Key result
A deep learning-based artificial intelligence program integrating pre-ICU and ICU continuous vital signs detected severe surgery-related major adverse cerebral injury with an AUROC of 0.826.
Why the study?
Perioperative stroke remains a significant concern in high-risk cardiothoracic and vascular surgery, but early detection is hindered by sedation and mechanical ventilation postoperatively.
Does a deep learning-based AI program using continuous vital signs improve the early detection of major adverse cerebral injuries in high-risk cardiothoracic and vascular surgery patients compared to conventional scoring systems?
Observational (n=4,455)
No
Does a deep learning-based AI program using continuous vital signs improve the early detection of major adverse cerebral injuries in high-risk cardiothoracic and vascular surgery patients compared to conventional scoring systems?
Effect estimate: AUROC 0.826 (95% CI 0.781-0.871)
A deep learning model integrating continuous perioperative vital signs outperformed conventional early warning scores in detecting severe cerebral and systemic injuries within 24 hours of ICU admission after cardiothoracic and vascular surgery.
May enable earlier stroke detection in sedated CTVS patients; hypothesis-generating until prospective validation.
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.
No takes yet. Share an insight, caveat, or question.
Tae et al. (2025) conducted an observational in High-risk cardiothoracic and vascular surgery (CTVS) (n=4,455). Deep learning-based artificial intelligence program (Model 2) vs. Conventional early warning scores (NEWS, MEWS) and other machine learning algorithms was evaluated on Detection of severe, surgery-related major adverse cerebral injury (sMACI) within 24 hours of ICU admission (AUROC 0.826, 95% CI 0.781-0.871). A deep learning-based artificial intelligence program integrating pre-ICU and ICU continuous vital signs detected severe surgery-related major adverse cerebral injury with an AUROC of 0.826.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: