Reconstructing and forecasting disease trajectories of patients with Alzheimer's disease using routine data in resource-constrained settings

2026-06-05

AI Summary

This work addresses the significant inter-individual heterogeneity in cognitive trajectories among Alzheimer’s disease patients and the challenge of simultaneously reconstructing past trajectories, forecasting future decline, and quantifying uncertainty in resource-constrained settings where costly imaging or biomarker data are unavailable. The authors propose GNOVA, a unified framework based on a GRU-Neural ODE variational autoencoder, which enables continuous-time bidirectional modeling of cognitive scores using only routine clinical visit data—such as age, BMI, and APOE4 status—to support interpolation and extrapolation at arbitrary time points with well-calibrated uncertainty estimates. Evaluated on 1,727 patients from the ADNI dataset over ten years of follow-up, GNOVA achieves mean absolute errors of 1.35 for CDR-SB and 2.28 for MMSE prediction using clinical variables alone, marking the first successful full-disease-trajectory modeling without MRI, PET, or CSF biomarkers.

Abstract

Alzheimer's disease is a progressive neurodegenerative disorder, and its progression varies substantially across patients. Existing work aims to forecast patients' future cognitive state, with minimal focus on reconstructing the state from past visits. Furthermore, in current research, quantifying predictive uncertainty remains underexplored and relies on costly modalities such as MRI, PET, and CSF, limiting their deployment in resource-limited settings. In this research, our primary objectives are: First, bidirectional prediction of cognitive scores from irregular visits to present the complete disease trajectory. Second, to enable interpolation and extrapolation capabilities to assist clinicians in informed prognostic decision making, and third, to provide a well-calibrated uncertainty estimate for all predictions, and finally, to achieve the objectives using the modalities available during routine visits. We propose a unified framework, GNOVA: A GRU-Neural ODE Variational Autoencoder. The architecture combines a Gated Recurrent Unit encoder and a Neural ODE decoder within a variational autoencoder framework. In our work, we forecast the CDR-SB and MMSE Scores. The GRU encoder allows for any number of inputs at any time point. The Neural-ODE decoder performs continuous estimation, allowing interpolation and extrapolation at any desired time point. The Variational autoencoder allows for uncertainty estimation in predictions. We worked with 1,727 patients from the ADNI dataset over 10 years; the model achieved mean absolute errors of 1.35 and 2.28 for CDR-SB and MMSE scores, respectively, without requiring any neuroimaging or biomarker data. Feature-ablation studies revealed that age, BMI, and APOE4 status were strong predictors. The proposed framework enables the reconstruction of incomplete patient histories and the anticipation of future cognitive states.

Problem

• Alzheimer's disease
• disease trajectory reconstruction
• predictive uncertainty
• resource-constrained settings
• cognitive score forecasting

Innovation

• Neural ODE
• Variational Autoencoder
• Bidirectional Prediction
• Uncertainty Quantification
• Resource-Constrained Settings