LaTiM: Longitudinal representation learning in continuous-time models to predict disease progression
This work addresses disease progression modeling for medical applications, but it appears incremental as it combines existing methods like NODEs and SSL with a novel integration approach.
The authors tackled disease progression prediction by proposing a framework that integrates neural ordinary differential equations with self-supervised learning, achieving statistically significant improvements in AUC and Kappa metrics for diabetic retinopathy prediction.
This work proposes a novel framework for analyzing disease progression using time-aware neural ordinary differential equations (NODE). We introduce a "time-aware head" in a framework trained through self-supervised learning (SSL) to leverage temporal information in latent space for data augmentation. This approach effectively integrates NODEs with SSL, offering significant performance improvements compared to traditional methods that lack explicit temporal integration. We demonstrate the effectiveness of our strategy for diabetic retinopathy progression prediction using the OPHDIAT database. Compared to the baseline, all NODE architectures achieve statistically significant improvements in area under the ROC curve (AUC) and Kappa metrics, highlighting the efficacy of pre-training with SSL-inspired approaches. Additionally, our framework promotes stable training for NODEs, a commonly encountered challenge in time-aware modeling.