the patient's actual arrival time and the appointment time, and outputting the first lateness feature: If the appointment time minus the actual arrival time is a positive number or 0, the first lateness feature is not late; If the appointment time minus the actual arrival time is a negative number, the first lateness feature is lateness.

[0010] Among them, in the steps of obtaining timeliness data, extracting timeliness feature data, and converting it into a timeliness identifier: Collect real-time traffic data, weather data and parking data respectively; Preprocess and integrate the collected data to obtain a data set; A second late feature is created based on the data set, and the second late feature is converted into a timeliness identifier.

[0011] Among them, in the steps of respectively collecting real-time traffic data, weather data and parking lot data: Traffic data includes road congestion; weather data includes rainfall, temperature, and wind speed; parking lot data includes the number of vacant parking spaces and congestion at parking lot entrances.

[0012] Among them, in the step of dividing the appointment registration time period, querying the patient's registration status in the appointment registration time period, and outputting the registration identifier: Set up multiple appointment registration time periods; the appointment registration time period is the time period before the patient's appointment time, and multiple appointment registration time periods do not overlap; According to the time sequence of each appointment registration time period, query the patient's registration status, create a third late feature, and convert the third late feature into a registration identifier.

[0013] Among them, in the steps of setting the judgment threshold, obtaining the current calculation threshold according to the history identifier, the time identifier, and the registration identifier, comparing the judgment threshold with the current calculation threshold, and outputting the patient's lateness prediction information: Set a first judgment threshold and a second judgment threshold respectively; Obtain the history identifier, time identifier and registration identifier, and calculate the current calculation threshold; Compare the first judgment threshold, the second judgment threshold and the current calculation threshold, and output prediction prompt data.

[0014] Among them, in the step of comparing the first judgment threshold, the second judgment threshold and the current calculation threshold, and outputting the prediction prompt data: If the current calculation threshold is less than the first judgment threshold, the output prediction prompt data is: no lateness occurs; If the current calculation threshold is between the first judgment threshold and the second judgment threshold, the output prediction prompt data is: lateness is expected to occur; If the current calculation threshold is greater than the second judgment threshold, the output prediction prompt data is: there is a late arrival situation.

[0015] The present invention also provides a device for predicting lateness of nuclear magnetic resonance appointments, comprising a historical data acquisition module, a timeliness data acquisition module, a registration data acquisition module, and a judgment output module; wherein: The historical data acquisition module is used to acquire MRI appointment data, extract the patient's unique identifier, query the patient's information data through the identifier, extract historical feature data, and convert it into a historical identifier; The timeliness data acquisition module is used to acquire timeliness data, extract timeliness feature data, and convert it into a timeliness identifier; The registration data acquisition module is used to divide the appointment registration time period, query the patient's registration status in the appointment registration time period, and output a registration identifier; The judgment output module is used to set a judgment threshold, obtain a current calculation threshold according to a history identifier, a time identifier and a registration identifier, compare the judgment threshold with the current calculation threshold, and output the patient's lateness prediction information.

[0016] A method and device for predicting lateness of a nuclear magnetic resonance appointment of the present invention sequentially uses the historical data acquisition module, the timeliness data acquisition module, the registration data acquisition module and the judgment output module to perform the following steps: acquiring nuclear magnetic resonance appointment data and extracting the patient's unique identifier, querying the patient's information data through the identifier, extracting historical feature data, and converting it into a historical identifier; acquiring timeliness data, extracting timeliness feature data, and converting it into a timeliness identifier; dividing the appointment registration time period, querying the patient's registration status in the appointment registration time period, and outputting the registration identifier; setting a judgment threshold, obtaining the current calculation threshold based on the historical identifier, the timeliness identifier and the registration identifier, comparing the judgment threshold with the current calculation threshold, and outputting the patient's lateness prediction information; by combining the patient information data, the timeliness data and the patient registration status to predict the patient's lateness, the accuracy of the prediction is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 It is a flowchart of the steps of the method for predicting lateness of nuclear magnetic resonance appointments of the present invention.

[0019] Figure 2 It is a step flow chart of S100 of the present invention.

[0020] Figure 3 It is a step flow chart of S200 of the present invention.

[0021] Figure 4 It is a step flow chart of S300 of the present invention.

[0022] Figure 5 It is a step flow chart of S400 of the present invention.

[0023] Figure 6 It is a structural principle diagram of the nuclear magnetic resonance appointment lateness prediction device of the present invention.

[0024] Figure 7 It is a structural principle diagram of the electronic device of the present invention.

[0025] 501 - historical data acquisition module, 502 - timeliness data acquisition module, 503 - registration data acquisition module, 504 - judgment output module. DETAILED DESCRIPTION

[0026] Exemplary embodiments are described in detail herein, with examples illustrated in the accompanying drawings. When the following description refers to the drawings, identical numerals in different drawings represent identical or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with this application.

[0027] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. As used in this application and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0028] It should be understood that although the terms first, second, third, etc. may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0029] See also Figures 1 to 5 The present invention provides a method for predicting lateness of a nuclear magnetic resonance appointment, comprising the following steps: S100: Obtain MRI appointment data, extract the patient's unique identifier, query the patient's information data through the identifier, extract historical feature data, and convert it into a historical identifier; In this embodiment, MRI appointment data is obtained, and the patient's unique identifier is extracted. The patient's information data is queried using the identifier, and historical feature data is extracted and converted into a historical identifier. The specific steps are as follows: S101: Connecting to a database, querying patient information data based on the patient's unique identifier extracted from the MRI appointment data, and outputting the information; S102: Process the data, extract historical feature data and create a first late arrival feature; S103: Convert the first late feature into a history identifier.

[0030] First, connect to the hospital's local database and query the patient's information data based on the patient's unique identifier extracted from the MRI appointment data. The unique identifier can be the patient's ID card or the ID data planned by the hospital itself; then process the data, extract historical feature data, calculate the lateness time for each appointment and arrival data, calculate the difference between the patient's actual arrival time and the appointment time, and output the first lateness feature; if the appointment time minus the actual arrival time is a positive number or 0, the first lateness feature is not late; if the appointment time minus the actual arrival time is a negative number, the first lateness feature is late; finally, convert the first lateness feature into a historical identifier.

[0031] S200: Acquire timeliness data, extract timeliness feature data, and convert it into a timeliness identifier; In this embodiment, timeliness data is obtained, timeliness feature data is extracted, and converted into a timeliness identifier. The specific steps are as follows: S201: Real-time traffic data, weather data, and parking lot data are collected respectively; the traffic data includes road congestion; the weather data includes rainfall, temperature, and wind speed; and the parking lot data includes the number of available parking spaces and parking lot entrance congestion. S202: Preprocessing and integrating the collected data to obtain a data set; S203: Create a second late feature according to the data set, and convert the second late feature into a timeliness identifier.

[0032] First, real-time traffic data, weather data, and parking lot data are collected separately; traffic data includes road congestion; weather data includes rainfall, temperature, and wind speed; parking lot data includes the number of available parking spaces and congestion at parking lot entrances; the collected data are then preprocessed and integrated to obtain a data set; a prediction model is constructed using machine learning algorithms (such as support vector machines and neural networks), and the processed data set is input into the model for training and optimization to obtain time-sensitive identifiers that can affect patients in terms of traffic, weather, and parking.

[0033] S300: Divide the appointment registration time period, query the patient's registration status in the appointment registration time period, and output the registration identifier; In this embodiment, the appointment registration time period is divided, the patient's registration status in the appointment registration time period is queried, and the registration identifier is output; the specific steps are as follows: S301: Setting up multiple appointment registration time periods; wherein the appointment registration time period is the time period before the patient's appointment time, and the multiple appointment registration time periods do not overlap; S302: querying the patient's registration status according to the time sequence of each appointment registration time period, creating a third lateness feature, and converting the third lateness feature into a registration identifier.

[0034] First, set up multiple appointment registration time periods; for example, divide the time period from 0 to 15 minutes before the patient's appointment time into 5-minute units, which is the appointment registration time period; query the patient's registration status according to the time sequence of each appointment registration time period, and create a third lateness feature. The third lateness feature includes the registration status in each time period, and the registration status includes unregistered and registered. The third lateness feature is converted into a registration identifier.

[0035] S400: Setting a judgment threshold, obtaining a current calculation threshold according to a history identifier, a timeliness identifier, and a registration identifier, comparing the judgment threshold with the current calculation threshold, and outputting the patient's lateness prediction information.

[0036] In this embodiment, a judgment threshold is set, a current calculation threshold is obtained based on the historical identifier, the time identifier, and the registration identifier, the judgment threshold is compared with the current calculation threshold, and the patient's lateness prediction information is output; the specific steps are as follows: S401: Setting a first judgment threshold and a second judgment threshold respectively; S402: Obtain the history identifier, time identifier, and registration identifier, and calculate the current calculation threshold; S403: Compare the first judgment threshold, the second judgment threshold and the current calculation threshold, and output prediction prompt data.

[0037] If the current calculation threshold is less than the first judgment threshold, the output prediction prompt data is: no lateness occurs; if the current calculation threshold is between the first judgment threshold and the second judgment threshold, the output prediction prompt data is: lateness is expected to occur; if the current calculation threshold is greater than the second judgment threshold, the output prediction prompt data is: lateness occurs.

[0038] First, set the first judgment threshold and the second judgment threshold. According to the sources of historical identifiers, time identifiers, and registration identifiers, including historical data, traffic data, weather data, parking lot data, and registration data, the first judgment threshold can be set to 1 and the second judgment threshold to 5 according to the amount of data. At the same time, the middle threshold can also be set to 3. The data intervals of this setting are: 0, 1~2, 3~4, 5; When there is late data, the historical identifier is 1, and when there is no late data, the historical identifier is 0; when the traffic data is congested, the timeliness identifier generated by the traffic data is 1, otherwise it is 0; when the weather data is windy or rainy, the timeliness identifier generated by the weather data is 1, otherwise it is 0; when the parking lot data is congested, the timeliness identifier generated by the parking lot data is 1, otherwise it is 0; when the patient registers in the appointment registration time period, the registration identifier is 0, otherwise it is 1, where the registration identifier changes according to the appointment registration time period; the above logical values ​​are quantitatively superimposed to calculate the current calculation threshold; At the same time, the prompt data can be divided into levels: If the current calculation threshold is 0, the output prediction prompt data is: no lateness occurs; If the current calculation threshold is 5, the output prediction prompt data is: there is a late situation, a level 1 prompt; In case of possible lateness: If the current calculation threshold is 1 or 2, the output prediction prompt data is: there is a late situation, three-level prompt; If the current calculation threshold is 3 or 4, the output prediction prompt data is: there is a late arrival situation, a second-level prompt.

[0039] Corresponding to the aforementioned embodiment of the method for predicting lateness of a nuclear magnetic resonance appointment, the present application also provides an embodiment of an apparatus for predicting lateness of a nuclear magnetic resonance appointment.

[0040] Figure 6 FIG. 1 is a block diagram of a device for predicting lateness of a nuclear magnetic resonance appointment according to an exemplary embodiment. Figure 6 The device may include: a historical data acquisition module 501, a timeliness data acquisition module 502, a registration data acquisition module 503 and a judgment output module 504; wherein: The historical data acquisition module 501 is used to acquire MRI appointment data, extract the patient's unique identifier, query the patient's information data through the identifier, extract historical feature data, and convert it into a historical identifier; The timeliness data acquisition module 502 is used to acquire timeliness data, extract timeliness feature data, and convert it into a timeliness identifier; The registration data acquisition module 503 is used to divide the appointment registration time period, query the patient's registration status in the appointment registration time period, and output a registration identifier; The judgment output module 504 is used to set a judgment threshold, obtain a current calculation threshold according to the history identifier, the time identifier and the registration identifier, compare the judgment threshold with the current calculation threshold, and output the patient's lateness prediction information.

[0041] In this embodiment, the historical data acquisition module 501 acquires the nuclear magnetic resonance appointment data and extracts the patient's unique identifier, queries the patient's information data through the identifier, extracts the historical feature data, and converts it into a historical identifier; the timeliness data acquisition module 502 acquires the timeliness data, extracts the timeliness feature data, and converts it into a timeliness identifier; the registration data acquisition module 503 divides the appointment registration time period, queries the patient's registration status in the appointment registration time period, and outputs the registration identifier; the judgment output module 504 sets a judgment threshold, obtains the current calculation threshold based on the historical identifier, timeliness identifier and registration identifier, compares the judgment threshold and the current calculation threshold, and outputs the patient's lateness prediction information; by combining the patient information data, timeliness data and patient registration status to predict the patient's lateness, the accuracy of the prediction is improved.

[0042] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0043] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial description of the method embodiments. The device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0044] Accordingly, the present application also provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the above-mentioned method for predicting lateness of nuclear magnetic resonance appointments. Figure 7 As shown in the figure, a hardware structure diagram of a device with data processing capability for predicting late arrival of a nuclear magnetic resonance appointment provided by an embodiment of the present invention is provided. Figure 7 In addition to the processor, memory, and network interface shown, any device with data processing capabilities in which the apparatus in the embodiment is located may also include other hardware, generally based on the actual functions of the device with data processing capabilities, which will not be described in detail.

[0045] Accordingly, the present application also provides a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the above-mentioned method for predicting lateness for nuclear magnetic resonance appointments. The computer-readable storage medium can be an internal storage unit of any device with data processing capabilities described in any of the aforementioned embodiments, such as a hard disk or memory. The computer-readable storage medium can also be an external storage device, such as a plug-in hard disk, a smart media card (SMC), an SD card, a flash card, etc. equipped on the device. Furthermore, the computer-readable storage medium can also include both an internal storage unit and an external storage device of any device with data processing capabilities. The computer-readable storage medium is used to store the computer program and other programs and data required by any device with data processing capabilities, and can also be used to temporarily store data that has been output or is to be output.

[0046] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the contents disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of this application and include common knowledge or customary techniques in the art that are not disclosed in this application.

[0047] It will be understood that the present application is not limited to the exact construction that has been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof.

Claims

1. A method for predicting lateness of a nuclear magnetic resonance appointment, characterized in that: The steps include: Obtain MRI appointment data and extract the patient's unique identifier, query the patient's information data through the identifier, extract historical feature data, and convert it into a historical identifier; Obtain timeliness data, extract timeliness feature data, and convert it into a timeliness identifier; Divide the appointment registration time period, query the patient's registration status in the appointment registration time period, and output the registration identifier; Set the judgment threshold, obtain the current calculation threshold according to the historical identifier, time identifier and registration identifier, compare the judgment threshold with the current calculation threshold, and output the patient's lateness prediction information.

2. The method for predicting lateness of a nuclear magnetic resonance appointment as claimed in claim 1, characterized in that: In the steps of obtaining MRI appointment data, extracting the patient's unique identifier, querying the patient's information data through the identifier, extracting historical feature data, and converting it into a historical identifier: Connect to the database, query the patient's information data based on the patient's unique identifier extracted from the MRI appointment data, and output it; Process the data, extract historical feature data and create the first late arrival feature; Convert the first late feature to a history identifier.

3. The method for predicting lateness of a nuclear magnetic resonance appointment as claimed in claim 2, characterized in that: In the step of processing the data, extracting historical feature data and creating the first late arrival feature: According to the historical feature data, the lateness time is calculated for each appointment and arrival data, the difference between the patient's actual arrival time and the appointment time is calculated, and the first lateness feature is output.

4. The method for predicting lateness of a nuclear magnetic resonance appointment as claimed in claim 3, characterized in that: In the step of calculating the lateness time for each appointment and arrival data according to the historical feature data, calculating the difference between the patient's actual arrival time and the appointment time, and outputting the first lateness feature: If the appointment time minus the actual arrival time is a positive number or 0, the first lateness feature is not late; If the appointment time minus the actual arrival time is a negative number, the first lateness feature is lateness.

5. The method for predicting lateness of a nuclear magnetic resonance appointment as claimed in claim 1, characterized in that: In the steps of obtaining timeliness data, extracting timeliness feature data, and converting it into a timeliness identifier: Collect real-time traffic data, weather data and parking lot data respectively; Preprocess and integrate the collected data to obtain a data set; A second late feature is created based on the data set, and the second late feature is converted into a timeliness identifier.

6. The method for predicting lateness of a nuclear magnetic resonance appointment as claimed in claim 5, characterized in that: In the steps of collecting real-time traffic data, weather data and parking lot data respectively: Traffic data includes road congestion; weather data includes rainfall, temperature, and wind speed; parking lot data includes the number of vacant parking spaces and congestion at parking lot entrances.

7. The method for predicting lateness of a nuclear magnetic resonance appointment as claimed in claim 1, characterized in that: In the step of dividing the appointment registration time period, querying the registration status of the patient in the appointment registration time period, and outputting the registration identifier: Establish multiple appointment registration time periods; the appointment registration time period is the time period before the patient's appointment time, and multiple appointment registration time periods do not overlap; According to the time sequence of each appointment registration time period, query the patient's registration status, create a third late feature, and convert the third late feature into a registration identifier.

8. The method for predicting lateness of a nuclear magnetic resonance appointment as claimed in claim 1, characterized in that: In the step of setting the judgment threshold, obtaining the current calculation threshold according to the history identifier, time identifier and registration identifier, comparing the judgment threshold with the current calculation threshold, and outputting the patient's lateness prediction information: Set a first judgment threshold and a second judgment threshold respectively; Obtain the history identifier, time validity identifier and registration identifier, and calculate the current calculation threshold; The first judgment threshold, the second judgment threshold and the current calculation threshold are compared, and the prediction prompt data is output.

9. The method for predicting lateness of a nuclear magnetic resonance appointment as claimed in claim 8, characterized in that: In the step of comparing the first judgment threshold, the second judgment threshold and the current calculation threshold, and outputting the prediction prompt data: If the current calculation threshold is less than the first judgment threshold, the output prediction prompt data is: no late arrival occurs; If the current calculation threshold is between the first judgment threshold and the second judgment threshold, the output prediction prompt data is: it is expected that there will be a late arrival; If the current calculation threshold is greater than the second judgment threshold, the output prediction prompt data is: there is a late arrival situation.

10. A device for predicting lateness of a nuclear magnetic resonance appointment, applied to the method for predicting lateness of a nuclear magnetic resonance appointment as claimed in claim 1, characterized in that: It includes a historical data acquisition module, a timeliness data acquisition module, a registration data acquisition module and a judgment output module; wherein: The historical data acquisition module is used to acquire the nuclear magnetic resonance appointment data, extract the patient's unique identifier, query the patient's information data through the identifier, extract the historical feature data, and convert it into a historical identifier; The timeliness data acquisition module is used to acquire timeliness data, extract timeliness feature data, and convert it into a timeliness identifier; The registration data acquisition module is used to divide the appointment registration time period, query the patient's registration status in the appointment registration time period, and output the registration identifier; The judgment output module is used to set a judgment threshold, obtain a current calculation threshold according to a historical identifier, a time identifier and a registration identifier, compare the judgment threshold with the current calculation threshold, and output the patient's lateness prediction information.

Images