Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Perioperative Risk Stratification with AI-Powered Chatbots: A Systematic Review and Meta-Analysis.

Valentina Bellini1, Matteo Panizzi1, Stefano Delrio1

  • 1Anesthesiology, Critical Care and Pain Medicine Division, Department of Medicine and Surgery, University of Parma, Viale Gramsci 14, 43126 Parma, Italy.

Journal of Clinical Medicine
|June 26, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Smarter rules for digital health: How the digital omnibus can simplify without sacrificing patient rights.

Digital health·2026
Same author

Artificial intelligence in the prediction of intraoperative red blood cell transfusion in cardiac surgery: a systematic review and diagnostic test accuracy meta-analysis.

Brazilian journal of anesthesiology (Elsevier)·2026
Same author

Operator wellbeing as a translational endpoint: a dimension missing from the AI implementation framework in anesthesiology.

Journal of clinical monitoring and computing·2026
Same author

Identification of physiological clusters in acute hypoxemic respiratory failure patients undergoing non-invasive respiratory support using EIT-based t-SNE and spectral clustering.

Intensive care medicine experimental·2026
Same author

Artificial Intelligence-Guided Artificial Nutrition in Critical Illness: Integrating Indirect Calorimetry and BIVA for Metabolic Precision.

Nutrients·2026
Same author

From Measuring to Protecting "Days at Home": Toward Frailty-Informed Monitoring After Serious Health Events.

Journal of the American Geriatrics Society·2026
Same journal

Evidence-Based Clinical Recommendations for the Appropriate Use of Diagnostic Tests in Pediatric Allergology: Focus on Asthma, Rhinoconjunctivitis, and Keratoconjunctivitis Vernal.

Journal of clinical medicine·2026
Same journal

Surgical and Transcatheter Approach of a Failed Mitral Valve Repair: A Comprehensive Review on Selecting the Most Suitable Approach.

Journal of clinical medicine·2026
Same journal

Hybrid Metaheuristic Feature Selection for Breast Cancer Detection in Digital Mammography: A Feasibility Study with Nested Validation, Benchmarking, and External Stress Testing.

Journal of clinical medicine·2026
Same journal

Identity Transformation and the Role of Accountability in Recovery from Problematic Pornography Use: A Phenomenological-Hermeneutical Study.

Journal of clinical medicine·2026
Same journal

Does Early Surgical Treatment in Degenerative Cervical Myelopathy Have a Favorable Clinical Outcome and Impact on Quality of Life?

Journal of clinical medicine·2026
Same journal

Shear Wave Elastography in Musculoskeletal Imaging: A Narrative Review.

Journal of clinical medicine·2026
See all related articles
This summary is machine-generated.

Large language model (LLM)-based chatbots show promise in routine perioperative risk stratification but are unreliable for complex cases. Evidence certainty is low, recommending clinician-supervised use for standard assessments only.

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Healthcare
  • Anesthesiology

Background:

  • Chatbots offer rapid medical information access, documentation aid, and patient education in clinical settings.
  • Their potential for personalized perioperative risk stratification (PRS) and anesthesia planning is recognized but not fully established.
  • The definitive role of chatbots in PRS requires evaluation against standard clinical judgment.

Purpose of the Study:

  • To evaluate the performance of large language model (LLM)-based chatbots in perioperative risk stratification (PRS).
  • To compare chatbot performance with standard clinical judgment.
  • To assess the certainty of evidence supporting chatbot use in PRS.

Main Methods:

  • Systematic review following PRISMA guidelines, searching multiple databases through January 2026.
Keywords:
anesthesia planningartificial intelligencechatbotclinical decision supportperioperativerisk assessmentrisk managementrisk stratification

Related Experiment Videos

  • PICO framework defined: adult surgical patients (P), LLM-based chatbots for PRS (I), clinician assessment (C), performance metrics (O).
  • Risk of bias, study quality, and evidence certainty assessed using PROBAST-AI, RoB-2, ROBINS-I, and GRADE; random-effects meta-analysis performed.

    • Main Results:

    • Eleven studies (N=227,059) included; meta-analysis showed pooled chatbot accuracy of 0.90 for AI-clinician concordance in PRS and ASA classification.
    • Subgroup analysis: ASA status prediction accuracy was 0.91, while exploratory PRS accuracy was 0.73; performance decreased with patient complexity.
    • Evidence limited by small sample sizes, single-center bias, inconsistent metrics, and incomplete adverse event reporting; publication bias possible.

    Conclusions:

    • LLM-based chatbots demonstrate promising performance in routine perioperative risk stratification but are unreliable for complex cases, posing potential safety concerns.
    • Very low GRADE certainty of evidence necessitates cautious use.
    • Recommended as clinician-supervised decision support for routine ASA assessment, not for autonomous use in complex cases or general PRS.