KR102501195B1 - Apparatus, method, computer-readable storage medium and computer program for decision making by hospital - Google Patents

Abstract

A decision-making device of a hospital according to an embodiment includes an input/output unit for receiving medical treatment information about a patient; a memory in which medical treatment information for a plurality of patients is converted into data in a predetermined structure format and stored therein; and a processor electrically connected to the memory, wherein the memory determines at least one medical event that may occur with respect to the plurality of patients as a correct answer, based on the input data of the predetermined structure format. At least one medical event for the patient is predicted through the deep learning learning model, and at least one medical event for the predicted patient, medical treatment information for the patient, and hospital status information are considered. It may include a command to perform the decision-making of the hospital.

Description

Hospital decision-making device, method, computer readable recording medium and computer program

The present invention relates to a hospital decision-making apparatus, method, computer readable recording medium and computer program.

Recently, as patient waiting time increases due to backlogs in hospitals, patients' discomfort is increasing.

In addition, if a plurality of patients in the hospital perform scheduling of treatment, hospitalization, and surgery in the order of the time when treatment was received, a problem that cannot be considered when treatment of a specific patient should be given priority according to the characteristics of each patient may occur. could

Therefore, there is a need for a technology capable of performing hospital decision-making so as to minimize the waiting time of patients while considering the characteristics of each patient and to efficiently operate the hospital's medical resources.

Korean Registered Patent Publication, No. 10-1834993 (registered on February 27, 2018)

The problem to be solved by the present invention is to provide a hospital decision-making device, method, computer readable recording medium and computer program.

In addition, such a hospital decision-making device predicts a patient's medical event through a deep learning learning model, and comprehensively considers the predicted medical event, patient treatment information, and hospital condition information to perform hospital decision-making. And the like may be included in the problem to be solved by the present invention.

However, the problem to be solved by the present invention is not limited to those mentioned above, and another problem to be solved that is not mentioned can be clearly understood by those skilled in the art from the description below. will be.

A decision-making device of a hospital according to an embodiment includes an input/output unit for receiving medical treatment information about a patient; a memory in which medical treatment information for a plurality of patients is converted into data in a predetermined structure format and stored therein; and a processor electrically connected to the memory, wherein the memory determines at least one medical event that may occur with respect to the plurality of patients as a correct answer, based on the input data of the predetermined structure format. At least one medical event for the patient is predicted through the deep learning learning model, and at least one medical event for the predicted patient, medical treatment information for the patient, and hospital status information are considered. It may include a command to perform the decision-making of the hospital.

In addition, the treatment information for the patient may include treatment information according to the time of the patient's first visit to the hospital, treatment information according to the time of visiting the hospital after the patient's first visit to the hospital, and other information other than the hospital. It may include at least one of medical information obtained from the hospital.

In addition, the medical event is a mortality rate within a predetermined period after discharge of the patient, a re-hospitalization rate within a predetermined period after discharge of the patient, a period from the time the patient is re-hospitalized to the time of discharge, and within a predetermined period after discharge of the patient. It may include at least one of the incidence of heart disease.

In addition, the hospital's decision-making may include determining the patient's operating room schedule.

In addition, the state information of the hospital may include the number of treatment rooms in the hospital, the number of treatment rooms used by each medical staff in the hospital, outpatient support manpower information for each medical staff, session opening status information for each day of the week of other medical staff within the same department of the hospital, and It may include at least one of hospital bed information, inpatient status information of the hospital, status information for each department, type and number of operating rooms of the hospital, schedule information for each operating room, and expected time required for each operation of the patient. .

In addition, the processor determines the patient's treatment order based on the patient's treatment information and the predicted patient's medical event, and further considers the patient's treatment order and the medical staff information of the hospital to determine the patient's treatment order. can determine your treatment schedule.

In addition, the medical staff information of the hospital includes treatment schedule information for each medical staff, information for each patient type, time information generated by the patient's treatment, schedule information for at least one of surgery, procedure, and research for each medical staff, and each medical staff. It may include at least one of performance information and whether or not the medical staff is assigned to the hospital.

In addition, the processor determines the patient's bed assignment order based on the patient's treatment information and the predicted patient's medical event, and determines the patient's bed assignment by further considering the determined patient's bed assignment order. can decide

A decision-making method of a hospital according to an embodiment includes the steps of converting medical treatment information for a plurality of patients into data in a predetermined structure format, and generating data for the plurality of patients by inputting the data in the predetermined structure format. Learning a deep learning learning model by setting at least one possible medical event as a correct answer; receiving medical information about a patient and predicting at least one medical event for the patient through the deep learning learning model; and making a decision of the hospital in consideration of the predicted at least one medical event for the patient, treatment information for the patient, and state information of the hospital.

In addition, the treatment information for the patient may include treatment information according to the time of the patient's first visit to the hospital, treatment information according to the time of visiting the hospital after the patient's first visit to the hospital, and other information other than the hospital. It may include at least one of medical information obtained from the hospital.

In addition, the medical event is a mortality rate within a predetermined period after discharge of the patient, a re-hospitalization rate within a predetermined period after discharge of the patient, a period from the time the patient is re-hospitalized to the time of discharge, and within a predetermined period after discharge of the patient. It may include at least one of the incidence of heart disease.

In addition, the hospital's decision-making may include determining the patient's operating room schedule.

In addition, the state information of the hospital may include the number of treatment rooms in the hospital, the number of treatment rooms used by each medical staff in the hospital, outpatient support manpower information for each medical staff, session opening status information for each day of the week of other medical staff within the same department of the hospital, and It may include at least one of hospital bed information, inpatient status information of the hospital, status information for each department, type and number of operating rooms of the hospital, schedule information for each operating room, and expected time required for each operation of the patient. .

The step of making a decision of the hospital may include determining the patient's treatment order based on the patient's treatment information and the predicted patient's medical event, and the determined patient's treatment order and the hospital's medical staff information. With further consideration, the patient's treatment schedule may be determined.

In addition, the medical staff information of the hospital includes treatment schedule information for each medical staff, information for each patient type, time information generated by the patient's treatment, schedule information for at least one of surgery, procedure, and research for each medical staff, and each medical staff. It may include at least one of performance information and whether or not the medical staff is assigned to the hospital.

In addition, the step of performing the decision-making of the hospital may include determining a bed allocation order of the patient based on the medical information about the patient and the predicted medical event of the patient, and further considering the determined bed assignment order of the patient. Thus, the bed assignment of the patient can be determined.

A computer-readable recording medium according to an embodiment is a computer-readable recording medium storing a computer program, and when the computer program is executed by a processor, the medical information on a plurality of patients is stored as data in a predetermined structure. The step of converting the data of the predetermined structure format into an input, at least one medical event that may occur for the plurality of patients as a correct answer, and learning a deep learning learning model; Receiving information and predicting at least one medical event for the patient through the deep learning learning model, the predicted at least one medical event for the patient, medical treatment information for the patient, and state of the hospital It may include instructions for causing the processor to perform a method including making a decision of the hospital in consideration of the information.

A computer program according to an embodiment is a computer program stored on a computer-readable recording medium, and the computer program, when executed by a processor, converts medical treatment information for a plurality of patients into data in a predetermined structure format. Step of learning a deep learning learning model by taking at least one medical event that can occur with respect to the plurality of patients as a correct answer by inputting the data of the predetermined structure format; and inputting medical information about the patient. and predicting at least one medical event for the patient through the deep learning learning model, considering the predicted at least one medical event for the patient, medical treatment information for the patient, and hospital status information. It may include instructions for causing the processor to perform a method including the step of performing the decision-making of the hospital.

According to an embodiment, the decision-making device of a hospital uses a deep learning learning model to use a medical event (e.g., mortality rate within a predetermined period after discharge of a patient, re-hospitalization rate within a predetermined period after discharge of a patient, time point at which a patient is re-hospitalized) It is possible to manage the system in the hospital by predicting the period from hospitalization to the time of discharge and the incidence of heart disease within a predetermined period after the patient's discharge, and comprehensively considering the predicted medical event, patient treatment information, and hospital condition information. Therefore, it is possible to provide a patient-specific hospital process.

1 is a block diagram of a decision-making device of a hospital according to an embodiment.
2 is a data table for explaining an example of medical information on a patient according to an embodiment.
3 is a diagram illustrating an example of converting medical treatment information for a plurality of patients into data in a predetermined structure format according to an embodiment.
4A to 4B are diagrams illustrating medical treatment information for a plurality of patients stored in a memory of a decision-making device of a hospital according to an embodiment.
5A and 5B are diagrams for explaining that data stored in a memory of a decision-making device of a hospital is converted into a standardized structure format and stored according to an embodiment.
6 is a flowchart illustrating training of a deep learning learning model according to an embodiment.
7 is a diagram for explaining an example of data input to a deep learning learning model according to an embodiment.
8 is a flowchart for explaining an example of performing decision-making in a hospital according to an embodiment.
9 is a flowchart illustrating an example of performing decision-making in a hospital according to another embodiment.
10 is an exemplary flowchart of a decision-making method of a hospital according to an embodiment.

Advantages and features of the present invention, and methods of achieving them, will become clear with reference to the detailed description of the following embodiments taken in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only these embodiments make the disclosure of the present invention complete, and common knowledge in the art to which the present invention belongs. It is provided to completely inform the person who has the scope of the invention, and the present invention is only defined by the scope of the claims.

In describing the embodiments of the present invention, if it is determined that a detailed description of a known function or configuration may unnecessarily obscure the subject matter of the present invention, the detailed description will be omitted. In addition, terms to be described later are terms defined in consideration of functions in the embodiment of the present invention, which may vary according to the intention or custom of a user or operator. Therefore, the definition should be made based on the contents throughout this specification.

1 is a block diagram of a decision-making device 100 of a hospital according to an embodiment.

Referring to FIG. 1 , a decision-making device 100 of a hospital according to an embodiment may include an input/output unit 101, a communication unit 102, a memory 110, and/or a processor 120.

The input/output unit 101 transmits, for example, commands or data input from a user or other external device to other component(s) of the decision-making device 100 of a hospital according to an embodiment, or in one embodiment Commands or data received from the other component(s) of the decision-making device 100 of the hospital according to the example may be output to a user or other external device.

As an embodiment, the input/output unit 101 may receive input of medical treatment information about a patient.

Here, the treatment information on the patient may include treatment information according to the time when the patient first visits the hospital and treatment information according to the time when the patient visits the hospital after the first time the patient visits the hospital. That is, the patient's medical treatment information may include the patient's past treatment information and the patient's current treatment information.

In addition, the medical treatment information on the patient may include medical treatment information at other hospitals other than the hospital where the patient currently obtains medical treatment information.

Hereinafter, an example of medical treatment information for a patient received through the input/output unit 101 will be described with reference to FIG. 2 .

2 is a data table for explaining an example of medical information on a patient according to an embodiment.

Referring to FIG. 2 , medical treatment information about a patient input to the input/output unit 101 may include hospital visit information (visit table) and medication information (medication table).

At this time, the hospital visit information includes the patient's visit number, hospital visit classification (for example, it can be classified as outpatient, hospitalized, emergency), hospitalization time and discharge time information, or among them (patient's visit number, Information on hospital visit classification, hospitalization time and discharge time) may be partially included.

Medication information (medication table) includes information on the patient's visit number, drug prescription date, drug type, and drug dose, or includes information on the patient's visit number, drug prescription date, drug type and dose ) may include some.

The communication unit 102 may support establishment of a wired or wireless communication channel between the decision-making device 100 of the hospital and an external device, and communication through the established communication channel.

The memory 110 includes various data used by at least one component (the processor 120, the input/output unit 101 and/or the communication unit 102) of the decision-making device 100 of the hospital, for example, software. (eg, a program) and input data or output data for commands related thereto may be stored. The memory 110 may include volatile memory or non-volatile memory.

As an example, the memory 110 may store medical treatment information for a plurality of patients converted into data in a predetermined structure format.

In this case, the medical treatment information on a plurality of patients may be accumulated data of the medical treatment information on the patients input through the input/output unit 101 .

Hereinafter, the conversion of medical treatment information for a plurality of patients stored in the memory 110 through FIGS. 2 to 5 into data in a predetermined structure format and storage thereof will be described.

3 is a diagram illustrating an example of converting medical treatment information for a plurality of patients into data in a predetermined structure format according to an embodiment.

The decision-making apparatus 100 of a hospital according to an embodiment may convert treatment information for a plurality of patients into data in a predetermined (or standardized) structure format and store the data in the memory 110 .

Referring to FIG. 3 , text data included in medical treatment information for a plurality of patients may be standardized into numeric data.

For example, in FIG. 2, dividing the hospital visit classification information into "outpatient", "hospitalization", and "emergency" can be converted into "373864002", "416800000", and "4525004", respectively, and drug information is "stain", Divided by "lnsulin" and "aspirin" can be converted to "1158753", "106892" and "315431", respectively.

At this time, medical information on a plurality of patients may be converted into data in a standardized structure format using a linkage database, but is not limited thereto.

4A to 4B are diagrams illustrating medical treatment information for a plurality of patients stored in the memory 110 of the decision-making apparatus 100 of a hospital according to an embodiment.

Referring to FIG. 4A , information on a plurality of patients stored in the memory 110 includes visit time points (visit 1 to visit 5) and treatment categories (eg, “hospitalization”, “examination”, “medication” and “medication”). The data may be sorted according to "surgery").

At this time, as shown in FIG. 4B, the decision-making device 100 of the hospital according to an embodiment converts the stored data (medical treatment information for a plurality of patients) to other data (visit 1 to visit 5) adjacent to the visit time point (visit 1 to visit 5). It is possible to embed a correlation with medical treatment information for a plurality of patients). At this time, embedding the correlation with other data adjacent in time of each data in this way is called history-aware embedding.

5A and 5B are views for explaining that data stored in the memory 110 of the decision-making device 100 of a hospital according to an embodiment is converted into a standardized structure format and stored.

As shown in FIG. 5A, information on a plurality of patients stored in the memory 110 includes visit time (visit 1 to visit 5) and treatment category (eg, "hospitalization", "examination", "medication"). and “surgery”), the data is sorted, and information on a plurality of patients may be stored as “○”.

In this case, when information on a plurality of patients is converted into a standardized structure format and stored, as shown in FIG. 5B , information on a plurality of patients may be changed from “○” to “□”.

The processor 120 (also referred to as a control unit, control unit or control circuit) is connected to at least one other component (eg, hardware component (eg, input/output unit 101), communication unit 102 of the decision-making device 100 of the hospital). ) and/or memory 110) or software components), and may perform various data processing and calculations.

As an embodiment, the processor 120 takes the information stored in the memory 110 (data obtained by converting medical treatment information for a plurality of patients into a standardized structure format) as an input, and generates data that can be generated for a plurality of patients. At least one medical event for a patient may be predicted through a deep learning learning model that has been learned by taking at least one medical event as a correct answer.

Hereinafter, training of the deep learning learning model in the processor 120 will be described with reference to FIGS. 6 and 7 .

6 is a flowchart illustrating training of a deep learning learning model according to an embodiment.

Referring to FIG. 6, first, in order to learn a deep learning learning model, medical information on a plurality of patients is input, and at least one medical event that may occur for the plurality of patients is used as the correct answer to form a deep learning learning model. It can be learned (step S1).

Then, in order to evaluate the accuracy of the deep learning learning model, the learned deep learning learning model may input some of the medical information about a plurality of patients into the deep learning learning model and check whether a desired medical event is output ( Step S2).

At this time, it can be checked whether the error value of the medical event output from the deep learning learning model is less than or equal to a preset value (step S3), and if the error value of the medical event output from the deep learning model exceeds the preset value, The deep learning learning model may be learned again in step S2.

Meanwhile, when the error value of the medical event output from the deep learning learning model is less than or equal to a preset value, the deep learning learning model may be stored (step S4).

Thereafter, it can be checked whether new data (eg, patient's medical information) is introduced (step S5). At this time, if new data (eg, patient's medical information) is introduced, go to step S1, New data may be input as input data for training the learning learning model. However, it may be terminated when no new data is introduced.

On the other hand, as shown in FIG. 7, as the input data of the deep learning learning model, medical information on a plurality of patients may be input. It can include treatment information (institution B) at other hospitals other than (institution A).

Referring back to FIG. 1 , the processor 120 may predict at least one medical event for the patient by inputting the patient's medical information to the deep learning learning model.

Here, the medical event is the mortality rate within a predetermined period after discharge of the patient, the readmission rate within a predetermined period (eg, 30 days) after discharge of the patient, the period from the time the patient is re-hospitalized to the time of discharge, and the patient's discharge and at least one of the incidence of heart disease within a predetermined period of time (eg, which may be 30 days).

More specifically, mortality within a predetermined period after discharge of a patient may include in-hospital death and death due to cancer.

In addition, as shown in Table 1 below, the mortality rate within a predetermined period after discharge of patients is the total number of patients in the hospital (total number of hospitalizations) and the number of patients who died within 30 days from the time of discharge among all patients in the hospital (30 days from the time of discharge). It can be calculated using the number of deaths within days).

[Table 1]

In this case, in Table 1, AUROC is a value representing the accuracy of mortality within a predetermined period after discharge of a patient predicted through a deep learning learning model. For example, the accuracy of the mortality rate within a predetermined period after discharge of a patient predicted through the deep learning learning model may be 92.39% by multiplying the value of AUROC by 100.

The readmission rate within a predetermined period (eg, it may be 30 days) after discharge of the patient is information on readmission within 30 days from the time of discharge of the patient in consideration of treatment information of patients before and during hospitalization. In this case, re-hospitalization refers to a case in which the time of re-hospitalization from the point of discharge is within 30 days, limited to patients with a record of being hospitalized at least once.

In addition, as shown in Table 2 below, among patients readmitted within a predetermined period of time (eg, it may be 30 days) after the patient's discharge, the long-term hospitalized patient rate is among the total patients in the hospital who are readmitted within 30 days. Using the number of patients (number of readmissions within 30 days) and the number of patients whose duration from readmission to discharge exceeded 7 days among all patients in the hospital (number of long-term hospitalizations (>7 days) during readmission) can be calculated by

[Table 2]

At this time, AUROC in Table 2 is a value representing the accuracy of the rate of long-term hospitalized patients among patients re-hospitalized within a predetermined period (eg, may be 30 days) after discharge of the patient predicted through the deep learning learning model. . For example, the accuracy of the rate of long-term hospitalized patients among patients who were re-hospitalized within a predetermined period (eg, it may be 30 days) after the patient's discharge through the deep learning learning model is 81.26% by multiplying the value of AUROC by 100. can be said

Table 3 below shows data on patients who were re-hospitalized within 30 days after the patient was discharged, and among them, a table showing whether the period from the time the patient was re-hospitalized to the time of discharge was less than or equal to a predetermined period. Here, the predetermined period is exemplarily expressed as 10 days.

In addition, as shown in Table 3 below, the period from the time the patient was readmitted to the time of discharge is the number of patients readmitted within 30 days (number of readmitted cases within 30 days) and the total number of patients in the hospital, as shown in Table 3 below. It can be calculated using the number of patients who were hospitalized for less than 10 days among patients who were re-hospitalized within 30 days (the number of cases hospitalized for less than 10 days among them).

[Table 3]

At this time, in Table 3, R^2 is an index that can confirm how accurately the number of hospitalization days or hospitalization period was predicted. In addition, the mean absolute error may mean an error rate of a period from the time the patient is re-hospitalized to the time of discharge.

The incidence of heart disease within a predetermined period (eg, which may be 30 days) after discharge of a patient is an event that predicts whether heart disease occurs within 30 days after discharge among all patients in the hospital. Here, the heart disease includes at least one of death, revascularization, myocardial infarction, and stroke, and the earliest occurring event within 30 days is considered.

In addition, as shown in Table 4 below, the incidence of heart disease within a predetermined period (eg, it may be 30 days) after the patient's discharge is the number of patients who visited the hospital again after being discharged (total number of visits), as shown in Table 4 below. ) and the number of patients with heart disease (eg, death, revascularization, myocardial infarction, stroke) among all patients in the hospital (the number of major cardiac events among them).

[Table 4]

On the other hand, the deep learning model used to predict medical events is a feed-forward neural network (FFNN) with boosted time-aware embeddings (or features) and a gradient boosting tree. It may be at least one of the models (GBM: Gradient Boosting Machine).

The processor 120 may perform hospital decision-making in consideration of the predicted patient's medical event, the patient's medical treatment information input from the input/output unit 101, and the state information of the hospital (which may be the hospital where the patient was treated). can

Here, the hospital status information includes the number of treatment rooms in the hospital, the number of treatment rooms used by each medical staff in the hospital, outpatient support manpower information by medical staff, session opening status information by day of the week of other medical staff in the same department of the hospital, hospital ward bed information, and hospital financial resources It may include at least one of patient condition information, condition information for each medical department, type and number of operating rooms, schedule information for each operating room, and expected time required for each operation of the patient, but is not limited thereto.

The hospital's decision-making may include at least one of determining a patient's treatment schedule, determining a patient's operating room schedule, and determining a patient's bed assignment.

As an embodiment, the processor 120 may determine a patient's treatment order based on medical information about the patient and a medical event of the patient predicted using a deep learning learning model.

For example, the processor 120 makes a hospital decision by considering a patient's medical event predicted using a deep learning learning model, treatment information about the patient, hospital status information, patient's treatment order, and hospital staff information. can be performed.

Here, the medical staff information of the hospital includes treatment schedule information for each medical staff, information for each patient type, time information generated by the patient's treatment, schedule information for at least one of surgery, procedure, and research for each medical staff, performance information for each medical staff, and appointment of medical staff at the hospital. It may include at least one of whether or not information, but is not limited thereto.

As another embodiment, the processor 120 may determine a patient's bed assignment order based on medical information about the patient and a patient's medical event predicted using a deep learning learning model.

For example, the processor 120 makes a hospital decision by considering a patient's medical event predicted using a deep learning learning model, treatment information about the patient, hospital status information, and the patient's bed (or room) assignment order. can be performed.

Hereinafter, an example (or scenario) of performing decision-making at a hospital using the decision-making apparatus 100 for a hospital according to an embodiment will be described.

8 is a flowchart for explaining an example of performing decision-making in a hospital according to an exemplary embodiment.

Referring to FIG. 8 , the decision-making apparatus 100 of a hospital according to an embodiment may first receive input of medical treatment information of a patient through the input/output unit 101 (step S11).

At this time, the decision-making device 100 of the hospital according to an embodiment includes the past patient's medical treatment information (eg, the patient's hospitalization history record) including other hospitals other than the hospital where the patient obtained the medical information in the patient's medical information ) can be checked whether or not exists (step S12).

If the patient's treatment information does not include the patient's treatment information (for example, the patient's hospitalization history record) including other hospitals other than the hospital where the patient obtained the treatment information, the patient's treatment order may be maintained.

At this time, the initial treatment order of the patient may be set to the last order of treatment among all patients in the hospital, but is not limited thereto.

Afterwards, if the patient's medical information includes past patient's medical information (eg, patient's hospitalization history record) including other hospitals other than the hospital where the patient obtained the medical information, deep learning is performed on the patient's medical information Through the model, it is possible to predict the mortality rate of a patient during a medical event within a predetermined period after being discharged from hospital, and confirm whether the predicted mortality rate within a predetermined period after discharge of a patient exceeds a predetermined probability (step S13).

In this case, if the predicted death rate of the patient within a predetermined period after being discharged is equal to or less than a predetermined probability, the patient's treatment order may be maintained as it is.

At this time, if the predicted mortality rate within a predetermined period after discharge of the patient exceeds a predetermined probability, the patient's treatment ranking may rise (step S14).

Thereafter, according to the patient's treatment order, the hospital decision-making apparatus 100 according to an embodiment provides the predicted patient's medical event, treatment information about the patient, hospital status information, patient's treatment order, and hospital staff information. Taking this into consideration, the patient's treatment schedule may be determined during decision-making at the hospital (step S15).

At this time, among the information used to determine the patient's treatment schedule in step S15, the treatment information on the patient includes the patient's mortality rate within a predetermined period after discharge, the number of hospital visits before the reference point in hospital visits, treatment waiting time, and treatment time required. , It may include at least one information of hospital visit information including at least one of diagnosis information, medication history information, surgery/procedure/treatment information, and body measurement information.

In addition, the information on the medical staff side may be information on the treatment schedule (eg, the number of openings per week, day of the week, morning and afternoon, total treatment hours, number of patients per hour, outpatient return rate (absence rate, additional treatment rate) information), and patient type Information (for example, patient type ratio, number of seats, re-examination rate, reservation rate, reservation-to-visit rate, non-visit rate, ratio of critically ill patients), average waiting time for each patient, treatment time for each patient, It may include at least one of patient end delay time information, medical staff operation/operation/research schedule, number of operations/operation/research results, post-outpatient surgery connection ratio, and position information.

In addition, the hospital state information may include at least one information of the number of treatment rooms in the department, the number of treatment rooms used by medical staff/by department, outpatient support personnel by medical staff, and session opening status information by other medical staff in the same department by day of the week.

Meanwhile, after step S15, the patient may be treated according to the determined patient's treatment schedule.

9 is a flowchart illustrating an example of performing decision-making in a hospital according to another embodiment.

Referring to Figure 9, first, according to an embodiment The decision-making apparatus 100 of the hospital may receive input of information on a list of patients reserved for hospitalization among treatment information on patients (step S21).

Thereafter, the decision-making device 100 of the hospital according to an embodiment predicts the incidence of heart disease within a predetermined period after the patient is discharged from the hospital during a medical event through a deep learning learning model for the patient's treatment information (reservation patient list information) , It is possible to check whether the incidence of heart disease within a predetermined period after discharge of the predicted patient exceeds a predetermined probability (step S22), and if the incidence of heart disease within a predetermined period after discharge of the predicted patient is less than the predetermined probability, the patient's The order of bed (or room) assignment may remain the same.

In this case, the initial bed (or ward) allocation order of the patient may be set to the last among the bed (or ward) allocation ranks of all patients in the hospital, but is not limited thereto.

On the other hand, if the predicted incidence of heart disease within a predetermined period after discharge of the patient exceeds a predetermined probability, the patient's bed (or ward) assignment order may rise (step S23).

Thereafter, the decision-making apparatus 100 of a hospital according to an embodiment includes a predicted medical event of a patient, treatment information about the patient, status information of the hospital, and the patient's bed (or room) according to the patient's bed (or room) assignment order Patient's bed assignment can be determined during hospital decision-making in consideration of the order of hospital room assignment (step S24).

At this time, among the information used to determine the patient's bed assignment in step S24, the patient's treatment information includes the patient's registration number (or visit number), name, gender, age, type of patient (new/second/return), etc. Basic information including diagnosis, diagnosis information including diagnosis name, department, doctor in charge, severity level, precautions, special notes, patient condition information including isolation type/reception date/required period, procedure/surgery name, expected date of surgery, It may include at least one information of the patient's surgery information including the surgeon, type of anesthesia, treatment information of the patient including the type/prescription/treatment of medicines and materials during the hospitalization period, and result information of various diagnostic tests and imaging tests. can

In addition, hospital condition information includes total bed information including names/numbers/numbers of wards, rooms, beds, etc., number of beds currently used by all hospitalized patients by ward/ward/bed, Inpatient status (hospitalization period, surgery/procedure/treatment status, etc.), ward/ward/bed status by department, type and number of operating rooms, schedule status by operating room (surgery name, operation timetable), and estimated operation time by surgery, at least It may contain one piece of information.

Furthermore, in determining the bed assignment of the patient in step S24, the total number of patients whose hospitalization period prediction value is 31 days or more at the time of admission (the total number of patients with a long hospitalization period), the hospitalization period prediction value at the time of admission A predetermined value less than 30 days The total number of patients with a predicted length of hospitalization within N days (for example, where N is 3 days) (the total number of patients with a short hospitalization period) and the total number of patients likely to be readmitted within 30 days At least one piece of information of the number of may be considered, but is not limited thereto.

Meanwhile, after step S24, the patient's bed assignment may succeed or fail, and if the patient's bed assignment succeeds, the patient may perform hospitalization procedures according to the determined bed assignment.

10 is an exemplary flowchart of a decision-making method of a hospital according to an embodiment. The hospital decision-making method shown in FIG. 10 can be performed by the hospital decision-making apparatus 100 shown in FIG. In addition, the decision-making method of the hospital shown in FIG. 10 is merely exemplary.

First, the decision-making apparatus 100 of a hospital according to an embodiment may convert medical treatment information for a plurality of patients into data having a predetermined structure (step S100).

Thereafter, the decision-making device 100 of the hospital may learn a deep learning learning model by taking at least one medical event that may occur for a plurality of patients as the correct answer by inputting data of a predetermined structure (step S200).

At least one medical event for the patient may be predicted through a deep learning learning model by receiving medical information about the patient (step S300).

Hospital decision-making may be performed in consideration of at least one medical event for a predicted patient, treatment information for the patient, and hospital status information (step S400).

As described above, according to an embodiment, the decision-making device of a hospital uses a deep learning learning model to perform medical events (e.g., mortality rate within a predetermined period after discharge of a patient, re-hospitalization rate within a predetermined period after discharge of a patient, The period from the time the patient is re-hospitalized to the point of discharge, and the incidence of heart disease within a certain period after the patient's discharge Because the system can be managed, it can provide patient-specific hospital processes.

Combinations of each block of the block diagram and each step of the flowchart accompanying the present invention may be performed by computer program instructions. Since these computer program instructions may be loaded into an encoding processor of a general-purpose computer, special-purpose computer, or other programmable data processing equipment, the instructions executed by the encoding processor of the computer or other programmable data processing equipment are each block or block diagram of the block diagram. Each step in the flow chart creates means for performing the functions described. These computer program instructions may also be stored in a computer usable or computer readable memory that can be directed to a computer or other programmable data processing equipment to implement functionality in a particular way, such that the computer usable or computer readable memory It is also possible for the instructions stored in to produce an article of manufacture containing instruction means for performing the function described in each block of the block diagram or each step of the flow chart. The computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operational steps are performed on the computer or other programmable data processing equipment to create a computer-executed process to generate computer or other programmable data processing equipment. It is also possible that the instructions performing the processing equipment provide steps for executing the functions described in each block of the block diagram and each step of the flowchart.

Additionally, each block or each step may represent a module, segment or portion of code that includes one or more executable instructions for executing specified logical function(s). It should also be noted that in some alternative embodiments it is possible for the functions recited in blocks or steps to occur out of order. For example, two blocks or steps shown in succession may in fact be performed substantially concurrently, or the blocks or steps may sometimes be performed in reverse order depending on their function.

The above description is merely an example of the technical idea of the present invention, and various modifications and variations can be made to those skilled in the art without departing from the essential qualities of the present invention. Therefore, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention, but to explain, and the scope of the technical idea of the present invention is not limited by these embodiments. The protection scope of the present invention should be construed according to the claims below, and all technical ideas within the scope equivalent thereto should be construed as being included in the scope of the present invention.

100: Hospital decision-making system
101: input/output unit
102: communication department
110: memory
120: processor

Claims (18)

an input/output unit for receiving medical information about a patient;
a memory in which medical treatment information for a plurality of patients is converted into data in a predetermined structure format and stored therein; and
And a processor electrically connected to the memory, wherein the memory, the processor,
Predicting at least one medical event for the patient through a deep learning learning model learned by taking at least one medical event that may occur for the plurality of patients as a correct answer by inputting the data of the predetermined structure format. and a command for performing decision-making of the hospital in consideration of the predicted at least one medical event for the patient, medical treatment information for the patient, and state information of the hospital,
the processor,
Determine the patient's treatment order based on the patient's treatment information and the predicted patient's medical event, and if a past hospitalization history record exists in the treatment information, after the patient's discharge from the hospital through the deep learning learning model Predicting mortality within a predetermined period as the medical event, and raising the determined patient's treatment priority when the mortality within a predetermined period after discharge from the hospital exceeds a predetermined probability;
The predicted patient's medical event, the patient's medical treatment information (the number of hospital visits before the reference point of visit to the hospital, treatment waiting time and treatment required time, diagnosis information, medication history information, surgery/procedure/treatment information, and body measurement information), determining the patient's treatment schedule in consideration of the hospital's status information, the determined patient's treatment order, and the hospital's medical staff information
Hospital decision-making equipment. According to claim 1,
Medical information about the patient,
At least one of medical information according to the time when the patient first visited the hospital, treatment information according to time when the patient visited the hospital after the first time the patient visited the hospital, and treatment information obtained from other hospitals other than the hospital more inclusive
Hospital decision-making equipment. According to claim 1,
The medical event,
Further comprising at least one of a readmission rate within a predetermined period after discharge of the patient, a period from the time the patient is readmitted to the hospital to the time of discharge, and an incidence rate of heart disease within a predetermined period after discharge of the patient
Hospital decision-making equipment. According to claim 1,
The hospital's decision-making is
Including determining the patient's operating room schedule
Hospital decision-making equipment. According to claim 1,
The condition information of the hospital,
The number of treatment rooms in the hospital, the number of treatment rooms used by medical staff in the hospital, outpatient support manpower information by medical staff, session opening status information by day of the week of other medical staff in the same department of the hospital, ward bed information in the hospital, in-patients in the hospital At least one of status information, status information for each department, type and number of operating rooms of the hospital, schedule information for each operating room, and expected time required for each operation of the patient
Hospital decision-making equipment. delete According to claim 1,
The information of the medical staff of the hospital,
The medical treatment schedule information for each medical staff, the information for each patient type, the time information generated by the patient's treatment, the schedule information for at least one of surgery, procedure, and research for each medical staff, the performance information for each medical staff, and whether or not the medical staff is assigned to the hospital containing at least one of the
Hospital decision-making equipment. According to claim 1,
the processor,
determining a bed assignment order of the patient based on medical information about the patient and the predicted medical event of the patient;
Determining the bed assignment of the patient by further considering the determined bed assignment order of the patient
Hospital decision-making equipment. As a decision-making method performed by the decision-making device of the hospital,
Converting medical treatment information for a plurality of patients into data in a predetermined structure format;
Learning a deep learning learning model by taking at least one medical event that may occur for the plurality of patients as a correct answer by inputting the data of the predetermined structure format;
receiving medical information about the patient and predicting at least one medical event for the patient through the deep learning learning model;
Performing decision-making of the hospital in consideration of at least one medical event for the predicted patient, treatment information for the patient, and state information of the hospital;
The step of making the decision of the hospital is,
Determine the patient's treatment order based on the patient's treatment information and the predicted patient's medical event, and if a past hospitalization history record exists in the treatment information, after the patient's discharge from the hospital through the deep learning learning model Predicting mortality within a predetermined period as the medical event, and raising the determined patient's treatment priority when the mortality within a predetermined period after discharge from the hospital exceeds a predetermined probability;
The predicted patient's medical event, the patient's medical treatment information (the number of hospital visits before the reference point of visit to the hospital, treatment waiting time and treatment required time, diagnosis information, medication history information, surgery/procedure/treatment information, and body measurement information), determining the patient's treatment schedule in consideration of the hospital's status information, the determined patient's treatment order, and the hospital's medical staff information
How hospitals make decisions. According to claim 9,
Medical information about the patient,
At least one of medical information according to the time when the patient first visited the hospital, treatment information according to time when the patient visited the hospital after the first time the patient visited the hospital, and treatment information obtained from other hospitals other than the hospital more inclusive
How hospitals make decisions. According to claim 9,
The medical event,
Further comprising at least one of a readmission rate within a predetermined period after discharge of the patient, a period from the time the patient is readmitted to the hospital to the time of discharge, and an incidence rate of heart disease within a predetermined period after discharge of the patient
How hospitals make decisions. According to claim 9,
The hospital's decision-making is
Including determining the patient's operating room schedule
How hospitals make decisions. According to claim 9,
The condition information of the hospital,
The number of treatment rooms in the hospital, the number of treatment rooms used by medical staff in the hospital, outpatient support manpower information by medical staff, session opening status information by day of the week of other medical staff in the same department of the hospital, ward bed information in the hospital, in-patients in the hospital At least one of status information, status information for each department, type and number of operating rooms of the hospital, schedule information for each operating room, and expected time required for each operation of the patient
How hospitals make decisions. delete According to claim 9,
The information of the medical staff of the hospital,
The medical treatment schedule information for each medical staff, the information for each patient type, the time information generated by the patient's treatment, the schedule information for at least one of surgery, procedure, and research for each medical staff, the performance information for each medical staff, and whether or not the medical staff is assigned to the hospital containing at least one of the
How hospitals make decisions. According to claim 9,
The step of making the decision of the hospital is,
determining a bed assignment order of the patient based on medical information about the patient and the predicted medical event of the patient;
Determining the bed assignment of the patient by further considering the determined bed assignment order of the patient
How hospitals make decisions. A computer-readable recording medium storing a computer program,
When the computer program is executed by a processor,
Converting medical treatment information for a plurality of patients into data in a predetermined structure format;
Learning a deep learning learning model by taking at least one medical event that may occur for the plurality of patients as a correct answer by inputting the data of the predetermined structure format;
receiving medical information about the patient and predicting at least one medical event for the patient through the deep learning learning model;
Performing decision-making of the hospital in consideration of at least one medical event for the predicted patient, treatment information for the patient, and state information of the hospital;
The step of making the decision of the hospital is,
Determine the patient's treatment order based on the patient's treatment information and the predicted patient's medical event, and if a past hospitalization history record exists in the treatment information, after the patient's discharge from the hospital through the deep learning learning model Predicting mortality within a predetermined period as the medical event, and raising the determined patient's treatment priority when the mortality within a predetermined period after discharge from the hospital exceeds a predetermined probability;
The predicted patient's medical event, the patient's medical treatment information (the number of hospital visits before the reference point of visit to the hospital, treatment waiting time and treatment required time, diagnosis information, medication history information, surgery/procedure/treatment information, and body measurement information), including instructions for causing the processor to perform a method of determining the patient's treatment schedule in consideration of the state information of the hospital, the determined treatment order of the patient, and medical staff information of the hospital
A computer-readable recording medium. As a computer program stored on a computer-readable recording medium,
When the computer program is executed by a processor,
Converting medical treatment information for a plurality of patients into data in a predetermined structure format;
Learning a deep learning learning model by taking at least one medical event that may occur for the plurality of patients as a correct answer by inputting the data of the predetermined structure format;
receiving medical information about the patient and predicting at least one medical event for the patient through the deep learning learning model;
Performing decision-making of the hospital in consideration of at least one medical event for the predicted patient, treatment information for the patient, and state information of the hospital;
The step of making the decision of the hospital is,
Determine the patient's treatment order based on the patient's treatment information and the predicted patient's medical event, and if a past hospitalization history record exists in the treatment information, after the patient's discharge from the hospital through the deep learning learning model Predicting mortality within a predetermined period as the medical event, and raising the determined patient's treatment priority when the mortality within a predetermined period after discharge from the hospital exceeds a predetermined probability;
The predicted patient's medical event, the patient's medical treatment information (the number of hospital visits before the reference point of visit to the hospital, treatment waiting time and treatment required time, diagnosis information, medication history information, surgery/procedure/treatment information, and body measurement information), including instructions for causing the processor to perform a method of determining the patient's treatment schedule in consideration of the state information of the hospital, the determined treatment order of the patient, and medical staff information of the hospital
computer program.

Images