Leveraging artificial intelligence for surgical site infection surveillance: A comparison of 5 large language models - 27/03/26
, Faisal Jamil, MS b, Ahsan Shaikh, MS b, Sehrish Ilyas, BS b, Abdullah Bin Masood, BS b, Muhammad Usman Afzal, MS b, Awais Touseef, BS b, Ali Noor, BS b, Mirza Wasim-ud-Din, MCS b, Muhammad Tayyib Akbar, MCS b, Sajid Ali, MS b, Muhammad Abid Nazir, MCS b, Amir Mukhtar, MS b, Faisal Sultan, MBBS aRésumé |
We conducted a retrospective study to evaluate the performance of 5 large language models in detecting surgical site infections (SSIs), compared with manual surveillance by an infection preventionist nurse. Forty abdominal surgery patients were included. Manual review achieved 100% diagnostic accuracy. All large language models demonstrated high accuracy (90%-95%) and strong agreement with manual review (κ = 0.80-0.90), with no statistically significant differences in performance ( P > .05). AI-based tools may enhance the efficiency of surgical site infection surveillance.
Le texte complet de cet article est disponible en PDF.Highlights |
• | We compared 5 LLMs with manual review for SSI surveillance. |
• | Manual review achieved 100% accuracy in SSI detection. |
• | LLMs demonstrated high accuracy and agreement with manual review. |
• | LLMs detected deep and organ-space SSIs better than superficial infection. |
• | AI tools hold promise for SSI detection and need further optimization. |
Key Words : Infection control, Healthcare-associated infections, Healthcare epidemiology
Plan
| Conflicts of interest: None to report. |
Vol 54 - N° 4
P. 451-453 - avril 2026 Retour au numéroBienvenue 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 ?
