Summary of Automated Multi-task Learning For Joint Disease Prediction on Electronic Health Records, by Suhan Cui and Prasenjit Mitra
Automated Multi-Task Learning for Joint Disease Prediction on Electronic Health Records
by Suhan Cui, Prasenjit Mitra
First submitted to arxiv on: 6 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed AutoDP framework is an automated approach for multi-task learning (MTL) in Electronic Health Records (EHR) data. It reduces human intervention by searching for the optimal configuration of task grouping and architectures simultaneously, using surrogate model-based optimization to efficiently explore the vast joint search space. The framework achieves significant performance improvements over hand-crafted and automated state-of-the-art methods while maintaining a feasible search cost. This is demonstrated through experimental results on real-world EHR data. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The AutoDP framework helps computers learn better from big amounts of health data. It lets machines pick the best combination of tasks to work together, which makes predictions about patients’ future health conditions more accurate. The new approach saves time and effort by not needing human experts to decide what tasks to group together or how to design the machine learning models. |
Keywords
* Artificial intelligence * Machine learning * Multi task * Optimization
