We are the Computational Medicine Group at the Inselspital Bern, under the supervision of Prof. Dr. Alexander Leichtle. Our research focuses on leveraging machine learning and big data to improve clinical diagnostics and personalized medicine.
Computational Medicine is a new field of medicine at the interface between data generating (mainly diagnostic) medical disciplines (e.g. "-omics") and data science (informatics, statistics). It provides information on patients, their health and underlying processes and pathways by exhaustive computational and statistical methodology, that exceed the capacities of conventional approaches.
Computational medicine tries to generate and assess models from existing data to predict/classify/diagnose new patients. It uses large-scale standard modeling approaches (GLMs, GEEs &c.), but also "deep" machine learning and digitally resembles complex decision-finding processes that today depend on physician's experience, knowledge, and intuition.
Our group works on exciting projects such as Swiss BioRef, which aims to create personalized reference ranges for laboratory medicine using automated tools. We also engage in PGXLink, a project linking pharmacogenomic data to drug metabolism, enhancing personalized treatment options.
We specialize in applying Bayesian models and AI-driven approaches to analyze clinical and metabolomic data, contributing to better predictions of disease outcomes, especially in fields like cardiovascular health and organ transplantation.
Our group is funded by the Swiss Personal Health Network as well as the Swiss National Science Foundation and the Bern Center of Precision Medicine.
Blatter, T. U., Nakas, C. T. & Leichtle, A. B. Direct, age- and gender-specific reference intervals: applying a modified M-estimator of the Yeo-Johnson transformation to clinical real-world data. J. Lab. Med. 0, (2024).
Blatter, T. U., Schär, D., Witte, H., Nakas, C. T. & Leichtle, A. B. Data Mining Reference Intervals by ICD-10 Stratified Differential Distributions. Clin. Chem. hvae089 (2024) doi:10.1093/clinchem/hvae089.
Blatter, T. U. et al. The BioRef Infrastructure, a Framework for Real-Time, Federated, Privacy-Preserving, and Personalized Reference Intervals: Design, Development, and Application. J. Méd. Internet Res. 25, e47254 (2023).
Liniger, Z., Ellenberger, B. & Leichtle, A. B. Computational Evidence for Laboratory Diagnostic Pathways: Extracting Predictive Analytes for Myocardial Ischemia from Routine Hospital Data. Diagnostics 12, 3148 (2022).
Blatter, T. U., Witte, H., Nakas, C. T. & Leichtle, A. B. Big Data in Laboratory Medicine—FAIR Quality for AI? Diagnostics 12, 1923 (2022).
