Master Thesis: Data-Mining and Survival Analysis using Electronic Health Records

Description

Electronic health records (EHR) store a patient's hospital/physician visits, where disease diagnosis, prescribed medications, and results of diagnostics tests are recorded for each patient. As such EHR present an extensive description of a patient's health over time and can help to identify patient subgroups that are more susceptible to certain diseases. The challenges in analyzing this data are: 1) the data is highly heterogeneous, consisting of demographic information, lab measurements, questioners and clinical tests, 2) the number of variables is high with only a subset of variables being relevant when studying a particular outcome, and 3) only a small subset of variable is available for all patients.

In this project, you are going to work with data from the Framingham Heart Study, which followed a cohort of people over 30 years to investigate which factors influence the risk of suffering from cardiovascular disease. Every 3-4 years, a follow-up was performed where hundreds of different indicators were recorded as well as any diseases or adverse events patients suffered since the last follow-up. This data can be used to develop a model that predicts the probability of experiencing one or more pre-defined events, such as myocardial infarction, cancer or death, at a given time point t. This type of analysis is called survival analysis, and models are referred to as survival models. Using this model, it is usually of most interest to find subgroups of patients at differ significantly in their expected survival. Since the data is heterogeneous (a mix of continuous and categorical variables), high-dimensional and correlated, traditional statistical learning techniques such as the Cox Proportional Hazards model cannot be applied.

Expected results

Your task in this projects, is to develop machine learning techniques for survival analysis that address the challenges of heterogeneous set of variables, varying relevance of variables, and missing values. Developed algorithms are going to be applied on data from the Framingham Offspring Cohort to identify patient subgroups with varying patterns of survival. Results can be compared with results of clinical studies based on the same data set.

Requirements

• Interest in interdisciplinary research field
• Very good programming skills in Python
• Basic knowledge of machine learning and statistics

Contact

Please, contact Sebastian Pölsterl for further details or questions on this project.