PhilHumans: Benchmarking Machine Learning for Personal Health

TL;DR

PhilHumans introduces a comprehensive benchmark suite for evaluating machine learning models across diverse healthcare applications and learning tasks, aiming to accelerate progress in personal health AI systems.

Contribution

It provides the first holistic set of benchmarks for ML in healthcare, covering multiple settings and learning tasks to standardize evaluation and foster development.

Findings

Benchmark suite spans various healthcare scenarios and learning tasks.

Facilitates standardized evaluation of ML models in healthcare.

Aims to guide future research and improve AI tools in personal health.

Abstract

The use of machine learning in Healthcare has the potential to improve patient outcomes as well as broaden the reach and affordability of Healthcare. The history of other application areas indicates that strong benchmarks are essential for the development of intelligent systems. We present Personal Health Interfaces Leveraging HUman-MAchine Natural interactions (PhilHumans), a holistic suite of benchmarks for machine learning across different Healthcare settings - talk therapy, diet coaching, emergency care, intensive care, obstetric sonography - as well as different learning settings, such as action anticipation, timeseries modeling, insight mining, language modeling, computer vision, reinforcement learning and program synthesis