Treatment support system and treatment support method

Abstract

The aim is to provide technology that improves the precision of treatments in alternative medicine. [Solution] A treatment support system that supports treatment as alternative medicine for a person receiving treatment, comprising: a reaction acquisition unit that acquires reaction information showing the person receiving treatment's response to the practitioner's actions; an analysis unit that analyzes the reaction information using AI including a machine learning model to identify at least one of the affected area and the cause of the affected area; and an output unit that outputs the analysis results from the analysis unit.

Description

Technical Field

[0004] , , , , , , ,

[0006] , , , ,

[0005] , , , , , ,

[0001] The present invention relates to a treatment support system and a treatment support method.

Background Art

[0002] Conventionally, in alternative medicine performed by a practitioner, the practitioner hears the physical condition of the patient and performs the treatment. Also, during the treatment, the practitioner may adjust the treatment content based on the reaction of the patient.

[0003] For example, in the treatment support system disclosed in Patent Document 1, the practitioner causes the patient to select a troubled part where the patient feels unwell from among the parts of the human body diagram displayed on the treatment support device 10. The troubled pattern presentation unit 12 of the treatment support device 10 acquires data for displaying one or more troubled patterns related to the selected troubled part from the cloud server 30, and causes the troubled pattern display image D3 to be displayed on the display of the treatment support device 10.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] In the field of alternative medicine, it is common for a practitioner to determine a treatment policy based on the patient's complaints and reactions, etc., and based on the practitioner's own experience and knowledge. In such a method, since the judgment and response vary for each practitioner, the effect of the treatment is likely to vary. In particular, in alternative medicine represented by kinesiology and innate therapy, etc., an approach is taken to estimate related parts based on the patient's reaction such as muscle reflex, but the evaluation depends largely on the subjectivity of the practitioner, and there is a problem that it is difficult to reproduce with a certain accuracy.

[0006] In the technology described in Patent Document 1, the final determination of the treatment location and content is still left to the practitioner's judgment, which is insufficient from the standpoint of standardizing treatment and ensuring reproducibility. Furthermore, the system displays muscle information that is pre-associated with the affected area, which limits the ability to flexibly plan treatment strategies that take into account the complexity of each patient's symptoms and individual differences.

[0007] This invention has been made in view of the above points, and aims to provide a technology that improves the accuracy of treatments in alternative medicine. [Means for solving the problem]

[0008] This application includes several means for solving the above-mentioned problems, some examples of which are as follows.

[0009] To solve the above problems, a treatment support system according to one aspect of the present invention is a treatment support system that supports treatment as alternative medicine for a person to be treated, and is characterized by comprising: a reaction acquisition unit that acquires reaction information showing the person to respond to the practitioner's actions; an analysis unit that analyzes the reaction information using AI including a machine learning model to identify at least one of the affected area and the cause of the affected area; and an output unit that outputs the analysis results from the analysis unit.

[0010] The output unit outputs candidate malfunction sites identified by the analysis unit, and the analysis unit may be characterized by identifying the candidate malfunction sites and using the reaction information to the candidate malfunction sites to identify the malfunction sites.

[0011] The output unit outputs candidate causes of malfunction in the candidate malfunctioning area identified by the analysis unit, and the analysis unit identifies the candidate causes of malfunction and identifies the cause of malfunction using the reaction information obtained using the candidate causes of malfunction.

[0012] The output unit outputs candidate areas of dysfunction or candidate causes of dysfunction identified by the analysis unit, and the analysis unit may further obtain a degree of confidence for each candidate area of ​​dysfunction or candidate cause of dysfunction based on the response information obtained by the response acquisition unit in response to the practitioner's actions on the candidate areas of dysfunction or candidate causes of dysfunction, and identify the candidate areas of dysfunction or candidate causes of dysfunction whose degree of confidence meets a predetermined standard as the site of dysfunction or cause of dysfunction.

[0013] The reaction acquisition unit may be characterized by acquiring the reaction information indicating the muscle response of the practitioner or the person being treated, obtained using a contact-type sensor.

[0014] The reaction acquisition unit may be characterized by acquiring biological signals emitted by the practitioner or the person being treated, obtained using a sensor, as reaction information.

[0015] The reaction acquisition unit may be characterized by acquiring the biological signal using a biophoton sensor.

[0016] The reaction acquisition unit may acquire the subject's biological data, and the analysis unit may use the AI ​​to analyze the biological data and reaction information to identify at least one of the affected area and the cause of the discomfort.

[0017] The output unit may be characterized by displaying the candidate areas of dysfunction in a model image of the body of the person being treated, differently from other areas, and the model image may include images showing internal organs.

[0018] The treatment support system may be characterized by comprising a method request unit that requests treatment method information by identifying at least one of the affected area and the cause of the affected area identified by the analysis unit, the analysis unit identifying the treatment method information by analyzing at least one of the affected area and the cause of the affected area identified by the method request unit using AI including a machine learning model, and the output unit outputting the treatment method information identified by the analysis unit.

[0019] The treatment method information may be characterized in that it includes electrotherapy for applying an electric current to the skin of the subject or manual therapy by the technique of the operator.

[0020] The method request unit requests the analysis unit for a pre-treatment image showing the subject before the treatment according to the treatment method information specified by the analysis unit and a post-treatment image showing the subject after the treatment, the analysis unit acquires the pre-treatment image and the post-treatment image, and the output unit may be characterized in that it outputs the pre-treatment image and the post-treatment image acquired by the analysis unit.

[0021] The reaction acquisition unit acquires the reaction information of the subject after the treatment according to the treatment method information specified by the analysis unit, the analysis unit analyzes the reaction information by using AI including a machine learning model to specify treatment result information indicating the treatment result, and the output unit may be characterized in that it outputs the treatment result information.

[0022] Also, in order to solve the above problems, a treatment support method according to another aspect of the present invention is a treatment support method for supporting a treatment as alternative medicine for a subject, and includes a reaction acquisition procedure for acquiring reaction information indicating the reaction of the subject to the approach of the operator, an analysis procedure for specifying at least one of a malfunction site and a cause of the malfunction by analyzing the reaction information by using AI including a machine learning model, and an output procedure for outputting the analysis result in the analysis procedure.

Effects of the Invention

[0023] According to the present invention, it is possible to provide a technique for improving the treatment accuracy in alternative medicine.

[0024] Problems, configurations, and effects other than those described above will be clarified by the description of the following embodiments.

Brief Description of the Drawings

[0025] [Figure 1] It is a diagram showing an example of the outline of the treatment support system. [Figure 2] It is a diagram showing an example of the functional blocks of the treatment support system. [Figure 3] It is a diagram showing an example of the hardware configuration of the treatment support device. [Figure 4] It is a sequence diagram showing an example of the malfunction site identification process. [Figure 5] It is a sequence diagram showing an example of the malfunction cause identification process. [Figure 6] It is a sequence diagram showing an example of the treatment method identification process. [Figure 7] It is a sequence diagram showing an example of the treatment result acquisition process. [Figure 8] It is a diagram (estimated / schematic diagram) (part 1) showing an example of the malfunction site candidate display screen. [Figure 9] It is a diagram (estimated / schematic diagram) (part 2) showing an example of the malfunction site candidate display screen. [Figure 10] It is a diagram (estimated / schematic diagram) (part 1) showing an example of an image indicating the change of the patient. [Figure 11] It is a diagram (estimated / schematic diagram) (part 2) showing an example of an image indicating the change of the patient. [Figure 12] It is a diagram (part 1) showing an example of the treatment method data classified by cause. [Figure 13] It is a diagram (part 2) showing an example of the treatment method data classified by cause. [Figure 14] It is a diagram (part 3) showing an example of the treatment method data classified by cause. [Figure 15] It is a diagram (part 4) showing an example of the treatment method data classified by cause. [Figure 16] It is a diagram (part 1) showing an example of the countermeasure data classified by symptom. [Figure 17] It is a diagram (part 2) showing an example of the countermeasure data classified by symptom. [Figure 18] It is a diagram (part 3) showing an example of the countermeasure data classified by symptom.

Embodiments for Carrying Out the Invention

[0026] Hereinafter, examples of embodiments of the present invention will be described based on the drawings. In all drawings used to describe the embodiments, the same reference numerals will be used for identical components, and repeated descriptions will be omitted. Furthermore, in the following embodiments, the components (including element steps, etc.) are not necessarily essential unless specifically stated, or unless they are clearly essential in principle. Also, when referring to "consisting of A," "being made of A," "having A," or "including A," other elements are not excluded unless specifically stated to refer only to that element. Similarly, in the following embodiments, when referring to the shape, positional relationship, etc., of the components, etc., it includes those that are substantially similar or approximate to their shape, etc., unless specifically stated, or unless it is clearly not the case in principle.

[0027] <Overview of Treatment Support System 1> Figure 1 shows an example of the overview of the treatment support system 1. The treatment support system 1 comprises a treatment support device 10, a sensor group 20, a practitioner terminal device 30, and a generation AI system 40. The treatment support device 10 is a device that supports treatment performed by practitioner Y on patient X, and is communicated with the sensor group 20, the practitioner terminal device 30, and the generation AI system 40.

[0028] Patient X is a person receiving treatment from practitioner Y. Practitioner Y is a person who performs treatment on patient X, either through contact or non-contact. In this embodiment, treatment includes manual therapy, osteopathic therapy, and electrotherapy, which involves applying an electric current to patient X's skin, as alternatives to Western medicine, and includes a variety of therapies such as those listed below. The alternative medical treatments described below are considered to be effective for health management and improving physical condition.

[0029] Manual therapy: Traditional massage, acupressure, chiropractic, osteopathy, myofascial release, etc. • Manual physical therapy: A method of selecting the most appropriate treatment technique after evaluating and diagnosing each system (sensory system, connective tissue, muscular system, nervous system, joint system, circulatory system, visceral system, etc.). • Energy therapies: Qigong therapy, Reiki, healing touch, innate activation therapy, etc. • Brain and nervous system adjustment therapy: Cerebrospinal fluid adjustment (craniosacral therapy), autonomic nervous system adjustment therapy, neurofeedback, etc. • Therapies utilizing body movement: Sotaiho, Feldenkrais Method, Rolfing, etc. • Osteopathic therapy: Skeletal correction, pelvic correction, spinal correction, etc. • Therapies based on Oriental medicine: acupuncture, moxibustion, meridian therapy, herbal acupressure, etc. • Relaxation therapies: Aromatherapy, reflexology, hot stone therapy, Ayurveda, etc. Other therapies: Ionization therapy, antimatter bonding therapy, trigger point therapy, balance therapy, lymphatic drainage, sports massage, etc.

[0030] The treatment support device 10 acquires biological signals detected using the sensor group 20. For example, the sensor group 20 acquires a signal indicating the response of at least one of patient X or practitioner Y and transmits it to the treatment support device 10 as response information. The sensor group 20 may be contact-type or non-contact-type.

[0031] The treatment support device 10 acquires the patient X's biometric data. The biometric data includes, for example, the following information: • Medical history, current medications • Information regarding current or past symptoms, complaints, etc. • Physical condition, including information on pregnancy status, surgical treatment history, injuries, inflammation, and stress. • Physiological indicators such as height, weight, electromyography, skin temperature, blood pressure, heart rate, blood oxygen saturation, and blood test data. • Time information associated with them • Information based on external tests (EEG results, X-rays, CT or MRI images, DNA test results, gut microbiota test results, exercise performance test results, etc.) • Information regarding the patient's family relationships, occupation, living environment, concerns, etc.

[0032] In the following example, biometric data is defined as information relating to the physical or mental state of patient X, obtained from a medical institution's testing system, and information obtained from patient X's explanation. Biosignals are defined as measurement data detected by sensor group 20.

[0033] Response information is defined as information indicating the patient X's response when practitioner Y interacts with the patient X. Response information includes biosignals obtained by the sensor group 20 and information regarding the responses of patient X or practitioner Y, which are input into the treatment support system 1 by patient X or practitioner Y. The information regarding patient X's response input into the treatment support system 1 includes information evaluated by the inputter based on pre-designed evaluation criteria, allowing for numerical or gradual expression of pain intensity, presence or absence of discomfort (including YES / No responses), and comfort / discomfort. The treatment support system 1 can accept input using a user interface designed to facilitate the input of response information by patient X or practitioner. Response information includes at least response intensity, left-right differences, and response latency, and may include electromyography amplitude, acceleration, and differences from the recorded findings as needed.

[0034] The generation AI system 40 returns information obtained using biological data, biological signals, reaction information, etc., transmitted from the treatment support device 10 to the treatment support device 10. Alternatively, the treatment support device 10 and the generation AI system 40 may be integrated by integrating the functions of the generation AI system 40 into the treatment support device 10.

[0035] The treatment support device 10 analyzes reaction information and biological data using the generation AI system 40 to identify at least one of the affected area or cause of the patient X's discomfort. The treatment support device 10 transmits the identified affected area or cause of discomfort to the practitioner terminal device 30. The practitioner Y can recognize the affected area or cause of discomfort of patient X by viewing the display of the practitioner terminal device 30 or listening to the output audio. Patient X may also be able to visually view or listen to the information output from the practitioner terminal device 30.

[0036] The treatment support device 10 identifies at least one of the affected area and the cause of the discomfort and requests treatment method information from the generating AI system 40. In response to the request, the generating AI system 40 identifies a treatment method to resolve the discomfort using at least one of the affected area and the cause of the discomfort, and transmits it to the treatment support device 10 as treatment method information. When the treatment support device 10 transmits the treatment method information to the practitioner terminal device 30, the practitioner terminal device 30 outputs the treatment method information to the practitioner Y. The treatment method information includes electrotherapy, which involves applying an electric current to the patient X's skin, and manual therapy performed by the practitioner Y.

[0037] After the treatment is performed by practitioner Y, the sensor group 20 acquires response information from patient X or practitioner Y. The treatment support device 10 requests the generating AI system 40 to analyze the treatment results and obtains treatment result information. The treatment support device 10 outputs the treatment result information to the practitioner terminal device 30. Subsequently, if necessary, the treatment support system 1 performs the identification of new areas of discomfort or causes of discomfort.

[0038] Recently, "Innate Activation Therapy" has become known, which posits that the cause of physical pain and discomfort lies in "invisible problems" that lie behind superficial symptoms, and that by treating areas identified as central treatment points, problems in the joints can be resolved. The treatment support system 1 in this embodiment can also be used in treatments using Innate Activation Therapy.

[0039] For example, practitioner Y may, as needed, perform actions to facilitate conscious communication (brain-to-brain) with patient X. These actions are expected to help patient X focus their consciousness on healing. As an example, practitioner Y may, without using words, visually and tactilely indicate the position and movement of their hands to guide patient X's consciousness in the intended direction. As another example, practitioner Y may support patient X, who is lying on their back, while using their other hand to indicate the direction the body should face. Patient X will unconsciously try to move their body in the indicated direction. Through such nonverbal guidance, a sense of physical and conscious unity is formed between patient X and practitioner Y, promoting concentration and cooperation toward healing. It should be noted that actions for communication are not limited to these examples and may also be performed remotely via telephone calls or video calls using images.

[0040] Furthermore, as a preliminary step to communication, practitioner Y may encourage both practitioner Y and patient X to perform preparatory actions. For example, the pineal gland, an organ located in the brain, is known to be involved in regulating the body clock and secreting melatonin, and is thought to play an important role in regulating the sleep-wake rhythm. For example, practitioner Y may encourage both practitioner Y and patient X to perform actions that promote the activation of the pineal gland.

[0041] Furthermore, the brainstem, composed of the diencephalon, midbrain, pons, and medulla oblongata from top to bottom, is an essential part of life support and plays a vital role in life-sustaining functions. The hypothalamus and pituitary gland control the autonomic nervous system and hormone secretion. In addition, the cerebellum is responsible for regulating movement, balance, posture, and eye movements, and contains many nerve cells that perform regulatory functions to make movement smooth. When the cerebellum functions normally, it is possible to move the limbs smoothly and walk while maintaining posture. It is also useful to perform actions that stimulate the activation of these organs, not just the pineal gland. Furthermore, practitioner Y may encourage either practitioner Y or patient X to perform an adjustment called ground balance adjustment in order to guide patient X's mental state to a state suitable for treatment.

[0042] Next, practitioner Y interacts with patient X to find treatment points. For example, practitioner Y uses a technique called "kinesiology" to find treatment points by applying light resistance to patient X's muscles and observing the fluctuations (strength and weakness) of muscle strength, thereby reading the body's nerve transmission and potential stress responses. When the treatment support system 1 presents potential problem areas to practitioner Y, practitioner Y interacts with patient X regarding the potential problem areas and obtains patient X's response. The treatment support device 10 acquires response information as response to the practitioner's actions, including biosignals detected by sensors included in the sensor group 20 and information about patient X's response input by patient X or practitioner Y. Furthermore, when practitioner Y inputs an explanation of patient X's response obtained using the kinesiology technique into the practitioner terminal device 30, the treatment support device 10 acquires the input information as response information.

[0043] The treatment support device 10 uses response information to query the generating AI system 40 to determine whether a candidate for a problem area is indeed a problem area. If the candidate for a problem area is not a problem area, the practitioner Y interacts with patient X on the newly presented candidate for a problem area. By repeating these interactions, practitioner Y recognizes the problem areas identified by the treatment support system 1 as treatment points. The treatment support device 10 may also find a coordinating treatment point by querying the generating AI system 40 for a coordinating treatment point that oversees the treatment points. The interactions performed by practitioner Y are questions directed at patient X's body within practitioner Y's brain and can be treated as internal "questions."

[0044] It should be noted that, regarding response information, the biosignals detected by the sensors included in the sensor group 20 may differ from the information input by the practitioner Y to the treatment support system 1. Possible factors include the intensity of the patient X's response, the sensing ability of the sensors, and the skill level of the practitioner Y. The generating AI system 40 collects this response information and reflects it in the accuracy of the next response based on the final treatment results.

[0045] One example of intervention by practitioner Y is manual muscle testing (MMT). Practitioner Y applies light pressure to the muscles of a candidate area of ​​discomfort displayed on the practitioner terminal device 30, or to muscles in other areas that practitioner Y considers to be related to the candidate area of ​​discomfort. The muscle response of patient X due to the pressure applied by practitioner Y is transmitted to the treatment support device 10 via a sensor. Alternatively, instead of, or in addition to, the muscle response of practitioner Y based on patient X's response may be transmitted to the treatment support device 10 via a sensor. If the muscles respond strongly, it is judged that the patient is in good health, and if they respond weakly, it is judged that the candidate area of ​​discomfort is indeed the area of ​​discomfort. The treatment support device 10 may acquire response information indicating muscle response that has been input to the practitioner terminal device 30 by practitioner Y. Note that muscle testing includes an action called trigger point testing.

[0046] Another example of intervention by practitioner Y is the O-ring test (registered trademark). Patient X interlocks their fingers in an O shape, and practitioner Y determines how easily patient X's fingers can collapse. For example, if practitioner Y points to a potential problem area and checks how easily patient X's O-ring can collapse, the muscle response of patient X or practitioner Y is transmitted to the treatment support device 10 via a sensor. If the O-ring is difficult to collapse, it is judged that the patient is in good health, and if the reaction is weak, it is judged that the potential problem area is indeed a problem area. Alternatively, the O-ring test can be performed by practitioner Y interlocking their own fingers in an O shape and pointing to a potential problem area and determining how easily it can collapse. The treatment support device 10 may also acquire response information indicating muscle responses that practitioner Y has input to the practitioner terminal device 30.

[0047] Another example of the intervention by practitioner Y is palpation. For example, practitioner Y may point to a potential area of ​​discomfort in patient X and slide other fingers near the joints of patient X's or practitioner Y's own fingers to determine if they slide easily or stop. Practitioner Y may also slide fingers on the knees or ankles to determine if they slide easily or stop. The assessment by palpation may also be done using patient X's own fingers. Furthermore, as practitioner Y becomes more skilled, it may be possible to obtain muscle responses using the practitioner's own fingers without pointing to the area of ​​discomfort, for example, by focusing their gaze or awareness on the area, or by visualizing it in their mind.

[0048] When practitioner Y performs an action, the sensor group 20 can acquire biological signals emitted by practitioner Y or patient X as response information. For example, some of the sensors in the sensor group 20 are non-contact and acquire at least one of electromagnetic waves, vibration waves, or light waves as biological signals. For example, the treatment support system 1 uses a sensor such as a highly sensitive conductive antenna that measures electromagnetic signals as an electromagnetic wave sensor 22 (described later) to acquire extremely weak electromagnetic waves emitted from patient X as biological signals.

[0049] For example, the treatment support system 1 acquires biosignals using a vibration generator (not shown). The vibration generator is an ultra-low frequency sound wave generator with a frequency of 10Hz-50Hz, which generates vibrations on the patient X's skin. A MEMS acceleration sensor 24, described later and included in the sensor group 20, converts the vibrations irradiated onto the skin into electrical signals, and acquires the vibration components as biosignals. For example, the treatment support system 1 also acquires weak light emitted from patient X as a biosignal using a biophoton sensor 23, described later and one of the sensors in the sensor group 20. The treatment support system 1 may also treat information input by the practitioner Y to the practitioner terminal device 30 as response information to the intervention.

[0050] When the treatment support system 1 identifies the area of ​​discomfort, practitioner Y can identify the cause of the discomfort by performing a similar action. In the example shown below, the treatment support system 1 identifies both the area of ​​discomfort and the cause of discomfort, but in this embodiment, the treatment support system 1 only needs to identify at least one of the area of ​​discomfort and the cause of discomfort. Once the treatment support system 1 identifies at least one of the area of ​​discomfort and the cause of discomfort, it uses the generating AI system 40 to identify a treatment method. Practitioner Y performs the treatment on patient X using the treatment method displayed on the practitioner terminal device 30.

[0051] In modern medicine, it has become clear that the causes of diseases and chronic pain are often not singular, but rather a complex interplay of various factors. Even if the area with the most severe symptoms is treated temporarily, it is not uncommon for symptoms to appear in another area next. The existence of Conditioned Pain Modulation (CPM) is becoming recognized, and for example, patient X, who initially complained of knee pain, may then complain of discomfort in the ankle, hip, or lower back after the knee pain is relieved. Such phenomena are the result of the body's inherent balance mechanisms and compensatory movements, meaning that simply resolving the "surface symptoms" will not lead to a fundamental solution. Furthermore, chronic pain and limited range of motion are often caused by a combination of factors such as adhesions of fascia and joint capsules, impaired gliding, and muscle weakness. In other words, symptomatic treatment alone may only provide temporary relief, and it is desirable to implement interventions that focus on the structural and functional balance of the entire body in order to bring about fundamental change.

[0052] In this embodiment, the treatment support system 1 may, after the practitioner Y has finished treating the affected area, interact with patient X regarding other ailments. After the treatment, the treatment support system 1 acquires biosignals using sensors and also acquires response information to practitioner Y's actions on the affected area after the treatment. The treatment support system 1 uses the biosignals and response information to cause the generating AI system 40 to generate treatment result information. The treatment result information may include suggestions for treatment of new areas.

[0053] <Data on treatment methods by cause and data on coping strategies by symptom> Figure 12 is a diagram (1) showing an example of treatment data by cause, Figure 13 is a diagram (2) showing an example of treatment data by cause, Figure 14 is a diagram (3) showing an example of treatment data by cause, and Figure 15 is a diagram (4) showing an example of treatment data by cause.

[0054] Figure 16 is a diagram (1) showing an example of symptom-specific treatment method data, Figure 17 is a diagram (2) showing an example of symptom-specific treatment method data, and Figure 18 is a diagram (3) showing an example of symptom-specific treatment method data. In this embodiment, the generation AI system 40 can generate information in response to requests from the treatment support device 10 based on cause-specific treatment method data and symptom-specific treatment method data. Although the examples shown in Figures 16 to 18 show treatment methods in line with conventional medical practices, a wider variety of symptom-specific treatment methods can be used by targeting treatments such as manual therapy and osteopathic therapy as described above. An overview is shown below. ○ Osteopathic therapy (skeletal, pelvic, and spinal correction) Expected ailments: Chronic lower back pain, neck pain, pelvic area discomfort, poor posture Causal hypotheses: Poor skeletal alignment, imbalance of supporting muscles, lifestyle habits Method: Manual correction, muscle balance adjustment, self-care guidance Expected effects: Improved alignment, improved range of motion, pain relief Caution: High-speed thrusts should be performed with particular caution in the cervical spine. Avoid treatment if there are any red flag findings. 〇 Therapies based on Oriental medicine (acupuncture, meridian therapy, herbal acupressure) Expected ailments: Chronic pain, coldness / fatigue, indigestion, menstrual-related symptoms, stress Causal hypothesis: Imbalance of qi, blood, and bodily fluids, or yin and yang, and blockage of meridians (traditional theory) Method: Acupuncture, moxibustion, meridian acupressure, and acupoint approach based on constitutional assessment. Expected effects: Pain relief, autonomic nervous system regulation, improved blood circulation, relief from cold extremities. Points to note: Infection control measures (disposable needles), consideration for pregnant women and those prone to bleeding. Relaxation Therapies (Aromatherapy, Reflexology, Hot Stone Therapy, Ayurveda) Expected symptoms: stress, insomnia, stiff shoulders, fatigue Causal hypothesis: Sympathetic nervous system dominance, poor sleep hygiene, muscle tension Method: Essential oil treatment, foot reflexology stimulation, heated stones, oil treatment, herbs Expected effects: Calming of mind and body, subjective improvement in sleep quality, and relaxation of muscle tension. Precautions: Consideration for essential oil allergies, skin irritation, underlying medical conditions, and pregnancy. Other therapies (trigger point therapy, lymphatic drainage, sports massage, balance therapy, ionization therapy, antimatter bonding therapy, etc.) Possible side effects: Localized muscle pain, swelling, post-exercise fatigue, poor posture and balance. Causal hypothesis: Trigger point formation, lymphatic flow stagnation, accumulated exercise stress, and disruption of systemic coordination. Methods: Sustained pressure on tender points, superficial lymphatic drainage techniques, sports-specific massage, posture and foot assessment. Expected effects: Local pain relief, reduced edema, and support for athletic performance. Caution: Lymphatic procedures are contraindicated in patients with infection, heart failure, or deep vein thrombosis. Therapies with questionable scientific validity in their name (e.g., antimatter bonding therapy) have unknown evidence and require caution. ○ Electrotherapy (applying electric current to the skin) Expected ailments: Acute and chronic pain, muscle atrophy, edema, wound healing support Causal hypotheses: inflammation, pain transmission, decreased muscle activity, poor circulation. Methods: TENS (Transcutaneous Electrical Stimulation), EMS (Electrical Muscle Stimulation), Microcurrent, Interferential Current, etc. Expected effects: Suppression of pain perception, induction of muscle contraction, promotion of blood flow, support of the healing process. Precautions: Contraindicated in pacemakers / implanted devices, early pregnancy, skin lesions, and near the heart. Appropriate output and electrode placement are essential.

[0055] In the example above, when a danger sign (an indication that seeking medical attention should be prioritized) is detected, the suggestion is stopped, a medical consultation guide is displayed at the forefront, and the log is saved. Furthermore, if a contraindication is detected, the relevant procedure can be hidden or displayed with a warning, and an alternative can be suggested. It should be noted that the handling of the device requires continuous improvement of specific sensor signal processing, model updates, and UI operation techniques.

[0056] <Configuration of Treatment Support System 1> Figure 2 shows an example of a functional block of the treatment support system 1.

[0057] The treatment support device 10 is an information processing device such as a server computer, PC (Personal Computer), or workstation, and is, for example, a device owned by a business operator that provides treatment support services. The treatment support device 10 comprises a processing unit 110, a storage unit 120, an input unit 130, an output unit 140, and a communication unit 150. The processing unit 110 comprehensively controls the entire treatment support device 10. The storage unit 120 stores information necessary for processing by the processing unit 110. The input unit 130 receives information input to the treatment support device 10 from an input device connected via an input interface of the treatment support device 10.

[0058] The output unit 140 outputs the information stored in the treatment support device 10 to an output device connected via the output IF of the treatment support device 10. The output unit 140 may, instead of the output unit 340 of the practitioner terminal device 30, display the analysis results, including candidate areas of discomfort, candidate causes of discomfort, treatment method information, and treatment result information, on the display of the treatment support device 10. The communication unit 150 mediates the transmission and reception of information with other information processing devices connected via the network N.

[0059] The processing unit 110 comprises a reaction acquisition unit 111, an analysis unit 112, and a method request unit 113. The reaction acquisition unit 111 acquires reaction information indicating the patient X's response to the practitioner Y's actions. The reaction acquisition unit 111 acquires reaction information indicating the muscle response of practitioner Y or patient X, obtained using a contact-type or non-contact-type sensor. The reaction acquisition unit 111 acquires biological signals emitted by practitioner Y or patient X, obtained using a contact-type or non-contact-type sensor, as reaction information. For example, the reaction acquisition unit 111 acquires biological signals using a biophoton sensor 23, which will be described later.

[0060] The analysis unit 112 identifies at least one of the affected area and the cause of the affected area by analyzing the response information using AI, including a machine learning model. For example, the analysis unit 112 requests the generation AI system 40 for candidate affected areas. The analysis unit 112 transmits information indicating the candidate affected areas obtained as a result of the request to the practitioner terminal device 30. Once response information for the candidate affected area is obtained, the analysis unit 112 transmits a request for identification of an affected area to the generation AI system 40, which specifies information identifying the candidate affected area and the response information for the candidate affected area. The analysis unit 112 repeats this process until the affected area is identified. The response information included in the judgment request may be the response of patient X or the response of practitioner Y.

[0061] Furthermore, the analysis unit 112 requests the generation AI system 40 to provide candidate causes of the disorder. The analysis unit 112 transmits information indicating the candidate causes of the disorder obtained as a result of the request to the practitioner terminal device 30. Once response information for the candidate causes of the disorder is obtained, the analysis unit 112 transmits a disorder cause determination request to the generation AI system 40, which specifies information identifying the candidate causes of the disorder and the response information for the candidate causes of the disorder. The analysis unit 112 repeats this process until the cause of the disorder is identified.

[0062] Furthermore, the analysis unit 112 identifies treatment method information by analyzing at least one of the affected area and the cause of the affected area, as identified by the method request unit 113, using AI including a machine learning model. For example, the analysis unit 112 sends a treatment method determination request including the affected area and the cause of the affected area to the generation AI system 40. The analysis unit 112 then identifies the treatment method determined by the generation AI system 40.

[0063] Furthermore, the analysis unit 112 generates treatment result request information using the biosignals and reaction information obtained as a result of the treatment and transmits it to the generation AI system 40. The analysis unit 112 transmits treatment result information indicating the treatment result obtained as a result of the request to the practitioner terminal device 30 and has the practitioner Y output it.

[0064] The method request unit 113 identifies at least one of the affected area and the cause of the affected area identified by the analysis unit 112, and requests treatment method information from the generating AI system 40.

[0065] Furthermore, the analysis unit 112 may identify the affected area or cause of discomfort using a machine learning model trained to estimate the affected area or cause of discomfort from biological data and biological signals. In this case, the analysis unit 112 uses the machine learning model to analyze the biological data (short-term and long-term time-series data) and biological signals transmitted from the treatment support device 10, and identifies candidate affected areas and candidate causes of discomfort as analysis results. The analysis unit 112 uses the machine learning model to analyze the response information to the candidate affected area or candidate cause of discomfort, and obtains information as analysis results indicating whether the candidate affected area is indeed an affected area, or whether the candidate cause of discomfort is indeed the cause of discomfort. In addition, the analysis unit 112 uses the machine learning model to analyze the biological signals and response information obtained as a result of the treatment, and obtains treatment result information. The analysis unit 112 may use AI that includes a machine learning model that analyzes the effects of the treatment and corrects for factors other than the treatment.

[0066] For example, the AI ​​is trained to analyze biometric data and biosignals to identify potential areas of discomfort in patient X. The AI ​​is trained on a training dataset that includes treatment results for the identified areas of discomfort, and by learning the correlation between post-treatment improvement trends and biometric data and biosignals, it becomes possible to estimate potential areas of discomfort that are tailored to the individual patient X's condition. Similarly, the AI ​​is trained to analyze biometric data and biosignals to identify potential causes of discomfort in patient X.

[0067] For example, the AI ​​is trained to analyze biometric data and response information to identify the affected area and its cause. The AI ​​is trained on a training dataset that includes treatment results on the affected area, and by learning the correlation between the improvement trend after treatment and biometric data and response information, it can estimate the affected area and its cause in accordance with the patient X's condition. The AI ​​is also trained to analyze the affected area and its cause to identify treatment methods and estimate treatment methods in accordance with the patient X's condition. Furthermore, the AI ​​is trained to analyze response information to interventions on the affected area after treatment and identify treatment result information.

[0068] Furthermore, the analysis unit 112 can periodically retrain the model using newly collected biological data, biological signals, reaction information, etc., to improve accuracy. The analysis unit 112 also visualizes the decision-making process using the model and provides the results to the practitioner Y in an explainable format. In addition, the treatment support system 1 may obtain each analysis result using the functions of other information processing devices connected via the network N that are capable of analysis using machine learning models. The treatment support device 10 or other information processing device that performs analysis using machine learning models can, if necessary, use data stored in a data server that is connected via communication. That is, the treatment support system 1 may have an information processing device that performs analysis using a machine learning model instead of the generation AI system 40.

[0069] Furthermore, it is desirable that the analysis unit 112 stores all information, including patient X's information, practitioner Y's information, and past treatment details (reactions, judgments, treatments, results, etc.), in a database such as the storage unit 120 in order to obtain analysis results from the generating AI system 40 or machine learning model. In addition, the analysis unit 112 can also store other references and exchange and collect information among practitioners.

[0070] The sensor group 20 includes an electromyography sensor 21, an electromagnetic wave sensor 22, a biophoton sensor 23, and an acceleration sensor 24. The electromyography sensor 21 is attached to the user's skin to detect the potential of the skin surface and quantifies muscle movement as a muscle response. The electromagnetic wave sensor 22 is a device that detects weak electromagnetic signals in the human body, and can use, for example, a high-sensitivity magnetic detection element. By placing the electromagnetic wave sensor 22 near the user's skin, it can detect electromagnetic signals on the body surface of patient X or practitioner Y.

[0071] The biophoton sensor 23 is a device that detects weak light emitted from the human body, such as a photon counter or a high-sensitivity CCD (Charge Coupled Device) camera. The acceleration sensor 24 is a device that acquires vibrations irradiated onto the skin of patient X using the vibration generator described above. The sensors described above are just examples of devices included in the sensor group 20, and the sensor group 20 does not have to include all of these sensors; the sensor group 20 may include other sensors. For example, the sensor group 20 may include an electroencephalogram (EEG) machine. Electroencephalograms contain alpha waves and theta waves, and it is said that healing ability increases when in an alpha wave or theta wave state; therefore, EEG measurement can be used for training to improve the accuracy of treatments. The sensor group 20 can acquire biosignals emitted by the practitioner Y or patient X. In this embodiment, the biosignals obtained by the actions of practitioner Y are described as reaction information.

[0072] In this embodiment, practitioner Y can perform treatment on patient X who is located remotely. When any of the sensors in the sensor group 20 acquire the biosignals of patient X, the sensor may be located near patient X, and when any of the sensors in the sensor group 20 acquire the biosignals of practitioner Y, the sensor may be located near practitioner Y. In other words, the distance between multiple sensors included in the sensor group 20 may be large.

[0073] Furthermore, in this embodiment, the treatment support system 1 does not necessarily require the sensor group 20; it is sufficient for the practitioner Y to input response information such as kinesiology. In addition, the generating AI system 40 can guide practitioner Y to improve their skill level by suggesting deficiencies in the treatment and proposing areas for improvement as treatment result information.

[0074] The practitioner terminal device 30 is an information processing device such as a PC, smartphone, PDA (Personal Data Assistant), or tablet device owned by practitioner Y. The practitioner terminal device 30 comprises a processing unit 310, a storage unit 320, an input unit 330, an output unit 340, and a communication unit 350. The processing unit 310 comprehensively controls the entire practitioner terminal device 30. The storage unit 320 stores information necessary for processing by the processing unit 310. The input unit 330 receives information input to the practitioner terminal device 30 from input devices connected via an input interface of the practitioner terminal device 30.

[0075] The output unit 340 outputs information stored in the practitioner terminal device 30 to an output device connected via the output IF of the practitioner terminal device 30. The output unit 340 outputs the analysis results from the analysis unit 112 of the treatment support device 10. For example, the output unit 340 outputs candidate areas of dysfunction or candidate causes of dysfunction identified by the analysis unit 112. The output unit 340 may display candidate areas of dysfunction differently from other areas in a model image of patient X's body. In this case, the model image may include images showing the internal organs of patient X. The output unit 340 also outputs treatment method information identified by the analysis unit 112. The communication unit 350 mediates the transmission and reception of information with other information processing devices connected via the network N.

[0076] The generation AI system 40 utilizes machine learning and natural language processing to generate and output various documents, images, videos, audio, program code, etc., in response to prompts. If an API (Application Programming Interface) is provided, the treatment support device 10 can also access the API function to input prompts. The generation AI system 40 can utilize LLMs (Large Language Models) such as OpenAI's CHATGPT® or Google's Gemini. The generation AI system 40 may be built locally, and the treatment support device 10 may access it via a LAN (Local Area Network).

[0077] Hereinafter, the generation AI system 40 will be described as a device that generates text data in response to instructions using an LLM. However, the model used by the generation AI system 40 is not limited to an LLM. For example, the generation AI system 40 may use an image input as biometric data or biometric signals to derive analysis results and generate a document or image containing the analysis results.

[0078] Furthermore, instead of the generation AI system 40, advanced AI technologies such as AGI (Artificial General Intelligence) and ASI (Artificial Super Intelligence) may be adopted. The AI ​​analysis function and utilization of biometric data of the present invention have high applicability in growing fields such as medical technology, psychotherapy and neurofeedback, and digital health analysis using wearable devices, which are currently in the demonstration stage.

[0079] When using the generation AI system 40, the analysis unit 112 may be provided with all of the biological data, biological signals, and reaction information, or it may be provided with one or more selected from these. It may also be provided with historical data linked to a time series. Furthermore, the generation AI system 40 can employ federated learning or edge AI processing to ensure the protection of personal information and data security. This makes it possible to safely analyze patient X's data without centrally managing it on the cloud.

[0080] Furthermore, even when using the generation AI system 40, the analysis unit 112 can compare the results with past medical research and academic data to evaluate the scientific validity of the treatment effects. This makes it possible to provide objective evidence regarding the effects of alternative medicine treatments and to verify the effectiveness of the treatments.

[0081] <Hardware Configuration> Figure 3 shows an example of the hardware configuration of the treatment support device 10. The treatment support device 10 comprises a processor 101, memory 102, storage 103, communication device 104, and a bus 105 connecting the devices. In addition, the treatment support device 10 may also include input devices and output devices.

[0082] The processor 101 is a computing device such as a CPU (Central Processing Unit) or GPU (Graphics Processing Unit), and it performs processing according to a program recorded in memory 102 or storage 103. In the treatment support device 10, processing is performed by the processor 101, which operates according to a program read from memory 102 or storage 103. The processing unit 110, the reaction acquisition unit 111, the analysis unit 112, and the method request unit 113 each realize their respective functions when the processor 101 executes a program.

[0083] Memory 102 is a storage device such as RAM (Random Access Memory) or flash memory, and functions as a storage area where programs and data are temporarily read. Storage 103 is a writable and readable storage device. The storage unit 120's functions are realized by either memory 102 or storage 103. Alternatively, the storage unit 120 may be realized by a storage device connected via communication device 104.

[0084] The communication device 104 is an interface for connecting the treatment support device 10 to an external device. For example, the communication device 104 uses an antenna that can utilize predetermined radio waves (e.g., 5GHz band, 2.4GHz band, etc.) to establish a connection with other information processing devices using the Wi-Fi standard for wireless communication. The communication unit 150's functions are realized by the communication device 104.

[0085] The processor 101, memory 102, storage 103, and communication device 104 are connected to each other by connecting wires such as a bus 105.

[0086] Each processing unit (reaction acquisition unit 111, analysis unit 112, and method request unit 113) may be constructed using dedicated hardware (ASIC, GPU, etc.) to realize its respective function. Furthermore, the processing of each processing unit may be executed on a single piece of hardware or on multiple pieces of hardware.

[0087] Furthermore, since the practitioner terminal device 30 and the generation AI system 40 basically have the same hardware configuration as the treatment support device 10, their explanation will be omitted.

[0088] <Identification of the affected area> Figure 4 is a sequence diagram showing an example of the process for identifying the affected area. This process is started, for example, when the practitioner terminal device 30 receives an input operation for a start command. The start command is notified from the practitioner terminal device 30 to the treatment support device 10.

[0089] First, the response acquisition unit 111 of the treatment support device 10 acquires the chief complaint (step S11). For example, when patient X provides the chief complaint to practitioner Y using paper or a tablet device (not shown), the chief complaint is input into the practitioner terminal device 30 and transmitted to the treatment support device 10. In this embodiment, acquiring the chief complaint is not mandatory.

[0090] Furthermore, obtaining the chief complaint in step S11 is not limited to doing so on the day of the treatment. For example, obtaining it in advance, such as when making a reservation, allows the practitioner Y to prepare necessary sensors and appropriate questions.

[0091] Next, the reaction acquisition unit 111 of the treatment support device 10 acquires the patient X's biological data (step S12). For example, if patient X provides the biological data to practitioner Y using paper or a tablet device (not shown), the biological data is input into the practitioner terminal device 30 and transmitted to the treatment support device 10. It should be noted that the acquisition of biological data in step S12 is not limited to being performed on the day of treatment. For example, if there is a possibility of fracture and the treatment facility to which practitioner Y belongs does not have equipment such as X-ray imaging or MRI, the reaction acquisition unit 111 can send a notification to patient X prompting them to provide the biological data in advance. Also, if the test takes time, such as blood test data, the reaction acquisition unit 111 can send a notification to patient X prompting them to prepare past data, etc.

[0092] Next, the response acquisition unit 111 of the treatment support device 10 acquires biosignals using sensors (step S13). Specifically, the response acquisition unit 111 acquires biosignals of patient X or practitioner Y using each sensor of the sensor group 20. The response acquisition unit 111 may also acquire, along with or in lieu of, biosignals, a description of information about patient X's body or mind that has been input by practitioner Y. Practitioner Y can recognize information about the patient's body or mind using kinesiology or the like. The response acquisition unit 111 acquires the information input to the practitioner terminal device 30.

[0093] Next, the analysis unit 112 of the treatment support device 10 requests the generation AI system 40 to identify candidate areas of discomfort (step S14). Specifically, the analysis unit 112 generates a prompt requesting candidate areas of discomfort, which includes the information indicating the chief complaint acquired in step S11, the biometric data acquired in step S12, and the biometric signals acquired in step S13. In step S13, if the response acquisition unit 111 acquires information about patient X from practitioner Y, the analysis unit 112 includes the patient X information acquired by the response acquisition unit 111 in the prompt. Furthermore, if response information to practitioner Y's actions on a candidate area of ​​discomfort has already been acquired, the analysis unit 112 includes information indicating the candidate area of ​​discomfort for which response information has been obtained, along with the response information, in the prompt. The analysis unit 112 requests the generation AI system 40 to identify candidate areas of discomfort by transmitting the prompt.

[0094] Next, the generating AI system 40 identifies candidate areas of dysfunction using the information included in the request (step S15). Specifically, the generating AI system 40 obtains information to identify candidate areas of dysfunction in patient X by inputting prompts into the AI. The generating AI system 40 transmits information indicating candidate areas of dysfunction to the treatment support device 10. The generating AI system 40 may also generate an image indicating candidate areas of dysfunction in response to a request from the analysis unit 112. In that case, the generated image is transmitted to the treatment support device 10 as information indicating candidate areas of dysfunction.

[0095] Next, the analysis unit 112 of the treatment support device 10 transmits information indicating candidate areas of dysfunction received in step S15 to the practitioner terminal device 30 (step S16).

[0096] Next, the output unit 340 of the practitioner terminal device 30 outputs the candidate areas of discomfort received from the treatment support device 10 in step S16 (step S17). The method of outputting the candidate areas of discomfort is not limited. Subsequently, the practitioner Y interacts with the patient X at the candidate areas of discomfort.

[0097] Next, the reaction acquisition unit 111 of the treatment support device 10 acquires reaction information to the practitioner Y's actions on the candidate area of ​​discomfort (step S18). Specifically, the reaction acquisition unit 111 acquires reaction information indicating the muscle response of patient X or practitioner Y obtained using sensors included in the sensor group 20. Alternatively, the reaction acquisition unit 111 acquires biological signals of patient X or practitioner Y obtained using contact-type or non-contact-type sensors as reaction information. For example, the reaction acquisition unit 111 terminates the acquisition of reaction information in response to an input operation from practitioner Y. Even if the reaction acquisition unit 111 does not accept an input operation from practitioner Y, it may acquire biological signals acquired within a predetermined period starting from the transmission of the candidate area of ​​discomfort in step S16 as reaction information.

[0098] Next, the analysis unit 112 transmits a request for identification of a dysfunctional area to the generating AI system 40 (step S19). Specifically, the analysis unit 112 generates information indicating a request for identification of a dysfunctional area, which includes information indicating candidate dysfunctional areas received from the generating AI system 40 in step S15 and reaction information acquired in step S18. The request for identification of a dysfunctional area may also include biological data acquired in step S12. The analysis information generates a prompt indicating a request for identification of a dysfunctional area and transmits it to the generating AI system 40. The analysis unit 112 can include information in the prompt that serves as a criterion for the generating AI system 40 to use to identify the dysfunctional area. The analysis unit 112 can also include information in the prompt requesting that the dysfunctional area be identified as a somewhat limited area rather than a wide area.

[0099] Next, the generating AI system 40 notifies the treatment support device 10 of the judgment result using the reaction information (step S20). Specifically, the generating AI system 40 obtains a judgment result of whether or not the problematic area has been identified by executing the prompt received in step S19. The generating AI system 40 notifies the treatment support device 10 of the judgment result. If the problematic area has been identified, the judgment result will include the identified problematic area.

[0100] Next, the analysis unit 112 of the treatment support device 10 determines whether or not the problematic area has been identified (step S21). Specifically, the analysis unit 112 determines whether or not the determination result received in step S20 is information indicating that the problematic area has been identified. If the analysis unit 112 determines that the problematic area has been identified (if the result is "YES" in step S21), the processing shown in this sequence diagram is terminated.

[0101] If the analysis unit 112 determines that the area of ​​discomfort has not been identified (i.e., "NO" in step S21), it proceeds to step S14. That is, the practitioner Y continues to work on patient X until the area of ​​discomfort is identified.

[0102] As described above, according to this embodiment, the affected area can be appropriately identified using the patient X's response, or the practitioner Y's response based on the patient X's response. Furthermore, by combining AI technology with muscle reflex measurement when performing kinesiology, it is possible to improve measurement accuracy, allowing for simple and accurate identification of the affected area without the need for large-scale examination equipment.

[0103] Furthermore, when generating a prompt requesting the identification of a problem area, the analysis unit 112 of the treatment support device 10 can generate a prompt that sequentially narrows down the list of body parts in a parallel relationship to specify them as candidate problem areas. In that case, for example, if the chief complaint "I can't lift my arm" is obtained in step S11, the generating AI system 40 sequentially identifies body parts such as "arm," "shoulder," and "chest" as candidate problem areas until the problem area is identified.

[0104] Furthermore, when generating prompts, which are request information for candidate areas of dysfunction, the analysis unit 112 may generate prompts that specify candidate areas of dysfunction in a manner that sequentially narrows down from higher-level concepts to lower-level concepts of the body. For example, after specifying either the left or right side of the body as a candidate area of ​​dysfunction, the analysis unit 112 may further specify either the upper or lower body of the specified side as a candidate area of ​​dysfunction, and then, for example, specify either the upper or lower limb belonging to the right lower body as a candidate area of ​​dysfunction. In other words, the analysis unit 112 can generate prompts that narrow down the areas of dysfunction in a hierarchical manner.

[0105] In step S19, the analysis unit 121 generates a prompt to the generation AI system 40 indicating a request for identification of a faulty area, and in step S20, it obtains information identifying the faulty area as a response. However, in step S19, the analysis unit 121 may also generate a prompt to the generation AI system 40 requesting a confidence level. The confidence level is a value indicating the probability that a candidate faulty area is a faulty area. In that case, the analysis unit 121 obtains a confidence level for the faulty area candidate as a response from the generation AI system 40. In step S21, the analysis unit 121 compares the confidence levels obtained for each faulty area candidate and can identify the faulty area candidate with the highest confidence level as the faulty area.

[0106] Furthermore, practitioner Y can use the narrowing down of the range of candidate areas of discomfort by the generating AI system 40 in this embodiment as navigator-like information. On the other hand, if the candidate areas of discomfort identified by the generating AI system 40 in steps S14 to S21 differ from practitioner Y's findings, practitioner Y can notify the generating AI system 40 of this and request candidate areas of discomfort again. If there is a difference between the two in the end, practitioner Y may select the area of ​​discomfort. Also, if the generating AI system 40 determines a danger sign or contraindication, the processing of this flowchart ends at that point.

[0107] <Disorder area candidate display screen> Figure 8 is a diagram (estimated / schematic) (part 1) showing an example of the dysfunction area candidate display screen 360. In step S15 of Figure 4, if the generating AI system 40 generates screen information for the screen showing the dysfunction area candidates, in step S17, the dysfunction area candidate display screen 360 is displayed on the practitioner terminal device 30. For example, the output unit 340 of the practitioner terminal device 30 displays the dysfunction area candidate display screen 360 on the display, which displays the dysfunction area candidates differently from other areas in the model image of patient X's body.

[0108] The dysfunction area candidate display screen 360 shown in Figure 8 shows the lower body of the model image displayed differently from other parts. In other words, the dysfunction area candidate display screen 360 in this figure shows that the lower body of patient X has been identified as a dysfunction area candidate. When practitioner Y performs an action on the lower body, which is a dysfunction area candidate, the response acquisition unit 111 acquires response information to the action. In the example shown in this figure, when the analysis unit 112 acquires positive response information regarding the lower body, it further causes the generation AI system 40 to identify the dysfunction area candidates belonging to the lower body in order to narrow down the options. In other words, the dysfunction area is narrowed down hierarchically through internal "questions" by practitioner Y.

[0109] Figure 9 is a diagram (estimated / schematic) (part 2) showing an example of the dysfunction site candidate display screen 360. The model image shown in Figure 9 includes an image showing internal organs. The model image shown in Figure 9(A) schematically shows the state in which the generating AI system 40 identifies the upper part a, the central part b, and the lower part c of the lung as successive dysfunction site candidates when a chief complaint regarding the lungs or positive response information regarding the lungs is obtained. The analysis unit 112 of the treatment support device 10 instructs the output unit 340 to display the upper part a, which has been designated as a dysfunction site candidate, differently from the other parts. If the response information for upper part a is negative, it displays the central part b, which has been designated as a dysfunction site candidate, differently from the other parts. If the response information for central part b is negative, it displays the lower part c, which has been designated as a dysfunction site candidate, differently from the other parts.

[0110] In addition, the analysis unit 112 may display the upper part a, the central part b, and the lower part c differently from other parts on the common dysfunction area candidate display screen 360. That is, multiple dysfunction area candidates may be displayed on the dysfunction area candidate display screen 360. In that case, in step S18 of Figure 4, the reaction acquisition unit 111 of the treatment support device 10 accepts a specification of which of the dysfunction area candidates the reaction information is for when acquiring reaction information, and in step S19, transmits the combination of information identifying the specified dysfunction area candidate and the reaction information to the generation AI system 40.

[0111] Similar to the example shown in Figure 9(A), the model image shown in Figure 9(B) schematically illustrates a state in which, when a chief complaint regarding the kidneys or positive response information regarding the kidneys is obtained, the generating AI system 40 identifies the abdominal aorta d, ureter e, and left kidney f in that order as candidate sites of dysfunction within the kidneys.

[0112] By displaying potential problem areas using model images, practitioner Y can easily identify potential problem areas, improving convenience. The problem area display screen 360 may also be displayed for patient X.

[0113] <Processing to identify the cause of malfunction> Figure 5 is a sequence diagram showing an example of the process for identifying the cause of a problem. This process is started, for example, when the practitioner terminal device 30 identifies a problematic area in the problematic area identification process shown in step S4. The process for identifying the cause of a problem does not need to have been performed before the problematic area identification process is executed.

[0114] The processes performed in steps S31 to S33 are the same as those performed in steps S11 to S13 shown in Figure 4, so their explanation is omitted. Note that if the malfunction cause identification process shown in this figure is performed following the malfunction part identification process shown in Figure 4, the processes performed in steps S11 to S13 in Figure 4 may be treated as if they were performed in steps S31 to S33, and the processes in steps S31 to S33 may be omitted.

[0115] Next, the analysis unit 112 of the treatment support device 10 requests the generation AI system 40 to identify a candidate cause of the ailment (step S34). Specifically, the analysis unit 112 generates a prompt indicating a request for identification of a candidate cause of the ailment, which includes information indicating the chief complaint obtained in step S31, biological data obtained in step S32, and biological signals obtained in step S33. If response information to the practitioner Y's actions on the candidate cause of the ailment has already been obtained, the analysis unit 112 includes information indicating the candidate cause of the ailment for which response information has been obtained, and the response information, in the prompt. In addition, the analysis unit 112 may include in the prompt information that serves as a criterion for the generation AI system 40 to use in identifying the candidate cause of the ailment, such as the conditions for being identified as a candidate cause of the ailment. The analysis unit 112 requests the generation AI system 40 to identify a candidate cause of the ailment by transmitting the prompt.

[0116] Next, the generating AI system 40 identifies candidate causes of the ailment using the information contained in the request (step S15). Specifically, the generating AI system 40 obtains information that identifies candidate causes of patient X's ailment by inputting prompts into the AI. The generating AI system 40 transmits the information indicating the candidate causes of the ailment to the treatment support device 10.

[0117] Next, the analysis unit 112 of the treatment support device 10 transmits information indicating candidate causes of the disorder, received from the generation AI system 40 in step S35, to the practitioner terminal device 30 (step S36).

[0118] Next, the output unit 340 of the practitioner terminal device 30 outputs the candidate causes of discomfort received from the treatment support device 10 in step S36 (step S37). The method of outputting the candidate causes of discomfort is not limited. Subsequently, the practitioner Y interacts with patient X regarding the candidate causes of discomfort.

[0119] Next, the response acquisition unit 111 of the treatment support device 10 acquires response information to the practitioner Y's actions on the candidate cause of the discomfort (step S38). Specifically, the response acquisition unit 111 acquires response information indicating the muscle response of patient X or practitioner Y obtained using sensors included in the sensor group 20, similar to step S18 in Figure 4. Alternatively, the response acquisition unit 111 acquires biological signals of patient X or practitioner Y obtained using contact-type or non-contact-type sensors as response information. For example, the response acquisition unit 111 terminates the acquisition of response information in response to an input operation from practitioner Y. Even if the response acquisition unit 111 does not accept an input operation from practitioner Y, it may acquire biological signals acquired within a predetermined period starting from the transmission of the candidate cause of discomfort in step S36 as response information.

[0120] Next, the analysis unit 112 transmits a malfunction cause determination request to the generation AI system 40 (step S39). Specifically, the analysis unit 112 generates information indicating a malfunction cause determination request that includes information indicating candidate malfunction causes received from the generation AI system 40 in step S35 and reaction information acquired in step S38. The malfunction cause determination request may also include biological data acquired in step S32. The analysis unit 112 generates a prompt indicating the malfunction cause determination request and transmits it to the generation AI system 40. The prompt may include information that serves as a criterion for determining the cause of the malfunction.

[0121] Next, the generating AI system 40 notifies the treatment support device 10 of the judgment result using the reaction information (step S40). Specifically, the generating AI system 40 obtains a judgment result of whether or not the cause of the discomfort has been identified by executing the prompt received in step S39. The generating AI system 40 notifies the treatment support device 10 of the judgment result. If the cause of discomfort has been identified, the judgment result will include the identified cause of discomfort.

[0122] Next, the analysis unit 112 of the treatment support device 10 determines whether or not the cause of the malfunction has been identified (step S41). Specifically, the analysis unit 112 determines whether or not the determination result received in step S40 is information indicating that the cause of the malfunction has been identified. If the analysis unit 112 determines that the cause of the malfunction has been identified (if the result is "YES" in step S41), the processing shown in this sequence diagram is terminated.

[0123] Furthermore, if the generating AI system 40 determines a danger sign or contraindication, the processing of this flowchart ends at that point. In addition, when the candidate cause of the ailment is transmitted in step S36, the analysis unit 112 can confirm whether it is okay to proceed with the intervention and obtain a response from patient X. For example, when the processing unit 310 of the practitioner terminal device 30 receives an input operation regarding patient X's judgment on whether it is okay to proceed with the intervention or whether it should be stopped, it transmits the input information to the treatment support device 10. If the analysis unit 112 of the treatment support device 10 obtains information from patient X indicating that the intervention should be stopped, it terminates the processing of this flowchart. This process may always be performed before practitioner Y performs the intervention.

[0124] If the cause of the problem has not been identified (if the result is "NO" in step S41), the analysis unit 112 proceeds to step S34. That is, the practitioner Y continues to work on patient X until the cause of the problem is identified.

[0125] As described above, according to this embodiment, the cause of discomfort can be appropriately identified using the patient X's response, or the practitioner Y's response based on the patient X's response. For example, for each candidate cause of discomfort identified as a problematic area, the cause can be determined using the response information. For example, if the problematic area is the "foot," the cause can be identified using the response information for candidate causes of discomfort such as "bruise," "frostbite," "burn," and "fracture." According to this embodiment, for example, when performing kinesiology, combining AI technology with muscle reflex measurement makes it possible to improve measurement accuracy, and the problematic area can be identified simply and accurately without using large-scale examination equipment.

[0126] In this embodiment, the process for identifying the cause of the problem is performed after the process for identifying the problematic area. In each process, a determination is made using the response information for the candidate problematic area or the candidate cause of the problem. In this embodiment, the process for identifying the problematic area and the process for identifying the cause of the problem may be performed in parallel. For example, if "lower back" is identified as a candidate problematic area and the response information regarding "lower back" is positive, the analysis unit 112 identifies "lumbago" as a candidate cause of the problem related to "lower back". If the response information regarding "lumbago" is negative, the analysis unit 112 may identify "lower abdomen" as a candidate problematic area and acquire response information regarding "lower abdomen". That is, the analysis unit 112 may identify candidate problematic areas and candidate causes of the problem and acquire response information until the problematic area and the cause of the problem are identified.

[0127] <Treatment Method Identification Process> Figure 6 is a sequence diagram showing an example of the treatment method identification process. This process begins, for example, when at least one of the treatment site determination process in Figure 4 or the treatment cause determination process in Figure 5 is completed. The treatment method information identified in this process is for advice and support, and the feasibility and scope of implementation are based on the clinical judgment of the practitioner Y.

[0128] First, the method request unit 113 of the treatment support device 10 generates treatment method request information that includes at least one of the affected area and the cause of the affected area (step S51). Specifically, the method request unit 113 generates a prompt requesting a treatment method to resolve the affected area or cause of the affected area, which includes at least one of the affected area identified in the affected area identification process shown in Figure 4 and the cause of the affected area identified in the treatment cause determination process shown in Figure 5. The prompt may also include the patient X's biological data and biological signals including reaction information. In addition to the prompt requesting a treatment method, the method request unit 113 may also generate a prompt requesting an image showing the changes that occur in patient X when the treatment related to the treatment method is performed. An image showing the changes that occur in patient X is, for example, an image showing the appearance of patient X before and after the treatment.

[0129] Next, the analysis unit 112 transmits the treatment method request information to the generation AI system 40 (step S52). Specifically, the analysis unit 112 transmits the prompt generated in step S52 to the generation AI system 40 as treatment method request information.

[0130] Next, the generating AI system 40 identifies the treatment method request information and generates an image showing the change (step S53). Specifically, the generating AI system 40 identifies the treatment method information by executing prompts received from the treatment support device 10. The generating AI system 40 may also generate an image showing the change that occurs in patient X when the treatment related to the identified treatment method information is performed, in response to the prompts. The identified treatment method information and the image showing the change are transmitted to the treatment support device 10 as a response to the treatment method request information.

[0131] Next, the analysis unit 112 of the treatment support device 10 transmits treatment method information to the treatment terminal device (step S54). Furthermore, if the analysis unit 112 receives an image showing changes in patient X from the generation AI system 40, it transmits the received image to the practitioner terminal device 30.

[0132] Next, the output unit 340 of the practitioner terminal device 30 outputs treatment method information (step S55). When the output unit 340 receives an image showing a change in patient X, it outputs the received image. Specifically, the output unit 340 displays the treatment method information transmitted from the treatment support device 10 in step S54 and the image showing the change on the display of the treatment support device 10. After that, the output unit 340 terminates the processing shown in this sequence diagram. The image showing the change is, for example, a pre-treatment image and an estimated post-treatment image, and it is desirable that this be disclosed to patient X. The image is for reference display for patient education and informed consent support and does not provide definitive evidence as a diagnostic image. The final decision is made by the practitioner Y. In addition, the information output by this system is for the purpose of advice and support, and the final clinical judgment and decision on whether or not to perform the treatment are made by the practitioner Y.

[0133] <Image showing changes in patient X> Figure 10 is an example of an image showing changes in patient X (estimated / schematic diagram) (part 1). For example, the analysis unit 112 causes the AI ​​system 40 to generate images that clearly show the changes before and after treatment. In the example shown in Figure 10, the treatment improves the overall sagging of the body, and the spine and head are restored to a normal position where they rest on the heels. Also, after the treatment, the patient's height has increased and their facial expression has brightened. By displaying a model image showing the appearance of patient X from a side view where the changes are easily visible, the effects of the treatment can be made clear to patient X. Furthermore, visualizing the changes helps to guide the patient regarding the treatment and makes the changes easier to remember. The image in Figure 10 is a line drawing, but the AI ​​could be used to create a more realistic image of the facial expression and posture. This image is for reference display to support patient education and explanation, and does not directly provide medical image findings for confirming a diagnosis. The final decision is made by the practitioner Y.

[0134] Figure 11 is an example of an image showing the changes in patient X (estimated / schematic diagram) (part 2). Figure 11(A) is an estimated diagram showing the state of patient X's blood vessels before treatment. By performing the specified treatment method, it is expected that the condition will improve to the state shown in Figure 11(C) through the process shown in Figure 11(B). In this embodiment, the pre-treatment and post-treatment images include not only the external appearance of patient X, but also images showing the state of tissues and organs within the body, as shown in Figure 11.

[0135] <Processing to obtain treatment results> Figure 7 is a sequence diagram showing an example of the treatment result acquisition process. This process starts, for example, when the practitioner terminal device 30 receives an input operation indicating that the treatment has been completed. Information related to this input operation is notified from the practitioner terminal device 30 to the treatment support device 10.

[0136] The processes performed in steps S61 to S62 are the same as those performed in steps S11 to S12 shown in Figure 4, so their explanation is omitted. Note that if the treatment result acquisition process shown in this figure is performed following the process for identifying the affected area shown in Figure 4 or the process for identifying the cause of the affected area shown in Figure 5, the process performed in step S11 in Figure 4 or step S31 in Figure 5 may be treated as if it were performed in step S61 of this figure, and the process in step S61 may be omitted.

[0137] Next, the reaction acquisition unit 111 acquires reaction information to the practitioner Y's actions on the affected area or cause of the discomfort (step S63). Practitioner Y performs actions on at least one of the affected area and / or cause of the discomfort. The reaction acquisition unit 111 acquires reaction information indicating the muscle response of patient X or practitioner Y obtained using sensors. Alternatively, the reaction acquisition unit 111 acquires the biosignals of patient X or practitioner Y obtained using contact or non-contact sensors as reaction information after the practitioner Y's actions have been performed. In other words, the reaction acquisition unit 111 acquires the reaction information of patient X after treatment related to the treatment method identified in the treatment method identification process shown in Figure 6. The reaction acquisition unit 111 may also acquire reaction information to actions performed by practitioner Y on areas presumed to be related to the affected area, as needed. In that case, the analysis unit 112 associates information indicating the area targeted by the actions with the reaction information.

[0138] Next, the analysis unit 112 transmits treatment result request information, which identifies the pre- and post-treatment biosignals and reaction information, to the generation AI system 40 (step S64). Specifically, in the dysfunction area identification process shown in Figure 4, the analysis unit 112 identifies the biosignals acquired in step S13 and the reaction information acquired in step S18 when the dysfunction area was identified as pre-treatment biodata and reaction information. The analysis unit 112 identifies the biosignals acquired in step S62 and the reaction information acquired in step S63 as post-treatment biodata and reaction information. The analysis unit 112 generates a prompt that includes the pre- and post-treatment biosignals and reaction information, indicating that a treatment result is requested, and transmits it to the generation AI system 40 as treatment result request information.

[0139] The prompt may include information that serves as a basis for determining the treatment outcome. Furthermore, the prompt may include a request to include newly discovered areas of discomfort or causes of discomfort in the treatment outcome information.

[0140] Next, the generating AI system 40 identifies treatment result information using biosignals and response information (step S65). Specifically, the generating AI system 40 identifies treatment result information by executing prompts sent from the treatment support device 10. The generating AI system 40 transmits the identified treatment result information to the treatment support device 10.

[0141] Next, the analysis unit 112 of the treatment support device 10 transmits the treatment result information received from the generation AI system 40 to the practitioner terminal device 30 (step S66).

[0142] Next, the output unit 340 of the practitioner terminal device 30 outputs treatment result information (step S67). The treatment result information output by the output unit 340 may be in the form of a document, image, audio, or a combination thereof. For example, a model image of patient X's body may be used, with the parts where the discomfort has improved being displayed differently from other parts. The model image may be an image showing the external appearance of patient X, or an image showing internal organs. Furthermore, the treatment result information may also include improvement measures such as future hospital visits to maintain or further improve the improved state of discomfort, rehabilitation methods, and self-care guidance. In that case, it may be presented as an explanatory document for patient X. The information output by this system is for the purpose of advice and support, and the final clinical judgment and decision on whether or not to perform the treatment rests with the practitioner Y.

[0143] As described above, according to this embodiment, practitioner Y can recognize treatment results objectively determined based on biosignals or reaction information, thereby improving the accuracy and safety of treatment and enabling the appropriate treatment to be performed for patient X. Furthermore, by maintaining consistency in treatment results, variations in treatment quality by multiple practitioners Y are suppressed, contributing to improved reliability in the entire field of alternative medicine.

[0144] Furthermore, the treatment result information identified by the AI ​​system 40 based on instructions from the analysis unit 112 of the treatment support device 10 may include suggestions for treatment of new areas. This allows for treatment of areas that are presumed to be related to the area of ​​discomfort. In other words, a comprehensive approach becomes possible even when symptoms may be caused by multiple factors. This enables treatment from a broader perspective, in addition to conventional localized treatment, and is expected to lead to improvement of chronic discomfort and prevention of recurrence.

[0145] To add to the aforementioned kinesiology, it can be said that kinesiology has two main aspects. One is its aspect as "kinesiology," which scientifically deals with bodily movement, and the other is its aspect as an alternative and complementary approach, such as "applied kinesiology," "Touch for Health," and "O-ring test," which use muscle reflex testing. In the latter, muscle reflexes (changes in muscle strength) are considered a "mirror" that reflects the state of the body, and weakened muscles are used as clues to explore and adjust imbalances in nutrition, posture, stress, meridians, etc., in an attempt to promote the body's self-healing power. In everyday use, it is sometimes applied as a tool to identify "things that don't suit you" by using latent reactions as clues.

[0146] Conventionally, since practitioner Y assesses the muscle response of patient X and performs treatment, it requires high skill and experience from practitioner Y, and the treatment results vary greatly depending on practitioner Y. Furthermore, it often relies on the subjective judgment of practitioner Y, and the reproducibility of the treatment is often insufficient. With the treatment support system 1 in this embodiment, even when performing treatment based on kinesiology, the affected area, cause of the discomfort, treatment method, and treatment results are objectively determined using response information, thereby improving the accuracy of the treatment.

[0147] The above describes an embodiment in which Treatment Support Service 1 supports alternative medicine treatments. However, the treatments supported by Treatment Support Service 1 are not limited to alternative medicine treatments. Treatment Support Service 1 can also be applied to treatment support in a wide range of medical and healthcare fields, such as medical examinations and treatments by physicians based on Western medicine, physical therapy, occupational therapy, orthopedic procedures, rehabilitation, cosmetic medicine, and various treatments aimed at health promotion. As a result, Treatment Support Service 1 can flexibly respond to treatments performed by physicians, physical therapists, and other medical professionals, contributing to improvements in the quality and efficiency of treatments.

[0148] <Formulating a hypothesis> As mentioned earlier, when various factors are intricately intertwined to cause discomfort, it is not easy to identify the affected area or its cause. When the analysis unit 112 of the treatment support device 10 requests the generation AI system 40 to identify the affected area, it can have the generation AI system 40 formulate a hypothesis and obtain treatment method information based on that hypothesis.

[0149] As an example, assuming that the heart and lungs are closely related as part of the circulatory system, the generating AI system 40 formulates the hypothesis (Hypothesis 1) that the heart and lungs have a master-servant relationship. Alternatively, the generating AI system 40 formulates the hypothesis (Hypothesis 2) that the lungs and heart have a master-servant relationship. In the treatment support system 1, if the results of the dysfunction identification process for a patient X indicate that there are problems with the heart and lungs, the practitioner Y interacts with patient X in the treatment method identification process shown in Figure 6, regarding performing treatment based on Hypothesis 1. If positive response information is obtained as a result of the interaction, the analysis unit 112 of the treatment support device 10 receives information from the generating AI system 40 indicating that treatment based on Hypothesis 1 should be performed as treatment method information. If improvement in the dysfunctional areas is found in the treatment result information obtained after the treatment, it can be seen that Hypothesis 1 was correct.

[0150] As another example, it is said that the brain and internal organs also have a molecular-level information transmission network structure mediated by exosomes. For example, the brain and heart are said to be closely connected and influence each other. Nerves, hormones, and bodily fluids are thought to exchange information via exosomes. In recent years, it has become clear that exosomes secreted from the brain and heart mediate inter-organ communication and influence inflammation, stress response, and repair. The generating AI system 40 formulates two hypotheses: Hypothesis A, in which the heart is primary and the brain is secondary, and Hypothesis B, in which the brain is primary and the heart is secondary. For example, suppose the analysis unit 112 of the treatment support device 10 interacts with patient X regarding performing treatment based on Hypothesis A and performing treatment based on Hypothesis B, and receives negative response information for both hypotheses. The generating AI system 40 then formulates Hypothesis C, which states that the roles of primary and secondary are mutually reversed. If improvement in the affected area is found in the treatment result information obtained after the treatment, it can be seen that Hypothesis C was correct.

[0151] As mentioned above, practitioner Y can perform treatment on patient X who is located remotely. For example, the generating AI system 40 hypothesizes (Hypothesis X) that for patient X, whose autonomic nervous system is sympathetic dominant, slow nasal breathing will shift the parasympathetic nervous system to dominant and cause the brainwaves to change from beta waves to alpha waves and theta waves. The generating AI system 40 proposes to patient X that the treatment method involve playing binaural beats, monaural beats, natural sounds (such as birdsong, wind, rain, and flowing water), their harmonics, and Schumann waves (electromagnetic waves). If positive response information from patient X is obtained as a result of the treatment, it will be determined that Hypothesis X was correct.

[0152] In the process of identifying the affected area shown in Figure 4, the analysis unit 112 of the treatment support device 10 requests the generation AI system 40 to formulate a hypothesis when requesting the generation AI system 40 to identify candidate affected areas. The analysis unit 112 generates, for example, the following prompt and sends it to the generation AI system 40.

[0153] "You are a generative AI skilled in clinical reasoning. Based on the following patient X information, please propose possible internal causal relationships and related hypotheses that may be underlying the chief complaint, "knee pain." Medical history: e.g., osteoarthritis of the knee, history of ankle sprains. Other symptoms: lower back pain, feeling of tightness in the hip joint • Muscle strength and range of motion test results: Example: Quadriceps weakness, limited knee flexion • Lifestyle habits: frequency of exercise, amount of time spent sitting, sleep patterns, etc. Based on the information above, please organize your thoughts on possible master-servant relationships between body parts such as the heart and lungs, and hypotheses such as the transition from knee pain to compensation and then to pain in other areas.

[0154] Subsequently, in step S14, the analysis unit 112 requests the generation AI system 40 to identify candidate areas of dysfunction based on the hypotheses formulated by the generation AI system 40. For the identified areas of dysfunction, a treatment method is identified using the treatment method identification process shown in Figure 6, and the treatment is performed. In step S64 of Figure 7, the analysis unit 112 requests the generation AI system 40 to verify the hypotheses. The generation AI system 40 generates information indicating the results of the hypothesis verification as treatment result information and transmits it to the treatment support device 10. If hypotheses are formulated for multiple different areas, the treatment support device 10 sequentially performs the area of ​​dysfunction identification process in Figure 4, the treatment method identification process in Figure 6, and the treatment result acquisition process in Figure 7 for each area, thereby causing the generation AI system 40 to verify the hypotheses. Naturally, the cause of dysfunction identification process in Figure 5 may also be performed as appropriate.

[0155] By having the AI ​​system 40 learn the results obtained from the hypotheses described above, it becomes possible to perform treatments that are more tailored to the specific needs of patient X.

[0156] <Note> In the following, the integration, evaluation, and utilization of different types of information, such as text, images, and sensor values, will be described as "multimodal." For convenience, this also includes cases where these types of information are handled across conceptual divisions (hereinafter referred to as "layers"). Note that "layers" may include the "Seventh Plane of Being" in ThetaHealing® proposed by Vianna Stibal, or the hierarchy (Focus 27) proposed by the Monroe Institute.

[0157] Multimodal therapy involves practitioner Y locating a specific multimodal layer and utilizing its characteristics to address the problem in order to resolve the cause or symptoms. In other words, multimodal therapy involves practitioner Y accessing a specific multimodal layer and utilizing its characteristics. It is believed that each multimodal layer possesses different energy states and information, and that there are solutions corresponding to each problem. This embodiment is also considered applicable to therapy related to multimodal layers.

[0158] For example, ionization therapy is one of the treatments that treatment support system 1 can assist with. This treatment method is thought to be able to remove contaminants from the affected area using plasma. Plasma is an aggregate of charged particles, a mixture of ions (particles with a positive charge) and electrons (particles with a negative charge). In ionization therapy, the properties of plasma are used to convert contaminants present in the affected area into harmless substances, thereby improving the patient's condition without putting a burden on their body. Ionization therapy is expected to provide safe and effective treatment.

[0159] For example, one of the treatments that can be supported by Treatment Support System 1 is antimatter bonding therapy. Antimatter bonding therapy is an approach to eliminate malignant parts of the affected area, and it is expected that after identifying the malignant part, antimatter will be used to neutralize that part. Antimatter is thought to consist of antimatter particles whose charge and spin are reversed compared to ordinary matter particles (protons, neutrons, electrons, etc.). When antimatter particles come into contact with ordinary matter, they are thought to collide and annihilate each other while releasing energy. By utilizing this property, it is expected that malignant parts can be eliminated from the affected area.

[0160] Furthermore, there is a concept called "zero magnetic field," which refers to a state where the influence of external magnetic fields is suppressed and all magnetic fields are eliminated. In a zero magnetic field, physical and mental disorders are reduced, and energy flows smoothly, making it an ideal state for mental balance and health. Treatment methods and therapeutic techniques utilizing zero magnetic fields have been developed, and some believe they contribute to stress reduction. The treatment support system 1 of this embodiment can also be used for treatments in alternative medicine as described above. While some aspects of these treatments are not yet scientifically established, further research is anticipated, and it can be said that there is potential for new developments as the generating AI collects more data.

[0161] Furthermore, activating the pineal gland is expected to enhance the effectiveness of alternative therapies. The pineal gland primarily secretes the hormone melatonin, which is involved in regulating the body clock and is thought to play an important role in regulating the sleep-wake rhythm. Some also believe that the pineal gland is related to changes in mental state and consciousness, and that it is involved in the perception of so-called "qi" or paranormal phenomena. There is a view that the pineal gland is important as a means of high-level communication between people, and between living things and the environment, and that communication allows for deeper levels of connection and understanding. In addition, the pineal gland is said to have strong connections with the hypothalamus, vagus nerve, and respiration.

[0162] Although the embodiments of the present invention have been described above, the present invention is not limited to the examples of embodiments described above, and various modifications are included. For example, the examples of embodiments described above are explained in detail to make the present invention easier to understand, and the present invention is not limited to having all the configurations described herein. Furthermore, it is possible to replace a part of the configuration of one example of an embodiment with the configuration of another example. It is also possible to add a configuration of another example to the configuration of one example of an embodiment. Furthermore, it is possible to add, delete, or replace a part of the configuration of one example of each embodiment with a configuration of another example. In addition, some or all of the above configurations, functions, processing units, processing means, etc., may be realized in hardware, for example, by designing them as integrated circuits. Also, the control lines and information lines in the figures are shown only if they are considered necessary for explanation, and do not necessarily show all of them. It can be assumed that almost all of the configurations are interconnected.

[0163] Furthermore, the functional configurations of the treatment support device 10, sensor group 20, practitioner terminal device 30, and generation AI system 40 described above are classified according to their main processing content for ease of understanding. The present invention is not limited by the way the components are classified or named. As shown above, the configurations of the treatment support device 10, sensor group 20, practitioner terminal device 30, and generation AI system 40 can be further classified into many more components depending on the processing content. Alternatively, a single component can be classified to perform even more processing. [Explanation of symbols]

[0164] 1: Treatment support system, 10: Treatment support device, 20: Sensor group, 21: Electromyography sensor, 22: Electromagnetic wave sensor, 23: Biophoton sensor, 24: Acceleration sensor, 30: Practitioner terminal device, 40: Generative AI system, 101: Processor, 102: Memory, 103: Storage, 104: Communication device, 105: Bus, 110-310: Processing unit, 111: Reaction acquisition unit, 112: Analysis unit, 113: Method request unit, 120-320: Memory unit, 130-330: Input unit, 140-340: Output unit, 150-350: Communication unit, 360: Abnormal area candidate display screen, N: Network, X: Patient, Y: Practitioner, a Upper lung region, b Central lung region, c Lower lung region, d Abdominal aorta, e Ureter, f Left kidney

Claims

1. A treatment support system that assists in providing alternative medicine treatments to patients, A response acquisition unit that acquires response information showing the recipient's reaction to the practitioner's actions, An analysis unit that uses AI, including a machine learning model, to analyze the reaction information and identify at least one of the malfunctioning part and the cause of the malfunction, An output unit that outputs the analysis results from the aforementioned analysis unit, A treatment support system characterized by comprising the following features.

2. A treatment support system according to claim 1, The output unit outputs the candidate malfunctioning parts identified by the analysis unit. The treatment support system is characterized in that the analysis unit identifies candidate areas of dysfunction and uses the response information to identify the areas of dysfunction.

3. A treatment support system according to claim 1 or 2, The output unit outputs candidate causes of malfunction in the candidate malfunctioning part identified by the analysis unit. The treatment support system is characterized in that the analysis unit identifies candidate causes of the disorder and identifies the cause of the disorder using the response information obtained in response to interventions on the candidate causes of the disorder.

4. A treatment support system according to claim 1 or 2, The output unit outputs the candidate malfunctioning part or candidate cause of malfunction identified by the analysis unit. The treatment support system is characterized in that the analysis unit obtains a degree of confidence for each candidate of the candidate of the problematic area or the candidate of the problematic cause based on the response information obtained by the response acquisition unit in response to the practitioner's actions on the candidate of the problematic area or the candidate of the problematic cause, and identifies the candidate of the problematic area or the candidate of the problematic cause whose degree of confidence meets a predetermined standard as the problematic area or the problematic cause.

5. A treatment support system according to claim 1 or 2, The treatment support system is characterized in that the reaction acquisition unit acquires reaction information indicating the muscle reaction of the practitioner or the person being treated, obtained using a contact-type sensor.

6. A treatment support system according to claim 1 or 2, The treatment support system is characterized in that the reaction acquisition unit acquires biological signals emitted by the practitioner or the person being treated, obtained using a sensor, as reaction information.

7. A treatment support system according to claim 6, The treatment support system is characterized in that the reaction acquisition unit acquires the biological signal using a biophoton sensor.

8. A treatment support system according to claim 1 or 2, The reaction acquisition unit acquires the biological data of the person being treated, The treatment support system is characterized in that the analysis unit identifies at least one of the affected area and the cause of the affected area by analyzing the biological data and the reaction information using the AI.

9. A treatment support system according to claim 2, The output unit displays the candidate areas of discomfort in the model image of the body of the person being treated, distinguishing them from other areas. A treatment support system characterized in that the aforementioned model image includes an image showing internal organs.

10. A treatment support system according to claim 1 or 2, The system includes a method request unit that requests treatment method information by identifying at least one of the affected area and the cause of the affected area identified by the analysis unit, The analysis unit identifies the treatment method information by analyzing at least one of the affected area and the cause of the affected area identified by the method request unit using AI including a machine learning model. The treatment support system is characterized in that the output unit outputs the treatment method information identified by the analysis unit.

11. A treatment support system according to claim 10, A treatment support system characterized in that the treatment method information includes electrotherapy, which involves applying an electric current to the skin of the person to be treated, or manual therapy performed by the practitioner.

12. A treatment support system according to claim 10, The method request unit requests the analysis unit to provide a pre-treatment image showing the subject before treatment based on the treatment method information identified by the analysis unit, and a post-treatment image showing the subject after treatment. The analysis unit acquires the pre-treatment image and the post-treatment image, The treatment support system is characterized in that the output unit outputs the pre-treatment image and the post-treatment image acquired by the analysis unit.

13. A treatment support system according to claim 10, The reaction acquisition unit acquires the reaction information of the person who received the treatment after the treatment, relating to the treatment method information identified by the analysis unit. The analysis unit analyzes the reaction information using AI including a machine learning model to identify treatment result information indicating the treatment result. The treatment support system is characterized in that the output unit outputs the treatment result information.

14. A treatment support method, which is performed by one or more computers, to support a treatment as an alternative medicine for a person receiving treatment, A response acquisition procedure for obtaining response information that shows the response of the person being treated to the practitioner's actions, An analysis procedure that uses AI, including a machine learning model, to analyze the reaction information and identify at least one of the affected area and the cause of the affected area, An output procedure for outputting the analysis results in the aforementioned analysis procedure, A treatment support method characterized by comprising the following features.

Images