The promise of machine learning to transform all aspects of medicine and health care has been much celebrated, but to date this transformation remains largely aspirational.1-5 Medicine poses unique challenges compared with areas like recognizing images, driving autonomous vehicles, or gaming, for which machine learning has had remarkable success. Obstacles to successful application of machine learning in medicine include availability of large, high-quality databases to derive prediction models that are accurate and interpretable and deployment of these models in ways that improve, rather than simply complicate, medical practice.
JAMA Network Open, a fully open access journal in the JAMA Network of journals with an international audience of health care clinicians and policy makers, is pleased to announce a call for papers on “advancing health and health care using machine learning.” We are interested in reports of original research that describe ways in which validated applications of machine learning, artificial intelligence, and natural language processing provide the potential to advance the health of individuals or populations through improved health care and better understanding of factors that affect health. Appropriate studies include clinical research using machine learning to improve clinical diagnosis and prognosis of disease, identify high-risk individuals in a population, or provide information that can be used to most appropriately monitor risk factors and treat patients using precision medicine. Methodologic innovation in machine learning is welcome, provided that innovation is applied to a clinically meaningful problem and presented in a clinically interpretable manner. That is, we are seeking cutting-edge applications of machine learning with significant clinical validation that can move medical practice forward. The journal has published a number of such studies in recent months.6-11 Note that JAMA Network Open does not publish narrative review articles, basic science, or animal model studies.
All favorable research manuscripts undergo peer review, including statistical review. All machine learning articles accepted for publication will be eligible to have accompanying Invited Commentaries published by experts in the field and will be published quickly. In addition, all machine learning articles are included in the Health Informatics featured specialty on the JAMA Network Open website, and all will be featured in an online collection dedicated to the topic of machine learning.12JAMA Network Open was recently accepted into MEDLINE, and all published articles will be indexed in MEDLINE. Please see the journal’s Instructions for Authors for additional information on manuscript preparation and submission.13
We are pleased to respond to any presubmission inquires on this call for papers; please email us at jamanetworkopen@jamanetwork.org.
Published: December 21, 2018. doi:10.1001/jamanetworkopen.2018.7176
Open Access: This is an open access article distributed under the terms of the CC-BY License. © 2018 Rivara FP et al. JAMA Network Open.
Corresponding Author: Frederick P. Rivara, MD, MPH, University of Washington, 325 Ninth Ave, PO Box 359960, Seattle, WA 98104 (fpr@uw.edu).
Conflict of Interest Disclosures: Dr Perlis reported serving as scientific advisor to Psy Therapeutics, RID Ventures, and Genomind. No other disclosures were reported.
8.Wong
A, Young
AT, Liang
AS, Gonzales
R, Douglas
VC, Hadley
D. Development and validation of an electronic health record–based machine learning model to estimate delirium risk in newly hospitalized patients without known cognitive impairment.
JAMA Netw Open. 2018;1(4):e181018. doi:
10.1001/jamanetworkopen.2018.1018Google ScholarCrossref 10.Na
L, Yang
C, Lo
C-C, Zhao
F, Fukuoka
Y, Aswani
A. Feasibility of reidentifying individuals in large national physical activity data sets from which protected health information has been removed with use of machine learning.
JAMA Netw Open. 2018;1(8):e186040. doi:
10.1001/jamanetworkopen.2018.6040Google ScholarCrossref