SYSTEM FOR DETERMINING DEPRESSION RISK USING FUNDUS IMAGE, MACHINE LEARNING MODEL GENERATION DEVICE, DEPRESSION RISK DETERMINATION DEVICE, AND DEPRESSION RISK DETERMINATION METHOD

Provided is a depression risk determining system with which it is possible to determine the risk of depression from a fundus image. The system for determining depression risk according to the present invention comprises: a machine learning model generation device that generates a trained model for determining the risk of depression; and a depression risk determination device that determines the risk of depression by using the trained model generated by the machine learning model generation device. The machine learning model generation device includes a data acquisition unit that acquires at least inquiry data for training and a fundus image for training, and a machine learning model generation unit that generates a trained model. The depression risk determination device includes a determination data acquisition unit that acquires a fundus image used for determination, a depression risk determination unit that inputs at least the fundus image used for determination to the trained model to thereby output a prediction score indicating depression risk, and a determination result output unit that outputs the determination results of depression risk on the basis of the prediction score..

Medienart:

Patent

Erscheinungsjahr:

2024

Erschienen:

2024

Enthalten in:

Europäisches Patentamt - (2024) vom: 18. Jan. Zur Gesamtaufnahme - year:2024

Sprache:

Englisch

Beteiligte Personen:

FUKUMA YASUFUMI [VerfasserIn]
MAO ZAIXING [VerfasserIn]
KUROSE TAKAHIRO [VerfasserIn]
SONE KOHEI [VerfasserIn]
NISHIDA KOHJI [VerfasserIn]
KAWASAKI RYO [VerfasserIn]
MARUYAMA KAZUICHI [VerfasserIn]
MATSUSHITA KENJI [VerfasserIn]
HASHIDA NORIYASU [VerfasserIn]

Links:

Volltext [kostenfrei]

Themen:

Sonstige Themen:
615
G16H: Healthcare informatics, i.e. information and commun (...)
rest (...)

Anmerkungen:

Source: www.epo.org (no modifications made), First posted: 2024-01-18, Last update posted on www.tib.eu: 2024-02-23, Last updated: 2024-03-01

Patentnummer:

WO2024014175

Förderinstitution / Projekttitel:

PPN (Katalog-ID):

EPA019102291