Machine learning for prediction of cutaneous adverse events in patients receiving anti–PD-1 immunotherapy

To the Editor: One third of patients treated with programmed cell death protein 1 (PD-1) inhibitors experience cutaneous immune-related adverse events (irAEs). 1 Belum V.R. Benhuri B. Postow M.A. et al. Characterisation and management of dermatologic adverse events to agents targeting the PD-1 receptor. Eur J Cancer. 2016; 60: 12-25 Abstract Full Text Full Text PDF PubMed Scopus (212) Google Scholar ,2 Sibaud V. Dermatologic reactions to immune checkpoint inhibitors: skin toxicities and immunotherapy. Am J Clin Dermatol. 2018; 19: 345-361 Crossref PubMed Scopus (202) Google Scholar Given that these irAEs often require treatment and may have prognostic significance, 3 Chan L. Hwang S.J.E. Kyaw M. et al. The oncological survival and prognosis of individuals receiving PD-1 inhibitor with and without immunologic cutaneous adverse events. J Am Acad Dermatol. 2020; 82: 311-316 Abstract Full Text Full Text PDF PubMed Scopus (23) Google Scholar identifying patients at risk of cutaneous irAEs is important. Here, we developed a proof-of-concept neural network for the prediction of cutaneous irAEs from anti–PD-1 therapy.