WO2022173201A2 - Procédé de pronostic du diabète sucré de type 2 après une chirurgie du cancer de l'estomac - Google Patents
Procédé de pronostic du diabète sucré de type 2 après une chirurgie du cancer de l'estomac Download PDFInfo
- Publication number
- WO2022173201A2 WO2022173201A2 PCT/KR2022/001945 KR2022001945W WO2022173201A2 WO 2022173201 A2 WO2022173201 A2 WO 2022173201A2 KR 2022001945 W KR2022001945 W KR 2022001945W WO 2022173201 A2 WO2022173201 A2 WO 2022173201A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- diabetes
- prognosis
- gastric cancer
- type
- cancer surgery
- Prior art date
Links
- 238000001356 surgical procedure Methods 0.000 title claims abstract description 112
- 238000000034 method Methods 0.000 title claims abstract description 89
- 208000005718 Stomach Neoplasms Diseases 0.000 title claims abstract description 86
- 206010017758 gastric cancer Diseases 0.000 title claims abstract description 86
- 201000011549 stomach cancer Diseases 0.000 title claims abstract description 86
- 238000004393 prognosis Methods 0.000 title claims abstract description 82
- 208000001072 type 2 diabetes mellitus Diseases 0.000 title claims abstract description 82
- 206010012601 diabetes mellitus Diseases 0.000 claims abstract description 102
- 238000012795 verification Methods 0.000 claims abstract description 20
- 229940079593 drug Drugs 0.000 claims abstract description 15
- 239000003814 drug Substances 0.000 claims abstract description 15
- 239000008280 blood Substances 0.000 claims abstract description 14
- 210000004369 blood Anatomy 0.000 claims abstract description 14
- 238000004364 calculation method Methods 0.000 claims abstract description 12
- 208000024891 symptom Diseases 0.000 claims abstract description 10
- 238000010801 machine learning Methods 0.000 claims description 22
- 229940100389 Sulfonylurea Drugs 0.000 claims description 13
- YROXIXLRRCOBKF-UHFFFAOYSA-N sulfonylurea Chemical class OC(=N)N=S(=O)=O YROXIXLRRCOBKF-UHFFFAOYSA-N 0.000 claims description 13
- 238000011282 treatment Methods 0.000 claims description 12
- 238000010200 validation analysis Methods 0.000 claims description 9
- 206010020772 Hypertension Diseases 0.000 claims description 6
- 238000002648 combination therapy Methods 0.000 claims description 6
- 238000013110 gastrectomy Methods 0.000 claims description 6
- 238000009097 single-agent therapy Methods 0.000 claims description 6
- 238000000611 regression analysis Methods 0.000 claims description 5
- 230000000391 smoking effect Effects 0.000 claims description 5
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 claims description 4
- 208000019693 Lung disease Diseases 0.000 claims description 4
- 238000011226 adjuvant chemotherapy Methods 0.000 claims description 4
- 239000008103 glucose Substances 0.000 claims description 4
- 238000007477 logistic regression Methods 0.000 claims description 4
- 238000007637 random forest analysis Methods 0.000 claims description 4
- 206010007559 Cardiac failure congestive Diseases 0.000 claims description 3
- 206010012289 Dementia Diseases 0.000 claims description 3
- 208000032928 Dyslipidaemia Diseases 0.000 claims description 3
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 claims description 3
- 206010019280 Heart failures Diseases 0.000 claims description 3
- 208000017170 Lipid metabolism disease Diseases 0.000 claims description 3
- 208000006011 Stroke Diseases 0.000 claims description 3
- 230000036772 blood pressure Effects 0.000 claims description 3
- 208000020832 chronic kidney disease Diseases 0.000 claims description 3
- 208000019423 liver disease Diseases 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 7
- 230000000750 progressive effect Effects 0.000 abstract 1
- 238000013528 artificial neural network Methods 0.000 description 9
- 201000010099 disease Diseases 0.000 description 9
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 9
- 230000036541 health Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 208000017667 Chronic Disease Diseases 0.000 description 5
- 208000024172 Cardiovascular disease Diseases 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 4
- HVYWMOMLDIMFJA-DPAQBDIFSA-N cholesterol Chemical compound C1C=C2C[C@@H](O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2 HVYWMOMLDIMFJA-DPAQBDIFSA-N 0.000 description 4
- 229940029980 drug used in diabetes Drugs 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 230000014509 gene expression Effects 0.000 description 3
- 230000002503 metabolic effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 206010028980 Neoplasm Diseases 0.000 description 2
- 235000012000 cholesterol Nutrition 0.000 description 2
- 230000001684 chronic effect Effects 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 208000029078 coronary artery disease Diseases 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001537 neural effect Effects 0.000 description 2
- 238000012502 risk assessment Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- PCTMTFRHKVHKIS-BMFZQQSSSA-N (1s,3r,4e,6e,8e,10e,12e,14e,16e,18s,19r,20r,21s,25r,27r,30r,31r,33s,35r,37s,38r)-3-[(2r,3s,4s,5s,6r)-4-amino-3,5-dihydroxy-6-methyloxan-2-yl]oxy-19,25,27,30,31,33,35,37-octahydroxy-18,20,21-trimethyl-23-oxo-22,39-dioxabicyclo[33.3.1]nonatriaconta-4,6,8,10 Chemical compound C1C=C2C[C@@H](OS(O)(=O)=O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2.O[C@H]1[C@@H](N)[C@H](O)[C@@H](C)O[C@H]1O[C@H]1/C=C/C=C/C=C/C=C/C=C/C=C/C=C/[C@H](C)[C@@H](O)[C@@H](C)[C@H](C)OC(=O)C[C@H](O)C[C@H](O)CC[C@@H](O)[C@H](O)C[C@H](O)C[C@](O)(C[C@H](O)[C@H]2C(O)=O)O[C@H]2C1 PCTMTFRHKVHKIS-BMFZQQSSSA-N 0.000 description 1
- 241000282326 Felis catus Species 0.000 description 1
- 206010022489 Insulin Resistance Diseases 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 235000021068 Western diet Nutrition 0.000 description 1
- 230000003178 anti-diabetic effect Effects 0.000 description 1
- 239000003472 antidiabetic agent Substances 0.000 description 1
- 206010003246 arthritis Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000007681 bariatric surgery Methods 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 201000011510 cancer Diseases 0.000 description 1
- 210000003169 central nervous system Anatomy 0.000 description 1
- 238000002512 chemotherapy Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000012850 discrimination method Methods 0.000 description 1
- 230000035622 drinking Effects 0.000 description 1
- 235000006694 eating habits Nutrition 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 230000005713 exacerbation Effects 0.000 description 1
- 235000013410 fast food Nutrition 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000002496 gastric effect Effects 0.000 description 1
- 208000035474 group of disease Diseases 0.000 description 1
- 208000019622 heart disease Diseases 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 208000017169 kidney disease Diseases 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 208000031225 myocardial ischemia Diseases 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 208000015122 neurodegenerative disease Diseases 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000002980 postoperative effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000002271 resection Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000013077 scoring method Methods 0.000 description 1
- 238000011125 single therapy Methods 0.000 description 1
- 210000000225 synapse Anatomy 0.000 description 1
- 230000000946 synaptic effect Effects 0.000 description 1
- 230000035488 systolic blood pressure Effects 0.000 description 1
Images
Classifications
-
- 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
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording for evaluating the cardiovascular system, e.g. pulse, heart rate, blood pressure or blood flow
- A61B5/021—Measuring pressure in heart or blood vessels
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value ; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid or cerebral tissue
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value ; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid or cerebral tissue
- A61B5/14532—Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value ; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid or cerebral tissue for measuring glucose, e.g. by tissue impedance measurement
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4058—Detecting, measuring or recording for evaluating the nervous system for evaluating the central nervous system
- A61B5/4064—Evaluating the brain
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4076—Diagnosing or monitoring particular conditions of the nervous system
- A61B5/4088—Diagnosing of monitoring cognitive diseases, e.g. Alzheimer, prion diseases or dementia
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4869—Determining body composition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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
-
- 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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- 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
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Definitions
- the present invention relates to a method for predicting the prognosis of diabetes, and more particularly, for a group of patients with a history of type 2 diabetes before gastric cancer surgery, a diabetes prediction score is calculated using various pre-operative clinical indicators and comparison with various machine learning techniques. And it relates to a method for predicting the prognosis of type 2 diabetes after gastric cancer surgery that provides accurate predictive data by verifying it.
- Cancer, heart disease, chronic lung disease, kidney disease, diabetes, high blood pressure, arthritis, etc. are called chronic diseases because they do not occur in an instant but progress to chronic degenerative diseases over a long period of time.
- Lifestyle-related diseases refer to a group of diseases that are affected by lifestyle habits such as eating habits, exercise habits, recreation, smoking, and drinking on the onset and progression of diseases.
- cardiovascular diseases such as high blood pressure, ischemic heart disease, coronary artery disease, and arteriosclerosis is rapidly increasing due to an increase in consumption of instant food or fast food harmful to the body, lack of activity, excessive work, and the like.
- disease risk assessment is used to prevent and manage cardiovascular disease.
- the Framingham risk score is used, and it is an index that evaluates the risk of cardiovascular disease through various cardiovascular risk factors such as gender, age, systolic blood pressure, smoking, diabetes, total cholesterol, and HDL cholesterol.
- diabetes is classified into either type 1 (early onset type) or type 2 (adult onset type), and type 2 accounts for 90-95% of cases of diabetes.
- Diabetes mellitus is the final stage of the disease process, which begins to act on individuals considerably long before the diagnosis is made.
- type 2 diabetes takes 10 to 20 years to develop, and occurs as a result of the failure of glucose utilization ability (use of glucose, import of glucose in peripheral tissues) due to insulin resistance failure.
- the score calculation methods for predicting the prognosis of type 2 diabetes are to calculate the remission probability of type 2 diabetes after bariatric metabolic surgery using several clinical indicators that can be easily obtained before surgery.
- type 2 diabetes patients who have undergone gastric cancer surgery experience various symptoms of diabetes progression, such as remission, improvement, unchanged, and aggravation after surgery.
- remission is a symptom of maintaining normal blood sugar in a state in which diabetes drugs are stopped after gastric cancer surgery
- improvement means a state in which blood sugar or drugs taken are decreased although the degree of remission is not reached, and maintenance is changed before and after gastric cancer surgery It is a state in which there is no blood sugar, and exacerbation means a state in which the amount of medication taken increases as blood sugar rises after surgery.
- AI artificial intelligence
- ML Machine Learning
- Deep Learning which is derived from artificial neural network algorithms, is a technology used to cluster or classify data using artificial neural networks.
- An artificial neural network refers to an overall model that has problem-solving ability by changing the strength of synaptic bonds through learning in which artificial neurons (nodes) that form a network by combining synapses.
- the core of deep learning using artificial neural networks is prediction through classification.
- neural networks are used to solve a wide range of problems, such as computer vision or speech recognition, that are typically difficult to solve with rule-based programming.
- a random forest that outputs a class (classification) or average prediction (regression analysis) from multiple decision trees constructed during the training process, and an extreme that creates a strong learner by sequentially adding predictors to correct previous errors
- Various machine learning techniques such as gradient boosting (XGBoost) and LASSO regression that takes the absolute value of the regression coefficient as a penalty term and sets the weight to '0' are used in computer vision, speech recognition, natural language processing, speech/signal Applied diabetes prognosis prediction programs with excellent performance applied to fields such as treatment are being developed.
- the present inventors calculated a diabetes prediction score using various clinical indicators before surgery for a group of patients with a history of type 2 diabetes before gastric cancer surgery, and various progression of type 2 diabetes after surgery through linking with a diabetes prognosis prediction application
- the present invention was completed by developing a method for predicting the prognosis of type 2 diabetes after gastric cancer surgery that can be improved.
- the purpose of the present invention is to provide a method for predicting the prognosis of type 2 diabetes after gastric cancer surgery that can provide accurate predictive data for various progressions of type 2 diabetes.
- the method for predicting the prognosis of type 2 diabetes after gastric cancer surgery of the present invention for achieving the above object includes the steps of: (a) classifying a target classifier into a basic group and a verification group according to the duration of gastric cancer surgery for a target patient group; (b) selecting a preoperative variable for predicting the diabetic prognosis for a certain period after gastric cancer surgery in the classified target patient group by the variable selection unit; (c) calculating, by a score calculation unit, a diabetes prediction score for evaluating the symptoms of diabetes progression according to the reference value of each variable by receiving the selected pre-operative variables; and (d) verifying the usefulness of the scoring system by a predictive ability verification unit receiving the calculated diabetes prediction score and calculating an area under the receiver manipulation characteristic curve for the base group and the verification group; It is characterized in that it includes.
- the target classification unit consists of patients who underwent gastric cancer surgery in the first period among the target patient group. It is characterized in that it is classified into a population and the validation group consisting of patients who underwent gastric cancer surgery in a second period after the first period.
- the variable selection unit is logistic regression It is characterized in that the preoperative variable predicting the prognosis of the type 2 diabetes is selected using a model.
- the selected preoperative variables of the method for predicting the prognosis of type 2 diabetes after gastric cancer surgery of the present invention for achieving the above object include age just before surgery, body mass index, gastric cancer surgery method, fasting blood sugar, and diabetes drug treatment data. characterized.
- the variable selection unit sets the selected preoperative variable as an independent predictor of the prognosis of secondary diabetes mellitus and gender, smoking status, alcohol consumption, exercise, income status, blood pressure, adjuvant chemotherapy, hypertension, dyslipidemia, congestive heart failure, lung disease, liver disease, chronic kidney disease, stroke, and dementia as adjusted predictors. It is characterized in that it can be set.
- the score calculator determines the diabetes according to sub-items of variables in addition to the reference values of the selected pre-operative variables. It is characterized in that the prediction score is calculated.
- the sub-items of the variable are, when the selected preoperative variable is a gastric cancer surgery method, partial gastric Combination therapy with sulfonylurea, combination therapy without sulfonylurea, sulfonylurea monotherapy and sulfonylurea, including resection and total gastrectomy, and when the preoperative variable selected is diabetes medication It is characterized in that it includes a monotherapy that does not include
- the score calculator gives weight to each variable with reference to the odds ratio of the selected pre-operative variables. It is characterized in that the diabetes prediction score is calculated.
- the predictive ability verifying unit uses the calculated diabetes prediction score as a predictive value of a model using a plurality of machine learning techniques. verifying the usefulness of the scoring system by comparing with It is characterized in that it further comprises.
- the plurality of machine learning techniques of the method for predicting the prognosis of type 2 diabetes after gastric cancer surgery of the present invention for achieving the above object include a random forest technique, an extreme gradient boosting technique, and a Lasso regression analysis technique. do.
- the present invention it is possible to effectively predict the various progressions of type 2 diabetes that may occur after gastric cancer surgery, so that the appropriateness of blood sugar management after surgery is remarkably improved, and side effects due to repeated prescription of diabetes drug treatment after surgery can prevent
- the patient can easily and conveniently self-diagnose the prediction of various progressions of type 2 diabetes through a diabetes prognosis prediction application installed on a portable terminal or the like.
- FIG. 1 is a block diagram of a system for implementing a method for predicting the prognosis of type 2 diabetes after gastric cancer surgery according to an embodiment of the present invention.
- FIG. 2 is a block diagram of the apparatus 100 for predicting diabetes prognosis in the prediction system shown in FIG. 1 .
- FIG. 3 is a flowchart for explaining the overall operation of the method for predicting the prognosis of type 2 diabetes after gastric cancer surgery according to an embodiment of the present invention.
- FIG. 4 is an operation flowchart for explaining the detailed operation of step S100 in the method for predicting the prognosis of type 2 diabetes shown in FIG. 3 .
- FIG. 5 is a table of statistics calculated for each preoperative variable selected in step S200 of the method for predicting the prognosis of type 2 diabetes shown in FIG. 3 .
- step S300 is a table of the diabetes prediction score calculated in step S300 of the method for predicting the prognosis of type 2 diabetes shown in FIG. 3 .
- FIG. 7 is a table of results compared with prediction values of a model using a plurality of machine learning techniques in step S500 of the method for predicting the prognosis of type 2 diabetes shown in FIG. 3 .
- FIG. 8 is a diagram showing the actual progression rate of type 2 diabetes remission compared to the diabetes prediction scores calculated for the learning group (a) and the validation group (b) in step S300 of the method for predicting the prognosis of type 2 diabetes shown in FIG. 3 .
- the component when it is described that a certain component is "exists in or connected to" of another component, the component may be directly connected to or installed in contact with the other component.
- they may be installed spaced apart from each other at a certain distance, and in the case where they are installed spaced apart by a certain distance, there may be a third component or means for fixing or connecting the corresponding component to another component. .
- a unit means a unit capable of processing one or more functions or operations.
- FIG. 1 is a block diagram of a system for implementing a method for predicting the prognosis of type 2 diabetes after gastric cancer surgery according to an embodiment of the present invention.
- an institution server 400 .
- FIG. 1 An operation of a system for implementing the method for predicting the prognosis of type 2 diabetes after gastric cancer surgery according to an embodiment of the present invention will be schematically described with reference to FIG. 1 as follows.
- Diabetes prognosis prediction apparatus 100 classifies the target according to the period of gastric cancer surgery for the target patient group, selects preoperative variables for predicting the diabetic prognosis for a certain period after gastric cancer surgery, and predicts diabetes according to the reference value of each variable Scores are calculated and verified.
- the portable terminal 200 is in the form of a notebook computer, tablet PC, or smart phone, is loaded with a diabetes prognosis prediction application, and receives the diabetes prediction score calculated from the diabetes prognosis prediction apparatus 100 through a wireless communication network to receive the user's diabetes prognosis symptoms to self-diagnose.
- the personal PC 300 is in the form of a desktop, etc., loaded with a computer diabetes prognosis prediction program, and receives the diabetes prediction score calculated from the diabetes prognosis prediction device 100 through a wired communication network to self-report the user's diabetes prognosis symptoms. make a diagnosis
- the institution server 400 is a business server for various medical institutions, health insurance companies, various insurance companies, etc., and interlocks with the diabetes prognosis prediction device 100 under the user's approval to provide the user's diabetes prognosis prediction data through a wired communication network.
- FIG. 2 is a block diagram of the apparatus 100 for predicting diabetes prognosis in the prediction system shown in FIG. 1 .
- FIG. 2 is provided.
- FIG. 3 is a flowchart for explaining the overall operation of the method for predicting the prognosis of type 2 diabetes after gastric cancer surgery according to an embodiment of the present invention.
- the present invention calculates a diabetes prediction score using various clinical indicators before surgery for a group of patients with a history of type 2 diabetes before gastric cancer surgery, and links with a diabetes prognosis prediction application or diabetes prognosis prediction program after surgery for type 2 diabetes
- the following algorithm is provided in order to provide predictive data for various progressions of diabetes to the portable terminal 200 , the personal PC 300 and/or the institutional server 400 .
- the target classification unit 110 classifies the target patient group into a basic group and a verification group according to the period of gastric cancer surgery (S100).
- the variable selection unit 120 selects pre-operative variables for predicting the prognosis of diabetes for a certain period after gastric cancer surgery in the target patient group classified by the target classification unit 110 ( S200 ).
- the score calculator 130 receives the pre-operative variables selected by the variable selector 120 and calculates a diabetes prediction score for evaluating the symptoms of diabetes according to the reference value of each variable (S300).
- the predictive ability verification unit 140 receives the diabetes prediction score calculated by the score calculation unit 130 and calculates the area under the receiver manipulation characteristic curve for the base group and the verification group to verify the usefulness of the scoring system (S400).
- the prediction ability verification unit 140 compares the diabetes prediction score calculated by the score calculation unit 130 with prediction values of a model using a plurality of machine learning techniques to verify the usefulness of the scoring system ( S500 ).
- step S100 is an operation flowchart for explaining the detailed operation of step S100 in the method for predicting the prognosis of type 2 diabetes shown in FIG. 3 .
- FIG. 5 is a table of statistics calculated for each preoperative variable selected in step S200 of the method for predicting the prognosis of type 2 diabetes shown in FIG. 3 .
- step S300 is a table of the diabetes prediction score calculated in step S300 of the method for predicting the prognosis of type 2 diabetes shown in FIG. 3 .
- FIG. 7 is a table of results compared with prediction values of a model using a plurality of machine learning techniques in step S500 of the method for predicting the prognosis of type 2 diabetes shown in FIG. 3 .
- FIG. 8 is a diagram showing the actual progression rate of type 2 diabetes remission compared to the diabetes prediction scores calculated for the learning group (a) and the validation group (b) in step S300 of the method for predicting the prognosis of type 2 diabetes shown in FIG. 3 .
- An embodiment of the present invention was performed by collecting data from 5,150 patients who underwent gastric cancer surgery based on data from the Korea National Health Insurance Corporation.
- the target classification unit 110 classifies 61,179 patients who underwent gastric cancer surgery from 2002 to 2003 into the following 5 groups.
- the first subject (n 13,006) with a prior history of other cancers or chemotherapy within 2 years prior to the index date, had a code for diabetes or antidiabetic medication within 2 years prior to the index date.
- variable selection unit 120 performs an operation for predicting the prognosis of type 2 diabetes for a certain period after gastric cancer surgery, for example, 3 years, using a logistic regression model for a chronic disease patient who had a history of diabetes before gastric cancer surgery. Select all variables.
- logistic regression analysis is about which variable affects one dependent variable, which variable has the greatest influence among those variables, and what is the most appropriate model to explain the dependent variable?
- regression analysis which is a statistical method to reveal cognition, it refers to a statistical method mainly used when the dependent variable is a dichotomous variable that divides the group into two groups.
- Preoperative variables include age before surgery, body mass index (BMI), gastric cancer surgery method, fasting blood sugar, and diabetes drug treatment data.
- Such data may be provided with a health checkup cohort database through the health care big data open system of the Health Insurance Corporation Review and Assessment Service, which corresponds to the institutional server 400 , or may be provided with a treatment database of a medical institution.
- the score calculation unit 130 receives the pre-operative variables selected by the variable selection unit 120 and calculates a diabetes prediction score by differentially applying the preoperative variables according to the reference values or sub-items of each variable.
- the odds ratio refers to a value obtained by comparing the probability of occurrence of the same event in an individual or one group with the probability of occurrence in another individual or another group.
- diabetes may be compared and analyzed with reference diabetes (eg, 100 mg/dL) to calculate a score indicating relatively good or bad information about the user's health based on the difference between the comparison values.
- reference diabetes eg, 100 mg/dL
- the odds ratio of the gastric cancer surgical method for total gastrectomy patients is 1.46.
- the five preoperative variables are independent predictors of the prognosis of secondary diabetes after gastric cancer surgery, and the variables of the fully controlled predictive model include sex, smoking status, alcohol consumption, exercise, income status, blood pressure, and adjuvant chemotherapy (adjuvant chemotherapy). ), hypertension, dyslipidemia, congestive heart failure, lung disease, liver disease, chronic kidney disease, stroke and dementia.
- the event is counted as the number of medical-related activities associated with the probability of developing secondary diabetes, and the medical-related activity may include treatment at a hospital, prescription, or health checkup, and diabetes drug treatment data is the number of drug components. is counted as
- the score calculation unit 130 calculates a diabetes prediction score out of a maximum of 14 points for the five pre-operative variables selected by the variable selection unit 120 .
- a score of '0' is given if the age before surgery is 65 years or older, and a score of '1' if the age is under 65.
- the sub-item is '0' when the sub-item is combination therapy containing sulfonylurea, and '4' when the sub-item is combination therapy without sulfonylurea.
- the surgical method for gastric cancer is total gastrectomy
- the age immediately before surgery is less than 65 years
- the fasting blood sugar is 130 or less
- the diabetes drug treatment is monotherapy without sulfonylurea.
- a total score of '14' is applied.
- the predictive ability verification unit 140 calculates an area under the ROC curve of a receiver operating characteristic (ROC), divides the target patient group into a training cohort and a validation cohort, and scores a score Verify the usefulness of the system.
- ROC receiver operating characteristic
- the receiver operation characteristic is a graph for evaluating the performance of the classification model, and represents the performance according to a threshold value that divides true '1' and false '0', and the area under the receiver operation characteristic curve is '1' ' means a classification model with better performance.
- the diabetes prediction score calculated by the score calculation unit 130 for the classified basic group, that is, the training cohort and the verification group, the prediction ability verification unit 140 performs machine learning (machine learning). learning) method and compare it with the predicted values of the models.
- the diabetes prediction score calculated according to an embodiment of the present invention for the learning group and the verification group has an area under the receiver manipulation characteristic curve of 0.73 and 0.72, respectively, of the random forest among the machine learning techniques mentioned in the background art. 0.75, 0.71, 0.74, 0.70 for extreme gradient boosting (XGBoost), and 0.75 and 0.75 for LASSO regression analysis, which are almost identical at 95% confidence intervals.
- XGBoost extreme gradient boosting
- LASSO regression analysis which are almost identical at 95% confidence intervals.
- the prediction ability verification unit 140 of the present invention compares the diabetes prediction score calculated by the score calculation unit 130 with the prediction value of the model using the machine learning techniques to verify the usefulness of the prediction ability of the scoring system.
- the overall diabetes prediction score was higher It can be seen that the higher the rate of type 2 diabetes remission progressed, and the longer the number of years of gastric cancer surgery for each score, the lower the rate of type 2 diabetes remission progressed.
- the proportion of patients who maintain normal blood sugar after stopping diabetes medication It decreases in inverse proportion to this.
- the present invention calculates a diabetes prediction score using various clinical indicators before surgery for a group of patients with a history of type 2 diabetes before gastric cancer surgery, and connects with a diabetes prognosis prediction application or diabetes prognosis prediction program after surgery
- a method for predicting the prognosis of type 2 diabetes after gastric cancer surgery, which can provide accurate predictive data for various progressions of type 2 diabetes, is provided.
- the present invention can effectively predict the various progression of type 2 diabetes that may occur after gastric cancer surgery, so that the appropriateness of blood sugar management after surgery is remarkably improved, and side effects caused by repeated prescription of diabetes drug treatment after surgery It can be prevented.
- the patient can easily and conveniently self-diagnose the prediction of various progressions of type 2 diabetes through the diabetes prognosis prediction application installed on the portable terminal or the like.
- the present invention provides accurate predictive data by calculating and verifying diabetes prediction scores using various pre-operative clinical indicators and comparison with various machine learning techniques for a group of patients with a history of type 2 diabetes before gastric cancer surgery. It relates to a method for predicting the prognosis of type 2 diabetes, which remarkably improves the adequacy of blood sugar management after surgery, can prevent side effects caused by repeated prescription of diabetes medication after surgery, and allows patients to easily and conveniently self-report through applications, etc. Since the diagnosis is possible and the prediction accuracy is high, it can be usefully used in the field of diagnosing type 2 diabetes.
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Biophysics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Heart & Thoracic Surgery (AREA)
- Veterinary Medicine (AREA)
- Databases & Information Systems (AREA)
- Neurology (AREA)
- Physiology (AREA)
- Theoretical Computer Science (AREA)
- Cardiology (AREA)
- Software Systems (AREA)
- Psychology (AREA)
- Neurosurgery (AREA)
- Computing Systems (AREA)
- Vascular Medicine (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Optics & Photonics (AREA)
- Psychiatry (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Emergency Medicine (AREA)
- Hospice & Palliative Care (AREA)
Abstract
La présente invention divulgue un procédé de pronostic du diabète sucré de type 2 après une chirurgie du cancer de l'estomac. Le procédé comprend les étapes dans lesquelles : (a) une partie de classification de cible classifie une population de patients cibles en un groupe de base et un groupe de vérification selon la période de chirurgie du cancer de l'estomac ; (b) une partie de sélection de variables sélectionne une variable préopératoire pour effectuer un pronostic du diabète sucré pendant une certaine période de temps après une chirurgie du cancer de l'estomac dans les groupes de patients cibles classifiés ; (c) une partie de calcul de score reçoit les variables préopératoires sélectionnées et calcule un score de prédiction de diabète pour évaluer des symptômes progressifs du diabète en fonction de la valeur de référence de chaque variable ; et (d) une partie de vérification de capacité de prédiction reçoit le score de prédiction de diabète calculé et calcule la zone sous la courbe caractéristique d'opération de récepteur pour le groupe de base et le groupe de vérification pour vérifier l'utilité du système de score. Selon la présente invention, diverses procédures de progression du diabète sucré de type 2 qui peuvent se produire après une chirurgie du cancer de l'estomac peuvent être efficacement prédites, ce qui permet d'améliorer considérablement la gestion pertinente des taux de glycémie et d'empêcher les effets secondaires attribués à des prescriptions répétées de médicaments pour le diabète sucré après une chirurgie.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020210018747A KR102510347B1 (ko) | 2021-02-10 | 2021-02-10 | 위암 수술 이후 제2형 당뇨병 예후의 예측 방법 |
| KR10-2021-0018747 | 2021-02-10 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| WO2022173201A2 true WO2022173201A2 (fr) | 2022-08-18 |
| WO2022173201A3 WO2022173201A3 (fr) | 2022-10-06 |
Family
ID=82837800
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/KR2022/001945 WO2022173201A2 (fr) | 2021-02-10 | 2022-02-09 | Procédé de pronostic du diabète sucré de type 2 après une chirurgie du cancer de l'estomac |
Country Status (2)
| Country | Link |
|---|---|
| KR (1) | KR102510347B1 (fr) |
| WO (1) | WO2022173201A2 (fr) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2313773A1 (fr) | 2008-07-15 | 2011-04-27 | Metanomics Health GmbH | Moyens et méthodes de diagnostic d un pontage gastrique et des pathologies liées à celui-ci |
| CA2948575C (fr) * | 2014-05-16 | 2023-08-08 | Corcept Therapeutics, Inc. | Systemes et procedes de gestion du traitement d'un etat chronique par suivi de symptome |
| US11404166B2 (en) * | 2016-09-28 | 2022-08-02 | Medial Research Ltd. | Systems and methods for mining of medical data |
| KR102024373B1 (ko) * | 2016-12-30 | 2019-09-23 | 서울대학교 산학협력단 | 대사이상 질환의 질병 위험도를 예측하는 장치 및 방법 |
| KR102467999B1 (ko) * | 2019-06-27 | 2022-11-17 | 서울대학교산학협력단 | 위암의 다층 다요인 패널과 Computational biological network modeling을 통한 위암 발암에 대한 에티옴 모형 |
-
2021
- 2021-02-10 KR KR1020210018747A patent/KR102510347B1/ko active IP Right Grant
-
2022
- 2022-02-09 WO PCT/KR2022/001945 patent/WO2022173201A2/fr active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| KR102510347B1 (ko) | 2023-03-20 |
| KR20220115723A (ko) | 2022-08-18 |
| WO2022173201A3 (fr) | 2022-10-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Aggarwal | Data augmentation in dermatology image recognition using machine learning | |
| WO2018124854A1 (fr) | Dispositif et procédé de prédiction du risque de maladie rénale chronique | |
| KR20190030876A (ko) | 건강 위험 예측 방법 | |
| EP3979258A1 (fr) | Analyse et suivi de cicatrisation | |
| Solomon et al. | Extensive review on the role of machine learning for multifactorial genetic disorders prediction | |
| Hassan et al. | Early predictive analytics in healthcare for diabetes prediction using machine learning approach | |
| WO2022211385A1 (fr) | Système de consultation de soins de santé utilisant la distribution de valeurs de prédiction de maladie | |
| Rémy et al. | The prediction of good physicians for prospective diagnosis using data mining | |
| Agashua et al. | Predicting dietary non-compliance of patients on intermittent haemodialysis | |
| Mandava | MDensNet201-IDRSRNet: Efficient cardiovascular disease prediction system using hybrid deep learning | |
| WO2022173201A2 (fr) | Procédé de pronostic du diabète sucré de type 2 après une chirurgie du cancer de l'estomac | |
| KR20220101571A (ko) | 빅데이터 기반 딥러닝 모델을 이용한 응급실 환자 진단 시스템 및 방법 | |
| Polak et al. | Artificial intelligence technology as a tool for initial GDM screening | |
| KR20190031192A (ko) | 건강 위험 예측 방법 | |
| TW202211258A (zh) | 高齡流感病情預測系統、程式產品及其建立與使用方法 | |
| Saal | Prenatal diagnosis: when the clinician disagrees with the patient's decision | |
| EP3776593A1 (fr) | Procédé et dispositif électronique de détection d'état de santé assistée par intelligence artificielle (ai) dans un réseau de l'internet des objets | |
| Schneider et al. | The use of the Nursing Interventions Classification (NIC) with cardiac patients receiving home health care | |
| Lee et al. | Wearable-based kinematic analysis of upper-limb movements during daily activities could provide insights into stroke survivors’ motor ability | |
| Karim et al. | and Augmented Reality | |
| WO2020142035A1 (fr) | Système de diagnostic de maladie | |
| WO2024096464A1 (fr) | Procédé et dispositif de recommandation d'un produit | |
| WO2024117528A1 (fr) | Procédé et système de prédiction du diabète sucré en utilisant des données cliniques et des données génétiques appliquées à une fréquence spécifique à une race | |
| WO2022203140A1 (fr) | Système et procédé d'aide à la décision clinique concernant une lésion rénale aiguë à l'aide d'un modèle de prédiction de réseau neuronal récurrent | |
| WO2024147552A1 (fr) | Procédé et appareil de détermination de l'âge de santé |
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: 22752961 Country of ref document: EP Kind code of ref document: A2 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 22752961 Country of ref document: EP Kind code of ref document: A2 |