# A Comprehensive Evaluation of Multi-task Learning and Multi-task Pre-training on EHR Time-series Data

arXiv: https://arxiv.org/abs/2007.10185 · HTML: https://mlsanity.com/paper/2007.10185/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jul 2020.

## Built on by (most cited first, 8 of 8)

- [Neighborhood Contrastive Learning Applied to Online Patient Monitoring](https://mlsanity.com/paper/2106.05142/) (2021)
- [Meta-Learning to Improve Pre-Training](https://mlsanity.com/paper/2111.01754/) (2021)
- [Structure Inducing Pre-Training](https://mlsanity.com/paper/2103.10334/) (2021)
- [MEDS-Tab: Automated tabularization and baseline methods for MEDS datasets](https://mlsanity.com/paper/2411.00200/) (2024)
- [Recent Advances, Applications, and Open Challenges in Machine Learning for Health: Reflections from Research Roundtables at ML4H 2023 Symposium](https://mlsanity.com/paper/2403.01628/) (2024)
- [Multitask Learning for Time Series Data with 2D Convolution](https://mlsanity.com/paper/2310.03925/) (2023)
- [Universal EHR Federated Learning Framework](https://mlsanity.com/paper/2211.07300/) (2022)
- [Self-supervision for health insurance claims data: a Covid-19 use case](https://mlsanity.com/paper/2107.14591/) (2021)

## Abstract (arXiv)

Multi-task learning (MTL) is a machine learning technique aiming to improve model performance by leveraging information across many tasks. It has been used extensively on various data modalities, including electronic health record (EHR) data. However, despite significant use on EHR data, there has been little systematic investigation of the utility of MTL across the diverse set of possible tasks and training schemes of interest in healthcare. In this work, we examine MTL across a battery of tasks on EHR time-series data. We find that while MTL does suffer from common negative transfer, we can realize significant gains via MTL pre-training combined with single-task fine-tuning. We demonstrate that these gains can be achieved in a task-independent manner and offer not only minor improvements under traditional learning, but also notable gains in a few-shot learning context, thereby suggesting this could be a scalable vehicle to offer improved performance in important healthcare contexts.