Machine learning directed sentinel lymph node biopsy in cutaneous head and neck melanoma. Issue 4 (6th February 2022)

• Record Type: Journal Article
• Authors: Oliver, Jamie R.; Karadaghy, Omar A.; Fassas, Scott N.; Arambula, Zack; Bur, Andrés M.
• Is Part Of: Head & neck. Volume 44:Issue 4(2022)
• Page Start: 975
• Page End: 988
• Publication Date: 2022-02-06
• Subjects: artificial intelligence -- cutaneous melanoma -- head and neck melanoma -- machine learning -- sentinel lymph node biopsy; Head -- Diseases -- Periodicals; Neck -- Diseases -- Periodicals; Head -- Periodicals; Neck -- Periodicals; Face -- Periodicals; 617.51059
• DOI: 10.1002/hed.26993
• Languages: English
• ISSNs: 1043-3074

Abstract

Abstract: Background: The specificity of sentinel lymph node biopsy (SLNB) for detecting lymph node metastasis in head and neck melanoma (HNM) is low under current National Comprehensive Cancer Network (NCCN) treatment guidelines. Methods: Multiple machine learning (ML) algorithms were developed to identify HNM patients at very low risk of occult nodal metastasis using National Cancer Database (NCDB) data from 8466 clinically node negative HNM patients who underwent SLNB. SLNB performance under NCCN guidelines and ML algorithm recommendations was compared on independent test data from the NCDB ( n = 2117) and an academic medical center ( n = 96). Results: The top‐performing ML algorithm (AUC = 0.734) recommendations obtained significantly higher specificity compared to the NCCN guidelines in both internal (25.8% vs. 11.3%, p < 0.001) and external test populations (30.1% vs. 7.1%, p < 0.001), while achieving sensitivity >97%. Conclusion: Machine learning can identify clinically node negative HNM patients at very low risk of nodal metastasis, who may not benefit from SLNB.