biostudies-literatureLee JNLM NIH HHS11-20https://www.ebi.ac.uk/biostudies/studies/S-EPMC9842432biostudies-literatureUnknown13583Accurately predicting a patient's risk of progressing to late age-related macular degeneration (AMD) is difficult but crucial for personalized medicine. While existing risk prediction models for progression to late AMD are useful for triaging patients, none utilizes longitudinal color fundus photographs (CFPs) in a patient's history to estimate the risk of late AMD in a given subsequent time interval. In this work, we seek to evaluate how deep neural networks capture the sequential information in longitudinal CFPs and improve the prediction of 2-year and 5-year risk of progression to late AMD. Specifically, we proposed two deep learning models, CNN-LSTM and CNN-Transformer, which use a Long-Short Term Memory (LSTM) and a Transformer, respectively with convolutional neural networks (CNN), tMachine learning in medical imaging. MLMI (Workshop)Predicting Age-related Macular Degeneration Progression with Longitudinal Fundus Images Using Deep Learning.PMC9842432R00 LM013001Keenan TDLPeng YChen QGlicksberg BSChew EYLu ZLee JWanyan TWang FfalsePredicting Age-related Macular Degeneration Progression with Longitudinal Fundus Images Using Deep Learning.Accurately predicting a patient's risk of progressing to late age-related macular degeneration (AMD) is difficult but crucial for personalized medicine. While existing risk prediction models for progression to late AMD are useful for triaging patients, none utilizes longitudinal color fundus photographs (CFPs) in a patient's history to estimate the risk of late AMD in a given subsequent time interval. In this work, we seek to evaluate how deep neural networks capture the sequential information in longitudinal CFPs and improve the prediction of 2-year and 5-year risk of progression to late AMD. Specifically, we proposed two deep learning models, CNN-LSTM and CNN-Transformer, which use a Long-Short Term Memory (LSTM) and a Transformer, respectively with convolutional neural networks (CNN), t2022-01-01T00:00:00Z2022 Sep2025-04-04T00:02:54.478Z2025-04-04T00:02:54.478ZS-EPMC98424323665660410.1007/978-3-031-21014-3_2