Everyday life in the intensive care unit: Patients are surrounded by devices that record vital data, such as blood pressure, heart rate or oxygen saturation, and much more information. As a result, staff are confronted with an almost unmanageable number of displays, warning signals and screens.
To enable nurses and physicians to concentrate more on their patients, artificial intelligence techniques are to provide support in analyzing the diverse patient data. This is where the RIDIMP project of the Bremen hospital association Gesundheit Nord and the DFKI Cyber-Physical Systems research unit comes in.
In order to be able to learn meaningfully from the myriad of information, it must be evaluated. For this purpose, the medical experts at Gesundheit Nord define two numerical scores, which are composed of many individual parameters such as oxygen saturation, pulse or medication administration, and assess the condition of the circulation or respiration on the basis of the data on a scale from 0 (uncritical) to 9 (highly critical). These scores are in turn used to evaluate available historical patient data, and from this, using machine learning techniques, implement a prediction for the value of the scores in the future, and thus for the likelihood of a collapse (decompensation) of circulation or respiration.
In this way, the development of the two scores and thus the patient’s health status in the future can be predicted very precisely from the large amount of data collected. In this way, medical professionals can be alerted to impending problems at an early stage.
At the Hannover Messe, the project team will demonstrate a prediction algorithm on selected historical patient data from the intensive care unit. A prediction is calculated live on this data; the visitor can then compare how good this prediction is. The exhibit is interactive - visitors can move along the timeline, speed up, slow down or stop the passage of time.
The RIDIMP project is part of the overall KI-SIGS project funded by the German Federal Ministry of Economics and Climate Protection (BMWK), which is dedicated to building an AI space for intelligent health systems.