Server, terminal, method, program, and method for generating trained model for predicting changes in patient condition

Abstract

To provide a server capable of predicting change in condition of a patient suffering from chronic obstructive pulmonary disease, a terminal, a method, a program, and a method for generating a learnt model.SOLUTION: A server has an acquisition unit that acquires data on a first test item for respiratory function and a second test item for comorbidities for patients suffering from chronic obstructive pulmonary disease (COPD), and a prediction unit that predicts change in condition of the patient using the data on the first and second test items.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a server, a terminal, a method, a program, and a method for generating a trained model for predicting changes in a patient's condition. [Background technology]

[0002] Chronic obstructive pulmonary disease (COPD) is a chronic disease that is common among elderly men with a history of smoking. COPD patients are repeatedly re-admitted to hospital due to repeated exacerbations caused by respiratory infections, etc., and their quality of life (QOL) declines as the disease progresses, requiring appropriate intervention at key points. The number of COPD patients is on the rise, and it is said that by 2030, ischemic heart disease, stroke, COPD, and respiratory infections will be the four leading causes of death in the world.

[0003] If a patient with COPD is repeatedly re-admitted to hospital, medical costs will increase. Therefore, it is important to distinguish between patients who are at high risk of re-admission and those who are not among those who have been discharged from the hospital after contracting COPD, and to warn those at high risk in order to prevent re-admission.

[0004] A method for predicting the risk of a patient suffering from COPD has been reported (for example, Patent Document 1). Patent Document 1 discloses an apparatus for assessing the risk of exacerbation and / or hospitalization of a subject who is a COPD patient, the apparatus including an input unit for receiving time-dependent physical activity data of the subject, an activity data conversion unit for acquiring frequency-dependent activity data, a moment determination unit for calculating moments of the frequency-dependent activity data, and a risk assessment unit for assessing the risk of exacerbation and / or hospitalization of the subject based on at least the moments.

[0005] The device disclosed in Patent Document 1 predicts an increase in the risk of exacerbation or hospitalization from a decrease in a patient's moment, based on the fact that a decrease in moment corresponds to a decrease in the frequency and intensity of the activity cycle. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Patent No. 6367982 Summary of the Invention [Problem to be solved by the invention]

[0007] However, because factors other than a decline in the patient's activity cycle also influence the exacerbation or hospitalization of COPD patients, there was a problem in that it was difficult to accurately predict risk using the method described in Patent Document 1.

[0008] The present invention aims to provide a server, terminal, method, program, and method for generating a trained model that are capable of accurately predicting changes in the condition of patients suffering from COPD. [Means for solving the problem]

[0009] The server according to an embodiment of the present disclosure is characterized by having an acquisition unit that acquires data on a first test item related to respiratory function and a second test item related to a comorbid disease of a patient suffering from COPD, and a prediction unit that predicts changes in the patient's condition using the data on the first and second test items.

[0010] In a server according to an embodiment of the present disclosure, it is preferable that the prediction by the prediction unit is made using a trained model created based on data on the first and second test items of multiple patients suffering from COPD and data on changes in the condition of the multiple patients.

[0011] In a server according to an embodiment of the present disclosure, it is preferable that the trained model is created using a Boosting model.

[0012] In the server according to the embodiment of the present disclosure, the Boosting model is preferably an XGBoost model.

[0013] In the server according to the embodiment of the present disclosure, it is preferable that the acquisition unit acquires data of the patient before he or she is discharged from the hospital, and the prediction unit predicts a change in the patient's condition after he or she is discharged from the hospital.

[0014] In a server according to an embodiment of the present disclosure, the change in a patient's condition preferably includes the patient being re-admitted to the hospital.

[0015] In the server according to the embodiment of the present disclosure, it is preferable that the acquisition unit further acquires data on a third examination item related to a frailty factor.

[0016] In a server according to an embodiment of the present disclosure, it is preferable that the prediction by the prediction unit is made using a trained model created based on data on the first, second and third test items of multiple patients suffering from chronic obstructive pulmonary disease and data on changes in the condition of the multiple patients.

[0017] In a server according to an embodiment of the present disclosure, it is preferable that the data regarding the second test item related to a comorbid disease includes at least one of data regarding the name of the comorbid disease, data regarding a blood test, data regarding a vital sign test, and prescription data.

[0018] In a server according to an embodiment of the present disclosure, it is preferable that data regarding a third test item related to frailty factors includes data regarding at least one of age, body mass index (BMI), activities of daily living (ADL), nutritional status, and whether or not the person lives alone.

[0019] In the server according to the embodiment of the present disclosure, it is preferable to further have a determination unit that determines which of a plurality of predetermined hierarchies the prediction result of the patient's condition change predicted by the prediction unit corresponds to.

[0020] It is preferable that the server according to the embodiment of the present disclosure further includes an output unit that outputs the predicted state change.

[0021] In the server according to the embodiment of the present disclosure, the prediction by the prediction unit preferably predicts a physical state of a patient and / or a transition probability thereof.

[0022] A terminal according to an embodiment of the present disclosure is characterized in that it has an input unit for inputting data regarding a first test item related to respiratory function of a patient suffering from COPD and a second test item related to a comorbid disease, a transmitting unit for transmitting the input data to a server, a receiving unit for predicting a change in the patient's condition using the data regarding the first and second test items, respectively, and receiving the predicted change in condition from the server, and an output unit for outputting the received change in condition.

[0023] A method for predicting a change in condition according to an embodiment of the present disclosure includes obtaining data on a first test item related to respiratory function and a second test item related to a comorbid disease of a patient suffering from COPD, and calculating a predicted value of the change in condition of the patient using the data on the first and second test items.

[0024] A program according to an embodiment of the present disclosure is characterized in that it causes a computer to acquire data on a first test item related to respiratory function and a second test item related to a comorbid disease of a patient suffering from COPD, and to predict a change in the patient's condition using the data on the first and second test items.

[0025] A method for generating a trained model according to an embodiment of the present disclosure is characterized in that it acquires training data including data on a first test item related to respiratory function and a second test item related to a comorbid disease for multiple patients suffering from COPD, and data on changes in the condition of the multiple patients, and generates a trained model in which the data on the first and second test items are input and the data on the changes in condition are output. Effect of the Invention

[0026] According to the server, terminal, method, program, and method for generating a trained model according to the embodiments of the present disclosure, it is possible to accurately predict changes in the condition of a patient suffering from COPD. [Brief description of the drawings]

[0027] [Figure 1] FIG. 1 is a configuration diagram of a system including a server according to an embodiment of the present disclosure. [Diagram 2] FIG. 2 is a configuration diagram of a terminal according to an embodiment of the present disclosure. [Diagram 3] FIG. 1A is a diagram for explaining a calculation method using an XGBoost model used in a server according to an embodiment of the present disclosure, where FIG. 1A shows a model image and FIG. 1B shows a learning image. [Figure 4] 11 is a flowchart for explaining an example of a procedure for creating a learning model used in a server according to an embodiment of the present disclosure. [Diagram 5] FIG. 11 is a configuration diagram of a server according to a first modified example of the embodiment of the present disclosure. [Figure 6] FIG. 13 is a diagram showing an example of an output result by a server according to the first modified example of the embodiment of the present disclosure. [Figure 7] 11 is a flowchart for explaining an operation procedure of a server according to an embodiment of the present disclosure. [Figure 8] This table classifies patient conditions into five categories based on vital signs and blood test items. [Figure 9] 9 is a table showing the probability of the five states in FIG. 8 transitioning from the pre-transition state seven days later. [Figure 10] 8, the state transition probabilities in FIG. 9, and changes in patient condition suggested by the state sequences obtained by statistical methods. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0028] Hereinafter, a server, a terminal, a method, a program, and a method for generating a trained model for predicting a change in a patient's condition according to the present invention will be described with reference to the drawings. However, it should be noted that the technical scope of the present invention is not limited to those embodiments, but extends to the inventions described in the claims and their equivalents.

[0029] [System Configuration] 1 shows a configuration diagram of a system 1000 including a server 101 according to an embodiment of the present disclosure. The system 1000 includes the server 101 and a plurality of terminals 300. The server 101 and the plurality of terminals 300 are connected by a communication network 200 in a wired or wireless manner. Although a plurality of terminals 300 are illustrated in FIG. 1, the number of terminals 300 may be one.

[0030] The server 101 includes a control unit 10, a communication interface (I / F) 20, and a storage unit 30, which are connected by a bus 40.

[0031] The communication I / F 20 (output unit) is connected to a plurality of terminals 300 via the communication network 200 to exchange data.

[0032] The storage unit 30 may be a storage device such as a RAM or a ROM, or a storage device such as an optical disk. The storage unit 30 stores a program for controlling the server 101. It is also preferable that the storage unit 30 stores electronic medical record information of patients. This also includes an operation in which items required for this risk prediction program are extracted from the electronic medical record information of patients and the anonymized information is stored.

[0033] The control unit 10 includes a CPU. The control unit 10 controls the server 101 by executing a program stored in the storage unit 30.

[0034] 1, the control unit 10 of the server 101 includes an acquisition unit 11 and a prediction unit 12. The acquisition unit 11 and the prediction unit 12 are realized as software (programs) by a computer provided in the server 101 including a CPU, a ROM, a RAM, and the like.

[0035] [Device configuration] Next, a terminal according to an embodiment of the present disclosure will be described. Fig. 2 shows a configuration diagram of a terminal 300 according to an embodiment of the present disclosure. The terminal 300 includes a control unit 31, an input unit 32, a transmission unit 33, a reception unit 34, an output unit 35, and a storage unit 36, which are connected by a bus 37.

[0036] The control unit 31 includes a CPU. The control unit 31 controls the terminal 300 by executing a program stored in the storage unit .

[0037] As the input unit 32, an input device such as a touch panel, a mouse, a touch pad, or a keyboard can be used.

[0038] A display device such as a liquid crystal display device can be used as the output unit 35. Alternatively, an output device such as a printer can be used as the output unit 35.

[0039] [Data used to predict changes in patient condition] A system 1000 including a server 101 according to an embodiment of the present disclosure predicts a change in the condition of a patient suffering from COPD by using data on a first test item related to respiratory function and a second test item related to a comorbid disease. The system 1000 preferably further predicts a change in the condition of the patient by using data on a third test item related to a frailty factor. Each data will be described in detail below.

[0040] The data regarding the first test item related to respiratory function includes at least one of data regarding the GOLD (Global Initiative for Chronic Obstructive Lung Disease) classification, other data regarding spirometry measurements, data regarding the mMRC (Medical Research Council), and data regarding the CAT (COPD Assessment Test), preferably the GOLD classification and mMRC.

[0041] GOLD is a global initiative for chronic obstructive pulmonary disease and provides diagnostic criteria for COPD. The GOLD classification is divided into four categories. A predicted FEV1 of 80 or more is GOLD classification 1, a predicted FEV1 of 50-79 is GOLD classification 2, a predicted FEV1 of 30-49 is GOLD classification 3, and a predicted FEV1 of less than 30 is GOLD classification 4.

[0042] The mMRC is a modified MRC shortness of breath scale, a questionnaire with a modified MRC grade classification of 0 to 4. It is used as a scale to evaluate the severity of dyspnea.

[0043] The data on the second test item for the comorbid disease includes at least one of data on the name of the comorbid disease, data on a blood test, data on a vital sign test, and prescription data.

[0044] Data on the names of comorbid diseases is data on the names of diseases other than COPD. COPD patients have a high frequency of respiratory complications and systemic comorbidities. This is thought to be caused by systemic inflammation caused by COPD. Therefore, COPD needs to be managed as a systemic disease. Comorbid diseases include, for example, cardiovascular disease and cancer. For data on disease names, it is a good idea to refer to the names of ICD-10 codes (International Classification of Diseases).

[0045] The data on blood tests includes at least one of data on BUN (blood urea nitrogen), Alb (albumin), CRP (C-reactive protein), ChE (cholinesterase), pH (hydrogen ion index), NT-proBNP (N-terminal pro-B-type natriuretic peptide), IgM (immunoglobulin M), IgG (immunoglobulin G), LDH (lactate dehydrogenase), PT seconds (prothrombin time), γ-GTP (gamma-glutamyl transpeptidase), total protein, ALP (alkaline phosphatase), cTnI (cardiac troponin I), cTnT (cardiac troponin T), A / G ratio (albumin / globulin ratio), hematocrit, hemoglobin, white blood cell count, PaCO2 (arterial blood carbon dioxide partial pressure), and PaO2 (arterial blood oxygen partial pressure), and is preferably BUN, CRP, ChE, and pH.

[0046] BUN indicates the state of kidney and liver function. If the value is above the standard value, kidney disease is suspected, and if it is below the standard value, liver disease is suspected. The value also tends to rise when one is dehydrated. It is also one of the items in the severity classification of pneumonia (A-DROP system).

[0047] Alb is a useful indicator for comprehensively assessing the nutritional status of the whole body. If the value decreases, the patient is presumed to be malnourished, and if the value increases, the patient is presumed to be recovered.

[0048] CRP appears in the blood when an inflammatory response or tissue destruction occurs in the body, and high levels may indicate infection, cancer, myocardial infarction, etc.

[0049] ChE is an enzyme produced in the liver, and low levels indicate decreased liver function, while high levels suggest fatty liver or dyslipidemia caused by overnutrition. ChE, along with Alb, is also used as an indicator of nutritional status.

[0050] pH is measured by arterial blood gas analysis to determine whether blood is acidic or alkaline. Abnormal pH can result from serious diseases such as respiratory or renal failure and is therefore used as a treatment guide.

[0051] The data relating to the vital signs test includes at least one of data relating to respiration rate, pulse rate, body temperature, blood pressure, and SpO2, and is preferably data relating to respiration rate and SpO2.

[0052] Respiratory rate is the number of breaths taken per minute, and COPD patients tend to have an increased respiratory rate because they take in less ventilation per breath.

[0053] SpO2 stands for percutaneous arterial oxygen saturation, and the normal value is 96 to 99%, with respiratory failure being suspected if it is below 90%.

[0054] The prescription data includes data on medications prescribed to patients. When using the medication data, the medication data can be classified using a medication classification code or the like.

[0055] The data on the third test item related to the frailty factor includes data on at least one of age, BMI, ADL, nutritional status, and whether or not the patient lives alone, and preferably data on ADL and nutritional status.

[0056] Data on ADL is an index used in medical and nursing care settings to measure the degree of independence of patients. The Barthel Index (BI) and other methods can be used to evaluate ADL.

[0057] As data on nutritional status, in addition to BMI, for example, blood test data such as ChE and Alb can be used.

[0058] [Procedure for predicting changes in a patient's condition] A system 1000 including a server 101 according to an embodiment of the present disclosure predicts a change in the condition of a patient suffering from COPD by using data on a first test item related to respiratory function and a second test item related to a comorbid disease. The system 1000 preferably further predicts a change in the condition of the patient by using data on a third test item related to a frailty factor. The procedure for executing the prediction is described below.

[0059] Data on a first test item related to respiratory function and a second test item related to comorbid diseases for a patient suffering from COPD are inputted through the input unit 32 of the terminal 300. It is preferable that the input unit 32 further inputs data on a third test item related to frailty factors.

[0060] As shown in FIG. 1, the transmission unit 33 transmits the above data input by the input unit 32 to the server 101 via the communication network 200.

[0061] The acquisition unit 11 acquires the transmitted data on the first test item related to respiratory function and the second test item related to a comorbid disease of the patient suffering from COPD. The acquisition unit 11 may also process or convert the data acquired by the acquisition unit 11 so that processing in the prediction unit 12 described below proceeds smoothly. Although the processing has been described as being performed on the server side as one embodiment, it may also be performed on the terminal side (e.g., the control unit 31, the input unit 32, the transmission unit 33, etc.).

[0062] It is preferable that the acquiring unit 11 further acquires data on a third examination item related to a frailty factor.

[0063] The prediction unit 12 predicts a change in the patient's condition by using data on the first and second test items, respectively. That is, the prediction unit 12 predicts a change in the patient's condition by using not only data on the first test item related to the respiratory function of a patient suffering from COPD, but also data on the second test item related to a comorbid disease. Since COPD is a respiratory disease, but is also known as a systemic inflammatory disease, the change in the patient's condition may occur not only due to an exacerbation of COPD but also throughout the entire body. Therefore, the server according to the embodiment of the present disclosure predicts a change in the patient's condition more accurately by using data on the comorbid disease in addition to data on the respiratory function.

[0064] It is preferable that the prediction unit 12 further predicts the change in the patient's condition by using data on a third test item related to the frailty factor. The reason for adding the frailty factor is that it is said that the decline in lung function and comorbid diseases are also related to aging factors, and therefore, by using data on the frailty factor, the change in the patient's condition can be predicted more accurately.

[0065] The prediction by the prediction unit 12 is performed using a trained model created based on data on the first and second examination items of multiple patients suffering from COPD and data on changes in the condition of the multiple patients. That is, a trained model is created in advance by machine learning based on data on the first and second examination items of multiple patients suffering from COPD and data on changes in the condition of the multiple patients, and is stored in the storage unit 30. The method of creating the model will be described later.

[0066] The acquisition unit 11 preferably acquires data of the patient before discharge from the hospital, and the prediction unit 12 preferably predicts a change in the patient's condition after discharge from the hospital. The server 101 according to the embodiment of the present disclosure predicts a change in the patient's condition after discharge from the hospital, using data on a first test item related to the patient's respiratory function before discharge from the hospital and a second test item related to a comorbid disease, and preferably further using data on a third test item related to a frailty factor. Here, "before discharge from the hospital" preferably means immediately before discharge from the hospital, for example, "at the time of discharge from the hospital". This is because data on test items related to the patient's respiratory function and comorbid diseases immediately before discharge from the hospital is considered to best represent the condition of the patient being discharged from the hospital.

[0067] The change in the patient's condition includes the patient being re-admitted to hospital. Here, "re-admission" includes not only re-admission due to an exacerbation of COPD, but also re-admission due to factors other than an exacerbation of COPD. This is because patients with COPD may be re-admitted to hospital after discharge due to factors other than an exacerbation of COPD.

[0068] In addition, "readmission" includes being readmitted within a predetermined period. Here, the predetermined period may be, for example, 30 days after discharge. However, it is not limited to such an example, and may be any period such as 60 days after discharge, or 90 days after discharge.

[0069] The server 101 outputs the predicted state change. For example, it transmits it to the terminal 300 via the communication network 200. As another output destination, the predicted state change may be transmitted to a display device such as a liquid crystal display device or an output device such as a printer without passing through the communication network 200.

[0070] The receiving unit 34 receives the predicted state change from the server 101 .

[0071] The output unit 35 outputs the state change received from the server 101 .

[0072] As described above, the server 101 for predicting changes in a patient's condition according to an embodiment of the present disclosure uses not only data on a first test item related to respiratory function, but also data on a second test item related to a comorbid disease, or data on a third test item related to a test item related to a frailty factor, thereby making it possible to more accurately predict changes in the condition of a patient suffering from chronic obstructive pulmonary disease.

[0073] [Learning model creation method] The trained model is preferably one created by a Boosting model. Boosting is a method of continuously training weak learners to create a learning algorithm that is stronger than an algorithm using a single weak learner. Finally, a final model is created by weighting the models with high accuracy.

[0074] As the boosting model, the XGBoost (eXtreme Gradient Boosting) model, the GBDT (Gradient Boosting Decision Tree), the LightGBM (Light Gradient Boosting Model), etc. may be used, and the XGBoost model is preferable. The XGBoost model is an ensemble learning model that combines gradient boosting and random forest.

[0075] XGBoost is a method for constructing weak learners one by one in order, and is a model that uses the results of all previously constructed weak learners when constructing a new weak learner. Figures 3(a) and (b) are diagrams for explaining the calculation method by XGBoost. The vertical axis of Figure 3(a) shows the tree structure, and the vertical axis of Figure 3(b) shows the predicted value y i The horizontal axis indicates round t, and the horizontal axis indicates round t. In XGBoost, trees like those shown in Figure 3(a) are added one after another to compensate for the difference between the true value and the predicted values ​​(y1´, y2´, y3´, ...) as shown in Figure 3(b).

[0076] First, it is assumed that a predicted value y1' is obtained using the decision tree 41. In this case, if the true value is y0, the error is y0-y1'. Next, the second decision tree 42 is created so as to cancel this error. That is, the second decision tree 42 is created so that the accuracy is improved when the results of the first decision tree 41 and the second decision tree 42 are added together. In this case, it is assumed that a predicted value y2' is obtained using the decision tree 42, the error is y0-y2'. Furthermore, a third decision tree 43 is created so as to cancel this error, and a predicted value y3' is calculated. As described above, since XGBoost is an algorithm that fills in residuals, high accuracy can be obtained.

[0077] When performing data analysis to predict state changes for input data used in XGBoost, if too many explanatory variables are used, multicollinearity and noise can become a problem. In addition, there are a wide variety of test items, and it is not efficient to predict the probability of state changes using all of the test items. Therefore, it is preferable to calculate partial correlation coefficients by partial correlation analysis, for example, and extract important correlated explanatory variables.

[0078] Furthermore, it is preferable to set thresholds for the continuous values ​​of blood tests and vital signs measured by, for example, decision tree analysis for the extracted variables, and grade them. This makes it possible to make calculations by XGBoost more efficient.

[0079] This article describes the results of using machine learning to build a 30-day readmission and death risk prediction model and to search for risk factors using discharge data on the first test item related to respiratory function, the second test item related to comorbid diseases, and the third test item related to frailty factors.Basic information, respiratory function, disease name, prescribed medication, and device prescription information were added to the blood tests, vital signs, and ADL items extracted by decision tree analysis as described above, and machine learning (XGBoost analysis) was performed.

[0080] By using various parameters related to the first test item related to respiratory function, the second test item related to comorbid diseases such as disease name, prescribed medications, blood and vital signs, and the third test item related to frailty factors such as ADL and basic information in the analysis, it is estimated that it is possible to comprehensively determine the risk of re-hospitalization or death within 30 days (including hospitalization for reasons other than exacerbation) for patients with COPD as their underlying disease, rather than simply "predicting the patient's risk of COPD exacerbation."

[0081] In addition, by using blood and vital sign test items in the analysis, it is possible to link the patient's objective physical condition at the time of discharge with condition transitions and outcomes (re-admission).

[0082] Next, a method for creating a learning model by a server according to an embodiment of the present disclosure will be described. Fig. 4 shows a flowchart for explaining a procedure for creating a learning model used by a server according to an embodiment of the present disclosure.

[0083] First, in step S101, data on a first test item related to respiratory function for a patient suffering from COPD, a second test item related to comorbid diseases, and a third test item related to frailty factors are acquired. As an example, 1306 pieces of data were used as a dataset. For hold-out validation, 999 pieces of training data and 429 pieces of test data were used. The total number of pieces of training data and test data was 1428, and the ratio of labels was adjusted to be label 0: label 1 = 1:1. Here, label 0 is a label that does not have the outcome of readmission or death within 30 days, and label 1 is a label that has the outcome of readmission or death within 30 days.

[0084] Next, in step S102, partial correlation coefficients are calculated by partial correlation analysis for the data on the second and third test items, and important explanatory variables are extracted. A partial correlation coefficient is a correlation coefficient obtained by removing the influence of a third variable from two variables when the correlation between the two variables is increased or decreased by the third variable.

[0085] Next, in step S103, a threshold value for the continuous value of the data related to the second test item is set by decision tree analysis, and grading is performed. For example, the continuous value is divided into a high value, a reference value, and a low value based on the set threshold value.

[0086] Next, in step S104, the first test item is added to the extracted data on the second and third test items, and machine learning (XGBoost analysis) is performed. The analysis method using XGBoost is as described above.

[0087] Next, in step S105, important explanatory variables are extracted and the ROC-AUC is calculated. The ROC-AUC is a statistical method for analyzing how useful a discrimination method is. When the ROC-AUC is 1, the predictive ability and diagnostic ability are the best, and for a random and completely invalid model, it is 0.5.

[0088] First, we used the XGBoost model to calculate variable importance. As a result, we found that the multiple variables with high importance included not only variables related to respiratory function, but also variables related to comorbid diseases and variables related to frailty.

[0089] Next, the ROC-AUC of the created XGBoost model was calculated. The result was 0.758. Generally, a model is considered to be effective when this value is 0.7 or more, so an effective learning model was obtained by learning using data on the first test item related to respiratory function, the second test item related to comorbid diseases, and the third test item related to frailty factors. In contrast, the ROC-AUC when the learning model was created using only data on the first test item related to respiratory function was 0.65. From this, it can be said that a more accurate learning model can be created by creating a learning model using data on the first test item related to respiratory function, the second test item related to comorbid diseases, and the third test item related to frailty factors.

[0090] In the above explanation, an example has been described in which a learning model is created using data on a first test item related to respiratory function, a second test item related to a comorbid disease, and a third test item related to a frailty factor for a patient suffering from COPD. However, a learning model may also be created using data on the first test item related to respiratory function and the second test item related to a comorbid disease.

[0091] [Variation 1] FIG. 5 shows a configuration diagram of the server 102 according to the first modified example of the embodiment of the present disclosure. The server 102 preferably further includes a determination unit 13 that determines to which of a plurality of predetermined hierarchies the prediction result of the patient's condition change predicted by the prediction unit 12 corresponds. For example, the probability of the patient's condition change can be divided into a plurality of levels, ranging from a low level to a high level. By dividing the prediction result of the patient's condition change into a plurality of hierarchies, the patient or medical personnel can objectively recognize which of the plurality of hierarchies they are currently in.

[0092] In addition, if the change in the patient's condition is that the patient will be readmitted to hospital, the risk of the patient being readmitted to hospital may be divided into multiple hierarchies. Specifically, for example, the possibility that the patient will be readmitted to hospital within 30 days after discharge may be divided into four hierarchies.

[0093] As shown in Fig. 5, the server 102 preferably further includes an output unit 50 that outputs the predicted state change. A display device, a printer, or the like can be used as the output unit 50. The predicted state change may be output to a terminal 300 via a communication network 200 as shown in Fig. 1.

[0094] Fig. 6 shows an example of an output result by the server 102 according to the first modification of the embodiment of the present disclosure. Fig. 6 shows an example of an output screen 400 to a display device (not shown) as an example of the output result. On the output screen 400, the output result is displayed in four areas, a first area 401 to a fourth area 404.

[0095] A first area 401 indicates a COPD re-hospitalization risk level. For example, the possibility of being re-hospitalized within 30 days after discharge is displayed in four stages from a low level to a high level.

[0096] In addition, a triangular mark indicates the patient's risk level of readmission among the four risk levels. Patients with a high risk level of readmission can recognize from the output results that they have a high risk of being readmitted. For example, in the example shown in Figure 6, the patient's risk level of readmission is displayed as being at the second highest risk level out of the four levels.

[0097] The second area 402 indicates whether each piece of information included in the basic information of the patient is at high risk or low risk. As the basic information of the patient, for example, information on age, information on smoking history, information on whether the patient lives alone or with other people, and information on ADL may be displayed.

[0098] The third area 403 shows the results of the respiratory function test, including the "mMRC" shortness of breath scale and the "GOLD classification" stage classification indicating the severity of COPD. The level of functional decline of the patient can also be displayed for these test items.

[0099] The fourth area 404 shows the SpO2 and respiratory rate test results as vital signs test results, and the BUN and pH test results as blood test results, among the patient's test items. The normal range is hatched.

[0100] By showing not only the test results related to respiratory function shown in the third area 403 but also the test results related to vital signs and blood tests shown in the fourth area 404 in the output result 400, it is possible to display the impact that not only the test results related to respiratory function but also the test results related to vital signs and blood tests have on the risk level of readmission.

[0101] As described above, by displaying the output screen 400 as shown in FIG. 6 as the output result from the output unit 50 of the server 102 according to the first variant embodiment of the present disclosure, it is possible to display in which of multiple hierarchies the change in the patient's condition is located.

[0102] [How to determine risk level of readmission] Next, a procedure for predicting a patient's readmission probability and determining a risk level of readmission using a server according to an embodiment of the present disclosure will be described. Fig. 7 shows a flowchart for explaining an operation procedure of the server according to an embodiment of the present disclosure. First, in step S201, data on a first test item related to respiratory function, a second test item related to comorbid diseases, and a third test item related to frailty factors for a patient suffering from COPD are acquired.

[0103] Next, in step S202, a trained model created based on data on the first to third test items of multiple patients and data on readmission of multiple patients is used to predict the readmission probability of a patient. The trained model may be the learning model described with reference to FIG. 3. Here, readmission occurs within 30 days after discharge.

[0104] Next, in step S203, it is determined which of a plurality of predetermined risk levels corresponds to the predicted result of the readmission probability of the patient. As a plurality of risk levels (hierarchies), for example, four risk levels can be used. Specifically, for example, in the case of the possibility that the patient will be readmitted within 30 days after discharge, the analysis algorithm of XGBoost is used, and the predicted probability (probability of being readmitted within 30 days) of 0 to 10% is set as the first level, 10 to 30% is set as the second level, 30 to 60% is set as the third level, and 60 to 100% is set as the fourth level. In this way, by performing stratification according to the risk of the patient, it is possible to easily grasp which hierarchy the patient belongs to, from the highest hierarchy to the lowest hierarchy, in terms of the probability of being readmitted within 30 days after discharge.

[0105] Next, in step S204, the predicted risk level of readmission is output. The output of the risk level can be displayed as shown in FIG.

[0106] In the above description, an example has been described in which the probability of a patient being readmitted to hospital within 30 days is calculated using data on the first test item related to respiratory function, the second test item related to comorbid diseases, and the third test item related to frailty factors for a patient suffering from COPD, but the example is not limited to this. That is, the probability of a patient being readmitted to hospital within 30 days may be calculated using data on the first test item related to respiratory function and the second test item related to comorbid diseases.

[0107] [Variation 2] The above embodiment and modification 1 predict the change in the patient's condition using a trained model created using machine learning, but other methods for predicting the change in the patient's physical condition can also be used. For example, the change in the patient's condition can be predicted by performing a time-series analysis from the time of discharge using data on vital signs and blood tests. Examples of time-series analysis methods include a state space model and a hidden Markov model. When the input data is huge, a method such as a convolutional encoder can also be used. When a hidden Markov model is used, a distribution function capable of estimating the patient's condition, a state transition probability at a certain time interval, and various outcomes, for example, a state sequence for readmission within 30 days, can also be obtained.

[0108] From the results obtained by the above analysis, the patient's physical condition, re-admission, death, and condition changes related to exacerbation can also be estimated. For example, a time-series analysis is performed in advance based on data on the first and second test items of multiple patients suffering from COPD and data on the condition changes of multiple patients, a model of the patient's condition changes is created, and stored in the storage unit 30 of the server 101. The prediction unit 12 can use the stored model to predict the patient's physical condition and condition changes from, for example, the patient's information at the time of discharge, and it is also considered that the model can be used as a criterion for determining whether or not to intervene with the patient, i.e., as a monitoring index.

[0109] Furthermore, by utilizing information on the prediction of changes in the patient's condition using a trained model such as that shown in Figure 3 together with changes in the patient's physical condition obtained from time series analysis, preferably the state transition probability and state sequence described below, it becomes possible to determine and monitor whether or not to intervene in a way that is more tailored to the patient's condition.

[0110] [Time series analysis method] Next, we will explain the method of time series analysis of the impact that post-discharge test data of COPD patients has on the deterioration of the patient's condition or re-admission. The subjects of the time series analysis are test data related to vital signs and blood test items from the first discharge date onwards. Specifically, test data narrowed down by the learning model (XGBoost model) described above and items related to vital signs (respiratory rate, SpO2) were used. Data from the hospitalization period and after discharge were used for vital sign test values. BUN, Alb, CRP, and ChE were extracted as blood test items. The extracted items are just an example, so the method can be applied in the same way even if other items are added or removed.

[0111] For the time series analysis, we used a hidden Markov model, which models the probability distribution of states and outputs at each point in time of time series data and is a statistical method for predicting hidden states from observable variables.

[0112] Data from approximately 1,000 patients was used in the time series analysis. Data for each test item was divided into seven-day intervals from the date of initial discharge, and the average value was used. As hyperparameters for the hidden Markov model, a normal distribution was assumed for the distribution function, and there were five states (S0 to S4). Time series analysis was used to determine the estimated transition probability between the five states, and the state sequence of the time series data. The state sequence was calculated by calculating the proportion of each state (S0 to S4) for various outcomes, such as readmission within 30 days and the presence or absence of exacerbation.

[0113] Figure 8 shows a heat map of test values ​​related to the patient's vital signs and blood test items. The test values ​​for respiratory rate, SpO2, Alb, ChE, CRP, and BUN were classified into high, slightly high, low, and slightly low values ​​compared to normal values. In Figure 8, "-" indicates that the value is within the normal range. The normal ranges for these values ​​are as follows:

[0114] [Table 1] In addition, in Figure 8, states S1, S4, and S0, which are indicated by thick frames, include many abnormal test items, suggesting the possibility that treatment is required. In particular, S0 is presumed to suggest a serious condition, as it is significantly different from the normal value. In addition, S2 has a high respiratory rate and a tendency for SpO2 to be low, suggesting that the respiratory function tends to be poorer than that of a healthy person. However, since it is not possible to make a judgment based only on the extracted vital signs and blood test items, the meaning of each state will be considered by comprehensively analyzing the results of the state transition probability and state sequence.

[0115] The state transition probability for each of states S0 to S4 is shown in Figure 9. Figure 9 also shows the probability [%] of transitioning from each of pre-transition states S0 to S4 to each of states S0 to S4 after 7 days. As shown in Figure 9, there is a high probability that the state of states S0 to S4 after 7 days will remain as it is.

[0116] When we look at state S3, we can see that the probability of transitioning from S3 to another state is low, so state S3 is a stable state. Conversely, when we look at the probability of becoming state S3 after a transition, we can see that the probability of becoming state S3 from a state other than S3 is extremely low.

[0117] In addition, when focusing on the probability of transitioning to state S2, the probability of transitioning from S0 to S2 (1.52%) is higher than the probability of transitioning from S2 to S0 (0.342%), and the probability of transitioning from S4 to S2 (2.68%) is higher than the probability of transitioning from S2 to S4 (1.16%), so state S2 is inferred to be a stable state. Since S2 has a lower SpO2 value than S1 and S4, it is considered to be on the more severe side in terms of the severity of COPD, but it is suggested that it maintains a more stable state than S4.

[0118] In addition to the results of Figures 8 and 9, the results of a comprehensive consideration of the five patient states, including the results of the state sequence, are shown in Figure 10. The horizontal axis indicates the severity of COPD, and it is suggested that the severity increases in the order of S3 (mild) → S1 → S4 → S2 → S0 (severe). In particular, it shows that from S1 to S0, the condition worsens repeatedly and becomes more severe.

[0119] States S1 and S4 were considered to be states requiring treatment and prone to exacerbation, S2 was a state of medium to high severity but stable, and S0 was considered to be a state requiring treatment (severe). In Figure 10, states requiring treatment are hatched, and stable states are not hatched. Furthermore, states S3 and S1 indicate states with a tendency toward overnutrition and obesity, while S4, S2, and S0 indicate states of malnutrition. It is known that as the condition worsens, frailty progresses and malnutrition occurs, so it was considered that the present results showed a similar tendency.

[0120] If the patient's condition is S0, S1, or S4, it is recognized that treatment is required, and treatment can be administered immediately. In contrast, in state S2, the condition is stable, but the severity is higher than state S4. This indicates that, although state S2 is stable and does not require immediate treatment, it is closer to being severe, and therefore requires continuous management of the patient's condition.

[0121] Time series analysis suggests that changes in important test items affect the probability of readmission. Therefore, it is possible to infer a patient's condition from changes in important test items. In addition, because the five states of the hidden Markov model represent the physical condition, it is thought that they can also be used as monitoring indicators to infer a patient's condition.

[0122] In the second modification, the server 101 stores in the storage unit 30 an algorithm for creating a heat map of the vital signs of the patient and the test values ​​related to the blood test items shown in FIG.

[0123] The prediction unit 12 predicts a change in the patient's condition by using data on the first and second test items. Specifically, as in the embodiment and the first modification, the acquisition unit 11 acquires not only data on the first test item related to the respiratory function of a patient suffering from COPD, but also data on the second test item related to a comorbid disease, and compares the data with each test value corresponding to each state of the heat map in FIG. 8 to determine whether the current state of the patient is one of S0 to S4. Then, the prediction unit 12 predicts a change in the patient's condition based on the state transition probability from that state. Although COPD is a respiratory disease, it is also said to be a systemic inflammatory disease, so that the change in the patient's condition may occur not only due to an exacerbation of COPD but also throughout the entire body. Therefore, the server according to the embodiment of the present disclosure predicts a change in the patient's condition more accurately by not only using data on the respiratory function but also using data on the comorbid disease.

[0124] It is preferable that the prediction unit 12 further predicts the change in the patient's condition by using data on a third test item related to the frailty factor. The reason for adding the frailty factor is that it is said that the decline in lung function and comorbid diseases are also related to aging factors, and therefore, by using data on the frailty factor, the change in the patient's condition can be predicted more accurately.

[0125] As described above, the server 101 for predicting changes in a patient's condition according to an embodiment of the present disclosure uses not only data on a first test item related to respiratory function, but also data on a second test item related to a comorbid disease, or data on a third test item related to a test item related to a frailty factor, thereby making it possible to more accurately predict changes in the condition of a patient suffering from chronic obstructive pulmonary disease. [Explanation of symbols]

[0126] 10 Control section 11 Acquisition Department 12 Prediction Department 20 Communication I / F 30 Storage section 40 Bus 101, 102 Server 200 Communication Network 300 terminals

Claims

1. An acquisition unit that acquires data on a first test item related to respiratory function and a second test item related to a comorbidity of a patient suffering from chronic obstructive pulmonary disease (COPD) at the time of discharge from the patient, a prediction unit that predicts a change in condition of the patient after discharge from the hospital by using data on the first and second test items, respectively; having The acquisition unit further acquires data on a third examination item related to a frailty factor, The prediction by the prediction unit is made using a trained model created based on data on the first, second, and third test items of a plurality of patients suffering from chronic obstructive pulmonary disease (COPD) and data on changes in the condition of the plurality of patients after discharge from the hospital. A server comprising:

2. The server according to claim 1 , wherein the trained model is created using a Boosting model.

3. The server of claim 2 , wherein the Boosting model is an XGBoost model.

4. The server of claim 1 , wherein the change in the patient's status after discharge from the hospital includes the patient being re-admitted to the hospital.

5. The server according to claim 1 , wherein the data on the third examination item includes data on at least one of age, body mass index (BMI), activities of daily living (ADL), nutritional status, and whether or not the person lives alone.

6. The server according to claim 1 , wherein the data on the second test item related to the comorbid disease includes at least one of data on the name of the comorbid disease, data on a blood test, data on a vital sign test, and prescription data.

7. The server according to claim 1 , further comprising a determination unit that determines which of a plurality of predetermined hierarchies the predicted result of the change in the patient's condition after discharge from the hospital predicted by the prediction unit corresponds to.

8. The server according to claim 1 , further comprising an output unit for outputting the predicted state change.

9. The server according to claim 1 , wherein the prediction by the prediction unit predicts a physical state of the patient and / or a transition probability thereof.

10. An input unit for inputting data on a patient suffering from chronic obstructive pulmonary disease (COPD) at the time of discharge, the data relating to a first test item related to respiratory function, a second test item related to comorbidities, and a third test item related to frailty factors; A transmission unit that transmits the input data to a server; a receiving unit that predicts a change in condition of a patient after discharge from a hospital by using trained models created based on data on the first, second, and third test items of a plurality of patients suffering from chronic obstructive pulmonary disease (COPD) and data on changes in condition of the plurality of patients after discharge from a hospital, and receives the predicted changes in condition from the server; an output unit that outputs the received state change; A terminal comprising:

11. Acquiring discharge data of a patient suffering from chronic obstructive pulmonary disease (COPD) on a first test item related to respiratory function, a second test item related to comorbidities, and a third test item related to frailty factors; Calculating a predicted value of a change in condition of a patient after discharge from the hospital by using trained models created based on data on the first, second, and third test items of a plurality of patients suffering from chronic obstructive pulmonary disease (COPD) and data on a change in condition of the plurality of patients after discharge from the hospital; A method for predicting a state change, comprising:

12. On the computer, Acquiring discharge data of a patient suffering from chronic obstructive pulmonary disease (COPD) on a first test item related to respiratory function, a second test item related to comorbidities, and a third test item related to frailty factors; Predicting a change in condition of a patient after discharge from a hospital by using trained models created based on data on the first, second, and third test items of a plurality of patients suffering from chronic obstructive pulmonary disease (COPD) and data on a change in condition of the plurality of patients after discharge from a hospital; A program characterized by executing the above.

13. Acquire teacher data including data on a first test item related to respiratory function of a plurality of patients suffering from chronic obstructive pulmonary disease (COPD), a second test item related to a comorbid disease, and a third test item related to a frailty factor, the data including data on the patients at the time of discharge from the hospital and data on changes in condition of the plurality of patients after discharge from the hospital; Generate a trained model in which data on the patient regarding the first, second, and third test items is input and data on changes in the condition of the patient after discharge is output; A method for generating a trained model.

Images