Editorial
Copyright ©The Author(s) 2021. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Transl Med. Mar 15, 2021; 9(1): 1-10
Published online Mar 15, 2021. doi: 10.5528/wjtm.v9.i1.1
Machine intelligence for precision oncology
Nelson S Yee
Nelson S Yee, Department of Medicine, The Pennsylvania State University College of Medicine, Penn State Cancer Institute, Penn State Health Milton S. Hershey Medical Center, Hershey, PA 17033-0850, United States
Author contributions: Yee NS performed research and wrote the paper.
Conflict-of-interest statement: Dr. Yee reports grants from Ipsen Biopharmaceuticals, other from Caris Life Sciences, other from Novartis, outside the submitted work.
Open-Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: http://creativecommons.org/Licenses/by-nc/4.0/
Corresponding author: Nelson S Yee, BPharm, FACP, MD, PhD, Associate Professor, Attending Doctor, Department of Medicine, The Pennsylvania State University College of Medicine, Penn State Cancer Institute, Penn State Health Milton S. Hershey Medical Center, 500 University Drive, Hershey, PA 17033-0850, United States. nyee@pennstatehealth.psu.edu
Received: October 19, 2020
Peer-review started: October 19, 2020
First decision: November 16, 2020
Revised: December 22, 2020
Accepted: March 1, 2021
Article in press: March 1, 2021
Published online: March 15, 2021
Abstract

Despite various advances in cancer research, the incidence and mortality rates of malignant diseases have remained high. Accurate risk assessment, prevention, detection, and treatment of cancer tailored to the individual are major challenges in clinical oncology. Artificial intelligence (AI), a field of applied computer science, has shown promising potential of accelerating evolution of healthcare towards precision oncology. This article focuses on highlights of the application of data-driven machine learning (ML) and deep learning (DL) in translational research for cancer diagnosis, prognosis, treatment, and clinical outcomes. ML-based algorithms in radiological and histological images have been demonstrated to improve detection and diagnosis of cancer. DL-based prediction models in molecular or multi-omics datasets of cancer for biomarkers and targets enable drug discovery and treatment. ML approaches combining radiomics with genomics and other omics data enhance the power of AI in improving diagnosis, prognostication, and treatment of cancer. Ethical and regulatory issues involving patient confidentiality and data security impose certain limitations on practical implementation of ML in clinical oncology. However, the ultimate goal of application of AI in cancer research is to develop and implement multi-modal machine intelligence for improving clinical decision on individualized management of patients.

Keywords: Artificial intelligence, Deep learning, Machine learning, Precision oncology, Radiomics, Radiogenomics

Core Tip: Artificial intelligence represents the future of healthcare particularly precision oncology for prevention, detection, risk assessment, and treatment of cancer. Application of machine learning- and deep learning-based algorithms in translational research has been demonstrated to improve accuracy of cancer diagnosis and anti-cancer drug development. Multi-disciplinary collaboration with resolution of ethical and regulatory issues of multi-modal machine intelligence are indicated for implementation of computer-assisted clinical decision on individualized patient management.