Processing

Please wait...

PATENTSCOPE will be unavailable a few hours for maintenance reason on Saturday 31.10.2020 at 7:00 AM CET
Settings

Settings

Goto Application

1. WO2019057727 - SUBJECT CLUSTERING METHOD AND APPARATUS

Publication Number WO/2019/057727
Publication Date 28.03.2019
International Application No. PCT/EP2018/075238
International Filing Date 18.09.2018
IPC
G16H 50/70 2018.01
GPHYSICS
16INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
50ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
70for mining of medical data, e.g. analysing previous cases of other patients
CPC
G16H 50/70
GPHYSICS
16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
50ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
70for mining of medical data, e.g. analysing previous cases of other patients
Applicants
  • KONINKLIJKE PHILIPS N.V. [NL]/[NL]
Inventors
  • CONSOLI, Sergio
  • HENDRIKS, Monique
  • VOS, Pieter, Christiaan
  • KUSTRA, Jacek, Lukasz
  • HOFFMANN, Ralf, Dieter
  • MAVRIEUDUS, Dimitros
Agents
  • BECK, Christopher, Andrew
  • DE HAAN, Poul, Erik
Priority Data
17192198.420.09.2017EP
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) SUBJECT CLUSTERING METHOD AND APPARATUS
(FR) APPAREIL ET PROCÉDÉ DE REGROUPEMENT DE SUJETS
Abstract
(EN)
A method of clustering or grouping subjects that are similar to one another. A dataset contains, for each subject, a set of quantitative values which each represent a respective clinical or pathological feature of that subject. A principle component analysis, PCA, is performed on the dataset. Loadings of one of the first two principle components identified by the PCA are used to generate a respective dataset of weighting values. These weighting values are used to weigh or modify each set of quantitative values in the dataset. A clustering algorithm is performed on the weighted sets of subject data. The process may be iterated until user-defined stopping conditions are satisfied.
(FR)
L'invention concerne un procédé de regroupement ou de groupage de sujets qui sont similaires les uns aux autres. Un ensemble de données contient, pour chaque sujet, un ensemble de valeurs quantitatives qui représentent chacune une caractéristique clinique ou pathologique respective de ce sujet. Une analyse en composantes principales, ACP, est effectuée sur l'ensemble de données. Des charges de l'une des deux premières composantes principales identifiées par la ACP sont utilisées pour générer un ensemble de données respectif de valeurs de pondération. Ces valeurs de pondération sont utilisées pour pondérer ou modifier chaque ensemble de valeurs quantitatives dans l'ensemble de données. Un algorithme de regroupement est réalisé sur les ensembles pondérés de données de sujet. Le processus peut être répété jusqu'à ce que les conditions d'arrêt définies par l'utilisateur soient satisfaites.
Also published as
JP2020516730
Latest bibliographic data on file with the International Bureau