Machine learning analysis of heart rate variability to detect delayed cerebral ischemia in subarachnoid hemorrhage.

OBJECTIVES: Approximately 30% of patients with aneurysmal subarachnoid hemorrhage (aSAH) develop delayed cerebral ischemia (DCI). DCI is associated with increased mortality and persistent neurological deficits. This study aimed to analyze heart rate variability (HRV) data from patients with aSAH using machine learning to evaluate whether specific patterns could be found in patients developing DCI. MATERIAL & METHODS: This is an extended, in-depth analysis of all HRV data from a previous study wherein HRV data were collected prospectively from a cohort of 64 patients with aSAH admitted to Sahlgrenska University Hospital, Gothenburg, Sweden, from 2015 to 2016. The method used for analyzing HRV is based on several data processing steps combined with the random forest supervised machine learning algorithm. RESULTS: HRV data were available in 55 patients, but since data quality was significantly low in 19 patients, these were excluded. Twelve patients developed DCI. The machine learning process identified 71% of all DCI cases. However, the results also demonstrated a tendency to identify DCI in non-DCI patients, resulting in a specificity of 57%. CONCLUSIONS: These data suggest that machine learning applied to HRV data might help identify patients with DCI in the future; however, whereas the sensitivity in the present study was acceptable, the specificity was low. Possible confounders such as severity of illness and therapy may have affected the result. Future studies should focus on developing a robust method for detecting DCI using real-time HRV data and explore the limits of this technology in terms of its reliability and accuracy.

Cerebral ischemia detection using artificial intelligence (CIDAI)-A study protocol.

BACKGROUND: The onset of cerebral ischemia is difficult to predict in patients with altered consciousness using the methods available. We hypothesize that changes in Heart Rate Variability (HRV), Near-Infrared Spectroscopy (NIRS), and Electroencephalography (EEG) correlated with clinical data and processed by artificial intelligence (AI) can indicate the development of imminent cerebral ischemia and reperfusion, respectively. This study aimed to develop a method that enables detection of imminent cerebral ischemia in unconscious patients, noninvasively and with the support of AI. METHODS: This prospective observational study will include patients undergoing elective surgery for carotid endarterectomy and patients undergoing acute endovascular embolectomy for cerebral arterial embolism. HRV, NIRS, and EEG measurements and clinical information on patient status will be collected and processed using machine learning. The study will take place at Sahlgrenska University Hospital, Gothenburg, Sweden. Inclusion will start in September 2020, and patients will be included until a robust model can be constructed. By analyzing changes in HRV, EEG, and NIRS measurements in conjunction with cerebral ischemia or cerebral reperfusion, it should be possible to train artificial neural networks to detect patterns of impending cerebral ischemia. The analysis will be performed using machine learning with long short-term memory artificial neural networks combined with convolutional layers to identify patterns consistent with cerebral ischemia and reperfusion. DISCUSSION: Early signs of cerebral ischemia could be detected more rapidly by identifying patterns in integrated, continuously collected physiological data processed by AI. Clinicians could then be alerted, and appropriate actions could be taken to improve patient outcomes.