WO2017105196A1 - Système multi-agents d'assistance pour un diagnostic médical - Google Patents

Système multi-agents d'assistance pour un diagnostic médical Download PDF

Info

Publication number
WO2017105196A1
WO2017105196A1 PCT/MX2015/000204 MX2015000204W WO2017105196A1 WO 2017105196 A1 WO2017105196 A1 WO 2017105196A1 MX 2015000204 W MX2015000204 W MX 2015000204W WO 2017105196 A1 WO2017105196 A1 WO 2017105196A1
Authority
WO
WIPO (PCT)
Prior art keywords
sma
data
data matrix
cleaning
medical
Prior art date
Application number
PCT/MX2015/000204
Other languages
English (en)
Spanish (es)
Inventor
Pedro Gabriel GONZALEZ ESTRADA
Ramon SOTO DE LA CRUZ
Jose Alberto MEDINA COVARRUBIAS
Martin Eugenio LARIOS VELARDE
Original Assignee
Gonzalez Estrada Pedro Gabriel
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 Gonzalez Estrada Pedro Gabriel filed Critical Gonzalez Estrada Pedro Gabriel
Priority to PCT/MX2015/000204 priority Critical patent/WO2017105196A1/fr
Publication of WO2017105196A1 publication Critical patent/WO2017105196A1/fr

Links

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
    • G16H50/20—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
    • G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
    • G16Z99/00—Subject matter not provided for in other main groups of this subclass

Definitions

  • the present invention has its preponderant field of application in the medical field, particularly in those activities where it is necessary to obtain suggestions regarding a diagnosis using the architecture of a neuron network!
  • the present approach shows a novel method for obtaining the proposal of a diagnosis, taking as reference a database that includes the information of a large group of patients, recording different variables,
  • the procedure is based on the analysis of the database through the use of a Multiagent System that includes different dosing methods, the four propose the diagnosis of a patient. It has the peculiarity of being adaptive and generic.
  • the invention WO 2013045725 A2 presents a multiagent electronic device and procedure with diffuse control, by means of which the detection of stroke or stroke (CVA) is assisted, specifically through the detection of one of its main symptoms: the lack of mobility in the opposite body to the cerebral location of the stroke.
  • CVA stroke or stroke
  • the invention WO 2012136874 A1 shows a method of characterization and classification of kidney stones, applying the Artificial Neural Networks (ANN) technique for classification.
  • ANN Artificial Neural Networks
  • the invention WO 2010084211 A1 presents a device and a method for the defection of the alternation of cardiac ventricular repolarization. It is used to set e! diagnosis of heart diseases by means of peak detection techniques through neural networks.
  • the invention US 5333240 A indicates a diagnostic system for the condition of electrical equipment. The system is constructed of a neural network model to learn in advance, of one or more information samples, about the vibrations that occur in a specific operating state of the equipment.
  • the invention WO 2001026026 A2 relates to a method and system for the diagnosis of a medical condition.
  • a specific embodiment of the present invention uses a plurality of neural networks in a corresponding plurality of clinical sites to assist physicians in diagnosing a patient's medical condition.
  • the server can receive patient data that includes, for example, images, patient information, parameters, biopsy information, and medical diagnoses.
  • the central neural network can be trained in a large volume of medical cases, which come from the plurality of clinical sites. The neural network at a site can thus help a doctor to reliably determine the nature and probability of a medical condition, even when it is dependent on a wide variety of patient data and the condition is relatively rare.
  • the invention WO 2004047624 A2 indicates methods and systems for providing a clinically modeled automatic diagnosis of the patient's health.
  • One embodiment uses a medical device and the network to analyze patient data in a manner consistent with a standard of medical care.
  • the invention WO 2005081168 A2 provides cardiac imaging systems and applications, which implement methods to automatically extract and analyze the characteristics of a collection of patient information (including image data and / or non-image data) of a patient subject, and provide support in the decisions of the various aspects of medical workflow.
  • the invention WO 1997029447 A2 provides methods for the selection of medical and biochemical diagnostic tests using decision support systems, such as neural networks.
  • Patient data or information usually patient history or clinical data, is analyzed by decision support systems to identify important variables or relevant.
  • Decision support systems are trained in patient data and are complemented with biochemical test data to refine performance.
  • WO 2001069513 A2 there is a system and method for obtaining, processing and evaluating the information of a patient for the diagnosis of a disease and the selection of treatment based on medical records.
  • the automatically analyzed database of historical medical information is used as a search tool to determine the diagnosis and treatment of each identified medical problem.
  • Figure 1 shows the first stage of the method
  • FIG. 1 shows the general scheme of the proposal
  • Figure 3 shows the scheme of a characteristic of the SMA
  • Figure 4 shows the flow chart of the method
  • Figure 1 shows the basic elements of this proposal. From a real situation such as the presence of a disease, information is obtained that will support the analysis. The variables to be studied are determined and for each patient the observations are recorded. An analysis of the data matrix is necessary for the detection of missing data that could affect the estimates. The use of the Case Based Reasoning (RBC) method is proposed to clean the data matrix.
  • RBC Case Based Reasoning
  • FIG 2 shows the general scheme of work of the method. From a matrix of clean data, obtained after the application of the missing data treatment (RCB), the training of the neural network for the configuration of the architecture of the Multiagent System (SMA) is carried out.
  • the SMA consists of methods or classifying agents such as Artificial Neural Networks (RNA), Expert Systems (SE), Case Based Reasoning (RBC) and / or Bayesian Classifiers (CB).
  • RNA Artificial Neural Networks
  • SE Expert Systems
  • RBC Case Based Reasoning
  • CB Bayesian Classifiers
  • Figure 3 shows the scheme of the adaptive characteristic of an SMA, which consists in the partial or total replacement of a classifying method or agent. That is, according to the results it is detected that a method does not work according to what is expected and then another technique can be chosen. Or, an alternative version of the same method can be applied.
  • Figure 4 shows the flow chart of the method, where the start is determined from a database. It is very important to detect missing data, since this situation affects the estimates to be made, so it is necessary to perform a cleaning. Subsequently, the training of a neural network that will shape the architecture of the SMA Multiagent System is carried out, through which the diagnostic proposal will be provided. According to obtaining new data sets and proposals for new classification methods, adjustments are made to the SMA.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • Public Health (AREA)
  • Pathology (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

L'invention concerne un procédé mis en oeuvre dans une communauté médicale, lequel permet l'obtention de propositions de diagnostic, avec les étapes consistant: a. à enregistrer une matrice de données médicales; b. à détecter la nécessité de nettoyage de données, en cas de données manquantes; c. à entraîner le réseau neuronal préalablement à la configuration du système; d. à déterminer des méthodes ou des agents de classification; e. à intégrer un système multi-agents SMA; f. à générer une proposition de diagnostic; g. à ajuster le SMA par adaptation de celui-ci.
PCT/MX2015/000204 2015-12-17 2015-12-17 Système multi-agents d'assistance pour un diagnostic médical WO2017105196A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/MX2015/000204 WO2017105196A1 (fr) 2015-12-17 2015-12-17 Système multi-agents d'assistance pour un diagnostic médical

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/MX2015/000204 WO2017105196A1 (fr) 2015-12-17 2015-12-17 Système multi-agents d'assistance pour un diagnostic médical

Publications (1)

Publication Number Publication Date
WO2017105196A1 true WO2017105196A1 (fr) 2017-06-22

Family

ID=59057122

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/MX2015/000204 WO2017105196A1 (fr) 2015-12-17 2015-12-17 Système multi-agents d'assistance pour un diagnostic médical

Country Status (1)

Country Link
WO (1) WO2017105196A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107798388A (zh) * 2017-11-23 2018-03-13 航天天绘科技有限公司 基于Multi‑Agent与DNN的测控资源调度分配的方法
CN109144018A (zh) * 2018-10-26 2019-01-04 黑龙江大学 一种不同阶混合机电系统协同控制方法及控制系统

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2003057011A2 (fr) * 2002-01-04 2003-07-17 Canswers Llc Systemes et procedes destines a prevoir le comportement d'une maladie
WO2009083886A1 (fr) * 2007-12-28 2009-07-09 Koninklijke Philips Electronics N.V. Présentation d'études pertinentes de patients pour une prise de décision clinique
WO2013036677A1 (fr) * 2011-09-06 2013-03-14 The Regents Of The University Of California Groupe de calcul informatique médical

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2003057011A2 (fr) * 2002-01-04 2003-07-17 Canswers Llc Systemes et procedes destines a prevoir le comportement d'une maladie
WO2009083886A1 (fr) * 2007-12-28 2009-07-09 Koninklijke Philips Electronics N.V. Présentation d'études pertinentes de patients pour une prise de décision clinique
WO2013036677A1 (fr) * 2011-09-06 2013-03-14 The Regents Of The University Of California Groupe de calcul informatique médical

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107798388A (zh) * 2017-11-23 2018-03-13 航天天绘科技有限公司 基于Multi‑Agent与DNN的测控资源调度分配的方法
CN107798388B (zh) * 2017-11-23 2022-02-08 航天天绘科技有限公司 基于Multi-Agent与DNN的测控资源调度分配的方法
CN109144018A (zh) * 2018-10-26 2019-01-04 黑龙江大学 一种不同阶混合机电系统协同控制方法及控制系统
CN109144018B (zh) * 2018-10-26 2021-02-02 黑龙江大学 一种不同阶混合机电系统协同控制方法及控制系统

Similar Documents

Publication Publication Date Title
US9265441B2 (en) Assessment of traumatic brain injury
Turner et al. The classification of minor gait alterations using wearable sensors and deep learning
ES2659945T3 (es) Monitorización basada en residuos de la salud humana
CN110121749A (zh) 用于图像采集的深度学习医疗系统和方法
US11693071B2 (en) Systems and methods for mapping neuronal circuitry and clinical applications thereof
JP2011238252A5 (fr)
CN109770903A (zh) 功能磁共振影像的分类预测方法、系统、装置
CA3134081A1 (fr) Procede et systeme d'identification de sujets potentiellement affectes par un probleme de sante
Samant et al. Evaluation of artificial neural networks in prediction of essential hypertension
EP3612101A1 (fr) Bras d'articulation pour analyser des objets anatomiques utilisant des réseaux d'apprentissage profond
Lee et al. Analysis of gait sub-movements to estimate ataxia severity using ankle inertial data
US20200005095A1 (en) Integrative prediction of a cognitive evolution of a subject
TW201941220A (zh) 診斷支援裝置、程式製品、記錄有學習完成模型的記錄媒體及學習裝置
WO2017105196A1 (fr) Système multi-agents d'assistance pour un diagnostic médical
Abeyratne et al. Cough Sound Analysis-A new tool for diagnosing Pneumonia
Lynch Jr et al. Expansion of a frontostriatal salience network in individuals with depression
Ambastha Neuroanatomical characterization of Alzheimer’s disease using deep learning
Ozsahin et al. Neural network applications in medicine
KR102511511B1 (ko) 뇌졸중 환자의 임상 데이터를 이용한 운동 기능 회복 예후 예측 장치 및 그 방법
Matlani BiLSTM-ANN: early diagnosis of Alzheimer’s disease using hybrid deep learning algorithms
Patankar et al. AutiScan: Screening of Autism Spectrum Disorder Specific to Indian Region
Zalianty et al. Neural Network-based Classification of Alzheimer's Disease using MRI: A Comparative Performance Analysis
Holland et al. Clustering disease trajectories in contrastive feature space for biomarker discovery in age-related macular degeneration
Gayathri et al. A Comprehensive Review on Early Diagnosis of Alzheimer’s Disease Detection
Michelle et al. Covid-19 Detection from X-Rays with Aid of Convolutional Neural Network

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: 15910842

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 06.12.2018)

122 Ep: pct application non-entry in european phase

Ref document number: 15910842

Country of ref document: EP

Kind code of ref document: A1