Deep Learning–Based Early Detection of Major Adverse Cerebral Injuries in Cardiothoracic and Vascular Surgery
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Background
Despite advances in central nervous system (CNS)-protective anesthetic and surgical strategies, perioperative stroke remains a significant concern in high-risk cardiothoracic and vascular surgery (CTVS). Early detection, facilitating timely and prompt intervention, is often hindered by sedation and mechanical ventilation (MV) in the immediate postoperative period. This study aimed to develop and validate a deep learning (DL)-based artificial intelligence (AI) program for early detection of severe, surgery-related major adverse cerebral injury (sMACI), encompassing fatal CNS and systemic insults in high-risk CTVS patients.
Methods
We retrospectively analyzed data from 4,455 patients who underwent seven types of CTVS (2010–2021), requiring postoperative ICU admission and ongoing MV. Continuous vital signs (heart rate, blood pressures, respiratory rate, pulse oximetry saturation, temperature) were extracted from the operating room (OR) and intensive care unit (ICU), along with demographic and laboratory data. sMACI was defined as significant postoperative CNS injury (modified Rankin Scale ≥3 at 1 month) or 1-month mortality. Two-tier DL models were constructed: Model 1 using ICU data alone, and Model 2 integrating pre-ICU and ICU data. Performance in detecting sMACI within 24 hours of ICU admission was assessed using the area under the receiver operating characteristic curve (AUROC) and precision-recall curve (AUPRC).
Results
Among 4,455 patients, 5% experienced sMACI. Model 1 achieved an AUROC of 0.809 (95% CI: 0.759–0.858) and an AUPRC of 0.275 (0.195–0.375). Model 2 showed improved detection (AUROC 0.826 [0.781–0.871]; AUPRC 0.322 [0.233–0.423]). Both models outperformed conventional early warning scores and other machine learning algorithms, demonstrating robust performance as early as 4 hours after ICU admission. Key contributors included systolic blood pressure, heart rate, diastolic blood pressure, mean arterial pressure, and pulse oximetry saturation.
Conclusions
A DL-based AI program leveraging continuous vital signs enables effective early detection of severe surgery-related CNS and systemic injury in high-risk CTVS patients, outperforming established scoring systems and other machine learning approaches.
