The HEART research project explores a non-invasive method for monitoring the body’s fluid needs based on EKG signals. AI-powered analysis of large datasets supports precision medicine and offers significant benefits for patients.
The research project HEART explores a completely non-invasive method for accurately determining the body’s fluid needs using EKG signals. The use of artificial intelligence in analyzing large retrospective datasets represents a step towards precision medicine, where treatment decisions are based on individual criteria.
In healthy individuals, the autonomous regulation of fluid balance fails during prolonged surgical procedures or extreme stress. In long-term operations involving blood loss or excessive evaporation, the patient’s fluid needs must be accurately determined through advanced hemodynamic monitoring, as significant deviations from the optimal range can cause serious complications. All currently available methods for advanced monitoring are invasive (i.e., they require blood vessel punctures) and thus susceptible to complications. There is currently no precise, reliable, and easy-to-use non-invasive method for advanced monitoring.
The foundation of the targeted non-invasive method is the assumption that changes in fluid balance also affect the heart’s conduction system, and these changes must be reflected in the EKG. In the context of HEART, large amounts of retrospective data from the Kepler University Hospital Linz and appropriate public databases are analyzed to demonstrate a correlation between changes in EKG signals and fluid administration. State-of-the-art deep learning methods (e.g., CNN, LSTM, Transformer) are used to analyze the EKG excerpts, as well as more interpretable approaches based on established manually extracted EKG features from classical machine learning. The insights gained can then be validated in a potential follow-up project with prospective data.
HEART will pay special attention to balanced gender distribution and representative age distribution in data selection to prevent data biases and systematic prediction errors. The obtained analysis results will be tested for their applicability to different subpopulations.
The implementation of this novel and disruptive method would offer a much-needed, reliable, cost-efficient, and user-friendly patient monitoring system with several advantages of a non-invasive method: for anesthesiologists, a simple yet reliable first stage of advanced hemodynamic monitoring; for nursing staff, a time-saving application that staff can be quickly trained on; for patients, reduced risk and potentially shorter hospital stays; for hospital operators, a cost-effective solution. An extended benefit of non-invasive hemodynamic monitoring could also apply in extended (institutional) care or in the leisure sector. For example, low-threshold EKG measurements (e.g., wearables) could monitor the fluid needs of seniors or extreme athletes.
The research work on HEART is being carried out in close cooperation with the Department of Anesthesiology and Intensive Care Medicine at the Medical Faculty of the JKU Linz and the Division of General Anesthesia and Intensive Care Medicine at MedUni Vienna.
This project is funded by the FFG.
Head of Unit Medical Informatics
“`
Let me know if you need any further adjustments!
