Driving innovation for rare skin cancers: utilising common tumours and machine learning to predict immune checkpoint inhibitor response

Link to paper

J.S. Hooiveld-Noeken, R.S.N. Fehrmann, E.G.E. de Vries, M. Jalving

• Metastatic Merkel- and cutaneous squamous cell carcinoma are rare tumours.
• Immunotherapy gives impressive responses but most patients do not survive long-term.
• Small patients numbers prevent extensive biomarker research in clinical trials.
• Pooled data from common and rare tumours can be used to train neural networks (NN).
• In rare cancers such NN can help identify biomarkers and novel treatment targets.

Metastatic Merkel cell carcinoma (MCC) and metastatic cutaneous squamous cell carcinoma (cSCC) are rare and both show impressive responses to immune checkpoint inhibitor treatment. However, at least 40% of patients do not respond to these expensive and potentially toxic drugs. Development of predictive biomarkers of response and rational, effective combination treatment strategies in these rare, often frail patient populations is challenging. In this review we discuss the pathophysiology and treatment of MCC and cSCC with a special focus on potential biomarkers of response to immunotherapy. We discuss how transferred learning using big data collected from patients with common tumours can be used in combination with deep phenotyping of rare tumours to develop predictive biomarkers and elucidate novel treatment targets.