Integrating machine learning with web-based tools for personalized prognosis in oral adenoid cystic carcinoma

• Published in: Journal of stomatology, oral and maxillofacial surgery p. 102143
• Main Authors: Alshwayyat, Sakhr, Alkhatib, Mesk, Almahariq, Hebah, Alshwayyat, Mustafa, Alshwayyat, Tala Abdulsalam, Salieti, Hamza Al, Khasawneh, Lina
• Format: Journal Article
• Language: English
• Published: Elsevier Masson SAS 08.11.2024
• Subjects: Adenoid cystic carcinoma; Adjuvant radiotherapy; Head and neck neoplasms; Machine learning; Prognosis; Survival analysis; Adjuvant radiotherapy; Survival analysis; Prognosis; Head and neck neoplasms; Adenoid cystic carcinoma; Machine learning
• ISSN: 2468-7855; 2468-7855
• DOI: 10.1016/j.jormas.2024.102143

Adenoid cystic carcinoma (ACC) of the oral cavity is a rare head and neck cancer. This rarity contributes to the paucity of comprehensive research on this cancer thereby complicating the development of evidence-based treatment strategies. This study aims to use machine learning (ML) techniques to analyze survival outcomes and optimize treatment approaches of ACC. The SEER database (2000–2020) was used in this study. Cox regression analysis was used to identify the prognostic variables; prognostic models using five ML algorithms were constructed to predict the 5-year survival rates. A validation method incorporating the area under the curve (AUC) of the receiver operating characteristic (ROC) curve was used to validate the accuracy and reliability of ML models. Also, Kaplan-Meier survival analysis was performed. This study's sample included 645 patients. The most common primary site for ACC was the hard palate, followed by the cheek mucosa. Survival rates varied across treatment groups, with the highest rates observed in patients who underwent surgery only. ML models revealed that the most significant prognostic factors were age, metastasis, and surgery. This study contributes evidence and knowledge to the limited literature on ACC and emphasizes the importance of adjuvant radiotherapy. This study highlights that metastasis and age are key prognostic factors. Furthermore, the developed ML-based web tool offers a novel approach for the personalized prognosis of these rare cancer types.