Translational Informatics enables increasingly voluminous biomedical data to inform predictive, preventive, and personalized health applications.
In Translational Informatics, the focus is on studying and applying existing data to bridge new ways to improve diagnosis, staging, prognosis, and treatment of disease.
At BMIR, our research efforts have clinical significance for enhancing patient care and scientific significance for offering new insights into disease and diverse biological processes.
The Gevaert team focuses on biomedical data fusion: the development of machine learning methods for biomedical decision support using multi-scale biomedical data. The team has pioneered data-fusion work using Bayesian and kernel methods in the study of breast and ovarian cancer. Additionally, the team has developed computational algorithms for the identification of driver genes using multi-omics data.
Dr. Gevaert and his team work on multi-scale biomedical data fusion methods, reasoning across molecular data, cellular data, histological data, and medical imaging data to provide new insights and tools to address complex diseases.
Their work particularly focuses on identifying the mechanisms for how health is maintained, and how disease develops when normal biological systems go awry. They develop diagnostic and predictive tools that can be used for guiding patient treatment, and more accurately stratifying their risk level.
Despite decades of effort, cancer remains a highly intractable disease with a few notable exceptions. Dr. Gentles aims to identify why some patients and populations have better outcomes, and how certain treatments might be better for some patients and not others. Beyond cancer, they collaborate with groups in neuroscience and regenerative medicine.
The Khatri team has created an environment where people with different expertise and interests collaborate to improve understanding of the immune system and to accelerate translational medicine. Dr. Khatri and his team focus on how machine learning can turn the traditional paradigm in biomedical research on its head.
Instead of limiting heterogeneity in data, as a traditional biomedical research experiment does, they are embracing heterogeneity in data. The team of researchers firmly believes that, in this way, they can accelerate translational medicine. They have already repeatedly demonstrated that biological and technical heterogeneity in data, coupled with novel machine learning methods, is not only desired, but required, to identify robust disease signatures across patient populations that are diagnostic, prognostic, therapeutic, and mechanistic.