In NPJ precision oncology
Prognostic analysis for early-stage (stage I/II) melanomas is of paramount importance for customized surveillance and treatment plans. Since immune checkpoint inhibitors have recently been approved for stage IIB and IIC melanomas, prognostic tools to identify patients at high risk of recurrence have become even more critical. This study aims to assess the effectiveness of machine-learning algorithms in predicting melanoma recurrence using clinical and histopathologic features from Electronic Health Records (EHRs). We collected 1720 early-stage melanomas: 1172 from the Mass General Brigham healthcare system (MGB) and 548 from the Dana-Farber Cancer Institute (DFCI). We extracted 36 clinicopathologic features and used them to predict the recurrence risk with supervised machine-learning algorithms. Models were evaluated internally and externally: (1) five-fold cross-validation of the MGB cohort; (2) the MGB cohort for training and the DFCI cohort for testing independently. In the internal and external validations, respectively, we achieved a recurrence classification performance of AUC: 0.845 and 0.812, and a time-to-event prediction performance of time-dependent AUC: 0.853 and 0.820. Breslow tumor thickness and mitotic rate were identified as the most predictive features. Our results suggest that machine-learning algorithms can extract predictive signals from clinicopathologic features for early-stage melanoma recurrence prediction, which will enable the identification of patients that may benefit from adjuvant immunotherapy.
Wan Guihong, Nguyen Nga, Liu Feng, DeSimone Mia S, Leung Bonnie W, Rajeh Ahmad, Collier Michael R, Choi Min Seok, Amadife Munachimso, Tang Kimberly, Zhang Shijia, Phillipps Jordan S, Jairath Ruple, Alexander Nora A, Hua Yining, Jiao Meng, Chen Wenxin, Ho Diane, Duey Stacey, Németh István Balázs, Marko-Varga Gyorgy, Valdés Jeovanis Gil, Liu David, Boland Genevieve M, Gusev Alexander, Sorger Peter K, Yu Kun-Hsing, Semenov Yevgeniy R
2022-Oct-31
