A new open source tool to analyze complex health data

Under the leadership of Helmholtz Munich, scientists have developed an accessible software solution specifically designed for the analysis of complex medical data. The open source software called “ehrapy” allows researchers to systematically structure and examine large, heterogeneous data sets. The software is available to the global scientific community for use and further development.

Ehrapy is intended to fill a critical gap in health data analysis, says Lukas Heumos, one of the lead developers and a researcher at the Helmholtz Institute for Computational Biology Munich and the Technical University of Munich (TUM). “Until now, there has been no standardized tool that allows for the systematic and efficient analysis of diverse and complex medical data. With ehrapy, we have changed that,” says Lukas Heumos.

The team behind the ehrapy project comes from biomedical research and has extensive experience in analyzing complex scientific data sets. “The healthcare sector faces the same data analysis challenges as those working in laboratories,” Heumos noted at the start of the ehrapy project.

The study was published in Natural medicine.

Exploratory approach – hypothesis-free analysis

Working with many other contributors, Heumos used its expertise in scientific software development to create a solution for analyzing patient data. Heumos said, “Ehrapy can discover new patterns and generate insights without the need to analyze the data based on a specific guess or hypothesis.” This exploratory approach, Heumos explains, is a unique feature of ehrapy.

Ehrapy allows researchers to sort, cluster and analyze large, heterogeneous and complex datasets without any pre-existing assumptions. This opens up new insights that can then be explored in more depth.

“The exploratory approach brings new perspectives to the analysis of health data,” explains Heumos. “Due to their complexity and heterogeneity, these data are often not analyzed as efficiently as they could be.” Ehrapy thus opens up new perspectives to make health data more useful for medical research and practice.

The long-term goal: systematic use in clinical practice

Ehrapy was designed from the ground up as open source software. “It was important for us to make the software available to the scientific community from day one,” Heumos emphasizes.

The software is available as a Python package on GitHub, an online platform for software development, and can be used and developed by researchers around the world.

Currently, ehrapy is focused on efficient and rapid analysis of research datasets, such as those stored in large health research centers. “Routine use in clinical practice is a long-term goal, but for now, we are focused on providing the research community with a powerful tool,” Heumos said.

In the future, the team plans to provide standardized databases for electronic medical records (EMRs). These databases will enable better integration and analysis of large volumes of medical data. In addition, this will facilitate the development of EMR atlases that can serve as reference datasets to contextualize and annotate new datasets.

A long journey

“Ehrapy enables comprehensive data analysis across all systems, which can be a milestone for future AI systems in medicine. I therefore hope for relatively rapid adoption at different sites,” says Professor Fabian Theis, Director of the Helmholtz Institute for Computational Biology Munich and Professor at TUM. “Establishing such technologies in medicine is a long process that can take decades. Our goal is to bridge the gap between biomedical research and practical application in medicine.”

Theis further explains that the development team is focusing on exploratory data analysis methods in a holistic form to more easily reveal hidden connections and adds: “We are also trying to support academic and commercial players in the healthcare sector.”