Authors
Amarjeet Kumar, Sovan Kumar Subudhi, Chandni Sinha, Kunal Singh, Poonam Kumari, Ajeet Kumar
Published in
Anaesthesia, critical care & pain medicine. Pages 101984. Sep 30, 2026. Epub Sep 30, 2026.
Abstract
Preanesthetic evaluation is essential for perioperative safety, yet it remains time-consuming, heavily reliant on documentation, and vulnerable to variability in data collection, risk assessment, and clinical decision-making. The increase in surgical cases, patient complexity, and digital health records has created opportunities for artificial intelligence (AI) to assist anesthesiologists in preoperative screening, risk assessment, and perioperative planning. New AI applications in anesthesiology include machine learning models for predicting perioperative risks, natural language processing (NLP) systems for extracting key information from unstructured records, and large language model (LLM)-based tools for documentation support and structured clinical summaries. Studies indicate these systems may enhance workflow efficiency, expand preanesthetic data collection, aid ASA physical status classification, and generate structured recommendations for investigations, optimization, and anesthetic plans, all with clinician oversight. This review explores the current role of AI in preanesthetic evaluation and perioperative planning, focusing on practical uses such as automated history synthesis, investigation choices, risk stratification, preoperative orders, and personalized anesthetic decision support. It also addresses system limitations like hallucination, bias, privacy issues, lack of explainability, and medicolegal concerns. Based on current evidence, AI is best suited as a decision-support tool for clinicians rather than a standalone replacement for anesthesiologists.
PMID:
42994619
Bibliographic data and abstract were imported from PubMed on 07 Nov 2026.
Read full publication at:
Please sign in
to see all details.
Advertisement
Stats
- Recommendations n/a n/a positive of 0 vote(s)
- Views 23
- Comments 0