Roaa Yousry Goda, Amal Kamal Abdel‐Aziz
We also shed light on the FDA-approved AI-driven tools and reviewed the clinical trials evaluating the capabilities of AI-supported algorithms in the diagnosis, screening, risk stratification, anticancer drug response prediction, clinical trial matching, informed treatment decision-making, personalized prescription and supportive care of cancer patients.
Precision oncology considers the genetic makeup of both the tumor and the cancer patient, medical history, clinical metadata, lifestyle and environmental factors. Thus, adoption of precision cancer medicine mandates sophisticated integrative analysis. Being a master in sorting and solving the puzzle pieces, artificial intelligence (AI)-powered frameworks emerged to fill the gap via executing multimodal analysis and generating meaningful outputs. Herein, we systematically discussed the opportunities and challenges of exploiting AI-assisted models in preclinical cancer research and in clinical oncology to promote precision medicine of cancer patients. We also shed light on the FDA-approved AI-driven tools and reviewed the clinical trials evaluating the capabilities of AI-supported algorithms in the diagnosis, screening, risk stratification, anticancer drug response prediction, clinical trial matching, informed treatment decision-making, personalized prescription and supportive care of cancer patients. Despite the foreseen promise of AI-driven frameworks in revolutionizing cancer personalized medicine, large-scale multicenter prospective studies and consensus regulatory guidelines are urged to ensure their safe, efficient and responsible use. Precision cancer medicine mandates AI-powered integrative data analysis AI-driven tools promotes anticancer drug discovery and development AI-assisted models improve cancer screening, diagnosis and risk stratification AI-supported frameworks guide informed treatment-decision making Present limitations of AI-driven algorithms restrain their clinical utility