A Review on Application of Machine Learning and Deep Learning Algorithms in Head and Neck Cancer Prediction and Prognosis

Reiterative modeling of combined transcriptomic and proteomic features refines and improves the prediction of early recurrence in squamous cell carcinoma of head and neck

“…Most notably, The Cancer Genome Atlas (TCGA) [5] has data on over 520 SCCHN samples using various omics platforms. Exploring the relationships of these different datasets with clinical outcomes is challenging, and artificial intelligence (AI)-based methods are a rapidly growing area in medicine and healthcare to aid understanding and interpretability of such data [9,10]. In SCCHN, support vector machines (SVM) were used to develop a model for predicting recurrence/metastasis using whole genome copy number alteration (CNA) data with an accuracy of ~80% [11], and combining machine-learning methods with targeted proteomics has also been used to identify a prognostic signature in oral cancer [12].…”