PhilHumans: Benchmarking Machine Learning for Personal Health
This work addresses the need for robust benchmarks in healthcare machine learning to improve patient outcomes and accessibility, though it is incremental as it builds on existing benchmarking practices.
The authors introduced PhilHumans, a comprehensive benchmark suite for machine learning in healthcare across various settings and tasks, aiming to facilitate the development of intelligent systems by providing standardized evaluation metrics.
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