How DID YOU GET INTO Machine LEARNING?
It takes a tiny drop in the ocean to create a ripple effect. For me, my secondary school math teacher was that drop in the ocean. He was instrumental in showing me the beauty and wonder of mathematics and inspired me to pursue a career as a data scientist in the medical domain. After having studied in my home town in Trinidad, I moved to London to study a BSc in Business mathematics and statistics at the London School of Economics and an MSc at University College London. I was awarded a Microsoft PhD Scholarship and did my PhD in Statistics and Machine Learning at The University of Manchester. Education is not just a privilege, but also comes with a responsibility to share that knowledge to create a better society. I am a research fellow at Imperial College London. My research focuses on integrating expert scientific knowledge to develop statistical machine learning models to understand disease progression over time. I aim to develop probabilistic models in the context of asthma and allergic disease with approaches which are generalizable to identifying distinct subtypes of disease evolution and understanding the underlying mechanisms of these subtypes. I am passionate about using machine learning to improve human health and am particularly interested in machine learning to identify personalized disease management strategies through understanding the underlying latent manifestations of disease and their distinct genetic and environmental characteristics. I received an MRC Career Development Award in Biostatistics with the project “Unified probabilistic latent variable modelling strategies to accelerate endotype discovery in longitudinal studies”.
WhAT WILL YOU Be teaching?
In this tutorial I will focus on applications of machine learning in the healthcare domain. The grand challenge of bridging the gap between identifying causal mechanisms of diseases and translating this knowledge into personalized prevention and management strategies for medical conditions relies on the advancement of statistical learning methods for the discovery of subtypes of complex diseases (which may indicate disease "endotypes") by using 'intelligent phenotypes'. Statistical learning methods can provide a flexible framework for endotype discovery through the application of probabilistic modelling to disambiguate diseases where there are heterogeneous phenomena. Such a framework allows us to integrate high-dimensional and complex data. The flexibility of this framework enables us to encapsulate big biomedical data challenges such as missing data and inferring subtypes of disease from heterogeneous datasets. I will also present applications of machine learning to other domains in scientific and technological research. Applied machine learning to solve challenging problems which confront human existence is a worthwhile avenue to pursue.
What TOPIC Excites you most at the moment?
Machine learning has a huge potential for improving the quality of human life, wealth and health by using a predictive approach to healthcare, fairness and technological efficiency. There is a pressing need for cross-disciplinary research with an integrative approach to data science, whereby those working in the field of machine learning dialogue with scientists and researchers from different fields to engage in identifying meaning solutions to some of the world’s hardest problems. Hopefully, in the future, many of you will join me in this adventure to use machine learning algorithms to improve human life.