TY - JOUR
T1 - Development and validation of time-to-event models to predict metastatic recurrence of localized cutaneous melanoma
AU - Wan, Guihong
AU - Leung, Bonnie W.
AU - DeSimone, Mia S.
AU - Nguyen, Nga
AU - Rajeh, Ahmad
AU - Collier, Michael R.
AU - Rashdan, Hannah
AU - Roster, Katie
AU - Zhou, Xu
AU - Moseley, Cameron B.
AU - Nirmal, Ajit J.
AU - Pelletier, Roxanne J.
AU - Maliga, Zoltan
AU - Marko-Varga, Gyorgy
AU - Németh, István Balázs
AU - Tsao, Hensin
AU - Asgari, Maryam M.
AU - Gusev, Alexander
AU - Stagner, Anna M.
AU - Lian, Christine G.
AU - Hurlbert, Marc S.
AU - Liu, Feng
AU - Yu, Kun Hsing
AU - Sorger, Peter K.
AU - Semenov, Yevgeniy R.
N1 - Publisher Copyright:
© 2023 American Academy of Dermatology, Inc.
PY - 2024/2
Y1 - 2024/2
N2 - Background: The recent expansion of immunotherapy for stage IIB/IIC melanoma highlights a growing clinical need to identify patients at high risk of metastatic recurrence and, therefore, most likely to benefit from this therapeutic modality. Objective: To develop time-to-event risk prediction models for melanoma metastatic recurrence. Methods: Patients diagnosed with stage I/II primary cutaneous melanoma between 2000 and 2020 at Mass General Brigham and Dana-Farber Cancer Institute were included. Melanoma recurrence date and type were determined by chart review. Thirty clinicopathologic factors were extracted from electronic health records. Three types of time-to-event machine-learning models were evaluated internally and externally in the distant versus locoregional/nonrecurrence prediction. Results: This study included 954 melanomas (155 distant, 163 locoregional, and 636 1:2 matched nonrecurrences). Distant recurrences were associated with worse survival compared to locoregional/nonrecurrences (HR: 6.21, P < .001) and to locoregional recurrences only (HR: 5.79, P < .001). The Gradient Boosting Survival model achieved the best performance (concordance index: 0.816; time-dependent AUC: 0.842; Brier score: 0.103) in the external validation. Limitations: Retrospective nature and cohort from one geography. Conclusions: These results suggest that time-to-event machine-learning models can reliably predict the metastatic recurrence from localized melanoma and help identify high-risk patients who are most likely to benefit from immunotherapy.
AB - Background: The recent expansion of immunotherapy for stage IIB/IIC melanoma highlights a growing clinical need to identify patients at high risk of metastatic recurrence and, therefore, most likely to benefit from this therapeutic modality. Objective: To develop time-to-event risk prediction models for melanoma metastatic recurrence. Methods: Patients diagnosed with stage I/II primary cutaneous melanoma between 2000 and 2020 at Mass General Brigham and Dana-Farber Cancer Institute were included. Melanoma recurrence date and type were determined by chart review. Thirty clinicopathologic factors were extracted from electronic health records. Three types of time-to-event machine-learning models were evaluated internally and externally in the distant versus locoregional/nonrecurrence prediction. Results: This study included 954 melanomas (155 distant, 163 locoregional, and 636 1:2 matched nonrecurrences). Distant recurrences were associated with worse survival compared to locoregional/nonrecurrences (HR: 6.21, P < .001) and to locoregional recurrences only (HR: 5.79, P < .001). The Gradient Boosting Survival model achieved the best performance (concordance index: 0.816; time-dependent AUC: 0.842; Brier score: 0.103) in the external validation. Limitations: Retrospective nature and cohort from one geography. Conclusions: These results suggest that time-to-event machine-learning models can reliably predict the metastatic recurrence from localized melanoma and help identify high-risk patients who are most likely to benefit from immunotherapy.
KW - clinicopathologic factors
KW - locoregional recurrence
KW - metastatic recurrence
KW - stage I/II melanoma
KW - time-to-event prediction
UR - http://www.scopus.com/inward/record.url?scp=85176236181&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85176236181&partnerID=8YFLogxK
U2 - 10.1016/j.jaad.2023.08.105
DO - 10.1016/j.jaad.2023.08.105
M3 - Article
C2 - 37797836
AN - SCOPUS:85176236181
SN - 0190-9622
VL - 90
SP - 288
EP - 298
JO - Journal of the American Academy of Dermatology
JF - Journal of the American Academy of Dermatology
IS - 2
ER -