Deep learning models to predict primary open-angle glaucoma

Glaucoma is a major cause of blindness and vision impairment worldwide, and visual field (VF) tests are essential for monitoring the conversion of glaucoma. While previous studies have primarily focused on using VF data at a single time point for glaucoma prediction, there has been limited explorati...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Stat (International Statistical Institute) Ročník 13; číslo 1
Hlavní autori: Zhou, Ruiwen, Miller, J Philip, Gordon, Mae, Kass, Michael, Lin, Mingquan, Peng, Yifan, Li, Fuhai, Feng, Jiarui, Liu, Lei
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States 2024
Predmet:
dynamic prediction
convolutional neural network
landmark analysis
long short-term memory
ISSN:2049-1573, 2049-1573
On-line prístup:Zistit podrobnosti o prístupe
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Glaucoma is a major cause of blindness and vision impairment worldwide, and visual field (VF) tests are essential for monitoring the conversion of glaucoma. While previous studies have primarily focused on using VF data at a single time point for glaucoma prediction, there has been limited exploration of longitudinal trajectories. Additionally, many deep learning techniques treat the time-to-glaucoma prediction as a binary classification problem (glaucoma Yes/No), resulting in the misclassification of some censored subjects into the nonglaucoma category and decreased power. To tackle these challenges, we propose and implement several deep-learning approaches that naturally incorporate temporal and spatial information from longitudinal VF data to predict time-to-glaucoma. When evaluated on the Ocular Hypertension Treatment Study (OHTS) dataset, our proposed convolutional neural network (CNN)-long short-term memory (LSTM) emerged as the top-performing model among all those examined. The implementation code can be found online (https://github.com/rivenzhou/VF_prediction).
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2049-1573
2049-1573
DOI:10.1002/sta4.649