JP7150238B2 - Medical evaluation system, medical evaluation method and medical evaluation program - Google Patents

Description

The present invention relates to a medical evaluation system, a medical evaluation method and a medical evaluation program.

2. Description of the Related Art In recent years, in the medical field, a technology has been proposed in which information on examination or treatment is stored in an electronic chart and this information is used for treatment.

Patent Literature 1 describes a medical training device using a human body model that changes facial expressions and makes sounds according to the content of treatment detected by various sensors. This medical training device can automatically evaluate training contents by an external evaluation device.

In Patent Document 2, by recording medical images acquired by medical image diagnostic equipment such as X-ray imaging equipment, X-ray CT equipment, MRI equipment, and ultrasonic diagnostic equipment as electronic medical record information, medical history can be visualized. A recognizable medical imaging aid is described.

Patent Literature 3 describes a dental care worker evaluation system that manages evaluation information of dental care workers by patients in a patient database.

Non-Patent Document 1 describes a cavity formation skill evaluation device that performs 3D scanning of a cavity formation shape carved by training using a tooth model for training and scores by volume calculation.

Non-Patent Document 2 describes dentist clinical training in which artificial teeth after cavity formation are 3D scanned with an intraoral scanner in cavity shape training using tooth models for training, and comparative evaluation is performed with reference cavities created by CAD. It is

JP 2012-181363 A JP 2014-036880 A JP 2018-200652 A JP 2009-128486 A

Nissin Co., Ltd. website, 3D abutment/cavity formation skill evaluation device <URL: http://www.nissin-dental.jp/products/educationalmodels/etc/Fairgrader100/index.html> Nisso Dental Journal Vol.11 No.1 pp.58-65 October 2019 <URL: https://jsgd.jp/wordpress/wp-content/uploads/5c6e1aa47bea0ee4e8dce01dd27c09cc.pdf>

In Patent Document 1, since it is a medical training device using a human body model, there is no description of its application to actual medical examinations. Also, although it is described that it is possible to automatically evaluate the contents of training by an external evaluation device, the specific content of the external evaluation device is not described.

Patent Document 2 described above describes that medical images obtained by a medical image diagnostic apparatus are recorded as electronic medical record information so that the medical history can be visually recognized. It is provided only to the doctor in charge of the treatment and does not evaluate the contents of medical treatment.

In Patent Literature 3, since the patient evaluates the dental care worker, the managed evaluation information itself is not quantitative and objective, so there is a problem that the evaluation information lacks reliability.

In the above Non-Patent Document 1, it is described that the shape of the cavity formed by training using a tooth model for training is 3D scanned and scored by volume calculation, but it is only used for skill evaluation for training. However, since a training tooth model having a uniform shape prepared in advance is used, there is no description of actual evaluation of medical treatment.

In the non-patent document 2, it is described that the artificial tooth after cavity formation is 3D scanned by an intraoral scanner in the cavity shape training using the tooth model for training, and the reference cavity created by CAD is compared and evaluated. However, this is only for training evaluation, and all trainees use a training tooth model that has a uniform shape prepared in advance and is used to evaluate actual medical treatment. about it is not mentioned.

In view of the above-mentioned problems, the present inventors have made intensive research and development on actual medical treatment procedures and their evaluation in the medical field including dental treatment, and as a result, have completed the embodiments of the present invention. That is, the object of the present invention is to provide a medical evaluation system that can automatically perform an accurate evaluation of actual medical care, make use of this evaluation information in medical care, and provide the evaluation information to the user. .

Another object of the present invention is to provide a medical evaluation system that can apply the obtained evaluation information to medical insurance including the public medical insurance system, liability insurance, and other financial derivative products. . Although Patent Document 4 described above describes an automobile insurance premium setting system that calculates insurance premiums according to the driver's level of safe driving, it does not describe a medical evaluation system that can be used to calculate insurance premiums. not In addition, no system exists to assess whether standard care is being achieved accurately. Here, standard treatment is the best currently available treatment that has been evaluated as effective and safe based on scientific evidence (described later), and is recommended for patients with certain conditions. means any treatment that is Standard treatment is shown in treatment guidelines created and issued by each academic society (Japanese Society of Internal Medicine, Society of Conservative Dentistry, etc.) based on evidence. Although the treatment policy is determined by the judgment of the doctor/dentist, it is important that each doctor/dentist adheres to the guidelines in accordance with the standard treatment along with the skill of the doctor/dentist.

The above object of the present invention can be achieved by the following configurations. That is, a medical evaluation system according to one aspect of the present invention includes an electronic medical record device that stores information obtained from at least one of examination room image acquisition means, medical site image acquisition means, inquiry information input means, and diagnostic device sensors;
a medical evaluation device that inputs information stored in an electronic medical record device and outputs medical evaluation information;
A medical evaluation system for evaluating medical care content comprising
The medical evaluation system includes at least one of an evaluation information analysis system, a user system, another medical evaluation system, or an insurance system, and a network connected to freely share data including the medical evaluation information. and wherein the clinical evaluation information includes at least one of a standard treatment adherence index, a postoperative imaging evaluation index, or a treatment time evaluation index.

According to the embodiment of the present invention, the actual medical treatment is automatically evaluated based on accurate facts, and the evaluation information is fed back to the doctor/dentist of the operator so that the evaluation information can be utilized in the medical treatment. It is possible to provide a medical evaluation system that can provide anonymously processed information to users of the medical evaluation system of the present invention (doctors/dentists and their patients , etc. ). Also, it is possible to provide a medical evaluation system that can apply the obtained evaluation information to the insurance system.

FIG. 1 is a block diagram of a medical evaluation system.
FIG. 2 is an illustration of cavity formation.
FIG. 3 is a conceptual diagram of a medical evaluation system.
FIG. 4 is a block diagram of a medical evaluation system;
FIG. 5 is a detailed block diagram of the medical evaluation system.
FIG. 6 is an explanatory diagram of a blockchain database. The term "blockchain database" as used herein refers to a distributed ledger formed by a network that allows data including medical evaluation information with blockchain to be freely shared with each other. .
FIG. 7 is an explanatory diagram of medical information.
FIG. 8 is a conceptual diagram of a blockchain database.
FIG. 9 is an explanatory diagram of survival rate after treatment .

A medical evaluation system, a medical evaluation method, and a medical evaluation program according to embodiments of the present invention will be described below with reference to the drawings. However, the embodiments shown below are examples of a medical evaluation system, a medical evaluation method, and a medical evaluation program for embodying the technical idea of the present invention, and the present invention is not limited to these. It is equally applicable to other embodiments within the scope of the claims.

[Embodiment 1]
A medical evaluation system 1 according to Embodiment 1 of the present invention will be described with reference to FIGS. 1 to 3. FIG.

FIG. 1 is a block diagram of a medical evaluation system according to this embodiment. Evaluating actual medical care includes, for example, evaluating the technique of a doctor/dentist, and also includes evaluation other than the technique of the doctor, such as evaluation of the treatment environment and assistant's technique .

The medical evaluation system 10 includes an electronic medical record device 11 and a medical evaluation AI as a diagnostic evaluation device. The medical evaluation system 10 is connected to an examination room image acquisition device 14, a diagnostic region image acquisition device 15, an inquiry information input device 16, and a diagnostic device sensor 17, and information is input from each of these devices. The information from each of these devices is stored in the electronic medical record device 11, evaluated in the clinical evaluation AI 12, and evaluation information, which is an evaluation of medical care, is output. An input/output device 13 is connected to the medical evaluation system, and the input/output device includes a display device capable of displaying electronic chart information, evaluation information, and the like.

A plurality of medical evaluation systems 10 are connected to a blockchain database 20 . The blockchain database 20 is connected with an evaluation information analysis AI 21 as an evaluation information analysis system, a plurality of user systems 22, an insurance system 23, a guideline database 24, and the like. Furthermore, it is possible to connect other systems, such as a medical fee calculation system, to the blockchain database 20 . Although the insurance system 23 is representatively described in FIG. 1, what is connected to the blockchain database 20 is not limited to the insurance system 23. For example, medical insurance including public medical insurance system, Including systems that reflect economic principles such as liability insurance and other financial derivatives (same below).

The diagnostic device sensor 17 is a sensor provided in medical equipment. In the case of dental treatment, for example, a turbine sensor (detects the operation or operation time of the turbine), a bar detection sensor (detects the type of bar), a water purification sensor, or the like. A sensor etc. are mentioned. The diagnostic region image acquisition device 15 includes, for example, 3D scanning, X-ray CT, moving image acquisition means, and the like.

As the examination room image acquisition device 14, for example, a ceiling camera, a WEB camera, or the like can be adopted. If the examination room image acquisition device 14 is equipped with an image recognition device, such as an AI image analysis device, it is possible to determine the content of medical care by image recognition and issue a warning against contraindicated treatment on the spot.

FIG. 2 is an illustration of cavity formation according to this embodiment. An example of cavity formation for standard treatment is explained, and the concept of evaluation is explained. FIG. 2 is a plan view of the tooth. As shown in FIG. 2, it is necessary to form cavities appropriately along the three-dimensional shape of the tooth, and from the viewpoint of concave-convex fitting, it is desirable that the prosthesis can be stably fixed from the other direction. Moreover, it is necessary to form the cavity with an inverted trapezoidal cross-section. Moreover, it is necessary to provide a taper on the opening side of the cavity formation, and the angle thereof is desirably 120 degrees. Evaluation of cavity formation includes, for example, the above aspects.

Conditions necessary for cavity formation include, for example, the following (1) to (3).
(1) Contiguous pits and fissures are included in cavities.
(2) preserve cusp ridges ;
(3) Stay at 1/2 of the inner cusp slope.

FIG. 3 is a conceptual diagram of the medical evaluation system of this embodiment. The guideline database stores multiple guidelines related to standard dental care and multiple guidelines related to standard medical care. Based on the standard treatment information accumulated in these guideline databases, the clinical evaluation system objectively evaluates medical care.

FIG. 4 is a conceptual diagram of the entire AI system 30 of this embodiment. The AI system 30 of this embodiment consists of a medical evaluation AI 12 and an evaluation information analysis AI 21 .

The guideline information extracted from the guideline database 24 is input to the medical evaluation AI 12 as medical information via the medical evaluation AI training system 18 . This medical evaluation AI 12 outputs evaluation information composed of indices of a plurality of viewpoints to the evaluation information analysis AI 21 for medical information input using a neural network trained using teacher data.

The evaluation information analysis AI 21 analyzes multiple pieces of evaluation information output by the medical evaluation AI 12, performs quantitative evaluation including the selection of best practices, provides medical evaluation information to the user, and reports to the insurance system 23. provides basic insurance premium information, and provides guideline update information to the guideline database 24 .

Users can select their desired doctor or clinic based on medical evaluation information obtained through the blockchain database 20. The insurance system 23 can calculate insurance premiums based on basic insurance premium information. The evaluation information output from the evaluation information analysis AI 21 is also provided to governmental systems, and this evaluation information is also used for certifying medical specialists and calculating insurance points. In addition, in the evaluation information analysis AI 21, various medical information including medical evaluation information is analyzed by multivariate analysis, desirable medical treatment details are extracted, and guideline update information is generated. The guideline database 24 is updated with this guideline update information.

The evaluation information analysis AI 21 may refer to the second opinion information input by the doctor via the input/output device 13 of each medical evaluation system 10 for the evaluation information input from the medical evaluation AI 12 .

FIG. 5 is a detailed block diagram of the medical evaluation system. The medical evaluation system 10 includes an electronic chart device 11, a medical evaluation AI 12, a timer 19, and the like. The electronic medical chart device 11 has an electronic medical chart calculation unit 11a, an electronic medical chart database 11b, an evaluation information memory 11c, and an accounting calculation unit 11d. In addition, various medical information is input to the electronic medical chart device 11 from the consultation room image acquisition device 14, the diagnostic region image acquisition device 15, the inquiry information input device 16, the diagnostic device sensor 17, the input/output device 13, and the like. Store the information in an electronic medical record database. Further, the electronic medical record device 11 is connected to a treatment evaluation AI training system, a medical evaluation AI 12, a user system 22, and the like.

The clinical assessment AI 12 is provided with information from a trained neural net that has been trained in the clinical assessment AI training system 18 . In the medical evaluation AI training system 18, deep learning is used by an algorithm based on supervised learning classification (classification), as will be described later, using various guideline information and the like provided from the guideline database as training data.

The evaluation information analysis AI 21 uses a neural network trained by learning as described later. As an algorithm for this learning, for example, deep learning is used in clustering of unsupervised learning. The evaluation information analysis AI 21 can input a large amount of evaluation information and various types of evidence information, and can objectively evaluate the contents of the examination by multivariate analysis. The evaluation information analysis AI 21 receives medical evaluation information from a plurality of medical evaluation systems 10, uses it for neural network learning, and extracts desirable cases by analyzing the medical evaluation information using the learned AI. be able to. Guideline update information is generated based on this desirable case, and the guideline database 24 is updated.

Patients or doctors or dentists who are members or users of this system can use the user system 22 to obtain medical evaluation information for a fee. A blockchain database such as IOTA can also be used for accounting in this case.

Further, the medical evaluation information (see FIG. 7, etc.) output from the medical evaluation AI or the evaluation information analysis AI can also be used in the government system 25 and the insurance system 23 . In the government-affiliated system, it is used for certifying specialists in the specialist certifying section 25a and for calculating insurance points, ie, medical fees, in the insurance point calculation section 25b. In the insurance system 23, the medical evaluation information is used for calculation of the doctor's compensation for damages in the doctor's compensation for damages insurance fee calculation unit 23a, and determination of doctors covered by private insurance in the insured doctors certification unit 23b.

The patient and the doctor who treated the patient are given an ID together based on the medical information of the electronic medical chart calculation unit 11a. , m.
Data 1: Patient 1 + doctor A - Σ (preoperative information) k + Σ (postoperative information) k, k = 1 to n
Data 2: Patient 2 + doctor A - Σ (preoperative information) k + Σ (postoperative information) k, k = 1 to n
Data m:...

Information detected during treatment and information input/output to the clinical evaluation AI 12 are stored in the electronic medical record database 11b.

The evaluation information memory 11c is connected to the evaluation information analysis AI 21, the government system 25, and the accounting calculation unit 11d, and stores second opinion information input by the doctor through the input/output device 13, specialists set by the government system 25, and information on insurance points. is stored.
This evaluation information memory 11c is connected to the evaluation information analysis AI 21 and the government system so that the evaluation information analysis AI 21 can refer to the second opinion information.

The accounting calculation unit 11 d performs accounting processing based on the evaluation information memory 11 c and is connected to the insurance system 23 .

The government system 25 has a medical specialist certification unit 25a and an insurance points calculation unit 25b. The specialist certification unit 25a uses the quality of the specialist's procedure as a standard, and the standard treatment evaluation index S1, the postoperative image evaluation index S2, and the treatment time evaluation index S3 (there are about 100 evaluation items that should be included) are predetermined standards. Physicians who meet the requirements are certified as specialists. The insurance point calculation unit 25b sets up a medical fee system so that insurance points for medical fees are added to medical treatment by a doctor certified as a specialist by the specialist certification unit 25a.

The insurance system 23 calculates insurance premiums and the like based on the insurance premium basic information provided from the evaluation information analysis AI 21 . The insurance system 23 has a doctor liability insurance fee calculation unit 23a, an insured doctor certification unit 23b, and an accounting processing unit 23c.

The doctor's liability insurance premium calculation unit 23a calculates the insurance premium for the doctor's liability insurance based on the doctor's liability insurance fee calculation basic information included in the insurance premium basic information output from the evaluation information analysis system 21. to calculate

The insured doctor certifying unit 23b certifies excellent doctors who are subject to reduction of insurance premiums based on their treatment results.

The accounting processing unit 23c calculates insurance premiums based on the doctor liability insurance fee calculation unit 23a and the insured doctor certification unit 23b.

Further, in this embodiment, a user system 22 (see FIG. 5) connected to the medical evaluation system 10, the insurance system 23, and the evaluation information analysis AI is provided. The user system 22 has a user CPU 22a that controls connection from the input/output device 13, a payment processor 22b, and an evaluation information memory 22c.

The payment processing unit 22b is connected to the accounting processing unit 11d of the electronic medical chart device 11 and to the accounting processing unit 23c of the insurance system 23. processing. It is also used for reimbursement of fees for obtaining medical evaluation information. The evaluation information memory 22c is connected to the evaluation information analysis AI 21 and the insured doctor certifying unit 23b of the insurance system 23. Evaluation information from the medical evaluation AI, output information from the evaluation information analysis AI 21, and certification by the insured doctor certifying unit 23b It stores the information of the doctor who is covered by the insurance.

Further, in this embodiment, a timer 19 for measuring treatment time is connected to the medical evaluation system 10 . The treatment time information measured by this timer 19 is used to make a decision based on the treatment time evaluation index S3.

[About medical evaluation AI12]
The clinical evaluation AI 12 is equipped with an AI, and can formulate an appropriate treatment policy according to the case and evaluate the treatment results. For this purpose, the clinical assessment AI 12 has access to a guideline database 24 connected to a blockchain database 20, for example. The guideline database 24 is updated each time the guideline is revised, and always stores the latest information. This information is not only used by the medical evaluation system to evaluate medical care, but can also be referred to by doctors during medical care.

The guideline database 24 includes a plurality of types of guidelines that define standard medical care or standard dental care. EBM (evidence-based medicine) is a therapeutic action with highly reliable evidence. It is referred to determine whether or not the treatment policy has been achieved with appropriate techniques. Treatment evaluation information can be communicated to physicians during treatment as needed so that high EBM grades are not ignored. For example, when a rubber dam needs to be used, a doctor can be immediately alerted when non-use of the rubber dam is detected by image recognition.

AI analyzes image data and the like during treatment, warns that the treatment the doctor is performing or intends to perform during the operation is outside the standard treatment, and can provide feedback to the doctor.

First, through a medical interview, the doctor grasps the patient's condition and desires, and formulates a treatment plan according to the content of this medical interview. The clinical assessment AI 12 can assist physicians in determining clinical plans. Based on the information collected from medical interviews, guideline database information, electronic medical record information, etc., the clinical evaluation AI 12 divides medical problems, psychological problems, and economic problems into three categories and organizes them to solve problems. suggest a treatment plan for The medical evaluation AI 12 can similarly propose diagnostic plans and educational plans. For example, when cavity formation is involved, 3D-CAD data of cavity formation can be output from 3D scan images and X-ray CT images of the patient's teeth. The clinical evaluation AI 12 is trained using the guideline database as training data, and 3D-CAD data for cavity formation, which is the content of treatment, is obtained from the input clinical policy, 3D scan images of the patient's teeth, and X-ray CT images. can be output.

When medical progress information is input to the medical evaluation AI 12 according to the progress of treatment, the medical evaluation AI 12 can output the difference from the targeted treatment content. For example, when receiving 3D scan data during treatment, the clinical evaluation AI 12 can output 3D-CAD data showing the difference from cavity formation, which is the content of targeted treatment.

Taking the case of cavity formation as an example, when the medical evaluation AI 12 receives 3D scan data during treatment, it outputs 3D-CAD data showing the difference from cavity formation, which is the content of targeted treatment. The dentist performs treatment to eliminate the difference indicated by the clinical evaluation AI12, and then inputs the 3D scan data to the clinical evaluation AI12 again. By performing this treatment one or more times, the dentist is notified that the difference from the cavity formation, which is the content of targeted treatment output from the clinical evaluation AI 12, has reached a predetermined allowable range. After confirming this notification, the dentist proceeds to the next stage of filling and occlusal adjustment. By inputting the information of each stage, the medical evaluation AI 12 outputs the information of the difference from the target treatment content, so the doctor can take this information into consideration and implement the standard treatment according to the guideline. .

In addition, regarding the formation of abutment teeth to support prostheses such as bridges and dentures, the clinical evaluation AI 12 outputs target 3D-CAD data, and the 3D scan data after treatment by the dentist is used for clinical evaluation. When input to the AI 12, information about the difference from the shape of the abutment tooth, which is the content of targeted treatment, is output. As a result, as in the case of cavity formation, the doctor can refer to the information output from the clinical evaluation AI 12 and implement standard treatment according to the guideline.

When the post-treatment 3D scan data and the X-ray CT image are input, the clinical evaluation AI 12 can evaluate the details of the treatment.

When evaluating standard treatment, it is not just a two-choice evaluation, such as whether or not a rubber dam is used. For example, evaluation can be made from 100 points to 0 points, such as whether the angle of the inner surface of the cavity formation is an appropriate angle, whether the opening surface of the cavity formation is tapered at an appropriate angle, and the like.

Information detected during treatment and information input/output to the clinical evaluation AI 12 are stored as electronic medical record information in an electronic medical record database. By using the electronic medical record information accumulated by each medical evaluation system, it is possible to accurately grasp the patient's condition, create an accurate treatment plan, and provide appropriate and efficient medical treatment, as well as improve medical safety. It is possible to plan The electronic medical record database information accumulated by each medical evaluation system 10 can be used to train the clinical evaluation AI 12 and the evaluation information analysis AI 21 .

In addition, image recognition technology using clinical evaluation AI12 is also effective for treatment using caries detection liquid.
(1) Remove the prosthesis from the tooth.
(2) Apply caries detection liquid and wash.
(3) Scrape off the red and dark pink parts, leaving the pink part lighter than the standard color.
(4) Take a color image with a camera, input it to the clinical evaluation AI 12, and perform image recognition.
(5) Repeat the above (2) and (3).
(6) When the diagnosis AI 12 notifies of the completion of cavity formation, the dentist proceeds to the next stage of filling and occlusal adjustment.
By inputting the information for each stage in this way, the medical evaluation AI 12 outputs information on the difference from the target treatment content, so the doctor can take this information into consideration and implement the standard treatment according to the guideline. can be done. Determination of the color of the caries detection liquid has a subjective element in the judgment of the doctor, but by using the clinical evaluation AI12, it is possible to quickly and accurately determine the reference color.

Although an example of caries treatment has been described here, the present embodiment is not limited to this. It is possible to provide a system for objectively judging and recording caries by detecting caries detected by the caries detection liquid with an optical inspection instrument and comparing it with diagnostic criteria.

Evaluation is conducted mainly from three viewpoints.
(a) standard treatment rating index S1
(b) Postoperative image evaluation index S2
(c) treatment time evaluation index S3

(a) Standard treatment evaluation index S1 The standard treatment evaluation index S1 is
a-1. Selection and use of appropriate base material, rubber dam, turbine, bar selection a-2. How to use turbine, water injection, and engine a-3. Anesthesia a-4. Contraindicated treatment a-5. It is an index that indicates whether or not standard treatment is being performed according to guidelines regarding items such as evaluation of cavity formation. The higher the standard of care, the higher the evaluation. After preprocessing is performed on the moving image of the treatment being performed, which is acquired from the examination room image acquisition means, AI image recognition is performed and evaluated.

The evaluation information output from the clinical evaluation AI 12 includes examination room cameras, examination site cameras, medical inquiry input devices, examination device sensors (3D scanners, X-ray CT, drill micromotor sensors, turbine sensors, vacuum sensors, water purification sensors, etc.). , electronic medical record database, guideline database, etc., including objective and quantitative evaluation of medical treatment by doctors and dentists

(b) Postoperative image evaluation index The postoperative image evaluation index S2 is an index that determines whether the results of medical treatment are in line with the medical treatment policy (medical care content proposed by AI) derived from the medical interview. . How close it is to the cavity formation calculated by AI is determined, and the closer it is to the treatment policy based on the medical interview, the higher the evaluation. AI image recognition is performed from images such as 3D scans and X-ray CT for evaluation.

(c) Treatment Time Evaluation Index The treatment time evaluation index S3 is an index for determining whether or not the treatment time for standard treatment is within the appropriate time. Since there is an appropriate range of time required for standard treatment according to guidelines, this appropriate time range will result in a higher evaluation. Early treatment does not necessarily result in high scores. This is because some treatments require a certain amount of time to comply with the guidelines.

Evaluation information consisting of three indices obtained from multiple medical evaluation systems is statistically evaluated appropriately using the evaluation information analysis AI21. Evaluation information can be provided to the user (patient) using the blockchain database 20.

The clinical assessment AI 12 uses a trained neural network trained with multiple teacher data. Information of the guideline database 24 is included as teacher data. As an algorithm for this learning, for example, deep learning is used in classification of supervised learning. The neural network is trained, for example, with teacher data consisting of combinations of images of cavity formation and their adequacy (pass/fail or scores). The clinical evaluation AI 12 receives, for example, an image from the diagnostic region image acquisition means 15, and outputs a plurality of indices including a standard treatment adherence index, a postoperative image evaluation index, a treatment time evaluation index, etc. as evaluation information. In addition, as input information, the neural network can also receive each device from the examination room image acquisition device 14, the diagnostic region image acquisition device 15, the inquiry information input device 16, and the diagnostic device sensor 17. In this case, Data for learning the neural network also includes teacher data corresponding to inputs from each of these devices. For example, when inputting information from the examination room image acquisition device 14 to the neural network, or when training the neural network, preprocessing is applied to the moving image data. The preprocessing includes, for example, clipping of necessary images, size adjustment, color adjustment, and the like.

A neural network infers, for example, how closely the input data is cavitating to the guideline. This inference result is verified by expert evaluation and/or subsequent evaluation based on historical information, and used to train the neural network.

[About evaluation information analysis AI21]
As described above, the evaluation information analysis AI 21 analyzes multiple pieces of evaluation information output by the medical evaluation AI 12, performs quantitative evaluations including the selection of best practices, provides users with medical evaluation information, It provides premium basic information to the system 23 and guideline update information to the guideline database 24 . The medical evaluation AI 12 can output not only the above three types of evaluation information, but also subdivided information and various types of evidence information used for evaluation.

Evaluation information analysis AI21 uses a neural network trained by learning. As an algorithm for this learning, for example, deep learning is used in clustering of unsupervised learning. The evaluation information analysis AI 21 can input a large amount of evaluation information and various types of evidence information, and can objectively evaluate the contents of the examination by multivariate analysis.

[Use of medical evaluation information by users]
Users can select their desired doctor or clinic based on medical evaluation information obtained through the blockchain database 20. By using the blockchain database 20, it is possible to realize data management that cannot be falsified while ensuring anonymity.

[Usage of insurance premium basic information 35 by insurance system 23]
The insurance system 23 can calculate insurance premiums based on the basic insurance premium information.
Details will be described in a second embodiment.

[About the use of guideline update information in clinical evaluation AI 12]
The clinical evaluation AI 12 can update the guideline database 24 or consider updating the guideline database 24 based on the guideline update information. Guideline updates are derived from analysis of best practices based on current clinical results and can be used for guideline updates.

[About actions and effects]
Until now, no system existed for pre-operative and post-operative side-by-side analysis of the actual treatment to evaluate the actual practice, for example a doctor's or dentist's procedure. In addition to simply evaluating medical care, this evaluation information can be reflected in economic incentives (insurance fees, medical fees, etc.). This will lead to an appropriate number of doctors and dentists, which is said to be more than the number of convenience stores, and to correct the appropriate price. The medical evaluation system of this embodiment calculates evaluation information based on evidence, thereby contributing to the realization of patient-oriented medical care while securing the quality of doctors and dentists in the medical market.

[Effect of medical evaluation]
Physicians and dentists are obliged to perform treatment methods that should be recommended as standard treatment, but the quality of the treatment may differ depending on the doctor or dentist. For example, it is possible to judge whether the medical fee for a doctor/dentist who performs standard treatment in the shortest amount of time using an excellent procedure is an appropriate unit price as a medical fee per hour, based on the output from a neural network. can.

In addition to medical procedures, co-medical, for example, dental hygienists and dental assistants in dentistry, nurses and physical therapists in medical departments, placement and movement are appropriate, or placement and maintenance of equipment Appropriateness of etc. is also evaluated by a trained neural network. As a result, AI can be used to evaluate doctors based on evidence, as well as evaluate the environment in which the doctor examines, the management efficiency of the clinic, etc., and bring about the effect of improving consulting functions and education. In addition, physicians and dentists who use this system can refer to other excellent cases anonymously or under their real names. As a result, it is possible to provide an open system that is not bound by medical offices or affiliations, and to provide technical training at a low cost.

Patients who have registered with this system can select an excellent doctor/dentist from this open system by taking into account the treatment results of each doctor/dentist. So-called word-of-mouth information is easily available on websites, but there are problems such as insufficient evidence. Here, the evidence provided by this system and the evaluation based on this evidence will be used to understand medical malpractice, medical accidents, doctors, dentists and clinics that are unlikely to cause iatrogenic diseases, and the probability of success in difficult cases. be able to.

It can be applied to create a list of recommended doctors/dentists for each of the medical insurance subscribers according to the results of treatment that the doctor/dentist has taken charge of. This makes it possible to set the insurance premiums to be paid for each doctor and dentist, and calculate the liability insurance premiums for doctors and dentists, contributing to the optimization of public and private medical insurance premiums. This will lead to the prevention of medical malpractice and medical accidents that go against the ethics of doctors, as well as the occurrence of iatrogenic diseases and the rise of insurance premiums, and it will be possible to control external diseconomies. It also leads to an objective evaluation of how good the procedures of specialists and certified doctors of each academic society are.

In the present embodiment, the prosthetic treatment of a carious tooth, which involves the formation of an abutment tooth such as a cavity formation, has been described as an example, but the present embodiment is not limited to this. Abutment tooth formation is exemplified as one of many medical practices, and the medical evaluation system of this embodiment can be similarly applied to other medical practices. For example, it is applicable to diagnosis of oral cancer. Determining stomatitis and precancerous lesions is an important diagnosis, and it is useful to record the process of this diagnosis in an electronic medical record as a video, and to save and utilize it in a database together with appropriate evaluation information. Furthermore, the medical evaluation system of this embodiment can be applied to medical departments other than dentistry.

[Embodiment 2]
A medical evaluation system according to Embodiment 2 will be described with reference to FIG. The medical evaluation system of this embodiment evaluates doctors based on combined information from patients and doctors. According to the medical evaluation system of this embodiment, it is possible to provide anonymously processed information according to the patient's will by managing the private key information by the patient.

FIG. 6 is an explanatory diagram of a blockchain database, FIG. 6A is an explanatory diagram of a data structure in which an ID is assigned to a patient and a doctor who treated the patient, and FIG. FIG. 10 is an explanatory diagram of a database used; The electronic medical chart calculation unit gives an ID to the medical information by combining the patient and the doctor who treated the patient, and further by combining the preoperative information and postoperative information, etc., to obtain data 1, 2, . . . , m in the evaluation information memory 11c or the like. The medical evaluation system uses medical information with an ID that combines a patient and the doctor who treated the patient, and analyzes, evaluates, and memorizes the details of medical care based on this medical information.
Data 1: Patient 1 + doctor A - Σ (preoperative information) k + Σ (postoperative information) k, k = 1 to n
Data 2: Patient 2 + doctor A - Σ (preoperative information) k + Σ (postoperative information) k, k = 1 to n
Data m:...

Data 1 to data m (medical information), which are combinations of a patient and a doctor who treated the patient, are set as blocks, and the block chain is configured such that each block is added as an ordered record. In the example of FIG. 5, a plurality of blocks are added in a chain-like fashion upward from the lower block, and information consisting of a plurality of blocks is stored. For example, blocks are added sequentially such that a block of "Patient 1 and Doctor A" is added to a block of "Patient 1 and Doctor B", and then a block of "Patient 1 and Doctor C" is added. be done.

IDs are given to the first, second, and third patients by the number of patients such as patient 1, patient 2, and patient 3 that the doctor A takes charge of. As the information about the doctor A, types such as a specialist doctor, a certified doctor, and other doctors are also given. As for other doctors B and C, the data of patient 1, patient 2, patient 3, etc. are stored for the number of patients treated in the same manner.

Since each data is stored in an ordered block, the specific treatment and another treatment, such as that patient 1 had another treatment by doctor A before receiving a particular treatment by doctor C, is Along with pre-operative information, post-operative information, etc. regarding treatment, the treatment history is stored in a state in which access rights can be set by the patient 1 .

Each data is encrypted with public key data and private key data. In this embodiment, the patient manages the private key data, and the patient can set data access rights for others.

In conventional databases, anonymous information processors anonymize patient information, doctor information, etc. and provide data, but in the medical evaluation system of this embodiment, patient 1 can set access rights to his/her own medical information. . For example, patient 1 can voluntarily provide blockchain private key data to doctor B to allow him to access his medical history. In addition, the patient 1 can grant access rights to the doctor B, disclose his/her past medical history and treatment history, and utilize them for future medical treatment and health maintenance management with the doctor B.

The blockchain management server manages access rights to data and billing when accessing data for a fee.

By creating a database of treatment history information using a block chain that blocks the combination data of a patient and the doctor who treated the patient, there are various benefits for both the patient and the doctor, as well as for the user of this data. There is

For patients, having the right to access their treatment data allows them to easily access their own medical history, and gives them the right to disclose their medical history information to others. be done. By accessing your own medical history, you will be able to receive the next treatment after considering the past treatment history, and you will be able to view the contents of the doctor, pre-operative information, post-operative information, etc. It is possible to clarify the correlation with the symptoms of By associating patients with doctors, preoperative and postoperative tracing becomes possible. Information that shows how intraoperative procedures affected prognosis is recorded and analyzed by AI for physician evaluation.

If the patient in charge permits the doctor to access the disclosure of the past medical history information, the doctor can utilize the pre-operative information and post-operative information in the past treatment for the current treatment and future treatment. For example, when Doctor C wants to browse the cases of Patient 1 and Doctor A, in the medical evaluation system of this embodiment, based on the permission of Patient 1, Doctor C can browse such cases for a fee. Also, for example, if Doctor A wants to ask Doctor D or another doctor that the case of Patient 1 is a difficult case, in the same way, based on the access permission to his own data from the patient related to this case, such a case for a fee can be made available for viewing by Doctor A.

The medical evaluation AI can assist the doctor in appropriately determining the treatment policy and material content based on the past medical history, and can also notify caution information and warning information regarding the course of treatment. In addition, it is possible to evaluate the contents of medical care and the results of medical care in consideration of the history of medical treatment. In the clinical evaluation AI training system as well, the clinical evaluation AI 12 can be appropriately trained by using data 1 to data m, which are combinations of patients and doctors who treated the patients, as teacher data. The medical evaluation AI is trained by supervised learning, but the training data includes patient information, doctor information, pre-operative information, post-operative information, etc., and evaluation information for training on medical treatment details and medical treatment results. included. This evaluation information for training can be at least one of the output of the clinical evaluation AI, the output of the evaluation information analysis AI, or the evaluation by an experienced doctor such as a specialist.

For example, data 1 to data m are provided with objective evaluation information based on various evidences by the evaluation information analysis AI. This can be an objective evaluation of the medical care content of each data. The evaluation information analysis AI 21 analyzes the preoperative information and postoperative information that have the ID assigned to the patient and the doctor who treated the patient in this way, so that preoperative and postoperative traceable information can be obtained. It is possible to calculate the doctor's evaluation information using this. It is possible to more accurately analyze how the surgical procedure performed by the doctor affected the prognosis. Therefore, each data to which objective evaluation information is added can be used for fee calculation of medical liability insurance, private medical insurance, public medical insurance system such as medical fees, medical specialist system, etc. in Embodiment 3 described later. can.

In addition, since patient information can be treated as anonymously processed information, it is also possible to distribute it as information when a new patient chooses a doctor through this service. Since the database of this medical evaluation system is very useful when a patient selects a doctor or clinic that matches his or her current symptoms, it may be provided, for example, to members for a fee. In addition, doctors can formulate a treatment plan with reference to past cases, and can also use it as reference information for proceeding with treatment.

Furthermore, the medical evaluation AI can support the formulation of a treatment plan, and can also present information and caution information for appropriate treatment to doctors during treatment. It is also useful for helping doctors to master diagnostic techniques and for specialists to improve their diagnostic techniques. There are about 30 medical specialists and certified doctors in internal medicine, neurosurgery, orthopedics, and ophthalmology. Dental specialists and board certified practitioners include dental conservatives, dental oral surgery, dental anesthesiology, and pediatric dentistry.

Information on both doctors and patients is essential for assessing the provision and quality of medical services. An ID is given to the information that has not been received, and all the collected information related to treatment, including pre-treatment information and post-treatment information, etc. can evaluate the therapeutic actions of

It is possible to search and refer to doctors with better treatment results from a blockchain-based database based on data with objective evaluation information based on various evidence, enabling patients to select appropriate medical services and prevent medical malpractice It can contribute to avoiding , medical accidents, and iatrogenic diseases, and achieving better QOL after treatment.

By providing the research institution with anonymously processed information provided from the blockchain database of this embodiment, the research institution will be able to obtain evaluation information including the history of treatment by doctors and dentists for patients and the progress of patient symptoms. It is possible to use the analysis. In this embodiment, since the patient manages the encryption key information, the patient himself/herself can decide to what extent the electronic medical record information including his/her medical history should be disclosed. For example, patient information is its owner. Patients can voluntarily select information they wish to disclose and provide it to a third party.

In the present embodiment, the following five points of view are the actions and effects of management by the medical information block chain database including the evaluation information.
(1) Management of medical information on an information network (2) Always accessible (3) Encryption (4) Clarification of ownership (5) Ability to record access history

The above (1) effect of managing medical care information including evaluation information on an information network is that managing patient information, preoperative information, postoperative information, evaluation information, etc. on a network enables remote access. It is possible. Previously, medical information was managed in an isolated database independent of the network, making remote access impossible.

The effect of (2) being always accessible is due to the fact that the access right can be granted by the patient at any time.

Regarding the above (3) encryption, if access rights are not granted by the patient, no one can access the patient's medical information, and the medical information will not be disclosed without the patient's permission. That is, since a third party who does not store the encryption key information cannot access the medical information, there is an effect that the database is safe for the patient.

Regarding (4) clarification of ownership, since the encryption key information is given only to the patient, there is an effect that the ownership of the medical information is clear regardless of where the medical information exists on the network. be. No matter where the medical information is stored on the network, third parties, including physicians, cannot access the medical information unless the patient grants access rights.

(5) Since the access history can be recorded, it is possible to track who has accessed the medical information. This makes it possible to track unauthorized access to medical information, and since it is recorded up to the time the encryption key was changed, it is possible to track who accessed it and when, improving security on the network.

A modification of this embodiment will be described with reference to FIGS. 7 and 8. FIG. FIG. 7 is an explanatory diagram of medical information. FIG. 8 is a conceptual diagram of managing medical information in a blockchain database. The medical information includes a patient ID, a doctor ID, various case data (preoperative and postoperative), doctor's procedure determination data, prognosis data, doctor's evaluation data, and the like. FIG. 8 conceptually shows how medical information is managed in a blockchain database. The history of treatment of patient a000001 by doctor a0000001 is stored in association with patient a000001', which is the prognosis 1 status of the patient. Similarly, the history that doctor A0000001 subsequently treated patient a000001' is stored in association with patient a000001'' in prognosis 2 status.

In this modified example, the patient's prognosis is not known at the time of diagnosis by the doctor/dentist. In the medical evaluation system of this modified example, after a predetermined period of time has passed after treatment, when the patient's prognosis progress is known, the content of medical care performed by a doctor or dentist in the past is examined, and the medical care content is objective. valued. If the prognosis is good, the procedures performed by the doctor/dentist in the past are examined to determine whether the patient's prognosis is good. In addition, even if the prognosis is poor, it is possible to consider the treatment based on past medical care.

In addition, clinical information including patient's prognostic course is used as teacher data for training the clinical evaluation AI. By including the prognostic course of actual patients in the training data, the clinical assessment AI can be better trained according to actual cases and their prognostic outcomes.

In the medical evaluation system of the present embodiment, medical information is provided to a doctor/dentist who wants to refer to a case with a good prognosis when the patient grants an access right. Physicians/dentists can decide treatment policy by considering cases with good prognosis at the pre-treatment conference. Even cases that were previously introduced only in papers are managed by the blockchain database, making it easier to access the desired medical information. In the paper, the quality of the procedure by the doctor/dentist may not be fully considered, but according to the medical evaluation system of this embodiment, the evaluation information objectively judged by the medical evaluation AI is the medical information. , and medical information can be provided to a third party on the condition that access rights from the patient are granted on the blockchain database. The medical information thus provided is useful as material for case studies and as reference information for patients to select doctors and dentists. Furthermore, the clinic law containing such evaluation information can be used for medical insurance including the public medical insurance system, liability insurance, and other financial derivative products, as described later.

[Embodiment 3]
A medical evaluation system applied to an insurance system or the like according to Embodiment 3 will be described. In the present embodiment, the three evaluation indices described in the first embodiment are used for calculation of insurance premiums and the like. An example of application to fee calculation for medical liability insurance, an example of application to private medical insurance, an example of application to medical fees, and other examples of application will be described below.

(Embodiment 1) Application to Fee Calculation of Medical Liability Insurance for Physicians The insurance premium basic information output from the evaluation information analysis system 21 includes basic information for calculating fees for medical liability insurance. The basic information for calculation of medical liability insurance premiums includes an evaluation index Slia such that a doctor who practices medical care closer to the best practice has a lower insurance premium for medical liability insurance.

Although the calculation formula for calculating the doctor's liability insurance premium calculation index Slia is not particularly limited, for example, the following formula can be used. When the three evaluation indices described in Embodiment 1 are the standard treatment evaluation index S1, the postoperative image evaluation index S2, and the treatment time evaluation index S3, for example, the doctor's liability insurance premium Flia is
Flia = f1(S1, S2, S3), Flia_min ≤ Flia ≤ Flia_max
is required as where Fmin is the minimum premium and Fmax is the maximum premium. The function f1 (S1, S2, S3) is a function with S1, S2, S3 as variables, and is not necessarily limited to a continuous function, and may be a discontinuous function.

As another example of the above formula, a standardized evaluation value can be used as follows. When the three evaluation indices described in Embodiment 1 are the standard treatment evaluation index S1, the postoperative image evaluation index S2, and the treatment time evaluation index S3, for example, the standardized evaluation value Slia is
Slia=S1・a1+S2・a2+S3・a3+a0
Ask as Here, 0 ≤ a1 ≤ 1, 0 ≤ a2 ≤ 1, 0 ≤ a3 ≤ 1, and Slia is standardized with an average of 0 and a variance of 1, for example, the doctor's liability insurance premium Flia is
Flia = f(Slia), Flia_min ≤ Flia ≤ Flia_max
is required as where Fmin is the minimum premium and Fmax is the maximum premium. The function f(Slia) is a function with Slia as a variable, is not necessarily limited to a continuous function, and may be a discontinuous function.

The following (1) to (4) are given as methods of setting the functions f1 (S1, S2, S3) and f(Slia).
(1) Vary the insurance premium Flia according to the risk value. Standard treatment evaluation index S1, postoperative image evaluation index S2, treatment time evaluation index S3, and standardized evaluation value Slia are used as parameters of insurance premium risk values. For example, the risk value can be given as an insurance grade with a stepwise threshold, resulting in a function such that the higher the risk value, the higher the premium Flia. Considering the upper limit Flia_max and the lower limit Flia_min of the insurance premium Flia, the risk value threshold given as the risk grade is set according to the appropriate range for insurance business operations.

(2) Insurance premium Flia is calculated according to the risk value or risk grade in (1) above. This calculation takes into account cash flow related to the insurance business, reserves, policy status (pending, expired or ongoing, etc., policy year, policy period, policy type, rider, exclusions), risk value in each policy year, etc. can do. Further, the insurance premium Flia may be separated into a basic insurance premium and an additional insurance premium, and the additional insurance premium portion may be calculated according to the risk class. Moreover, instead of setting a single risk value or risk grade, a plurality of types of risk values or risk grades may be set, and the insurance premium Flia may be calculated based on the plurality of types of risk values or risk grades.

(3) In (2) above, an example of calculating additional insurance premiums according to the risk value or risk grade was explained. to calculate the insurance premium Flia. In the same way as in (1) and (2) above, for the calculation of the risk value or risk grade, for example, the standard treatment evaluation index S1, the postoperative image evaluation index S2, the treatment time evaluation index S3, the standardized evaluation value Slia can be used.

(4) Evaluation information analysis AI extracts risk indicators that affect insurance premium Flia by analyzing medical information including medical evaluation information using multivariate analysis. A correlation between the extracted risk index and the insurance premium Flia is calculated, and the insurance premium Flia is calculated based on the calculated correlation and the value of the risk information. Various information such as standard treatment evaluation index S1, postoperative image evaluation index S2, treatment time evaluation index S3, standardized evaluation value Slia, and medical evaluation information included in medical information can be used as the risk index. Further, in extracting the risk index, it is also possible to use indices obtained by further subdividing the standard treatment evaluation index S1, the postoperative image evaluation index S2, and the treatment time evaluation index S3. The medical evaluation AI can output more subdivided indices, and the various evidences used to extract the indices can also be used to calculate insurance premiums Flia.

The doctor's liability insurance premium Flia calculated in this way is such that a premium close to the minimum insurance premium Fmin is applied to a doctor who provides medical care close to best practice.

(Embodiment 2) Application to private medical insurance An insurance system can be established in which medical expenses are paid only for medical treatment by a doctor who provides medical treatment close to best practice to an insured person who has paid a predetermined insurance premium. In this insurance system, only doctors whose standard treatment evaluation index S1, postoperative image evaluation index S2, and treatment time evaluation index S3 satisfy predetermined standards are covered by insurance money. Insured persons are guaranteed to receive medical care that is close to best practice, and the medical expenses are paid from insurance premiums. Convergence of the insured is advantageous for the insured and the physician's correspondence. Furthermore, for the medical system as a whole, by providing medical care that is close to best practice, unnecessary treatment costs can be reduced, leading to overall optimization of medical care.

An example using a virtual transit IOTA will be described as a modification of the second embodiment. For example, assume that the insured person received medical treatment from a dentist covered by the insurance in Example 2 and incurred a cost of 100,000 yen for the medical treatment. In the case of an insurance system that requires regular medical examinations as a requirement for insurance payment, if the aforementioned insured person has undergone the prescribed regular medical examinations, the insurance company will provide the insurer with In addition to the periodic examination fee, for example, 20,000 yen, IOTA for a total of 120,000 yen, which is equivalent to the treatment fee of 100,000 yen, is provided. A non-insured person can pay a doctor for medical treatment or medical examination by the granted IOTA. As an example of the blockchain database, IOTA, for example, can be adopted in the case of payment as in this embodiment, but it is possible to use a blockchain other than IOTA.

The effects of adopting the medical evaluation system of this embodiment in the dental market will be described. There is a dental market of about 3 trillion yen and a medical market of about 25 trillion yen. It is estimated that about 10% of these treatments are contraindicated in dentistry, and about 30% are non-standard treatments such as non-use of rubber dams. In dentistry, reinfection during treatment due to non-use of rubber dam is expected to induce recurrence of dental caries due to dental treatment. It is estimated that 900 billion yen out of the approximately 3 trillion yen market is formed by retreatment. According to the medical evaluation system of this embodiment, multiple sensors, including indoor cameras, are used to monitor the quality of procedures performed by doctors and dentists. Scanner) is evaluated before and after treatment, and medical evaluation AI notifies the doctor of treatment warning information during treatment, medical evaluation AI evaluates medical treatment content and medical treatment results, or evaluation information analysis AI Objective evaluation information based on evidence is added to each medical information. Medical information to which evaluation information has been added is also useful for policy support that fosters an environment that prevents medical malpractice, medical accidents, and iatrogenic diseases. If the medical evaluation system of this embodiment is applied to private medical insurance, treatment data with an objective evaluation based on evidence will be implemented in order to implement an insurance system for providing treatment by highly evaluated doctors and dentists. is useful.

For example, in a case where oral cancer (gingival cancer) is misdiagnosed as gingivitis, when the medical evaluation system of the present embodiment is used, patient information, doctor information, preoperative information, postoperative information and Since medical information including objective evaluation information based on evidence is stored in the database, it is possible to provide doctors with information on medical treatment history, future appropriate treatment plans, and details of treatment.

In this embodiment, application to private medical insurance was explained, but the target of application of the medical evaluation system of this embodiment is not limited to private medical insurance, but is also applicable to other insurance products and financial derivative products. can do. In the present embodiment, an insurance system that pays medical expenses only for medical treatment by a doctor who provides medical treatment close to the best practice has been described, but such a mechanism can be applied to financial derivative products. For example, the medical evaluation system of this embodiment can also be applied to financial derivative products or the like that securitize the right to receive medical care from a doctor who provides medical care close to best practices.

(Example 3) Reflection in medical fees Fig. 9 (Conservative Restoration Clinical Guide 2nd Edition) shows the results of comparison between dental specialists and other dentists regarding the survival rate of teeth after treatment. From FIG. 9, it can be seen that treatment by a specialist tends to have a higher tooth survival rate. It is possible to optimize the public medical insurance system as a whole by discriminating doctors who have the same skills as specialists and increasing the medical fees for their treatment.

For example , based on the quality of a specialist's procedure, the standard treatment evaluation index S1, the postoperative image evaluation index S2, and the treatment time evaluation index S3 (there are about 100 evaluation items) meet predetermined criteria. Establish a medical fee system to add insurance points for medical fees. Acquisition of a specialist 's qualification should not necessarily depend on the content of actual medical treatment or cases, and there are doctors who are not specialists but have sufficient skills. Therefore, based on the standard treatment evaluation index S1, the postoperative image evaluation index S2, and the treatment time evaluation index S3 of the present embodiment, a doctor who has a predetermined procedure is identified, and the insurance score for the medical fee is added. , it is possible to provide incentives for acquisition of procedures that should be made by specialists or certified doctors, and to optimize the public medical insurance system as a whole. The specialist/certified physician system requires that a large number of cases be filled and papers written in order to become a specialist/certified physician. This system objectively evaluates the true skills of doctors and dentists,
It is possible to realize a specialist/certified physician system that does not depend only on the number of cases and the number of papers. Physicians and dentists with high-quality procedures have a low probability of causing medical errors, medical accidents, and iatrogenic diseases, and the prognosis of patients is good, so the economic effect is large. On the other hand, when the quality of the procedures performed by doctors and dentists is low, there is a high risk of medical malpractice, medical accidents, and iatrogenic diseases. When other doctors and dentists treat malpractice, medical accidents, and even iatrogenic diseases, the economic loss increases , which is not the true cost of treatment for patients, and is a burden on public health insurance and a beneficiary. It causes a lot of burden.
According to the medical evaluation system of the present embodiment, it is possible to objectively and quantitatively evaluate the contents of medical care and to find doctors and dentists with high-quality procedures. It can contribute to the reduction of the burden and the reduction of the beneficiary 's burden.

(Embodiment 4) Others It is possible to provide an indicator of the degree of attainment of best practices in the specialist certification requirements of the specialist system. If a doctor with the prescribed skills described in the third embodiment can be identified and qualified as a specialist, the specialist system can be optimized. Specifically, based on the standard treatment evaluation index S1, the postoperative image evaluation index S2, and the treatment time evaluation index S3 of this embodiment, a doctor with predetermined skills corresponding to the skills required of a specialist is determined, Physicians determined to have certain skills may be qualified as specialists.

In this embodiment, the use of the system when actually examining a patient has been described, but this embodiment can be applied not only to clinical practice but also to practical training using a dental model. For example, it is possible to verify and evaluate the training content of each volunteer based on training history information acquired in association with trainee information and identification information for each dental model.

Also, by linking with other systems that handle anonymously processed information, it becomes possible to utilize big data consisting of anonymously processed information for the medical evaluation AI 12 and the evaluation information analysis AI 22 . It is possible to provide the doctor's evaluation information to the user of this system, the insured person of the medical insurance provided by this system, and the like.

According to the medical evaluation system of this embodiment, the information of doctors and patients can be set and managed on the blockchain, and the access rights to the data can be managed by the patient, so that appropriate treatment can be performed based on guidelines. It is possible to create an environment in which doctors or dentists who perform For example, there are regulations such as not being able to reproduce dentures using the medical insurance system within six months. If the medical evaluation system of this embodiment is used, for example, whether or not the medical expenses of the insured person (patient) are appropriate (whether or not the medical insurance system complies with regulations, whether or not the treatment is appropriate according to guidelines, etc.) can be performed by an auditing organization. can be properly audited. In addition, as a result, hospitals (doctors and dentists) will be able to use appropriate medical insurance, and the insured will be able to properly pay their share, and the entire medical insurance system ( examination and payment institutions, insurers , Insured persons, insurance medical institutions, etc. ) will be optimized .

Although several embodiments of the present invention have been described above, these embodiments illustrate a medical evaluation system, a medical evaluation method, and a medical evaluation program for embodying the technical idea of the present invention, The present invention is not limited to these, but can be equally applied to other embodiments. It is possible to combine aspects. In addition, although dental treatment has been mainly described in the embodiments, the present invention is not limited to dentistry, and can be applied to any medical evaluation including medicine and dentistry.

10 ... medical evaluation system 11 ... electronic medical chart device 11a ... electronic medical chart calculation unit 11b ... electronic medical chart database 11c ... evaluation information memory 11d ... accounting calculation unit 12 ... medical evaluation AI
13 ... Input/output device 14 ... Examination room image acquisition device 15 ... Medical site image acquisition device 16 ... Interview information input device 17 ... Medical device sensor 18 ... Medical evaluation AI training system 19 ... Timer 20 ... Block chain database 21 ... Evaluation information AI
22 ... User system 22a ... User CPU
22b ... payment processing unit 22c ... evaluation information memory 23 ... insurance system 23a ... physician liability insurance fee calculation unit 23b ... insured doctor certification unit 23c ... accounting processing unit 24 ... guideline database 25 ... government system 25a ... medical specialist certification unit 25b ... Insurance point calculation unit 30 ... AI system

Claims (12)

an electronic chart device that stores information obtained from at least one of examination room image acquisition means, medical site image acquisition means, inquiry information input means, and diagnostic device sensors;
SaidStored in the electronic medical record deviceSaidA medical evaluation system for evaluating medical care contents, comprising: a medical evaluation device for inputting information and outputting medical evaluation information;
The medical evaluation system includes: At least one of evaluation information analysis system, user system, other medical evaluation system, or insurance systemconstructing a network in which the data including the medical evaluation information are connected to each other with a block chain so that they can be freely shared;
A medical evaluation system, wherein the medical evaluation information can be used in a system other than the medical evaluation system. an electronic medical record device that stores information obtained from at least one of examination room image acquisition means, diagnostic site image acquisition means, inquiry information input means, and medical device sensors; and inputting the stored information into the electronic medical chart device, A medical evaluation system that evaluates medical care contents, comprising: a medical evaluation device that outputs medical evaluation information;
The medical evaluation system constitutes a network in which the data including the evaluation information analysis system and the medical evaluation information are connected to each other with a block chain so that they can be freely shared,
and other medical assessment systems, user systems, government systems,other information systems,At least one of an insurance system or a financial system and data including the medical evaluation information are connected to each other with a block chain so that they can be freely shared.
The evaluation information analysis system is a plurality of medical evaluation informationto analyzecomputes the analytical information byCalculationwas doneconcernedThe analysis information is the medical evaluation system, the other medical evaluation system, the user system,Saidgovernment system,SaidA medical evaluation system that is used in at least one of another information providing system, the insurance system, and the financial system. an electronic medical record device that stores information obtained from at least one of examination room image acquisition means, diagnostic site image acquisition means, inquiry information input means, and medical device sensors; and inputting the stored information into the electronic medical chart device, and a medical evaluation device that outputs medical evaluation information. Configure a network in which at least one of the systems and data including the medical evaluation information are connected to each other with a block chain so that they can be freely shared; The medical evaluation information includes at least one of a standard treatment adherence index, a postoperative image evaluation index, or a treatment time evaluation index.medical rating system. 4. A medical evaluation system according to any one of claims 1 to 3 , wherein said medical evaluation device uses a neural network trained with image information relating to at least standard treatment. an electronic chart device that stores information obtained from at least one of examination room image acquisition means, medical site image acquisition means, inquiry information input means, and diagnostic device sensors;
a medical evaluation system that inputs the information stored in the electronic medical record device and outputs medical evaluation information;
The medical evaluation system can freely share data including the medical evaluation information with at least one of an evaluation information analysis system, a user system, another medical evaluation system, or an insurance system with a block chain. configure the network to be connected,
The information stored in the electronic medical chart device has video information,
The medical evaluation device is theElectronic medical record devicecharacterized by comprising a preprocessing device for preprocessing video information acquired from the neural network before inputting it to the neural networkmedical rating system. an electronic chart device that stores information obtained from at least one of examination room image acquisition means, medical site image acquisition means, inquiry information input means, and diagnostic device sensors;
a medical evaluation system that inputs the information stored in the electronic medical record device and outputs medical evaluation information;
The medical evaluation system constitutes a network in which the data including the evaluation information analysis system and the medical evaluation information are connected to each other with a block chain so that they can be freely shared,
The evaluation information analysis system analyzes the medical evaluation information output from the medical evaluation device by a trained neural network.medical rating system. an electronic medical record device that stores information obtained from at least one of examination room image acquisition means, diagnostic region image acquisition means, inquiry information input means, and medical device sensors; A medical evaluation system that evaluates medical care contents, comprising: a medical evaluation device that outputs medical evaluation information;
The medical evaluation system constitutes a network in which data including the insurance system and the medical evaluation information are connected to each other with a block chain so that they can be freely shared,
In addition, at least one of other medical evaluation systems, user systems, government systems, other information providing systems, or financial systems, and data including the medical evaluation information can be freely shared with each other using blockchain. configure the network to be connected,
A medical evaluation system, wherein the medical evaluation information is used for calculation of insurance premiums in the insurance system. 6. The medical evaluation information is managed by a network connected so that data including the medical evaluation information provided with a block chain can be freely shared with each other . 8. The medical evaluation system according to 7 . 4. The electronic medical chart device manages medical information to which a code that integrates a patient and a doctor who treated the patient is assigned , and a block chain is constructed with the medical information as a block. 8. The medical evaluation system according to 1, 2, 3, 5, 6 or 7. 10. The medical evaluation system according to claim 9 , wherein the medical information is encrypted with public key data and private key data, and the patient manages the public key data. a step of storing information obtained from at least one of an examination room image acquiring means, a diagnostic region image acquiring means, an inquiry information input means, and a diagnostic apparatus sensor in an electronic medical chart device;
A medical evaluation method for evaluating the content of medical care, comprising: inputting the information stored in an electronic medical chart device and outputting medical evaluation information in a medical evaluation system,
transmitting the medical evaluation information over a blockchain -equipped P2P network configured with at least one of a rating information analysis system, a user system, another medical rating system, or an insurance system;
A medical evaluation method, further comprising the step of using the data including the medical evaluation information transmitted by the P2P network equipped with the block chain in a system other than the medical evaluation system. A medical evaluation program for executing each step of the medical evaluation method according to claim 11 by computer means.

Images