Artificial Intelligence in the Context of Biomedical Signals
Mentored by Jochen Hampe & Jakob Kather
at EKFZ for Digital Health Dresden, TUD and UKD Dresden
The analysis of ECG signals is a key component in the detection and prediction of cardiac disease. In this research topic, we will explore the use of machine learning and neural networks for the prediction of cardiac attacks using ECG signals. The second research topic is the automation of sedation using deep learning analysis of multidimensional biosignals. This research will focus on developing a system for automatic monitoring of sedation levels in patients undergoing medical procedures.
Key research questions for this topic include:
- Improved detection algorithm for vectorcardiograms and reconstructing diagnostical ECG from orthogonal ECG.
- How can we incorporate variation in ECG signals due to different physiological factors, such as age and gender, in the synthetic data generation process?
- How can we leverage prior knowledge from the medical domain, such as anatomical knowledge, to improve the accuracy of the predictive models?
- How can we evaluate the performance of the models in predicting cardiac attacks and in the automatic monitoring of sedation levels using multidimensional biosignals?
Work Environment
The research will be conducted in close collaboration with medical experts in cardiology at the University Hospital Dresden (UKD) and the EKFZ for Digital Health. The EKFZ for Digital Health offers a unique research platform with a Working Lab in cooperation with AI experts in the field of oncology, which provides an ideal environment for interdisciplinary research in digital health.
Prerequisites
- Master's Degree (or equivalent) in computer science, electrical engineering, applied mathematics, or related fields of expertise
- Very good programming skills, with practical experience in Python
- Strong background and practical experience in time series analysis using PyTorch or equivalent packages
- Ability to collaborate effectively in an interdisciplinary environment
- Strong motivation to publish and present research results at conferences.
Topics All Topics
Adaptive / Context Sensitive Data Provision in Mobile Applications
AI Controlled Wireless Mesh Networks for Medical Applications in Crisis Situations (AWESOME)
Artificial Intelligence in the Context of Biomedical Signals
Explainable AI for reliable computer assisted surgery
External Systems Biology Knowledge Integration in Large Language Models
Features of Fitness Landscapes
From protein structure prediction to explainable AI in Oncology
GeoSOP: Geometry for surgical outcome prediction
Natural Neural networks inspire Artificial Neural Networks in Therapeutic Design
Reinforcement Learning for Mechanical Ventilation
StochasticAI – Integrating Stochastic Modeling with AI
SuperTouch - Data-driven tactile sensing for robot-assisted cancer surgery
Teaching artificial intelligence conformational dynamics of proteins
The Use of AI by the Civil Service in Light of the Principles of Democracy and the Rule of Law