Better medicine through machine learning: What’s real, and what’s artificial?
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Artificial intelligence (AI) as a field emerged in the 1960s when practitioners across the engineering and cognitive sciences began to study how to develop computational technologies that, like people, can perform tasks such as sensing, learning, reasoning, and taking action.Early AI systems relied heavily on expert-derived rules for replicating how people would approach these tasks.Machine learning (ML), a subfield of AI, emerged as research began to leverage numerical techniques integrating principles from computing, optimization, and statistics to automatically "learn" programs for performing these tasks by processing data: hence the recent interest in "big data."Although progress in AI has been uneven, significant advances in the present decade have led to a proliferation of technologies that substantially impact our everyday lives: computer vision and planning are driving the gaming and transportation industries; speech processing is making conversational applications practical on our phones; and natural language processing, knowledge representation, and reasoning have enabled a machine to beat the Jeopardy and Go champions and are bringing new power to web searches [1].Simultaneously, however, advertising hyperbole has led to skepticism and misunderstanding of what is and is not possible with ML [2,3].Here, we aim to provide an accessible, scientifically and technologically accurate portrayal of the current state of ML (often referred to as AI in medical literature) in health and medicine and its potential, using examples of recent research-some from PLOS Medicine's November 2018 Special Issue on Machine Learning in Health and Biomedicine, for which we served as guest editors.We have selected studies that illustrate different ways in which ML may be used and their potential for near-term translational impact. ML-assisted diagnosisOf the myriad opportunities for use of ML in clinical practice, medical imaging workflows are most likely to be impacted in the near term.ML-driven algorithms that automatically process 2-or 3-dimensional image scans to identify clinical signs (e.g., tumors or lesions) or determine likely diagnoses have been published, and some are progressing through regulatory steps toward the market.Many of these use deep learning, a form of ML based on layered representations of variables, referred to as neural networks.To understand how deep learning methods leverage image data to perform recognition tasks, imagine you are entering a dark room and
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Clinically applicable deep learning for diagnosis and referral in retinal disease
De Fauw, J., Ledsam, J. R., Romera-Paredes, B., Nikolov, S., Tomasev, N., Blackwell, S., Askham, H., Glorot, X., O’Donoghue, B., Visentin, D., et al. (2018) · Nature Medicine · doi:10.1038/s41591-018-0107-6 · Cited by 2,639
Zech, J. R., Badgeley, M. A., Liu, M., Costa, A. B., Titano, J. J., & Oermann, E. K. (2018) · PLOS Medicine · doi:10.1371/journal.pmed.1002683 · Cited by 1,719 · cited 1×
“Another pitfall of naive implementation lies in the capacity of ML, and particularly deep learning, to overfit to data—that is, to identify associations in the training dataset that are not truly intrinsic to the clinical prediction and will not be relevant externally [16].”
Rajpurkar, P., Irvin, J., Ball, R. L., Zhu, K., Yang, B., Mehta, H., Duan, T., Ding, D., Bagul, A., Langlotz, C. P., et al. (2018) · PLOS Medicine · doi:10.1371/journal.pmed.1002686 · Cited by 1,449
A targeted real-time early warning score (TREWScore) for septic shock.
Henry, K. E., Hager, D. N., Pronovost, P. J., & Saria, S. (2015) · Science Translational Medicine · doi:10.1126/scitranslmed.aab3719 · Cited by 598
Self-citationBeyond Atopy: Multiple Patterns of Sensitization in Relation to Asthma in a Birth Cohort Study
Simpson, A., Tan, V. Y. F., Winn, J., Svensén, M., Bishop, C. M., Heckerman, D. E., Buchan, I., & Custovic, A. (2010) · American Journal of Respiratory and Critical Care Medicine · doi:10.1164/rccm.200907-1101oc · Cited by 415 · cited 1×
“Using unsupervised ML, the group analyzed data from the Manchester Asthma and Allergy Study (MAAS) populationbased birth cohort and were able to identify novel phenotypes of childhood atopy [12].”
Corey, K. M., Kashyap, S., Lorenzi, E., Lagoo-Deenadayalan, S. A., Heller, K., Whalen, K., Balu, S., Heflin, M. T., McDonald, S. R., Swaminathan, M., et al. (2018) · PLOS Medicine · doi:10.1371/journal.pmed.1002701 · Cited by 204 · cited 1×
“For example, in the Special Issue, a study from Kristin Corey and colleagues considered the potential for reducing complications and mortality within 30 days following particular surgeries [7].”
Fontanella, S., Frainay, C., Murray, C. S., Simpson, A., & Custovic, A. (2018) · PLoS Medicine · doi:10.1371/journal.pmed.1002691 · Cited by 91 · cited 1×
“Through further interrogation of this same dataset, the authors have now identified clusters of component-specific immunoglobulin E (IgE) sensitization using network and hierarchical cluster analysis that can help better predict risk of childhood asthma [13].”
Cited by
Ahmed, Z., Mohamed, K., Zeeshan, S., & Dong, X. (2020) · Database · doi:10.1093/database/baaa010 · Cited by 1,035
Rajula, H. S. R., Verlato, G., Manchia, M., Antonucci, N., & Fanos, V. (2020) · Medicina · doi:10.3390/medicina56090455 · Cited by 606
Health information technology and digital innovation for national learning health and care systems
Sheikh, A., Anderson, M., Albala, S., Casadei, B., Franklin, B. D., Richards, M., Taylor, D., Tibble, H., & Mossialos, E. (2021) · The Lancet Digital Health · doi:10.1016/s2589-7500(21)00005-4 · Cited by 389
Self-citationEllahham, S., Ellahham, N., & Simsekler, M. C. E. (2020) · American Journal of Medical Quality · doi:10.1177/1062860619878515 · Cited by 177
“Algorithms should be designed and trained to reason for disease severity and trajectory.(57) Defining ethical standards will enable wider application of AI and also will help surmount the fears of AI overpowering human capabilities.”
Cabitza, F., & Zeitoun, J.-D. (2019) · Annals of Translational Medicine · doi:10.21037/atm.2019.04.07 · Cited by 72
“…systems (based on ML) were first recognized as riding “atop the peak of inflated expectations” (8), we can now behold from a distance what lies beyond this peak, what still separates us from the “plateau of productivity” 1 and what will attract major interest from multiple stakeholders: validation.”
Background
Metadata
- Authors
- Saria, S., Butte, A., & Sheikh, A.
- Venue
- PLOS Medicine
- Publisher
- Public Library of Science (PLoS)
- Published
- 2018-12-31
- Volume
- 15
- Issue
- 12
- Pages
- e1002721
- ISSN
- 1549-1277 (ISSN-L)
- 1549-1676
- OpenAlex
- W2908272298
- Cited by
- 127
- References
- 7
- FWCI
- 2.57
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Better medicine through machine learning: What’s real, and what’s artificial? https://app.cochat.ai/papers/10.1371/journal.pmed.1002721
- The paper
- Saria, S., Butte, A., & Sheikh, A. (2018). Better medicine through machine learning: What’s real, and what’s artificial? PLOS Medicine. https://doi.org/10.1371/journal.pmed.1002721
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.