Abstract: Building reliable predictive and prognostic models that leverage the growing scale of medical data and clinical records can make tremendous impact to the healthcare industry. Traditional survival analysis originated from clinical research focuses on identifying variates and factors that affect the hazard function; time series modelling approaches emphasize predicting future values based on previous observations; machine learning models are often formulated as mapping between large feature spaces to binary outcomes. However, all of these methods have their unique limitations and there are still much more to explore in the context of treating clinical survival analysis with machine learning models. In this talk, we will present our recent work on a new Bayesian framework that uniquely connects machine learning tasks (classification/regression) with event time analysis to provide risk prediction capabilities. We validate and demonstrate the utility of this approach with simulation data where the ground truths are known. We will then show a specific use case of this approach to perform risk prediction with real medical datasets. We will also discuss how this model can be implemented into clinical solutions.
Bio: Dr. Kang Liu is an Applied Data Scientist working at Wolters Kluwer Health. Kang received his PhD in statistical physics from Boston University in 2013 and had several years of postdoctoral research experience in physiological data analysis, biophysical modeling and simulation. He is passionate about novel machine learning techniques and almost anything Bayesian. At Wolters Kluwer Health Data Science team, Kang collaborates closely with clinicians, product managers and software engineers to build machine learning models for the early prediction of hospital acquired Clostridium Difficile Infection. He also contributes his expertise in statistical physics to the fast-growing culture of artificial intelligence at Wolters Kluwer, and continues to search for innovative ways of leveraging AI technology for better expert solutions in healthcare.