# Multi-task longitudinal forecasting with missing values on Alzheimer's Disease

arXiv: https://arxiv.org/abs/2201.05040 · HTML: https://mlsanity.com/paper/2201.05040/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 72 references that are in the map.
- First posted on arXiv 13 Jan 2022.

## Builds on (most cited first, 6 of 6)

- [Variational Inference: A Review for Statisticians](https://mlsanity.com/paper/1601.00670/) (2016)
- [Handling Incomplete Heterogeneous Data using VAEs](https://mlsanity.com/paper/1807.03653/) (2018)
- [Comparison of single and multitask learning for predicting cognitive decline based on MRI data](https://mlsanity.com/paper/2109.10266/) (2021)
- [Sparse Semi-supervised Heterogeneous Interbattery Bayesian Analysis](https://mlsanity.com/paper/2001.08975/) (2020)
- [Multi-view Learning as a Nonparametric Nonlinear Inter-Battery Factor Analysis](https://mlsanity.com/paper/1604.04939/) (2016)
- [High-Dimensional Longitudinal Classification with the Multinomial Fused Lasso](https://mlsanity.com/paper/1501.07518/) (2015)

## Built on by (most cited first, 3 of 3)

- [Multi-Objective Genetic Algorithm for Multi-View Feature Selection](https://mlsanity.com/paper/2305.18352/) (2023)
- [Optimizing Feature Selection for Binary Classification with Noisy Labels: A Genetic Algorithm Approach](https://mlsanity.com/paper/2401.06546/) (2024)
- [Longitudinal Causal Image Synthesis](https://mlsanity.com/paper/2410.17691/) (2024)

## Abstract (arXiv)

Machine learning techniques typically applied to dementia forecasting lack in their capabilities to jointly learn several tasks, handle time dependent heterogeneous data and missing values. In this paper, we propose a framework using the recently presented SSHIBA model for jointly learning different tasks on longitudinal data with missing values. The method uses Bayesian variational inference to impute missing values and combine information of several views. This way, we can combine different data-views from different time-points in a common latent space and learn the relations between each time-point while simultaneously modelling and predicting several output variables. We apply this model to predict together diagnosis, ventricle volume, and clinical scores in dementia. The results demonstrate that SSHIBA is capable of learning a good imputation of the missing values and outperforming the baselines while simultaneously predicting three different tasks.