Introduction Post
This summer, I’ll be working on a research project exploring interpretable ML in healthcare. Machine-learning systems are increasingly used to support diagnosis and risk prediction in hospitals, yet most remain difficult for clinicians to understand or trust. They produce scores and labels, but give little insight into the medical reasoning behind them, limiting their usefulness in real clinical decision-making. This project builds foundational machine-learning models that use human-interpretable medical concepts to understand tabular healthcare data for downstream disease prediction. I'm really interested to see how our outcomes change, and how this can help pave the way to more interpretable and scalable clinical machine learning models. Really excited to learn from you all and hear about the amazing work everyone is doing across different disciplines and countries!
