Supplementary Table S2 from Multimodal Approach Predicts Relapse upon Cessation of Immune Checkpoint Inhibitors in Advanced Melanoma

Noh, Ka-Won; Tolkach, Yuri; Helbig, Doris; Mitchell Barroso, Vincenzo; Foerster, Yannick; Schlaak, Max; Biedermann, Tilo; Buettner, Reinhard; Persa, Oana-Diana

doi:10.1158/1078-0432.30617794

Supplementary Table S2 from Multimodal Approach Predicts Relapse upon Cessation of Immune Checkpoint Inhibitors in Advanced Melanoma

https://doi.org/10.1158/1078-0432.30617794

journal contribution

posted on 2025-11-14, 08:21 authored by Ka-Won Noh, Yuri Tolkach, Doris Helbig, Vincenzo Mitchell Barroso, Yannick Foerster, Max Schlaak, Tilo Biedermann, Reinhard Buettner, Oana-Diana Persa

<p>Univariable Cox regression analysis of factors contributing to progression in the cessation cohort.</p>

Funding

Deutsche Stiftung für Dermatologie

Bayerisches Zentrum für Krebsforschung

Deutsche Krebshilfe (German Cancer Aid)

Bundesministerium für Bildung und Forschung (BMBF)

European Fond for Regional Development (EFRE)

Deutsche Forschungsgemeinschaft (DFG)

History

Related Materials

1.
DOI - Is supplement to Multimodal Approach Predicts Relapse upon Cessation of Immune Checkpoint Inhibitors in Advanced Melanoma

ARTICLE ABSTRACT

Treatment with immune checkpoint inhibitors (ICI) in advanced melanoma can result in durable responses, yet an algorithm to decide which patients can safely discontinue ICI is still lacking. We used a multimodal approach combining clinical data, artificial intelligence–based analysis of hematoxylin and eosin–stained whole-slide images of melanoma before ICI start, and gene expression signatures to identify biomarkers for relapse after discontinuing ICI in the absence of treatment progression. Univariable Cox regression analysis identified the best overall response, mRNA expression of six genes, tumor cell density, and the lymphocyte-to-plasma cell ratio as factors predictive of relapse upon the cessation of the ICI. Multivariable Cox regression analysis showed that both TGFBR1 expression and the integral digital pathology parameter–based prognostic system were independently associated with relapse after ICI discontinuation. Training a multivariate adaptive regression spline model achieved the highest overall predictive accuracy of 84.6% for relapse after ICI discontinuation. The identified prognostic markers are fully explainable and easily implementable in routine practice, facilitating risk stratification upon the cessation of ICI therapy.