Anna-Sophia Wahl is detecting motor behavior in health and disease with AI
26.04.2021 12:03
Branco Weiss Fellow Anna-Sophia Wahl designed and lead the biomedical research part as senior author of a paper published recently in Nature Machine Intelligence which reports the development of a new, fully automatic approach based on artificial intelligence to analyze motor behavior in animals and humans. The novel method detects and classifies behavior and its deviations which can be (e.g.) caused by neurological diseases. The paper presents the collaborative work by scientists from Heidelberg University, University of Zurich, University Hospital Zurich and Balgrist University Hospital.
Analysis of motor behavior —the dynamic change of posture— is essential to biomedical research and clinical diagnostics as it provides a non-invasive strategy for identifying motor impairment and its change caused by interventions. State-of-the-art instrumented movement analysis is time- and cost-intensive. In their study, the scientists introduce unsupervised behavior analysis and magnification (uBAM), an automatic deep learning algorithm for analyzing behavior by discovering and magnifying deviations. The research team has already been able to prove the effectiveness of this new approach with the aid of different animal models and studies with human patients. They tested, inter alia, the precision with which uBAM can differentiate between healthy and impaired motor activity. In their publication, the scientists report a very high retrieval rate both in mice and human patients. The approach based on artificial intelligence delivered even more detailed results than conventional methods – with significantly less effort.
UBAM could be applied both in basic biomedical research and in clinical diagnostics and beyond where traditional methods prove too complicated or not efficient enough. The scientists hope that it will lead to a better understanding of neuronal processes in the brain and the development of new therapeutic options.
Read the paper in Nature Machine Intelligence