PhD Research Opportunities in Machine Learning and Artificial Intelligence for Medicine
- 10:00 11th November 2019 ( week 5, Michaelmas Term 2019 )LTB Wolfson Building
Machine Learning and Artificial Intelligence are set to transform healthcare. My group, Machine Learning and Artificial Intelligence for Medicine (ML-AIM), is developing new, cutting edge theories, methods and algorithms specifically tailored to the needs of medicine rather than applying off-the-shelf, generic ML and AI techniques which often do not prove very useful in practice. To help structure and think about our approach and we have categorised medicine into five main challenges: 1) Lifestyle optimization and disease prevention; 2) Disease detection and prediction of disease progression (longitudinal); 3) Best interventions and treatments; 4) State-of-the-art tools for clinicians & healthcare professionals to deliver high-quality care; 5) Optimization of healthcare systems (quality, efficiency, cost effectiveness, robustness, scalability). My group is working on addressing all these challenges by developing new and targeted machine learning and AI methods.
In this talk, I will discuss the many research opportunities in the area of machine learning and AI for medicine and present our research results in three main areas (which span the 5 papers which ML-AIM is presenting at NeurIPS 2019):
- Building a comprehensive time-series model that accommodates irregularly sampled, temporally correlated, informatively censored and non-stationary processes in order to understand and predict the longitudinal trajectories of diseases.
- Establishing the theoretical limits of causal inference and using what has been established to create a new approach that makes it possible to better estimate individualized treatment effects.
- Developing systematic and general methods for making machine learning algorithms interpretable and their predictions easily explainable.
ML-AIM has current 6 fully funded PhD positions in the area of machine learning and AI for medicine. So come along and hear more about our research!