Trusting Machine Learning Results from Medical Procedures in the Operating Room
This addresses the critical problem of unreliable ML-based cerebral ischemia detection during medical procedures for clinicians and patients, but it is incremental as it highlights limitations rather than providing a solution.
The study investigated whether machine learning analysis of continuous physiological data from non-invasive monitors could detect cerebral ischemia during carotid endarterectomy and endovascular thrombectomy procedures. Results showed consistent detection for carotid endarterectomy patients but unreliable results (including extreme values like 1.0 accuracy) for thrombectomy patients, attributed to short procedure durations and poor-quality data.
Machine learning can be used to analyse physiological data for several purposes. Detection of cerebral ischemia is an achievement that would have high impact on patient care. We attempted to study if collection of continous physiological data from non-invasive monitors, and analysis with machine learning could detect cerebral ischemia in tho different setting, during surgery for carotid endarterectomy and during endovascular thrombectomy in acute stroke. We compare the results from the two different group and one patient from each group in details. While results from CEA-patients are consistent, those from thrombectomy patients are not and frequently contain extreme values such as 1.0 in accuracy. We conlcude that this is a result of short duration of the procedure and abundance of data with bad quality resulting in small data sets. These results can therefore not be trusted.