Predictive Deep Learning for Medicine and Healthcare
Photo: Anna Sposato
Wellcome to the Institut for Predictive Deep Learning for Medicine and Healthcare
|
Friedrichstrasse 25
|
|
The institute for Predictive Deep Learning for Medicine and Healthcare (PredLMed) at the Justus-Liebig-University is dedicated to developing machine learning and deep learning algorithms to advance systems medicine for analyzing multi-modal biomedical data and the critical transfer of such technologies into clinical practice. The group focuses particularly on the integrative analysis of multi-modal medical data, such as electronic patient records, molecular data such as gene and protein expression, and medical imaging data to support disease prediction and therapy optimization. ML technologies have been applied successfully in numerous health research domains, such as oncology, psychiatry, and cardiology. However, several challenges persist, impeding the translation of these advances into research and practice. Specifically, limited sample sizes, data privacy, and systematic biases within individual patient cohorts contribute to data scarcity and heterogeneity in medical registries and biomedical data. Additionally, the lack of interpretable and reliable predictions undermines trust in otherwise highly accurate models. Therefore, the PredLMed group aims to address these challenges through employing and developing novel computational architectures and algorithms, including transfer learning and foundation models to overcome data integration issues and accommodate small sample sizes, online and time-critical event prediction, federated learning for secure integration of distributed medical datasets and resources, as well as the use of explainable artificial intelligence methods to increase user trust by enhancing model and prediction reliability and interpretability. |
Lectures:
|