Skip to content

When you choose to publish with PLOS, your research makes an impact. Make your work accessible to all, without restrictions, and accelerate scientific discovery with options like preprints and published peer review that make your work more Open.

PLOS BLOGS EveryONE

Call for Papers: Machine Learning in Health and Biomedicine

**THIS CALL FOR PAPERS IS NOW CLOSED FOR SUBMISSIONS**

PLOS Medicine, PLOS Computational Biology and PLOS ONE announce a cross-journal Call for Papers for high-quality research that applies or develops machine learning methods for improvement of human health. The team of Guest Editors for this Collection seeks research with direct clinical and health policy implications, studies that elucidate biological processes underlying health and disease, innovations in machine learning methodology and data provision, and other advances in the field.

Research accepted for publication in PLOS Medicine will appear in a Special Issue to be published in late Fall 2018, along with commentary from leading experts in the field. The broader Collection, comprising all articles published in PLOS Computational Biology, PLOS ONE and PLOS Medicine, will launch in late Fall and continue into 2019. Articles must be submitted by May 25, 2018.

Scope

The PLOS ONE Guest Editors are Leo Anthony Celi (MIT), Luca Citi (University of Essex), Marzyeh Ghassemi (Verily/MIT) and Tom Pollard (MIT). The Collection will encompass a diverse range of research articles on machine learning in health and biomedicine. PLOS ONE assesses submissions for scientific rigor, rather than perceived impact, and encourages database and software submissions. The Guest Editors particularly welcome high-quality submissions reporting original research that contributes to solving the following challenges:

  • Relevant machine learning solutions to healthcare problems on all scales, from outbreak monitoring to personalized medicine.
  • Methodological contributions to health and biomedicine inspired machine-learning challenges, such as interpretability; algorithmic bias; multimodality; exploiting structure in information; making use of heterogeneous information in machine learning.
  • Improvements to the availability of training data, in particular through open data. This includes enhancing and standardizing data-taking, large-scale database submissions with a use-case for machine learning in health and reconciling the need for data and the open data paradigm with patient privacy.

PLOS Medicine’s Special Issue Guest Editors are Atul Butte, the Priscilla Chan and Mark Zuckerberg Distinguished Professor and Director of the Institute for Computational Health Sciences at UCSF, Suchi Saria, John C. Malone Assistant Professor in the Department of Computer Science, Statistics, and Health Policy at Johns Hopkins University, and Research Director of the Malone Center for Engineering in Healthcare, and Aziz Sheikh, Professor of Primary Care Research & Development and Director, Usher Institute of Population Health Sciences and Informatics, The University of Edinburgh. Submissions to PLOS Medicine should be of broad interest, meet PLOS Medicine’s general criteria, and leverage machine learning to advance clinical practice or health policy. Areas of focus are

  • Machine learning-based original research or evidence synthesis in medical decision making– encompassing detection, diagnosis, prognosis or treatment– that includes or comprises validation beyond a discovery dataset
  • Machine learning-driven research in health systems or public health, providing insights to allocation of healthcare resources or epidemiology
  • Formal comparisons between standard epidemiological and machine learning approaches, or methodological studies establishing a clear directive for the practice of health research
  • Molecular or cellular insights from machine learning that demonstrate a novel explanatory mechanism for a significant clinical problem, or justify a clinical trial

The PLOS Computational Biology Guest Editor will be Quaid Morris, Associate Professor of Molecular Genetics, Computer Science, and Electrical and Computer Engineering at the University of Toronto. PLOS Computational Biology seeks machine learning papers providing new insight into living systems, focusing on

  • New machine learning methods for analyzing new types of genomic and proteomic data, particularly those focusing on single cell assays
  • Scalable machine learning methods for analyzing large-scale datasets, including UK Biobank, cancer genomic datasets, GTeX and the epigenomic roadmap
  • Machine learning-driven research providing insights on biological mechanisms

Submission

Authors should specify the Call for Papers, “Machine Learning in Health and Biomedicine,” in their cover letter and, for PLOS ONE, in the ‘Collections’ field under ‘Additional Information.’ Manuscripts must be submitted in full; formal pre-submission inquiries will not be considered.

Submit to PLOS Medicine

Submit to PLOS Computational Biology

Submit to PLOS ONE

Submissions not selected for PLOS Medicine or PLOS Computational Biology may be offered transfer to PLOS ONE, before or after peer review, with the prospect of inclusion in the full Collection.

Data and code sharing

Data underlying the study’s findings will be a requirement of publication, per the PLOS data policy. Under this Call for Papers authors are responsible for providing, upon submission, the source code needed to replicate their findings, in a repository (such as GitHub or Bitbucket) or a cloud computing service (such as Code Ocean). Protection of authors’ intellectual property will not be cause for exception. Authors should explain in the manuscript’s Data Availability Statement how readers can access the shared code. For any referenced third party code that cannot be shared, authors are responsible for including, in the Data Availability Statement, contact information and steps by which an interested reader can acquire the code.

Authors are encouraged to provide executable documents, such as a Jupyter Notebook or an RMarkdown, to increase reproducibility. The Software Sustainability Institute provides guidance on choosing a repository and sharing code, as do these PLOS articles on Best Practices and Good Enough Practices in scientific computing.

Please direct any questions to ML4health@plos.org, and specify the relevant journal in the subject line.

Image Credit: StockSnap. Pixabay.com

Leave a Reply

Your email address will not be published. Required fields are marked *


Add your ORCID here. (e.g. 0000-0002-7299-680X)

Back to top