WO2022220129A1 - 情報処理装置、情報処理方法およびプログラム - Google Patents

情報処理装置、情報処理方法およびプログラム Download PDF

Info

Publication number
WO2022220129A1
WO2022220129A1 PCT/JP2022/016126 JP2022016126W WO2022220129A1 WO 2022220129 A1 WO2022220129 A1 WO 2022220129A1 JP 2022016126 W JP2022016126 W JP 2022016126W WO 2022220129 A1 WO2022220129 A1 WO 2022220129A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
user
treatment method
information processing
obesity
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2022/016126
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
重一 中津川
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to JP2023514592A priority Critical patent/JPWO2022220129A1/ja
Publication of WO2022220129A1 publication Critical patent/WO2022220129A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/40—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for data related to laboratory analysis, e.g. patient specimen analysis
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems

Definitions

  • the present invention relates to an information processing device, an information processing method, and a program.
  • overcoming obesity is an essential process for health promotion.
  • Obesity is usually diagnosed and determined by BMI, which is calculated from height and weight.
  • BMI is calculated from height and weight.
  • a BMI of 25 or more or a waist circumference of 85 cm or more is considered obese in men
  • a BMI of 25 or more or a waist circumference of 90 cm or more is considered obese in women.
  • Body weight can change rapidly depending on the amount of water in the body.
  • severe obesity with a BMI of 35 to 40 or more to be complicated by heart failure.
  • patients with acute heart failure may gain weight of 2 kg or more in a week due to pleural effusion, ascitic effusion, generalized edema, etc., even though the amount of food is not changed.
  • edema may become prominent in renal dysfunction such as nephrosis. Therefore, it is dangerous to judge obesity only by weight gain.
  • symptomatic obesity due to overeating associated with underlying diseases includes overeating as an appetite-related eating disorder, Cushing's syndrome, hypothyroidism, hypogonadism, adult growth hormone hyposecretion, and polycystic obesity.
  • Weight gain due to endocrine (hormone) abnormalities such as ovarian syndrome and hypothalamic obesity, overeating associated with neuropsychiatric disorders such as depression and schizophrenia, overeating associated with pancreatic dysfunction such as diabetes and insulinoma, narcolepsy (no sleep) It may be associated with a wide range of disorders, such as metabolic abnormalities due to sleep apnea syndrome (SAS) and obesity associated with sleep apnea syndrome (SAS). In particular, it is important not to overlook heart failure, renal dysfunction, diabetes, Cushing's syndrome, sleep apnea syndrome, depression, psychiatric complications, developmental disorders, and the like.
  • obesity due to side effects of drugs includes adrenocortical hormones, that is, steroids, insulin and similar drugs, and hisrone. Recent studies have also revealed that some obesity cannot be denied a genetic influence. In particular, male obesity is thought to have a genetic predisposition. On the other hand, obesity in women is believed to play a greater role than heredity in lifestyle habits. However, it is also known that obesity is caused not by a single factor, but by multiple causes, including cognitive functions such as developmental disorders and depression, and neuropsychiatric functions, in individual cases.
  • the diaphragm does not fall sufficiently even during inspiration, which suppresses inspiration and reduces oxygen uptake, hindering fat burning and lipid abnormalities.
  • the diagnosis to clarify the cause of obesity depends on factors such as the cause, predisposing factors such as family history, personality, timing and duration of obesity, past treatment or intervention (number of times, timing, content) for obesity.
  • predisposing factors such as family history, personality, timing and duration of obesity, past treatment or intervention (number of times, timing, content) for obesity.
  • Individually optimized treatment of obesity according to efficacy, rebound risk, etc. is essential.
  • obesity has different treatment methodologies depending on its cause, age, environment, degree, duration, complications, and the like. For example, it is said that the risk of diabetes is high when the weight at birth is at the level of a premature baby, the declining birthrate, double income, unbalanced diet from childhood, obesity in the whole family, and stress due to bullying, unemployment, broken heart, etc.
  • Asians especially Japanese-specific reactions to stress are regulated by the amount of serotonin secreted in the brain (involved in mental stability and peace of mind) as shown below.
  • the amount of serotonin secreted is said to be determined by the type of serotonin transporter gene. That is, compared to Westerners, Asians have a lower percentage of people with the positive personality LL gene. (Asia is a hot and humid region with a high risk of infectious disease infection, and there is also a theory that a gene that makes the human body sensitive to the stress of external enemies was incorporated.) Only 3% of the total have an easy-going, optimistic, and positive personality. In other words, it is the ethnic group with the highest percentage of people with the negative personality type SS gene (easy to feel anxiety and high risk of developing depression) in the world. In addition, the middle is the hetero SL type.
  • Patent Document 1 discloses a technique for estimating a user's obesity level using the viscoelasticity of subcutaneous tissue or the oxygen level of the whole body as an index. For example, it is conceivable that the obesity level estimated by the technique of Patent Literature 1 may be used to identify treatment methods for obesity.
  • the therapeutic methods are, for example, various methods for treating obesity, such as psychotherapy, lifestyle improvement therapy including dietary guidance and exercise guidance, drug therapy, and surgical therapy.
  • an object of the present invention is to specify an individual optimum treatment method for obesity in consideration of the individual circumstances of the user.
  • an information processing apparatus includes information on a user's biometrics, information on the life of the user, information on the body of the user, information on the disease of the user, and An acquisition unit that acquires at least one piece of information about test results for the user, and by inputting the information acquired by the acquisition unit into a learned model, a treatment method for obesity of the user is specified. and a specific part.
  • the treatment method for obesity is individually optimally specified in consideration of the individual circumstances of the user.
  • FIG. 1 is a block diagram illustrating the configuration of an information processing apparatus according to an embodiment
  • FIG. It is a block diagram which illustrates the functional composition of a control device.
  • 4 is a flowchart showing an example of processing of a control device
  • FIG. 11 is a configuration diagram illustrating the configuration of an information processing device according to a modification
  • FIG. 11 is a configuration diagram illustrating the configuration of an information processing device according to a modification
  • FIG. 1 is a block diagram illustrating the configuration of an information processing device 100 according to an embodiment of the present invention.
  • the information processing device 100 is a device that specifies a treatment method for obesity of the user U (patient). An appropriate treatment method is specified to make the user U slim in a healthy manner.
  • the information processing apparatus 100 is typically used in medical facilities capable of treating obesity.
  • portable information terminals such as smartphones and tablets, or portable or stationary information terminals such as personal computers are preferably used as the information processing device 100 .
  • a specific treatment method will be described later.
  • the information processing apparatus 100 of this embodiment includes a control device 11, a storage device 13, a display device 15, and an operation device 17.
  • the display device 15 (for example, a liquid crystal display panel) displays various images under the control of the control device 11. In this embodiment, the treatment method specified by the information processing apparatus 100 is displayed.
  • the operation device 17 is an input device that receives input from the user U.
  • a plurality of operators that can be operated by the user U or a touch panel that detects contact with the display surface of the display device 15 is preferably used as the operation device 17 .
  • the control device 11 (an example of a computer) is composed of one or more processing circuits such as a CPU (Central Processing Unit), and controls each element of the information processing device 100 in an integrated manner.
  • a CPU Central Processing Unit
  • the storage device 13 is, for example, one or more memories configured with known recording media such as magnetic recording media or semiconductor recording media, and stores programs executed by the control device 11 and various data used by the control device 11.
  • a portable recording medium detachable from the information processing apparatus 100 or an external recording medium (for example, online storage) with which the information processing apparatus 100 can communicate via a communication network may be used as the storage device 13. good.
  • FIG. 2 is a block diagram illustrating the functional configuration of the control device 11.
  • the control device 11 of the present embodiment functions as a plurality of functions (acquisition unit 112, identification unit 114, display control unit 116) for identifying the treatment method K for obesity of the user U. do.
  • the functions of the control device 11 may be realized by a set of a plurality of devices (that is, a system), or part or all of the functions of the control device 11 may be realized by a dedicated electronic circuit (for example, a signal processing circuit). good too.
  • the treatment method K is specified according to information P about the user (hereinafter referred to as "user information").
  • user information P information P about the user
  • biometric information (hereinafter referred to as “biometric information” P1)
  • life information (hereinafter referred to as "life information” P2)
  • P3 Information about the user's body
  • P4 Information on the user's illness
  • illness information (hereinafter referred to as "illness information” P4)
  • Test information Information on test results for users (hereinafter referred to as "test information” P5)
  • biometric information P1, life information P2, physical information P3, disease information P4, and examination information P5 will be described later.
  • the user information P (P1-P5) is stored in the storage device 13 in advance under the operation of the operation device 17 by the user U or the person in charge (typically a medical worker such as a doctor).
  • the acquisition unit 112 acquires the user information P (P1-P5) stored in the storage device 13.
  • the specifying unit 114 specifies the treatment method K according to the user information P (P1-P5) acquired by the acquiring unit 112. Specifically, the specifying unit 114 inputs the user information P (P1-P5) to the learned model M to determine the treatment method K for obesity of the user U (treatment method for slimming down the user U). K) is identified. In this embodiment, one of a plurality of treatment methods prepared in advance is specified as the treatment method K for user U's obesity.
  • Multiple treatment methods include, for example, surgical therapy (e.g., sleeve gastrectomy, adjustable gastric banding surgery, gastric bypass surgery, surgery for slimming such as intragastric balloon placement), lifestyle improvement therapy (dietary guidance including carbohydrate restriction, exercise guidance, supplement intake), psychotherapy, cognitive behavioral therapy, drug therapy, educational hospitalization (including fasting therapy), specialized clinical departments (e.g., gynecology, endocrinology, metabolism, diabetes) Specialist, cardiology, pulmonology, gastroenterology, neuropsychiatry, surgery, neurosurgery, orthopedics, urology, dermatology, ophthalmology, otorhinolaryngology, sleep apnea outpatient, eating disorder outpatient, fecal transplantation) and follow-up.
  • surgical therapy e.g., sleeve gastrectomy, adjustable gastric banding surgery, gastric bypass surgery, surgery for slimming such as intragastric balloon placement
  • lifestyle improvement therapy dietary guidance including carbohydrate restriction
  • the plurality of treatment methods are candidates for the treatment method K to be presented to the user U.
  • a trained model M is a statistical estimation model (eg, a neural network) that generates an output B according to an input A.
  • the learned model M includes a program (for example, a program module constituting artificial intelligence software) that causes the control device 11 to execute a calculation that specifies an output B from an input A, and a plurality of coefficients that are applied to the calculation. It is realized in combination with A plurality of coefficients of the trained model M are optimized by prior machine learning (deep learning) using a plurality of teacher data in which the input A and the output B are associated. That is, the trained model M is a statistical estimation model that has learned the relationship between the input A and the output B. The trained model M generates a statistically valid output B for the input A under the tendencies (relationship between the input A and the output B) latent in the multiple teacher data used for machine learning. .
  • input A is user information P (P1-P5)
  • output B is treatment method K for obesity.
  • the user information P (P1-P5) of a patient who has undergone obesity treatment in the past and the training data that associates the treatment method that the patient was actually able to eliminate obesity can be used for machine learning. be done.
  • the specifying unit 114 inputs the user information P (P1-P5) to the learned model M, and outputs the result output by the learned model M (that is, one of a plurality of treatment methods). , as the treatment method K for the user U.
  • the display control unit 116 causes the display device 15 to display the treatment method K specified by the specifying unit 114 .
  • FIG. 3 is a flow chart illustrating the process of identifying the treatment method K from the user information P (P1-P5). For example, the processing in FIG. 3 is started in response to an instruction from a person in charge (typically a medical worker).
  • a person in charge typically a medical worker
  • the acquisition unit 112 acquires the user information P (P1-P5) stored in the storage device 13 (SA1).
  • the specifying unit 114 specifies a treatment method K for obesity of the user U from the user information P (P1-P5) acquired by the acquiring unit 112 (SA2).
  • the identification unit 114 identifies the output of the user information P (P1-P5) input to the learned model M as the optimal treatment method K for the user U.
  • the display control unit 116 causes the display device 15 to display the treatment method K specified by the specifying unit 114 .
  • biometric information P1, life information P2, physical information P3, disease information P4, and examination information P5 are described below.
  • the biological information P1 includes at least one of blood pressure, pulse rate, body temperature, and electrocardiogram information.
  • the information included in the biometric information P1 is not limited to the above examples.
  • the lifestyle information P2 includes meals (meal times, content, number of meals, presence or absence of snacks, frequency of eating out, food preferences, etc.), stress (presence or absence of stress in interpersonal relationships at home, school, or work), sleep (time, Napping/double sleeping, sleeping position, quality of sleep, snoring, etc.), bathing (time, temperature, use of sauna, shower head, etc.), luxury items (drinking, smoking, etc.) intake, frequency and amount of intake of milk, yogurt, coffee, tea, juice), exercise (existence of exercise habits, content, etc.), work (content, working hours, etc.), school, and family (family members living together) including at least one of information on age/gender, presence/absence of family caregiver, presence/absence of spouse, relative composition, etc.).
  • the information included in the lifestyle information P2 is not limited to the above examples.
  • the lifestyle information P2 may include information on daily consumption/calorie intake, information on urination (number of times during the day and at night, etc.), defecation, and the like.
  • Information related to the past life of the user U such as past smoking, past drinking, past exercise, etc., may also be included as the life information P2.
  • Physical information P3 includes age, gender, height, weight (including changes in weight such as sudden weight change or chronic obesity), BMI (Body Mass Index), body composition (for example, muscle mass , body fat percentage), and/or waist circumference information.
  • the information included in the physical information P3 is not limited to the above examples.
  • the physical information P3 may include the result of measuring each part of the user U (for example, muscle mass of limbs).
  • the disease information P4 includes at least one of medical history (including current disease history and past history) and information on subjective symptoms.
  • Medical history for example, current or past various diseases (various cancers, hypertension, cerebral disease, subarachnoid hemorrhage, cerebral hemorrhage, cerebral infarction, severe cerebral dysfunction, lipid abnormalities, high uric acid Hepatitis, fatty liver, liver cyst, sleep apnea syndrome, obesity-related kidney disease, renal cyst, emphysema, hydronephrosis, menstrual abnormality/pregnancy complications, ovarian dysfunction, ovarian tumor, ovarian cyst, ascites, anemia, Asthma), as well as information on ongoing follow-up illnesses and co-morbidities leading to obesity (e.g., symptomatic obesity, depression, schizophrenia, hypothyroidism, Cushing's syndrome, cardiovascular disease, type 1 diabetes) (including autoimmunity), impaired glucose tolerance, type 2 diabetes, pediatric diabetes, eating disorders, motor dysfunction, etc.), information
  • Subjective symptoms include, for example, overeating, weight gain, tachycardia, palpitations, shortness of breath, swelling, cough/sputum, oliguria, jugular venous distension, paroxysmal nocturnal dyspnea, tachypnea, orthopnea, nocturnal cough, and exertional breathing.
  • the information included in the disease information P4 is not limited to the above examples.
  • blood relatives for example, up to the third degree
  • the examination information P5 includes, for example, blood examination, biochemical examination, X-ray examination, CT (Computed Tomography) examination, MRI (magnetic resonance imaging)/MRA (magnetic resonance angiography) examination, and ultrasonic examination (for example, abdominal/lower abdominal and ultrasonography for thyroid) and urinalysis.
  • SITH-1 activated SITH-1
  • HHV-6 salivas virus type 6
  • glucocorticoids glucocorticoids
  • LDL cholesterol various pituitary and hypothalamic hormones (growth hormone, oxytocin, vasopressin, etc.), thyroid hormone, parathyroid hormone, various adrenal (cortical/medullary) hormones, cortisol, aldosterone, angiotensin II, ovarian hormone, insulin (C-peptide), adiponectin, ghrelin, leptin, various cytokines, anemia, hyperemia , leukocytosis/decrease, thrombocytopenia/increase, dehydration, natriuretic peptide, NT-proBNP, BNP, TNF- ⁇ , IL-6, CRP, ST2 (IL-33 receptor), erythropoietin, vitamin D , ⁇ 2-myoglobin, urea nitrogen, serum creatinine
  • lipopolysaccharide In biochemical tests, lipopolysaccharide, serum amylase, uric acid, Na, K, Cl, Ca, P, etc. are tested.
  • X-ray examination revealed cardiac shadow enlargement, presence/absence/degree of left ventricular hypertrophy, patchy shadow in the left lower lung field, presence/absence of pleural effusion, bronchial wall thickening, inflammatory emphysematous change, mediastinum, lung tumor, lymphadenopathy, chest Aortic aneurysm, degenerative spondylosis, etc. are examined.
  • CT examination revealed visceral fat, thickness of subcutaneous fat, fatty liver, fecal impaction in the colon, diverticulum of the colon, splenomegaly, hepatomegaly, liver cyst, liver tumor, gallstones, renal mass, aortic calcification, aortic enlargement, liver cyst. ⁇ Presence or absence of adrenal tumor, renal tumor, ascites, lymphadenopathy, uterine fibroids, ovarian tumor, bone cyst, etc. will be examined.
  • MRI/MRA tests show various cerebrospinal diseases including subdural hematoma and cerebral aneurysm, pituitary lesions (adenoma, etc.), inner ear/middle ear, thyroid lesions, head and neck tumors, spinal lesions such as spondylolisthesis and intervertebral disc herniation, etc. will be inspected.
  • Ultrasonography revealed goiter, thyroid cyst, thyroid tumor, fatty liver, visceral fat accumulation, pancreatic mass, fecal impaction in the transverse colon, renal cyst, liver cyst, gallstones, aortic calcification, aortic enlargement, ascites, and lymphadenopathy. Presence or absence of large uterine fibroids, ovarian tumors, ovarian cysts, subcutaneous fat thickness, renal echo level changes, renal enlargement, renal pelvic enlargement, hydronephrosis, renal atrophy, renal calcification or calculi, urinary tract stones, The presence or absence of bladder mass, hepatomegaly, and pancreatic mass (including cysts) is examined.
  • the information included in the examination information P5 is not limited to the above examples.
  • the results of a stool test may be included as the test information P5.
  • tests related to sleep apnea syndrome PSG test: all-night polysomnography test, simple test
  • physical findings lymphadenopathy, goiter, presence or absence of edema, etc.
  • auscultatory findings preence or absence of abnormal sounds in the lungs, arrhythmia, heart murmur, etc.
  • examination information P5 when information on the result of gynecological examination is used as examination information P5, the presence or absence of papillomavirus infection and papilloma subtyping are also examined in addition to smear cytological examination (in particular, atypical cells, candida infection, etc.).
  • smear cytological examination in particular, atypical cells, candida infection, etc.
  • the examinations exemplified above for example, for confirmation of the therapeutic effect, confirmation of the occurrence of side effects and complications, if necessary, during the treatment period, the results of re-examinations are used as examination information P5. good too.
  • the treatment method K for the obesity of the user U is specified. It is possible to appropriately specify the treatment method K for obesity by taking into consideration. That is, the user U is provided with the therapeutic method K individually optimized. In particular, there is an advantage that the optimal treatment method K is identified by considering all of the user U's living body, lifestyle, body, disease, and examination results.
  • the user information P is input by the user U or the person in charge (medical worker).
  • user information P that can be input by the user U himself for example, lifestyle information P2 and disease information P4
  • user information P that can only be input by the person in charge for example, biometric information
  • the information P1, the disease information P4, and the examination information P5) are input by the person in charge. Therefore, for example, the configuration of the information processing apparatus 100 illustrated in FIG. 4 is also employed.
  • the server device is used as the information processing device 100.
  • FIG. The server device of FIG. 4 can communicate with the terminal device G of the user U and the terminal device G of the person in charge D via a communication network N such as the Internet.
  • the user U and the person in charge D input user information P using their own terminal devices G, and the input user information P is transmitted to the information processing apparatus 100 .
  • the information processing device 100 specifies the treatment method K, and the treatment method K is transmitted to the terminal device G of the user U and the terminal device G of the person in charge D.
  • the terminal device G of the person in charge D may be equipped with the functions of the information processing device 100 .
  • the user information P input from the terminal device G of the user U is transmitted to the terminal device G of the person in charge D.
  • FIG. 4 and 5 it is not essential to transmit the treatment method K to the terminal device G of the user U.
  • an information terminal for example, a tablet or a smart phone
  • the information processing apparatus 100 and the information terminal can communicate with each other via a communication network such as the Internet or short-range wireless communication.
  • the user information P input by the user U through the terminal device is transmitted to the information processing device 100 .
  • the information processing device 100 identifies the treatment method K using the user information P transmitted from the terminal device.
  • the information processing device 100 may be realized by a server device that communicates with a terminal device (for example, a tablet or a smartphone) via a communication network such as the Internet.
  • a terminal device for example, a tablet or a smartphone
  • the user information P is transmitted from the terminal device to the information processing device 100, and the information processing device 100 uses the user information P to specify the treatment method K.
  • the identified treatment method K is transmitted to the terminal device.
  • the user information P on his/her own terminal device for example, for the user information P that can change
  • the user information is sent to the user U at a specific cycle (for example, every day).
  • information on meals e.g., content and amount of meals
  • information on luxury items e.g., presence or absence and amount of alcohol
  • information on sleep e.g., time, quality, sleep quality
  • information on exercise e.g., presence or absence and content of exercise
  • Information on bathing for example, time
  • information on weight for example, presence or absence of fatigue or headache
  • impressions/satisfaction with current treatment method K, etc. may change daily.
  • the information processing apparatus 100 may, for example, re-specify (that is, update) the treatment method K each time the user U inputs the user information P. That is, with the input of new user information P as a trigger, the process of specifying the treatment method K is executed again.
  • the identification unit 114 inputs the updated user information P to the learned model M as an element for re-identifying the treatment method K. Function. Therefore, it is possible to appropriately identify the treatment method K in consideration of changes in the user U.
  • the information processing apparatus 100 takes into account changes in the user information P over a predetermined period (for example, an average of the user information P over a predetermined period, a comparison with the user information P in the immediately preceding period, etc.).
  • a therapeutic method K may be specified.
  • the user information P can be input both before specifying the first treatment method K (that is, before treatment) and during treatment based on the treatment method K after specification. Even after the treatment method K is specified, the treatment method K is specified (updated) again each time the user information P is input (updated). Therefore, by inputting the user information P into the learned model at any time before and during the treatment, there is an advantage that the individually optimized treatment method K can be identified at each time.
  • the identification unit 114 may use the user information P to determine whether the user U is obese before identifying the treatment method K.
  • a learned model for example, is used to determine whether a person is obese or not. Then, the identifying unit 114 identifies the treatment method K from the user information P when determining that the user U is obese.
  • the biometric information P1, life information P2, physical information P3, disease information P4, and examination information P5 are all used as the user information P to specify the treatment method K.
  • the user information P used for is not limited to the above examples. At least one of the biological information P1, the living information P2, the physical information P3, the disease information P4, and the examination information P5 may be used to specify the treatment method K. However, from the viewpoint of specifying the treatment method K that is most suitable for the user, there is a configuration in which all of the biometric information P1, the living information P2, the physical information P3, the disease information P4, and the examination information P5 are used to specify the treatment method K. preferred.
  • various user information P can be used to specify the treatment method K.
  • the user information P may include information such as whether the user has undergone a breast cancer/colon cancer examination, or has undergone a detailed examination for breast cancer, uterine cancer, or colon cancer.
  • the user information P may include various information related to the user U, such as viewing time, intake of health foods and supplements, and the like.
  • the user information P includes various types of information
  • the acquisition unit 112 functions as an element for acquiring the user information P
  • the identification unit 114 learns the user information P acquired by the acquisition unit 112. It functions as an element for specifying the treatment method K by inputting to the finished model M.
  • the multiple treatment methods that are candidates for treatment method K include the above examples (lifestyle improvement therapy, psychotherapy, cognitive behavioral therapy, drug therapy, educational hospitalization, recommendation to see a specialized department, follow-up). Not limited.
  • CPAP therapy continuous positive airway pressure therapy
  • a plurality of therapeutic methods that are candidates for the therapeutic method K may be obtained by further subdividing each therapeutic method.
  • the identifying unit 114 may identify a specific drug using a learned model when identifying drug therapy as an appropriate treatment method K for the user U.
  • Specific drugs include, for example, Jindol, liraglitide, SGLT2 inhibitors (including oral drugs and injections), Xenical, various Kampo medicines (Bofutsushosan, Daisaikoto, Boukito, etc.), GLP These include -1 receptor agonists (administered by injection).
  • the identifying unit 114 identifies the lifestyle improvement therapy as an appropriate treatment method K for the user U
  • the specific contents of the meal for example, intake of each nutrient such as carbohydrates and protein
  • specific contents of exercise for example, exercise time of aerobic exercise, exercise time of anaerobic exercise, site where anaerobic exercise should be performed, etc. may be specified as the treatment method K.
  • the identifying unit 114 may identify two or more treatment methods among a plurality of treatment methods. For example, two or more high-ranking treatment methods are specified in the order of appropriate treatment methods for the user U output by the learned model. As understood from the above description, the identifying unit 114 functions as an element that identifies at least one of the plurality of treatment methods.
  • the user information P that can be input by the user U is preferably configured to be input to the information processing apparatus 100 as, for example, an answer to an interview.
  • the medical inquiry corresponding to each user information P is displayed on the display device 15 by the display control unit 116 of the terminal device.
  • the answer to the question may be selected from a plurality of options or may be written arbitrarily.
  • the input of the user information P by the user U may be performed via the user U's terminal device.
  • the information processing apparatus 100 is implemented by cooperation between a computer (specifically, the control device 11) and a program.
  • the program according to the above-described form can be provided in a form stored in a computer-readable recording medium and installed in the computer.
  • the recording medium is, for example, a non-transitory recording medium, and an optical recording medium (optical disc) such as a CD-ROM is a good example.
  • the non-transitory recording medium includes any recording medium other than transitory (propagating signal), and does not exclude volatile recording media. It is also possible to provide the computer with the program in the form of distribution via a communication network.
  • the present invention acquires at least one of the user information P (P1-P5) and inputs the acquired user information P into the learned model, thereby obtaining a treatment method K for obesity of the user U. It is also specified as a computer-implemented information processing method that specifies the
  • the score is 1, and if neither can be said, 3;
  • the treatment method K may be specified.
  • how to assign scores for each factor is as follows. Each of the following items is scored. In addition, when it corresponds to A of each item, it is judged that the sleep-promoting factor, appetite-suppressing factor, awakening-promoting factor, and appetite-promoting factor are sufficient, and 1 is added. On the other hand, if it corresponds to B of each item, it is judged that the wakefulness-promoting factor/appetite-promoting factor is high, and 5 is given. Add 3 if neither A nor B applies. Note that each of the following items is an example, and other items are also adopted as appropriate.
  • the score (total) is divided into multiple stages, and the optimal treatment method K is specified for each division. Since the higher the score, the more problematic it is judged, a more specialized treatment method K is specified. When specifying treatment method K, for example, if there are many problems with factors over a long period of time, it will be difficult to lose weight and improve physical condition, and it will be necessary to review lifestyle habits, etc., so this should also be taken into account. Identify K.
  • Item (a1) Stable environment (financial, living environment, family relations)
  • B Unstable environment (financial, living environment, family relations)
  • Item (a2) A: My family was healthy, and my diet and exercise were well balanced. B: In addition to obesity, there was a sick person in the family who went to the hospital or was hospitalized.
  • Item (a3) A: I had enough knowledge and information about my family's health. B: My family's health knowledge and information was insufficient.
  • Item (a4) A: No one in my family smoked or drank alcohol. B: Someone in my family smoked or drank alcohol.
  • Item (a5) A: I like exercise, and I was tired and slept well for more than 8 hours.
  • I was not good at exercise, and my sleep was as short as about 6 hours or less.
  • Item (a6) A: Life rhythms such as dinner, bathing, and bedtime are stable. B: Unstable life rhythm such as dinner, bathing, and bedtime.
  • Item (a7) A: Body weight was normal or below. B: Body weight increased, obese or tending to be obese.
  • Item (c5) A: After returning home, eat, take a bath, and go to bed without using a smartphone or computer. B: After returning home, first take a bath, eat, drink coffee while smoking, and go to bed while using a smartphone or a computer. Item (c6) A: None smoked or drank alcohol. B: I started smoking and drinking. Item (c7) A: The commuting time was short and I didn't feel tired. B: I had a long commute and was always tired and fell asleep. Item (c8) A: There was little stress, and I was devising a solution. B: A lot of stress, solved by eating meals and snacks. Item (c9) A: Body weight was stable within the standard weight. B: Body weight increased and decreased repeatedly, and the average weight exceeded the standard weight.
  • Item (d1) The environment (financial, living environment, family relations) is stable. B: Unstable environment (financial, living environment, family relations).
  • Item (e1) A I was able to understand the content of the work, and my work performance was good. B: I could not understand the contents of the work, and the work performance was poor.
  • Item (e5) He was in good health and had not undergone surgery or treatment. B: Had surgery or treatment for another disease.
  • Item (e6) A: Life rhythms such as dinner, bathing, and bedtime are stable. B: Unstable life rhythm such as dinner, bathing, and bedtime.
  • Item (e7) A: None smoked or drank alcohol. B: Started or resumed smoking or drinking.
  • Item (e8) A: The commuting time was short and I didn't feel tired. B: I have a long commute, and I am always tired and doze off.
  • Item (e9) A: My stress level is low and stable these days. B: I have been particularly stressed recently and have no time to exercise.
  • Item (e10) A: Body weight was stable within the standard weight. B: Body weight is increasing or decreasing, but on average exceeds standard weight.
  • Items that have an impact on obesity may be appropriately weighted and scored.
  • sleep time wake-up time
  • bedtime indoor/outdoor temperature
  • bedroom conditions sleeping environment
  • eating habits psychological conditions
  • tension digestive conditions
  • blood pressure at sleep onset Physical fatigue
  • lactic acid concentration adrenaline concentration
  • melatonin concentration orexin concentration
  • amino acid balance amount of exercise per day
  • calorie consumption change in height, pulse, BMI
  • sweating subjective symptoms related to sleep (e.g., snoring, rolling over, sleep apnea), past treatment status (e.g., diet therapy, exercise therapy, etc. for weight loss, but failed, etc.), etc.
  • sleep time wake-up time
  • bedtime indoor/outdoor temperature
  • bedroom conditions sleeping environment
  • eating habits psychological conditions
  • tension digestive conditions
  • blood pressure at sleep onset Physical fatigue
  • lactic acid concentration adrenaline concentration
  • melatonin concentration orexin concentration
  • amino acid balance amount of exercise per day
  • calorie consumption change in height, pulse, BMI
  • sweating subjective symptoms related to sleep (e.g., snor
  • the score for each disease For family members (for example, within the third degree) and own medical history, specify the score for each disease, and input the score assigned to the disease into the learned model M to specify the treatment method K. good too. For example, COVID-19 is assigned 5, various malignant tumors are assigned 10, and cardiovascular disease is assigned 3. Alternatively, the treatment method K may be specified by inputting the score specified for the drug currently being taken into the learned model M.
  • Subjective symptoms other than sleep-related symptoms e.g., overeating, tachycardia, palpitations, shortness of breath, swelling, cough/sputum, oliguria, heartburn, heavy stomach, constipation, disturbance of consciousness, stiff shoulders, joint pain, muscle pain, Muscle cramps, numbness, thinning hair, rash, acne, painful urination, feeling of residual urine, hematuria, lower abdominal pain, flank pain, increased urine output, frequent urination, bad breath, eye strain, anxiety, depression, positive thinking
  • the treatment method K may be specified by inputting the specified scores for the learned model M into the learned model M. Furthermore, a treatment method K may be specified by inputting a score about one's own personality into the learned model M.
  • the user information P includes various information related to sleep. Specifically, it is as follows.
  • the user information P is, for example, subjective symptoms related to sleep disorders (e.g., sleep deprivation, inability to sleep without alcohol, early morning awakening, snoring, dry mouth when waking up, daytime sleepiness (Epworth sleepiness scale), presence or absence of tossing and turning, etc. Subjective symptoms), sleep time (including time of day, wake-up time, bedtime, nap time and double sleep time, etc.), sleep environment (e.g.
  • sleep content e.g., quality of sleep, halfway
  • the user information P includes blood pressure, pulse rate, body temperature, electrocardiogram, meal (meal time, content, number of meals, presence or absence of snacks, frequency of eating out, food preference, etc.), stress (interpersonal behavior at home, school, work, etc.). relationship stress), bathing (time, temperature, use of sauna, shower only, etc.), luxury items (drinking/smoking/intake amount, milk/yogurt/coffee/tea/juice intake frequency) ⁇ Amount of intake), exercise (existence of exercise habits, content, etc.), work (content, working hours, etc.), school, family (age and gender of family members living together, presence or absence of nursing care family, spouse, relative composition, etc.) ), information on daily consumption/calorie intake, urination (number of times during the day and night, etc.)/defecation, smoking, alcohol consumption, exercise, age, gender, height, weight (rapid weight change or chronic obesity) body mass index (BMI), body composition (e.g., muscle mass, body fat percentage),
  • Cognitive-behavioral therapy is preferably specified as treatment method K for those who are the type to listen, judge, and act.
  • Psychotherapy is preferably identified as treatment method K for those who stand by their beliefs.
  • the user's personality and habits are determined according to the cause of obesity, family environment, age, gender, personality, family history, medical history, current degree of obesity, complications, duration of obesity, etc. To specify an individual optimum treatment method K according to the condition.
  • the therapeutic method K may be specified to recommend regular cancer screenings.
  • Control device 13 Storage device 15: Display device 17: Operation device 100: Information processing device 112: Acquisition unit 114: Identification unit 116: Display control unit D: Person in charge G: Terminal device K: Treatment method N: Communication network P: User information U: User

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Pathology (AREA)
  • Primary Health Care (AREA)
  • Epidemiology (AREA)
  • Physics & Mathematics (AREA)
  • Biophysics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Veterinary Medicine (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Medical Treatment And Welfare Office Work (AREA)
PCT/JP2022/016126 2021-04-12 2022-03-30 情報処理装置、情報処理方法およびプログラム Ceased WO2022220129A1 (ja)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2023514592A JPWO2022220129A1 (https=) 2021-04-12 2022-03-30

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2021067290 2021-04-12
JP2021-067290 2021-04-12

Publications (1)

Publication Number Publication Date
WO2022220129A1 true WO2022220129A1 (ja) 2022-10-20

Family

ID=83639640

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/016126 Ceased WO2022220129A1 (ja) 2021-04-12 2022-03-30 情報処理装置、情報処理方法およびプログラム

Country Status (3)

Country Link
JP (1) JPWO2022220129A1 (https=)
TW (1) TW202247191A (https=)
WO (1) WO2022220129A1 (https=)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024106526A1 (ja) * 2022-11-18 2024-05-23 テルモ株式会社 学習用データ生成方法、学習モデル生成方法、出力プログラム、学習用モデルデータ生成装置、学習用データ生成プログラム、出力装置及び出力方法

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2019067447A (ja) * 2016-02-11 2019-04-25 糧三 齋藤 がん予防・改善アドバイス装置
US20200005928A1 (en) * 2018-06-27 2020-01-02 Gomhealth Llc System and method for personalized wellness management using machine learning and artificial intelligence techniques

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2019067447A (ja) * 2016-02-11 2019-04-25 糧三 齋藤 がん予防・改善アドバイス装置
US20200005928A1 (en) * 2018-06-27 2020-01-02 Gomhealth Llc System and method for personalized wellness management using machine learning and artificial intelligence techniques

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
ANONYMOUS: "The Practical Guide to the Identification, Evaluation, and Treatment of Overweight and Obesity in Adults", NHLBI OBESITY EDUCATION INITIATIVE, 1 January 2000 (2000-01-01), XP055977610, Retrieved from the Internet <URL:https://www.nhlbi.nih.gov/files/docs/guidelines/prctgd_c.pdf> [retrieved on 20221103] *
MIZAYAKI SHIGERU: "Obesity clinical practice guidelines", JOURNAL OF THE JAPANESE SOCIETY OF INTERNAL MEDICINE, vol. 107, no. 2, 1 January 2018 (2018-01-01), pages 262 - 268, XP055977609 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024106526A1 (ja) * 2022-11-18 2024-05-23 テルモ株式会社 学習用データ生成方法、学習モデル生成方法、出力プログラム、学習用モデルデータ生成装置、学習用データ生成プログラム、出力装置及び出力方法

Also Published As

Publication number Publication date
TW202247191A (zh) 2022-12-01
JPWO2022220129A1 (https=) 2022-10-20

Similar Documents

Publication Publication Date Title
US20230329561A1 (en) System and Method for Personalized Telehealth Management with Dynamic Monitoring
Davidson Primary care for children and adolescents with Down syndrome
Dalle Grave Multistep cognitive behavioral therapy for eating disorders: theory, practice, and clinical cases
Groher et al. Dysphagia unplugged
Atlantis et al. Physical capacity outcomes in patients with severe obesity after 12 months of physician‐led multidisciplinary team care: a case series from a public hospital clinical obesity service
Rexach Palliative care in dementia
Chockalingam et al. Healthy aging and quality of life of the elderly
JP2023182415A (ja) 情報処理装置、情報処理方法およびプログラム
WO2022220129A1 (ja) 情報処理装置、情報処理方法およびプログラム
Voelker Assessing quality of life in gastric bypass clients
US20220084654A1 (en) Health management system
Steinbeck Adolescent overweight and obesity: how best to manage in the general practice setting
Spaeth Insufficient sleep and obesity
Srivastava et al. Pediatric Obesity: Causes, Prevention, and Treatment, An Issue of Pediatric Clinics of North America: Pediatric Obesity: Causes, Prevention, and Treatment, An Issue of Pediatric Clinics of North America, E-Book
JP2024034950A (ja) 情報処理装置、情報処理方法およびプログラム
WO2020117897A1 (en) Health management system
Khoo et al. Meal replacements for weight loss in obesity
Arora et al. The Curious Case of Alagille Syndrome: A Case Report With NANDA-I Classification, NIC, and NOC Linkage to the Patient Care Plan
Nazaruk et al. Nursing care and education of the family of a child with duchenne muscular dystrophy
WO2008014005A2 (en) Method to evaluate a client by a physical therapist
Trautner et al. Unintentional Weight Loss and Bilirubinuria in an Adolescent Female
San Giovanni et al. Obesity and Lipid Disorders
Malarvizhi et al. Lewis's Adult Health Nursing I & II (2 Volume Edition) with Complimentary Textbook of Professionalism, Professional Values and Ethics including Bioethics-E-Book: Lewis MSN_4SAE (2 Volume Edition) and Complimentary Textbook of Professionalism Professional Values and Ethics including Bioethics_1e-E-Book
Куцела Medical English Translation
Dawson Spinal Muscular Atrophy Type II, Implications for the Life Care Plan: A Case Study Involving Opposite-sex Siblings with Spinal Muscular Atrophy Type II

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22788054

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2023514592

Country of ref document: JP

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22788054

Country of ref document: EP

Kind code of ref document: A1