Berlin 2024 – scientific programme
Parts | Days | Selection | Search | Updates | Downloads | Help
SOE: Fachverband Physik sozio-ökonomischer Systeme
SOE 3: Machine Learning
SOE 3.2: Talk
Monday, March 18, 2024, 12:30–12:45, MA 001
Enhancing Chronic Disease Management through machine learning-based analysis of population Data — •Anna Nitschke1, Carlos Brandl1, Jannis Demel1, Jonathan Berthold1, Carola Behr1, Till Bärnighausen2, and Matthias Weidemüller1 — 1Physikalisches Institut, Heidelberg University, Germany — 2Heidelberg Institute of Global Health (HIGH), Heidelberg University, Germany
To achieve decisive progress in diagnosis and treatment of non-infectious chronic diseases, focusing on significant conditions like diabetes, we employ machine learning techniques on publicly available census data. Together with the Heidelberg Institute for Global Health, our aim is to make precise and reliable predictions about which people in which region are likely to be affected by these diseases. Using machine learning allows us to analyse individual needs and healthcare requirements. We exemplify this for India on a publicly available census dataset and will present how those predictions can help us to extract valuable insights from social and medical perspectives. Additionally they enable early identification of high-risk groups and regions, as well as improved utilisation of scarce healthcare resources.
Keywords: Population Health; Developing Countries; Machine Learning