ENC-ODE: Event-level Neurodegenerative Modeling in Continuous Time with Neural ODEs
2026-06-29 • Artificial Intelligence
Artificial IntelligenceInformation RetrievalMachine Learning
AI summaryⓘ
The authors developed ENC-ODE, a method to predict how clinical biomarkers change over time in diseases like Alzheimer's, even when data is scarce or irregular. Their approach uses neural ordinary differential equations to model continuous changes based on diagnosis events. ENC-ODE also uses a special attention mechanism to focus on important events for specific future times and types of data without losing information from the past. Tests on a major Alzheimer's dataset showed ENC-ODE performs better than other models. This method could help doctors better understand and track disease progression.
clinical biomarkersneurodegenerative diseasesAlzheimer's diseaselongitudinal dataneural ordinary differential equationscontinuous-time modelingattention mechanismdiagnosis-conditioned modelingADNI datasetsequence models
Authors
Yujee Song, Seunghun Baek, Guorong Wu, Won Hwa Kim
Abstract
Accurately predicting the temporal evolution of clinical biomarkers is crucial for the early diagnosis and management of neurodegenerative diseases such as Alzheimer's disease. However, this relies on longitudinal data to capture biomarker changes over time, which is often sparse and irregular due to the high cost, labor-intensive nature, and patient burden. To address these challenges, we propose ENC-ODE, an Event-level Neurodegenerative modeling in Continuous time with neural Ordinary Differential Equations. ENC-ODE predicts future biomarker evolution by modeling clinical events through diagnosis-conditioned continuous dynamics. A target-conditioned attention mechanism weights and aggregates event-level predictions for the target time and modality without history compression. Extensive experiments on Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that ENC-ODE outperforms representative sequence models while offering a scalable and neuroscientifically grounded solution for clinical support. The code is available at https://github.com/JardinDelSol/enc-ode.