ABOUT

The research group AI and ML for Healthcare aims to develop machine learning-based solutions for clinical support applications, with emphasis on data analysis and feature extraction, timeseries prediction, and artificial intelligence-enabled diagnostic support.Medical infrastructure underwent severe strain during the initial onset of the COVID-19 pandemic, especially with medical staff being overwhelmed with the large amount of diagnoses necessary. This highlights the need for efficient initial triage methods, and effective early detection and diagnosis support systems that would alert hospital personnel to potentially life-threatening developments in patient states. The research group AI and ML for Healthcare is working to fulfil these needs through the application of modern machine learning and data analysis methods, supported by high-performance computing (HPC) infrastructure.

Within the Program-oriented Funding (PoF IV) of Helmholtz Information, this group contributes to Program 1 “Engineering Digital Futures”, Topic 1 “Enabling Computational- & Data-Intensive Science and Engineering” and it is part of the Joint Lab Supercomputing and Modeling for the Human Brain (SMHB), of the Center for Advanced Simulation and Analytics (CASA) and of the European Joint Virtual Lab on Artificial Intelligence, Data Analytics and Scalable Simulation (AIDAS).

RESEARCH TOPICS

• Developing a deep learning-based surrogate model for a mechanistic virtual patient simulation, and applying this model for the early diagnosis of Acute Respiratory Distress Syndrome (ARDS).
• Setting up pipelines for medical data analysis, processing, and visualisation.
• HPC-accelerated retraining of COVID-Net on newly obtained Chest X-rays with potential applications of transfer learning towards other conditions affecting the lungs.
• Parallelised hyperparameter optimization for clinical machine learning models.