go-v.orgdoi

Data-Driven Anesthesiology: The Expanding Role of Artificial Intelligence in Predicting Perioperative Risks

Ricardo Xavier Cárdenas Zambrano, Paulina Gutiérrez Medina, Edgar Felipe Carranza Vargas, Jesus Elias Benedetti López, Júnior Antonio Barreto Acevedo, Daniel Alberto Madrid González, Ingrid Monserrat Jaimes Hernández, Jorge Angel Velasco Espinal · IECCMEXICO · 2025

  • DOI 10.64784/027
  • Publisher OpenAlex
  • Type article
  • Issued 2025

Not cached yet. This record was fetched live for this request and is stored after the lookup. Reopening the page should serve the cached copy.

IECCMEXICO · OpenAlex · article · 2025

Abstract

Artificial intelligence (AI) has rapidly become one of the most significant technological innovations influencing modern anesthesiology. This review synthesizes recent evidence regarding the use of AI-based systems for perioperative risk prediction, intraoperative monitoring, clinical decision support, and postoperative surveillance. Across multiple studies, machine-learning models demonstrated superior predictive accuracy compared with conventional clinical tools, particularly in identifying patients at risk for postoperative complications and anticipating episodes of intraoperative hemodynamic instability.

Predictive systems based on arterial waveform analysis and deep-learning architectures consistently detected hypotension minutes before its clinical onset, allowing for more proactive management. Additionally, AI-enhanced interventions improved adherence to best practices, reduced variability in clinical decision-making, and strengthened early detection of physiologic deterioration. However, despite these promising advances, the literature also highlights important challenges. External validation remains limited, with many models showing reduced performance when applied to new populations or different healthcare systems.

Issues of transparency, explainability, and ethical implementation continue to hinder adoption, especially for complex deep-learning models. Infrastructure constraints in low- and middle-income countries further complicate implementation, emphasizing the need for context-adapted strategies. For healthcare systems in Mexico, Colombia, and Ecuador, the integration of AI offers opportunities to enhance perioperative safety but requires careful attention to local resource variability and workforce readiness. Overall, AI represents a powerful adjunct to anesthesiology practice when used with appropriate oversight, ethical safeguards, and clinical judgment.

Its continued development and responsible implementation hold substantial potential to improve patient safety, optimize perioperative care, and strengthen health system performance internationally.

Open the resolved locator · 10.64784/027

Metadata licence: OpenAlex metadata (CC0)