The Pitfalls and Potential of Using Machine Learning to Personalize Patient Treatments
* Register (or log in) to the AI4G Neural Network to add this session to your agenda or watch the replay
In this talk, I’ll discuss the idea of learning how to individualize patient treatments based on data such as electronic medical records, patient generated data, and clinical trial data. I will present the notion of causality and explain why “ordinary” supervised machine learning is insufficient in many cases for properly learning individualized treatments, and why learning such treatment is strictly more challenging. I will present a framework for evaluating whether a given clinical problem and dataset are amenable for learning individualized treatments, and will briefly show two case studies: one in chronic diabetes care and one in chronic heart failure care.
This live event includes a 30-minute networking event hosted on the AI for Good Neural Network. This is your opportunity to ask questions, interact with the panelists and participants and build connections with the AI for Good community.