HPI Digital Health Center

HPI Digital Health Center

The HPI Digital Health Center (DHC) brings together individuals from health sciences, human sciences, data sciences, digital engineering and society with a shared goal to improve health and wellbeing. The Center assumes an open, inclusive network structure of researchers, projects and research institutions with the shared goal to empower patients and to transform healthcare with innovative digital health solutions. The DHC has established a main hub at the HPI main campus in Potsdam outside Berlin, and a U.S. eastcoast location at the SAP Leonardo Center in New York City. 

In March 2019 theHasso Plattner Institute for Digital Health at Mount Sinaiin New York City became part of the HPI Digital Health family. The new institute was launched as the result of a merger of  the Mount Sinai Health System (MSHS) and the Hasso Plattner Institute (HPI).  With world-class expertise and complementary resources in health care, data sciences and biomedical and digital engineeting, the new Hasso Plattner Institute for Digital Health at Mount Sinai will conduct patient-engaged and data driven research.

The Digital Health Center Team in Summer 2019

Digital Health Research Topics

Here you find an overview of our current research topics. Detailed information can be found on our research page
  • Automated Measurement of Stress and Pain
  • Automated Evaluation of Physical Exercise
  • Clinical prediction models and interpretable machine learning
  • Elderly care planning
  • Electronic Registry for Elderly Care Services (ERPEL)
  • Gene Regulation and Transcriptomic Characterization  
  • Information Retrieval applied to the Medical Literature 
  • Integrated Healthcare: Data aggregation, analysis and visualization
  • Interactive Data Exploration using Shiny App on Quantitative Proteomis data
  • Molecular Tumor Board Process Facilitation
  • Predicting Psychological Crisis via Smartphone
  • Systems Medicine Approach for Heart Failure (SMART)
  • The digital doctor
  • Unsupervised Subgroup Detection for Mixed-Type Systems Medicine Data Sets