# FLARe: Forecasting by Learning Anticipated Representations

## TL;DR

This paper introduces FLARe, a novel forecasting model for Alzheimer's disease progression that generates sequential latent representations, improving accuracy and robustness over existing methods by better capturing temporal dynamics and handling missing data.

## Contribution

The paper presents a new model that generates sequences of latent representations for improved temporal modeling and robustness in disease progression forecasting.

## Key findings

- Outperforms baseline models in forecasting accuracy.
- Achieves higher F1 scores in predicting disease progression.
- Handles missing visits more robustly than previous methods.

## Abstract

Computational models that forecast the progression of Alzheimer's disease at the patient level are extremely useful tools for identifying high risk cohorts for early intervention and treatment planning. The state-of-the-art work in this area proposes models that forecast by using latent representations extracted from the longitudinal data across multiple modalities, including volumetric information extracted from medical scans and demographic info. These models incorporate the time horizon, which is the amount of time between the last recorded visit and the future visit, by directly concatenating a representation of it to the data latent representation. In this paper, we present a model which generates a sequence of latent representations of the patient status across the time horizon, providing more informative modeling of the temporal relationships between the patient's history and future visits. Our proposed model outperforms the baseline in terms of forecasting accuracy and F1 score with the added benefit of robustly handling missing visits.