CN115223705A - Physical examination system, physical examination result processing program, and physical examination result processing method - Google Patents

Abstract

The invention provides a physical examination system, a physical examination result processing program and a physical examination result processing method. The future risk of the examinee is predicted using the information of the existing health diagnosis without performing a special measurement, and is prompted by a method in which the examinee himself easily assumes his own future image. The health diagnosis examination result of a given item of the examinee is read out, the future physical activity level is predicted, and an action plan to be taken by the examinee is prepared. A report is generated in which the predicted physical activity level and the action plan are associated with each other, and the report is presented to the subject.

Description

Physical examination system, physical examination result processing program, and physical examination result processing method

Technical Field

The present invention relates to a system for presenting a risk prediction result based on a physical examination result of a subject and a countermeasure method therefor.

Background

With the rapid progress of recent aging, there is a social problem that elderly people who cannot walk independently due to the obstacle of the locomotor apparatus increase. For example, due to a decrease in muscle strength accompanying aging, diseases of joints and vertebrae, osteoporosis, and the like, functions of a motor organ may be weakened, and sometimes care may be required or bedridden. In addition, dyskinesia syndrome (hereinafter, referred to as dyskinesia) which indicates a state in which the risk of functional weakness of a moving organ is high, and sarcopenia which indicates a state in which the muscle mass is decreased and the muscle strength of the whole body is decreased due to aging are also known. In recent years, risk estimation is performed for preventing dyskinesia and sarcopenia, and biological information acquired from various measuring devices, lifestyle information of each person, and the like are used in a combined manner in the risk estimation.

Patent document 1 proposes a system for obtaining the posture ("head", "neck", "waist", and "foot" coordinates) and the external factors ("walking speed", "stride", "lateral stride", and walking angle ") of a subject, and numerically presenting a fall risk and a risk of dementia to the subject.

Documents of the prior art

Patent document

Patent document 1: JP 2020-146435A

Patent document 1 describes that the posture ("head", "neck", "waist", and "foot" coordinates) and external factors ("walking speed", "stride", "lateral stride", and walking angle ") of a subject are collected during a regular examination, but does not describe a specific collection method. Therefore, it is assumed that it is necessary to take an image of the subject person while walking, and to perform special measurement such as extracting the coordinates of "head", "neck", "waist", and "feet" or calculating the "walking speed", "stride", "lateral stride", and "walking angle" in a regular examination. Since such measurement is not performed in the normal health diagnosis, it is necessary to newly set a special measurement item when the measurement is to be performed in the normal health diagnosis.

In addition, since the subject needs to pay attention to daily activities and living habits in order to prevent dyskinesia and sarcopenia, it is important to communicate the risk of falling, the risk of dementia, and the like, and actions (exercise, gymnastics, nutritional attention, and the like) to be taken in daily life to avoid the risk, and to arouse the motivation to perform the actions, in an easily understandable manner. However, in the case of a system in which the prediction result of the risk is represented numerically as in patent document 1, it is difficult for the examinee to intuitively grasp the result, and information on the action to be taken next cannot be received. Therefore, a technique is desired that improves the effect of reducing the risk of falling or dementia in the future by effectively utilizing the prediction results in daily life.

Disclosure of Invention

The purpose of the present invention is to predict the future risk of a subject using existing health diagnosis information without performing any special measurement, and to present the risk by a method whereby the subject himself/herself can easily assume his/her future image.

In order to achieve the above object, the present invention provides a physical examination system comprising: an examination information acquisition unit which reads out an examination result of a predetermined item of the subject from a storage device in which the health diagnosis result is stored; a future prediction unit that predicts a future physical activity level of the subject; an action plan making-out part for making out an action plan to be taken by the examinee; and a report making unit for making a report to be presented to the subject. The future prediction unit includes a learned learning model, inputs the test result of a predetermined item into the learning model, and receives the future physical activity level of the subject predicted by the learning model. The action plan creation unit includes an action plan database in which a plurality of action plans are stored for each of a plurality of physical activity levels in advance, and selects an action plan corresponding to the future physical activity level of the subject predicted by the future prediction unit. A report generation unit generates a report for displaying the body activity level predicted by the future prediction unit in association with the action plan selected by the action plan generation unit.

Effects of the invention

According to the present invention, the future prediction of the subject can be performed without performing any special measurement using the examination information of the existing health diagnosis, the future image can be presented to the subject at a level assumed to facilitate the physical activity level, and a specific action plan can be presented to the subject, so that the subject can intuitively grasp his/her own risk.

Drawings

Fig. 1 is a functional block diagram of a physical examination system according to an embodiment of the present invention.

Fig. 2 is a block diagram showing a hardware configuration of a physical examination system according to an embodiment of the present invention.

Fig. 3 is a flowchart showing a flow of the process of the physical examination system according to embodiment 1.

Fig. 4 is a flowchart showing a flow of the process of the physical examination system according to embodiment 1.

Fig. 5 is a flowchart showing a process flow of the physical examination system according to embodiment 1.

Fig. 6 is a flowchart showing a process flow of the physical examination system according to embodiment 1.

Fig. 7 is a flowchart showing a flow of the process of the physical examination system according to embodiment 1.

Fig. 8 is an explanatory diagram of icons showing physical activity levels used for reports of the physical examination system according to embodiment 1.

Fig. 9 is an example of a table in the action plan database 6 of the physical examination system according to embodiment 1.

Fig. 10 is an explanatory view showing an example of a report of the physical examination system according to embodiment 1.

Fig. 11 is a flowchart showing a process flow of the physical examination system according to embodiment 2.

Fig. 12 is a flowchart showing a process flow of the physical examination system according to embodiment 2.

Fig. 13 is a flowchart showing a process flow of the physical examination system according to embodiment 2.

Fig. 14 is a flowchart showing a process flow of the physical examination system according to embodiment 2.

Fig. 15 is a flowchart showing a process flow of the physical examination system according to embodiment 2.

Fig. 16 is an explanatory diagram showing an example of the prediction result of the vertebral flexion prediction model in the physical examination system according to embodiment 2.

Fig. 17 is a schematic explanatory view showing the level of the risk of onset of dyskinesia used in the report of the physical examination system in embodiment 2.

Fig. 18 is an example of a table in the action plan database 6 of the physical examination system according to embodiment 2.

Fig. 19 is an explanatory diagram showing an example of a report of the physical examination system according to embodiment 2.

Fig. 20 is a flowchart showing a process flow of the physical examination system according to embodiment 3.

Fig. 21 is an explanatory diagram showing an example of a report of the physical examination system according to embodiment 3.

Description of the reference numerals

1: prompt system, 2: risk prediction model learning system, 3: inspection information acquisition unit, 4: future prediction unit, 5: action plan creation unit, 6: action plan database, 7: report creation unit, 8: learning data collection unit, 9: learning database, 10: model learning unit, 101: physical examination system, 103: in-facility network, 104: medical information system, 105: medical information storage, 107: main memory, 108: storage device, 109: display memory, 110: display device, 111: controller, 112: mouse, 113: keyboard, 114: printing device, 115: communication device, 116: common bus, 117: future prediction program, 118: action plan creation program, 119: report creation program, 120: external network, 121: large-scale physical examination results database, 122: subject terminal, 123: learning data collection program, 125: urine test device, 126: x-ray CT apparatus

Detailed Description

Embodiments of the present invention will be described below with reference to the drawings.

Fig. 1 shows a functional configuration of a physical examination system 101 according to the present embodiment. Fig. 2 shows a hardware configuration of the physical examination system 101.

As shown in fig. 1 and 2, the physical examination system 101 of the present embodiment includes a future prediction and presentation system 1 and a risk prediction model learning system 2. As shown in fig. 2, the future prediction and presentation system 1 and the risk prediction model learning system 2 are connected to an in-facility network 103, and are connected to a medical information storage 105 storing health diagnosis results and a medical information system 104 managing the same via the in-facility network 103. Further, devices for performing examination of physical examination items, for example, imaging devices such as a blood/urine examination device 125, an X-ray CT device 126, an MRI device, and an ultrasonic imaging device are connected to the in-facility network 103. The physical examination system 101 is connected to a large-scale physical examination result database 121 in which health diagnosis results of a large number of subjects in the past are accumulated, and a subject terminal 122 such as a smartphone via an external network 120.

First, the functions of the future prediction and presentation system 1 and the risk prediction model learning system 2 will be described with reference to fig. 1.

The future prediction and presentation system 1 includes an examination information acquisition unit 3, a future prediction unit 4, an action plan creation unit 5, an action plan database 6, and a report creation unit 7. The risk prediction model learning system 2 includes a learning data collection unit 8, a learning database 9, and a model learning unit 10.

In the future prediction and presentation system 1, the examination information acquisition unit 3 reads out the examination result of a predetermined item of the examinee from the medical information storage 105 in which the health diagnosis result is stored, and inputs the examination result to the future prediction unit 4.

The future prediction unit 4 predicts at least the future physical activity level as the future risk prediction of the subject using the learned learning model generated by the risk prediction model learning system 2. Specifically, the future prediction unit 4 inputs the examination result of the given item acquired by the examination information acquisition unit 3 into the learning model, and receives the future physical activity level of the examinee predicted by the learning model, and the like.

The action plan creation unit 5 creates an action plan to be taken by the subject based on the future prediction result obtained by the future prediction unit 4. A plurality of action plans are stored in advance for each physical activity level in the action plan database 6. The action plan creation unit 5 selects an action plan corresponding to the future physical activity level of the subject predicted by the future prediction unit 4 from the action plan database 6.

That is, the report generator 7 generates a report to be presented to the examinee. The report generator 7 generates and outputs a report in a predetermined format, which displays the prediction result such as the body activity level predicted by the future prediction unit in association with the action plan selected by the action plan generator 5.

In the risk prediction model learning system 2, the learning data collecting unit 8 collects examination results of given items of a large number of examinees and information (learning data) indicating the physical activity levels of the examinees from the large-scale physical examination result database 121, and stores the information in the learning database 9. The model learning unit 10 learns the learning model using the information stored in the learning database 9, and generates a learned learning model used by the future prediction unit 4.

The hardware configuration of the future prediction and presentation system 1 and the risk prediction model learning system 2 will be described with reference to fig. 2.

The future prediction and presentation system 1 and the risk prediction model learning system 2 include a CPU106, a main memory 107, a storage device 108, a learning database 9, a communication device 115, a common bus 116, a display memory 109, a display device 110, a controller 111, a mouse 112, a keyboard 113, and a printing device 114.

The storage device 108 stores, in advance, a data collection program 123 for learning, a model learning program, a future prediction program 117, an action plan creation program 118, a report creation program 119, an Operating System (OS), a device driver for peripheral devices, and the like.

The CPU106 is connected to other components via a common bus 116. The CPU106 reads out the learning data collection program 123, the model learning program, the future prediction program 117, the action plan creation program 118, and the report creation program 119 from the storage device 108, decompresses the programs in the main memory 107, and executes them, thereby realizing the functions of the learning data collection unit 8, the model learning unit 10, the future prediction unit 4, the action plan creation unit 5, and the report creation unit 7 by software.

The CPU106 controls operations of the respective components of the main memory 107, the storage device 108, the display memory 109, the controller 111, the keyboard 113, the printing device 114, and the communication device 115. The main memory 107 is used as a storage area for a control program or a work area during program execution. The display device 110 displays an image on the display device 110 based on the data received from the display memory 109. The mouse 112 and the keyboard 113 are input devices for the operator. The controller 111 inputs a signal including the position of the mouse pointer of the mouse 112 to the CPU106 or the like, thereby enabling the operator to perform an input operation by the mouse 112. Printing device 114 outputs a report. The communication device 115 is connected to the in-facility network 103 and the external network 120.

The medical information system 104 is an existing system such as an electronic medical record and an image management system, and receives data of the electronic medical record, image data captured by an imaging device such as an X-ray CT device, and physical examination result data such as examination result data of a blood/urine examination device, and stores the data in the medical information storage 105.

[ embodiment 1]

Next, embodiment 1 of the present invention will be described with reference to the flowcharts of fig. 3 to 7 and fig. 8 to 10. Fig. 8 is an icon for visually presenting the physical activity level in the report, and fig. 9 shows an example of a table stored in the action plan database 6. Fig. 10 shows an example of a report.

First, the process of the future prediction and presentation system 1 will be described with reference to fig. 3.

< step S1 >)

In step S1, the examination information acquiring unit 3 acquires examination information such as the height, weight, BMI, blood examination result, and urine examination result of the subject from the medical information storage 105. The blood test results and urine test results used serum BAP, serum P1NP, serum NTX, serum CTX, serum TRACP-5b, serum ucOC, urine DPD, urine NTX, and urine CTX as bone metabolism markers (refer to "guideline for prevention and treatment of osteoporosis 2015 edition"). Note that the items acquired as the inspection information by the inspection information acquiring unit 3 are not limited to the above, and only a part of the items may be used as needed, or other items may be added.

< step S2 >)

In step S2, the future prediction unit 4 performs future prediction using the check belief acquired in step S1. In embodiment 1, the future physical activity level and the cumulative cost of the subject are predicted. As shown in fig. 8 and 9, the physical activity level is predicted to be one that meets the 4-stage levels of "bedridden", "wheelchair", "walking stick required", and "walking possible". The accumulated cost of medical fees and/or nursing fees required by the examinee in the future is predicted as the accumulated cost. These will be described in detail later with reference to fig. 4 and the like.

< step S3 >)

In step S3, the action plan creation unit 5 creates a specific action plan of the subject based on the result of prediction of the physical activity level and the cumulative cost predicted by the future prediction unit 4 in step S2. The action plan is the best one among the action plans stored in advance in the action plan database 6 of fig. 1.

As shown in fig. 9 as an example, the action plan database 6 stores action plans in advance in the form of a table or the like for each combination of the cumulative cost and the plurality of physical activity levels. The action plan creation unit 5 selects an action plan by selecting an action plan corresponding to a combination of the cumulative cost and the physical activity level in the future of the subject predicted by the future prediction unit 4 from the table of fig. 9. The action plan is recommended to improve the future physical activity level and reduce the cumulative cost, and is a plan suitable for exercise and nutrition intake of the subject, for example, a walk of 30 minutes/day, a broadcast gymnastics of 1 time/day, a muscle training of 3 times/week, and the like are set.

< step S4>

In step S4, the report generator 7 generates a report that causes the future predictor 4 to predict the physical activity level and the cumulative cost to be displayed in association with the action plan selected by the action plan generator 5 in steps S2 and S3.

Fig. 10 shows an example of the report. In the example of fig. 10, the physical activity level is visually and easily comprehensibly displayed by the icons and characters shown in fig. 8 which of "bedridden", "wheelchair", "cane needed", "walkable". Further, an action plan corresponding to the physical activity level and the accumulated cost is displayed as a "recommended action plan". Further, the results of the blood and urine tests of the health diagnosis are also displayed.

The report may be output as a paper medium by printing by the printing device 114, or may be output by sending as electronic data to a terminal (smartphone, tablet, PC, etc.) 122 owned by the subject.

< future prediction >

The detailed processing of the future prediction in step S2 in fig. 3 will be described with reference to fig. 4.

< step S21>

In step S21, the future prediction unit 4 performs physical activity level prediction using the learning model for physical activity level prediction generated by the risk prediction model learning system 2.

< step S22>

In step S22, the future prediction unit 4 predicts the cumulative cost using the learning model for cumulative cost prediction generated by the risk prediction model learning system 2.

< creation of learning model >)

Here, the generation process of the learning model for predicting the physical activity level and the learning model for predicting the cumulative cost by the risk prediction model learning system 2 will be described with reference to fig. 5. The learning model for predicting the physical activity level and the learning model for predicting the cumulative cost are generated by learning a known learning model such as a neural network in advance using a method of supervised learning among machine learning algorithms.

< step S201>

First, in step S201, the learning data collection unit 8 collects, from the large-scale physical examination result database 121, the same items as the examination items acquired by the examination information acquisition unit 3 in step S1 of fig. 3, predetermined data indicating the future (for example, 10 years later) physical condition of the subject, and predetermined data for calculating the medical cost and care cost actually spent in the future (for example, during the period from the health diagnosis to 10 years later) of the subject for a large number of people, and stores the data in the learning database 9.

< step S202>

In step S202, the learning data collection unit 8 processes the collected information into a format usable for learning. Specifically, the units of numerical values of the inspection information are unified, and the numerical values are normalized.

The physical activity level is determined from predetermined data indicating the future physical state of the examinee (for example, 10 years later), and the processing assigned to the 4 levels of bedridden, wheelchair, required crutch, and walking is performed based on predetermined calculation.

Further, the amounts of the medical fee and the nursing fee are calculated based on a predetermined mathematical expression or the like based on predetermined data for calculating the medical fee and the nursing fee actually spent by the subject in the future (for example, a period from the health diagnosis to 10 years later).

< step S203>

In step S203, the model learning unit 10 generates a physical activity prediction model. The existing supervised machine learning is utilized to classify the body activity prediction model. Specifically, the model learning unit 10 learns and constructs a model using the data of the examination items collected in step S201 as input data of a learning model and the physical activity level (bedridden/wheelchair/walking required/walking capable person) obtained in step S202 as correct solution data, so that the correct solution physical activity level (bedridden/wheelchair/walking required/walking capable person) is output when the examination item data is input.

< step S204>

In step S204, the model learning unit 10 generates an integrated cost prediction model. In the learning of the cumulative cost prediction model, an algorithm for performing regression in existing supervised learning is used. Specifically, the model learning unit 10 learns and constructs a model using the data of the examination items collected in step S201 as input data of the learning model and using the amounts of medical fees and nursing fees obtained in step S202 as correct answer data so that the correct answer amounts of medical fees and nursing fees are output when the data of the examination items are input.

< < < prediction of physical Activity level > >)

Next, details of the prediction of the physical activity level by the future prediction unit 4 in step S21 in fig. 4 will be described with reference to fig. 6.

(step S211)

In step S211, the future prediction unit 4 reads the physical activity level prediction model learned in step S203 of fig. 5.

(step S212)

In step S212, the future prediction unit 4 inputs the data of the examination item of the examinee acquired by the examination information acquisition unit 3 in step S1 of fig. 3 into the physical activity level prediction model.

(step S213)

In step S213, the future prediction unit 4 receives the physical activity level (either bedridden, wheelchair, walking stick, or walking-capable person) output by the physical activity level prediction model, and outputs the received physical activity level as a prediction result.

< < prediction of cumulative cost > > >)

The details of the cumulative cost prediction by the future prediction unit 4 in step S22 in fig. 4 will be described with reference to fig. 7.

(step S221)

In step S221, the future prediction unit 4 reads the cumulative cost prediction model learned in step S204 of fig. 5.

(step S222)

In step S222, inspection information of the subject is input to the model.

(step S223)

In step S223, the future prediction unit 4 outputs the amount of the cumulative cost (medical fee, nursing fee) output by the cumulative cost prediction model.

As described above, in the physical examination system according to embodiment 1, the future image of the examinee, such as the physical activity level and the cumulative cost, can be presented by a method that can be easily assumed by the examinee, and a specific action plan for increasing the physical activity level and reducing the cumulative cost can be presented. Therefore, the subject himself can intuitively grasp the risk, and the motivation for the subject to want to execute the action plan can be improved.

[ embodiment 2]

Embodiment 2 will be described with reference to the flowcharts of fig. 11 to 15 and fig. 16 to 19. Fig. 16 shows an image of the vertebral body region and the bending line of the spine predicted by the future prediction unit 4. Fig. 17 is an icon for visually indicating the level of risk of onset of dyskinesia syndrome in a report. Fig. 18 is an example of a table showing the correspondence between the risk of onset of dyskinesia syndrome (hereinafter referred to as the risk of onset of dyskinesia) and the action plan stored in the action plan database 6. Fig. 19 shows an example of a report.

In the physical examination system 101 according to embodiment 2, the examination result of a predetermined item of the subject read from the medical information storage 105 by the examination information acquisition unit 3 includes a two-dimensional or three-dimensional image of a predetermined region of the subject. The examination information acquisition unit 3 calculates a feature quantity constituting a predetermined structure in the internal organ and/or tissue of the subject from the acquired image. The future prediction unit 4 predicts, as the physical activity level, not only which level corresponds to the 4 stages of "bedridden", "wheelchair", "walking stick required", and "walking possible", but also which level corresponds to the shape of future spinal curvature and a predetermined plurality of levels at which the risk of onset of dyskinesia is present. The following description will be specifically made.

First, the process of the future prediction and presentation system 1 will be described with reference to fig. 11.

< < step S11>

In step S11 of fig. 11, the examination information acquiring unit 3 acquires an X-ray CT image of a predetermined range (for example, from the clavicle to the hip joint) including the chest and the abdomen captured in the chest CT examination of the subject from the medical information storage 105. Here, an example of acquiring an X-ray CT image is described, but any two-dimensional or three-dimensional image of the subject may be used, and an MRI image or an ultrasound image may be used.

< < step S12 >)

In step S12, the examination information acquiring unit 3 extracts at least one of a vertebral body region, a muscle of the subject at a predetermined position, and a fat region of the subject at a predetermined position in a two-dimensional or three-dimensional manner using the image acquired in step S11. Here, the examination information acquisition unit 3 extracts a vertebral body region and automatically extracts a muscle and fat region (three-dimensional data) at the navel position. For the extraction, a known calculation method using machine learning or the like is used.

< < step S13>

In step S13, the inspection information acquisition unit 3 determines whether or not the correction of the automatic extraction result in step S12 is necessary. Specific examples of the case where the correction is required include the following cases: the condition that the centrum of the examined person is different from the normal shape and the sclerotin due to osteoporosis and the like, thereby not being taken as the centrum area for automatic extraction; the subject has a small muscle mass, and muscle is not extracted or is extracted erroneously.

< < step S14>

If it is determined in step S13 that correction is necessary, the inspection information acquisition unit 3 causes the operator to perform manual correction of the extraction area in step S14, and receives the manual correction by the operator.

< < step S15>

In step S15, the examination information acquisition unit 3 calculates the Bone Density (hereinafter referred to as BMD) of each vertebral body using the three-dimensional data of the vertebral body region extracted in step S12. For the measurement of BMD value, an existing Quantitative CT method (Quantitative computer tomography) was used. The Mean value of Young adults (Young Adult Mean, hereinafter referred to as "YAM") as a diagnostic standard for osteoporosis was calculated from the BMD value. The YAM is a value obtained by calculating a percentage by comparing the average BMD value (reference value) of the young age with the RMD value of the subject to be examined, assuming that the BMD value is 100%.

The examination information acquiring unit 3 calculates the present curve of the spine from the three-dimensional data of the vertebral body region extracted in step S12, and creates an image in which the vertebral body region and the curve are drawn.

< step S16 >)

In step S16, the examination information acquiring unit 3 extracts a CT value of at least one of a vertebral body region, a muscle of the subject at a predetermined position, and a fat region of the subject at a predetermined position from the X-ray CT image. That is, the examination information acquiring unit 3 calculates the areas of visceral fat and subcutaneous fat, the areas of the erector spinae muscle and the psoas major muscle, and the average CT value using the muscle and fat regions extracted in step S12. The CT value is a value obtained by performing CT imaging under the conditions that water is set to 0 and air is set to-1000, and the X-ray absorption value of a substance is expressed as a relative value of water with respect to the origin.

< < step S17>

In step S17, the examination information acquiring unit 3 acquires predetermined examination information such as the height, weight, BMI, blood examination result, urine examination result, and the like of the subject from the medical information storage 105. As the blood examination result and the urine examination result, serum BAP, serum P1NP, serum NTX, serum CTX, serum TRACP-5b, serum ucOC, urine DPD, urine NTX, urine CTX as bone metabolism markers were used (refer to "guideline for prevention and treatment of osteoporosis 2015 edition"). Note that items acquired as the inspection information by the inspection information acquiring unit 3 are not limited to the above, and only a part of the items may be used as necessary, or other items may be added.

< < step S18>

In step S18, the future prediction unit 4 performs future prediction using the information calculated in step S15 and step S16 and the check information acquired in step S17. Here, the future prediction unit 4 predicts, as the physical activity level, which of the levels in the 4 stages of "bedridden", "wheelchair", "walking stick required", and "walking possible", corresponds to the shape of future spinal curvature and which of a plurality of predetermined levels of the risk of onset of dyskinesia. These will be described in detail with reference to fig. 12 and the like.

< < step S19>

In step S19, the action plan creation unit 5 creates a specific action plan of the subject based on the result of prediction in step S18. The action plan database 6 stores in advance action plans corresponding to a plurality of levels of the risk of onset of dyskinesia as shown in fig. 18, and action plans corresponding to a combination of the cumulative cost and a plurality of physical activity levels as shown in fig. 9 of embodiment 1.

The action plan creation unit 5 selects an action plan corresponding to the level of the risk of onset of future dyskinesia of the subject predicted by the future prediction unit 4 and an action plan corresponding to a combination of the cumulative cost and the physical activity level from fig. 18 and 9, respectively.

< step S20 >)

In step S20, a report is generated that displays the risk of onset of dyskinesia predicted by the future prediction unit 4, the shape of future spinal curvature, the physical activity level and the cumulative cost in steps S18 and S19, in association with the action plan selected by the action plan generation unit 5.

Fig. 19 shows an example of the report. In the example of fig. 10, the dyskinesia onset risk is intuitively and easily displayed by icons and characters shown in fig. 17. The curved shape of the future spine is displayed by an image so as to be easily understood. Further, similarly to embodiment 1, it is displayed intuitively and easily understood which of "bedridden", "wheelchair", "walking stick required", and "walkable" the physical activity level is by the icons and characters shown in fig. 8. Further, an action plan corresponding to the physical activity level and the accumulated cost is displayed as a "recommended action plan". Further, an image showing the current curvature of the spine, bone density, fat, muscle area, value of YAM which is a diagnostic standard for osteoporosis, and the like used for prediction are displayed.

< future prediction >

Here, details of the future prediction in step S18 in fig. 11 will be described with reference to fig. 12.

< Steps S181 to 184>

The future prediction unit 4 performs spinal curvature prediction in step S181, dyskinesia onset risk prediction in step S182, physical activity level prediction in step S183, and cumulative cost prediction in step S184 using the learning models generated by the risk prediction model learning system 2.

< creation of learning model >)

Here, a process of generating a learning model by the risk prediction model learning system 2 will be described.

The process of generating the learning model for predicting the physical activity level used in step S183 and the learning model for predicting the cumulative cost used in step S184 is the same as the process of fig. 5 in embodiment 1, and therefore, the description thereof is omitted.

A learning method of the learning model for predicting spinal curvature used in step S181 and the learning model for predicting onset risk of dyskinesia used in step S182 will be described with reference to fig. 13.

< < step S1801>

First, in step S1801, the learning data collection unit 8 collects, for a large number of people, the image of the vertebral body/muscle/fat region acquired by the examination information acquisition unit 3 in step S12 of fig. 11, the information of the vertebral body acquired in step S15, the information of the muscle/fat acquired in step S16, and the same items as the examination information acquired in step S17 from the large-scale physical examination result database 121, and stores the same items in the learning database.

The learning data collecting unit 8 collects information from the large-scale physical examination result database 121, which can extract the bending state of the spine and predetermined information, which can grasp whether the dyskinesia syndrome has occurred, based on the health diagnosis data of the subject in the future (for example, after 10 years), and stores the information in the learning database 9.

< < step S1802>, a method for producing a semiconductor device, and a semiconductor device

In step S1802, the learning data collection unit 8 processes the collected information into a format usable for learning. Specifically, the units of numerical values of the inspection information and the like are unified, and the numerical values are normalized and the like. When the information acquired in step S1801 is an X-ray CT image, the examination information acquiring unit 3 performs extraction of the vertebral body/muscle/fat region, calculation of the vertebral body information, and the like by the same processing as the processing performed in step S16 and step S17.

Further, the vertebral curvature shape is generated from predetermined data indicating the vertebral curvature state of the subject in the future (for example, after 10 years). Further, it is determined whether or not the subject in the future has developed dyskinesia syndrome or risk of developing the same, and the process assigned to 4 levels of dyskinesia onset risk, that is, very high, low, and very low levels is performed based on a predetermined calculation.

< step S1803 >)

In step S1803, the model learning unit 10 generates a vertebral curvature prediction model. In learning of the vertebral curvature prediction model, a machine learning algorithm for generating an image in the existing supervised learning is used. Specifically, the model learning unit 10 uses the image of the vertebral body region, the vertebral body information, the muscle/fat information, and the examination information collected in step S1802 as input data of the learning model, and uses the vertebral body region and the curved line of the spine in the future (for example, after 10 years) as correct solution data to perform learning. Thus, a vertebral body bending prediction model is constructed, which outputs a vertebral body region 10 years after the examinee and a bending line of the spine, upon input of the image of the vertebral body region of the examinee, vertebral body information, muscle/fat information, and examination information. An example of the output vertebral body region and flexion lines of the spine is shown in fig. 16.

< < step S1804 >)

In step S1804, the model learning unit 10 generates a dyskinesia onset risk prediction model. The learning of the dyskinesia onset risk prediction model utilizes a machine learning algorithm that performs classification in existing supervised learning. Specifically, the model learning unit 10 uses the vertebral body information, muscle/fat information, and examination information collected in step S1802 as input data of the learning model, and uses the levels of 4 stages of the risk of onset of dyskinesia (see fig. 17) in the future (for example, after 10 years) calculated in step S1802 as correct solution data to perform learning. Thus, a dyskinesia onset risk prediction model is constructed, which outputs a level of dyskinesia onset risk 10 years after the examinee has inputted an image of a vertebral body region of the examinee, vertebral body information, muscle/fat information, and examination information.

< < prediction of spinal curvature > >)

Next, the details of the prediction of the spinal curvature by the future prediction unit 4 in step S181 in fig. 12 will be described with reference to fig. 14.

(step S1811)

In step S1811, the future prediction unit 4 reads the vertebral curvature prediction model learned in step S1803 of fig. 13.

(step S1812)

In step S1812, the future prediction unit 4 inputs the vertebral body image, the vertebral body information, the muscle/fat information, and the examination information of the subject acquired by the examination information acquisition unit 3 in steps S15 to S17 of fig. 11 into the vertebral curvature prediction model.

(step S1813)

In step S1813, the future prediction unit 4 receives and outputs the prediction results of the future vertebral body region of the examinee and the bending line of the spine predicted by the spine bending model.

< < < prediction of the risk of onset of dyskinesia > >)

Next, details of the prediction of the onset risk of dyskinesia by the future prediction unit 4 in step S182 in fig. 12 will be described with reference to fig. 15.

(step S1821)

In step S1821, the future prediction unit 4 reads the dyskinesia onset risk prediction model learned in step S1804 of fig. 13.

(step S1822)

In step S1822, the future prediction unit 4 inputs the vertebral body information, muscle/fat information, and examination information of the subject acquired by the examination information acquisition unit 3 in steps S15 to S17 in fig. 11 to the dyskinesia onset risk prediction model.

(step S1823)

In step S1823, the future prediction unit 4 receives and outputs the prediction result of the dyskinesia episode risk level (fig. 17) output by the dyskinesia episode risk prediction model.

The prediction of the physical activity level and the prediction of the cumulative cost in steps S183 and S184 in fig. 12 are the same as those in embodiment 1, and therefore, the description thereof is omitted.

According to embodiment 2 described above, by using an existing image or the like taken in a chest CT examination, it is possible to estimate a future risk at the time of physical examination without performing a special measurement. Furthermore, the risks associated with the muscles and bones, which are important elements of the locomotor apparatus, can be estimated simultaneously.

The above describes an example in which chest and abdomen images captured in the chest CT examination are used, but images of each part captured in the whole-body CT examination can also be used. In this case, for example, information on muscles and bones corresponding to the parts of the upper body and the lower body can be acquired, and a future prediction of the future (for example, after 10 years) can be presented for each part. Based on this, an action plan corresponding to the difference due to the part can be created. This can improve the accuracy of the action plan presented to the examinee, and can further improve the effect of preventing dyskinesia of the examinee.

In the present embodiment, the examination information acquiring unit 3 is configured to calculate the feature amount of the organ or structure from the image of the subject, but may be configured to calculate the feature amount by an external calculation device and receive the calculation result.

[ embodiment 3]

Next, a physical examination system according to embodiment 3 will be described with reference to the flowchart of fig. 20 and the report diagram of fig. 21.

In embodiment 3, the future prediction unit 4 is configured to store the physical activity level predicted for the subject or the like in a storage unit (for example, the medical information storage 105) connected thereto. In this way, after the physical activity level or the like is predicted based on the current health diagnosis result, the prediction result calculated for the same subject based on the previous health diagnosis result is read from the connected storage unit, and the difference between the current and previous physical activity levels and the integrated cost is calculated and output to the report making unit.

< step S31 >)

In step S31 of fig. 20, the future prediction unit 4 reads the previous prediction result of the physical activity level and the cumulative cost of the subject from the storage unit (for example, the medical information storage 105).

< step S32 >)

In step S32, the future prediction unit 4 acquires the current examination information such as the height, weight, BMI, blood examination result, urine examination result, and the like of the examinee in the same manner as in step S1 of fig. 3 of embodiment 1.

< step S33 >)

In step S33, the future prediction unit 4 predicts the future of the physical activity level and the cumulative cost in the same manner as in step S2 of fig. 3 of embodiment 1, using the examination information acquired in step S32.

< step S34 >)

In step S34, the future prediction unit 4 calculates a difference between the cumulative cost obtained in the future prediction in step S33 and the cumulative cost obtained from the past cumulative cost obtained in step S31.

< step S35 >)

In step S35, the action plan creation unit 5 creates a specific action plan of the subject based on the result of prediction of the physical activity level and the cumulative cost predicted in step S32, in the same manner as in step S3 of fig. 3 of embodiment 1.

< < step S36 >)

In step S36, the report creation unit compares the present risk prediction result with the previous risk prediction result, and creates a report as shown in fig. 21 clearly showing the change. In fig. 21, the physical activity level is presented in comparison of the previous time and the present time, and the accumulated cost is presented in comparison, and the difference thereof is also displayed.

According to embodiment 3, by predicting the risk again after a certain period of time or the like and presenting a change with time from the previous time, it is possible to expect active preventive activities of the examinee and reduction of the risk caused by the active preventive activities.

Embodiments 1 to 3 of the present invention have been described above, but the present invention is not limited to these embodiments.

Claims (11)

1. A physical examination system, comprising:

an examination information acquisition unit which reads out an examination result of a predetermined item of the subject from a storage device in which the health diagnosis result is stored;

a future prediction unit that predicts a future physical activity level of the subject;

an action plan creating unit for creating an action plan to be taken by the subject; and

a report making-up unit for making a report to be presented to the examinee,

the future prediction unit includes a learned learning model, inputs the examination result of the predetermined item to the learning model, receives the future physical activity level of the examinee predicted by the learning model,

the action plan creating unit includes an action plan database in which a plurality of action plans are stored for each of the plurality of physical activity levels in advance, selects an action plan corresponding to the future physical activity level of the subject predicted by the future predicting unit,

the report making unit makes a report that displays the physical activity level predicted by the future prediction unit in association with the action plan selected by the action plan making unit.

2. The physical examination system of claim 1,

the examination information acquisition unit reads a blood examination result and/or a urine examination result as an examination result of the predetermined item of the subject,

the future prediction unit predicts which of the 4 stages of "bedridden", "wheelchair", "walking stick required" and "walkable" levels is the physical activity level.

3. The physical examination system of claim 2,

the future prediction unit predicts a cumulative cost of medical fees and/or nursing fees required for the examinee in the future.

4. The physical examination system of claim 2,

storing an action plan in advance in the action plan database for each combination of the accumulated cost and a plurality of the physical activity levels,

the action plan making unit selects an action plan corresponding to a combination of the cumulative cost and the physical activity level of the subject in the future predicted by the future prediction unit.

5. The physical examination system of claim 2,

the inspection result of the given item of the examinee read from the storage device by the inspection information acquisition unit includes a two-dimensional or three-dimensional image of a given region of the examinee,

the examination information acquisition unit obtains a feature quantity constituting a predetermined structure in the internal organ and/or tissue of the subject from the image by calculation, or causes an external calculation device to calculate the feature quantity and receive the calculation result,

the future prediction unit predicts, as the physical activity level, which of a plurality of predetermined levels corresponding to the shape of future spinal curvature and/or the risk of onset of dyskinesia syndrome, in addition to which of the 4 stages of "bedridden", "wheelchair", "walking stick required" and "walkable" levels is to be matched.

6. The physical examination system of claim 5,

storing in advance in the action plan database action plans corresponding to a plurality of levels of the risk of onset of dyskinesia syndrome, and action plans corresponding to combinations of the accumulated cost and the plurality of levels of physical activity,

the action plan creating unit selects an action plan corresponding to the level of the risk of onset of the dyskinesia syndrome in the future of the subject predicted by the future predicting unit and an action plan corresponding to a combination of the cumulative cost and the physical activity level.

7. The physical examination system of claim 5,

the examination information acquisition unit extracts at least one of a vertebral body region, a muscle of the subject at a predetermined position, and a fat region of the subject at a predetermined position from the image in two dimensions or three dimensions.

8. The physical examination system of claim 7,

the image is an X-ray CT image, and the examination information acquisition unit extracts a CT value of at least one of a vertebral body region, a muscle of the subject at a predetermined position, and a fat region of the subject at a predetermined position from the X-ray CT image.

9. The physical examination system of claim 1,

the future prediction unit stores the physical activity level predicted for the subject in a storage unit connected to the future prediction unit, and after the physical activity level is predicted based on the current health diagnosis result, reads out the physical activity level calculated based on the previous health diagnosis result for the same subject from the storage unit connected to the future prediction unit, calculates a difference between the current and previous physical activity levels, and outputs the difference to the report creation unit.

10. A physical examination result processing program for causing a computer to execute:

a step 1 of reading an examination result of a predetermined item of a subject from a storage device in which a health diagnosis result is stored;

a 2 nd step of predicting a future physical activity level of the subject;

a 3 rd step of creating an action plan to be taken by the subject; and

a 4 th step of creating a report to be presented to the subject,

inputting the examination result of the given item to the learned learning model, accepting the future physical activity level of the examinee predicted by the learning model in the 2 nd step,

in the 3 rd step, an action plan corresponding to the predicted future physical activity level of the subject is selected from an action plan database in which a plurality of action plans are stored for each of a plurality of physical activity levels in advance,

in the 4 th step, a report is generated that displays the physical activity level predicted in the 2 nd step in association with the action plan selected in the 3 rd step.

11. A method for processing the results of a physical examination, comprising:

a step 1 of reading an examination result of a predetermined item of a subject from a storage device in which a health diagnosis result is stored;

a 2 nd step of predicting a future physical activity level of the subject;

step 3, making an action plan to be taken by the examinee; and

a 4 th step of creating a report to be presented to the subject,

inputting the examination result of the given item to the learned learning model, accepting the future physical activity level of the examinee predicted by the learning model in the 2 nd step,

in the 3 rd step, an action plan corresponding to the predicted future physical activity level of the subject is selected from an action plan database in which a plurality of action plans are stored for each of a plurality of physical activity levels in advance,

in the 4 th step, a report is generated that displays the physical activity level predicted in the 2 nd step in association with the action plan selected in the 3 rd step.

Images