Artificial Intelligence and Machine Learning Approaches for Diagnostic, Predictive, and Prognostic Cancer Biomarkers

Throughout the last few decades, various clinicians, from specialists to paramedics, have been asked to predict cancer prognosis based on their individual work experience. Clinicians have recognized the need to use AI technology, such as machine learning and deep learning, as a decision support tool to predict clinical cancer outcomes. Traditional statistical tools lack the ability to predict a patient’s cancer prognosis with high accuracy. Additionally, doctors are concerned about the risk of patients contracting the disease, having tumors return, or dying from the disease. Treatment choices and curative effects are highly dependent on such aspects. Currently, most cancer research focuses on predicting the correct outcome or determining the prognosis. A better understanding of patients' prognoses can help determine more appropriate and precise treatments for them; indeed, such treatments tend to be individualized. As of today, it is challenging to customize a patient's treatment according to their specific needs. Using artificial intelligence, however, the prognosis of cancer among patients, their survival time, and their disease progress can be more accurately predicted by processing and analyzing multivariate data from multiple patient examinations and their sequencing data.

The objective of this themed article collection is to welcome research articles focused on the prediction of new biomarkers in different cancer types at different cancer stages using AI and ML methods. We welcome articles related to multi-omics data analysis, single-cell data, AI algorithms for prognosis marker prediction using diagnostic data, image processing-based prediction, and clinical studies. Authors are welcome to submit research articles and review papers.