Artificial intelligence and machine learning applications in ambulatory surgery – A systematic review - 12/03/26
, Vinaytosh Mishra c, Venkatraman Manda dAbstract |
Background |
We aimed to systematically review applications of artificial intelligence (AI) technologies for ambulatory surgical patients.
Methods |
We systematically searched PubMed, Scopus, Web of Science, and EBSCOhost (2015–2025). Studies were included if they used artificial intelligence in ambulatory surgical populations.
Results |
Of 26 studies identified, machine learning was used in 25, with a predominantly orthopaedic (65.3 %) focus. Except for two, all were originated in the USA. We found four themes: (1) Preoperative patient selection (n = 10) – Random forest (RF) and eXtreme gradient boost (XGBoost) algorithms predicted appropriateness with an area under curve (AUC) 0.72–0.85, (2) Same-day discharge prediction (n = 8) – Ensemble models demonstrated the highest AUC values (3) Postoperative management and complications (n = 3) – Artificial neural network incorporating intra- and postoperative features predicted opioid refill needs (4) Cost prediction (n = 4) – Ensemble models consistently outperformed single-model approaches.
Conclusions |
Our review underscores the promising potential of machine learning applications in ambulatory surgery, particularly with ensemble methods. We observed inconsistencies in the models; data related issues and a lack of external validation.
Le texte complet de cet article est disponible en PDF.Highlights |
• | The potential of machine learning in ambulatory surgery is vast and promising, offering numerous applications for patients. |
• | Most studies in this field have concentrated on preoperative patient selection and same-day discharge, often using data from a single national, state, or academic centre database in the USA. |
• | Machine learning algorithms were primarily applied to patients undergoing joint replacement or reconstruction, as well as spine surgical procedures. |
• | Machine learning algorithms, such as random forest and extreme gradient boosting (XGBoost), have shown promising results, particularly in predicting same-day discharge. |
• | Equally significant is the potential of the ensemble models technique, which combines multiple models to enhance performance, in predicting costs following orthopaedic surgeries. |
• | While the results of the studies are promising, it is crucial to note that they are not yet fully generalizable due to biases, data imbalance, model inconsistencies, and the critical need for external validation. |
Keywords : Artificial intelligence, Machine learning, Ambulatory surgery, Day case surgery, Outpatient surgery, Same-day discharge, Day surgery
Plan
Vol 255
Article 116775- mai 2026 Retour au numéro
Article précédent
- NPSA 2025 Presidential Address:Innovation, clinical translation, and leadership in surgery: From concept to impact
- Chad G. Ball
- Impact of preference signaling and geographic preferencing on research productivity and regional matching in orthopaedic surgery residency
- Iyad S. Ali, Puranjay Gupta, Miguel Gutierrez, Sia Cho, Tony Y. Lee, Giancarlo Riccobono, Owen Lema, Justin J. Lee, Matthew J. Weintraub, Freddy P. Jacome
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?