Artificial intelligence and machine learning for prediction of postoperative complications: A systematic review focused on anesthesiology, perioperative risk stratification, and clinical applicability.
- 1Department of Anesthesiology and Critical Care, Mohammed V Military Teaching Hospital, Rabat, Morocco.
- 2Department of Plastic Surgery, Mohammed V Military Teaching Hospital, Rabat, Morocco.
Abstract
Artificial intelligence (AI) and machine learning (ML) are increasingly used to predict postoperative complications, but their clinical value for anesthesiologists depends on more than discrimination alone. This systematic review evaluated AI- and ML-based models for predicting postoperative complications in surgical patients, with emphasis on model performance, validation, calibration, timing of predictor availability, interpretability, and clinical applicability. The review followed Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 principles. Eligible studies developed, validated, or compared AI/ML models for postoperative complication prediction and reported at least one performance metric. Risk of bias was assessed using Prediction model Risk of Bias ASsessment Tool (PROBAST), and reporting quality was interpreted in light of Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) principles. Thirty-five studies were included. The most frequently predicted outcomes were acute kidney injury, postoperative delirium, cardiovascular complications, infectious complications, and composite postoperative morbidity. Reported best-model discrimination ranged approximately from 0.70 to 0.97. Models incorporating intraoperative variables often showed stronger performance than preoperative-only models, particularly for acute kidney injury and infectious complications, but this reduced their usefulness for early preoperative decision-making. External validation was uncommon, calibration was inconsistently reported, and the analysis domain was the most frequent source of concern in PROBAST assessment. Current AI/ML models for postoperative complication prediction are promising, but their routine use in anesthesiology requires stronger external validation, transparent calibration, workflow integration, and clinically interpretable decision-support strategies.
Related
- Association of a multimodal perioperative nutritional/ERAS care pathway with postoperative infectious complications following radical hysterectomy for cervical cancer: a retrospective nonconcurrent cohort study
- Impact of perioperative physical exercise on postoperative pulmonary complications in patients undergoing cardiac surgery: a systematic review and meta-analysis
- Assessing the Performance of Artificial Intelligence on Anesthesiology In-Training Examinations and Applicability in Medical Education
- Bridging the Artificial Intelligence Translation Gap in Perioperative Pulmonary and Respiratory Complications: A Practical Framework for Institution-Level Implementation
- Association between Perioperative Blood Glucose Levels and Wound Complications in Diabetic Patients Undergoing Adult Spinal Deformity Surgery: A Retrospective Cohort Study
BibTeX
@article{hafiani2026artificial,
title = {{Artificial intelligence and machine learning for prediction of postoperative complications: A systematic review focused on anesthesiology, perioperative risk stratification, and clinical applicability.}},
author = {Hamza Hafiani and Hamza Kassimi and Salma Bekkour and Rim Bentalba and Khalil Abou Elalaa},
journal = {Saudi journal of anaesthesia},
year = {2026},
month = oct,
doi = {10.4103/sja.sja_493_26},
url = {https://europepmc.org/article/MED/42960327},
note = {CC BY-NC-SA},
}
RIS
TY - JOUR
TI - Artificial intelligence and machine learning for prediction of postoperative complications: A systematic review focused on anesthesiology, perioperative risk stratification, and clinical applicability.
AU - Hamza Hafiani
AU - Hamza Kassimi
AU - Salma Bekkour
AU - Rim Bentalba
AU - Khalil Abou Elalaa
PY - 2026
DA - 2026/10/01
JO - Saudi journal of anaesthesia
DO - 10.4103/sja.sja_493_26
UR - https://europepmc.org/article/MED/42960327
AB - Artificial intelligence (AI) and machine learning (ML) are increasingly used to predict postoperative complications, but their clinical value for anesthesiologists depends on more than discrimination alone. This systematic review evaluated AI- and ML-based models for predicting postoperative complications in surgical patients, with emphasis on model performance, validation, calibration, timing of predictor availability, interpretability, and clinical applicability. The review followed Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 principles. Eligible studies developed, validated, or compared AI/ML models for postoperative complication prediction and reported at least one performance metric. Risk of bias was assessed using Prediction model Risk of Bias ASsessment Tool (PROBAST), and reporting quality was interpreted in light of Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) principles. Thirty-five studies were included. The most frequently predicted outcomes were acute kidney injury, postoperative delirium, cardiovascular complications, infectious complications, and composite postoperative morbidity. Reported best-model discrimination ranged approximately from 0.70 to 0.97. Models incorporating intraoperative variables often showed stronger performance than preoperative-only models, particularly for acute kidney injury and infectious complications, but this reduced their usefulness for early preoperative decision-making. External validation was uncommon, calibration was inconsistently reported, and the analysis domain was the most frequent source of concern in PROBAST assessment. Current AI/ML models for postoperative complication prediction are promising, but their routine use in anesthesiology requires stronger external validation, transparent calibration, workflow integration, and clinically interpretable decision-support strategies.
SN - 1658-354X
SN - 0975-3125
ER -