# Uncertainty-Aware Longitudinal Forecasting of Alzheimer's Disease Progression Using Deep Learning

arXiv: https://arxiv.org/abs/2606.24604 · HTML: https://mlsanity.com/paper/2606.24604/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 41 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting](https://mlsanity.com/paper/1912.09363/) (2019)
- [Deep Neural Networks for Rank-Consistent Ordinal Regression Based On Conditional Probabilities](https://mlsanity.com/paper/2111.08851/) (2021)
- [Training recurrent neural networks robust to incomplete data: application to Alzheimer's disease progression modeling](https://mlsanity.com/paper/1903.07173/) (2019)
- [Uncertainty Quantification for Machine Learning in Healthcare: A Survey](https://mlsanity.com/paper/2505.02874/) (2025)
- [ChronoFormer: Time-Aware Transformer Architectures for Structured Clinical Event Modeling](https://mlsanity.com/paper/2504.07373/) (2025)
- [Ordinal-ResLogit: Interpretable Deep Residual Neural Networks for Ordered Choices](https://mlsanity.com/paper/2204.09187/) (2022)
- [Mixture of Input-Output Hidden Markov Models for Heterogeneous Disease Progression Modeling](https://mlsanity.com/paper/2207.11846/) (2022)
- [A Stage-Aware Mixture of Experts Framework for Neurodegenerative Disease Progression Modelling](https://mlsanity.com/paper/2508.07032/) (2025)
- [Deep Ensembles for Epistemic Uncertainty: A Frequentist Perspective](https://mlsanity.com/paper/2510.22063/) (2025)
- [DeepAD: A Robust Deep Learning Model of Alzheimer's Disease Progression for Real-World Clinical Applications](https://mlsanity.com/paper/2203.09096/) (2022)
- [Uncertainty-Aware Ordinal Deep Learning for cross-Dataset Diabetic Retinopathy Grading](https://mlsanity.com/paper/2602.10315/) (2026)
- [A mixture model for subtype identification in the context of disease progression modeling](https://mlsanity.com/paper/2603.04286/) (2026)

## Built on by (most cited first, 1 of 1)

- [NeuronSifter: An Agent-in-Twin for Prioritizing Central Nervous System Interventions with World Action Models](https://mlsanity.com/paper/2609.35445/) (2026)

## Abstract (arXiv)

Longitudinal modelling of Alzheimer's disease progression is clinically useful only if it can describe not just the most likely next diagnosis, but how a patient may evolve over time and how reliable that forecast is. Most deep learning approaches reduce this problem to single-step classification, treating cognitively normal, mild cognitive impairment, and dementia as flat categories while providing limited insight into how uncertainty accumulates across future visits. We propose a probabilistic framework that combines ordinal diagnosis prediction, multi-horizon trajectory generation, and decomposed uncertainty estimation. A Temporal Fusion Transformer encoder is adapted with a CORAL ordinal output layer, asymmetric loss weighting, and converter oversampling to respect disease-stage ordering and improve sensitivity to MCI-to-dementia transitions. Conditioned on the learned patient-context representation, an autoregressive Mixture Density Network generates five-year probabilistic trajectories for diagnosis state, CDR Sum of Boxes, MMSE orientation, and hippocampal volume. On ADNI, the model outperforms linear, recurrent, and transformer baselines for next-visit diagnosis prediction, with the strongest gains on MCI-versus-dementia discrimination. Generated trajectories achieve near-nominal 90% credible interval coverage, widening uncertainty across the forecast horizon, and biomarker dynamics consistent with expected Alzheimer's disease progression. We further separate aleatoric from epistemic uncertainty using analytic mixture variance and a five-member bootstrap ensemble, which provides the strongest encoder diversity and output-level epistemic signal. Epistemic uncertainty is higher for rare progression archetypes, MCI and dementia patients, and under external evaluation on OASIS-3, where it increases alongside prediction error.