Development of machine learning models for the prediction of positive surgical margins in transoral robotic surgery (TORS)

• Published in: Head & neck Vol. 45; no. 3; pp. 675 - 684
• Main Authors: Costantino, Andrea, Sampieri, Claudio, Pirola, Francesca, De Virgilio, Armando, Kim, Se‐Heon
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.03.2023; Wiley Subscription Services, Inc
• Subjects: Algorithms; artificial intelligence; Carcinoma, Squamous Cell - pathology; Head & neck cancer; head and neck cancer; Head and Neck Neoplasms - etiology; Head and Neck Neoplasms - surgery; Humans; Laryngeal cancer; Learning algorithms; Machine Learning; Margins of Excision; Oropharyngeal Neoplasms - etiology; Oropharyngeal Neoplasms - surgery; personalized medicine; Retrospective Studies; Robotic surgery; robotic surgical procedures; Robotic Surgical Procedures - adverse effects; Squamous cell carcinoma; Treatment Outcome; robotic surgical procedures; head and neck cancer; artificial intelligence; personalized medicine; squamous cell carcinoma
• ISSN: 1043-3074; 1097-0347
• DOI: 10.1002/hed.27283

Purpose To develop machine learning (ML) models for predicting positive margins in patients undergoing transoral robotic surgery (TORS). Methods Data from 453 patients with laryngeal, hypopharyngeal, and oropharyngeal squamous cell carcinoma were retrospectively collected at a tertiary referral center to train (n = 316) and validate (n = 137) six two‐class supervised ML models employing 14 variables available pre‐operatively. Results The accuracy of the six ML models ranged between 0.67 and 0.75, while the measured AUC between 0.68 and 0.75. The ML algorithms showed high specificity (range: 0.75–0.89) and low sensitivity (range: 0.26–0.64) in detecting patients with positive margins after TORS. NPV was higher (range: 0.73–0.83) compared to PPV (range: 0.45–0.63). T classification and tumor site were the most important predictors of positive surgical margins. Conclusions ML algorithms can identify patients with low risk of positive margins and therefore amenable to TORS.