A Comparison of Artificial Intelligence and Human Doctors for the Purpose of Triage and Diagnosis
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
AI virtual assistants have significant potential to alleviate the pressure on overly burdened healthcare systems by enabling patients to self-assess their symptoms and to seek further care when appropriate. For these systems to make a meaningful contribution to healthcare globally, they must be trusted by patients and healthcare professionals alike, and service the needs of patients in diverse regions and segments of the population. We developed an AI virtual assistant which provides patients with triage and diagnostic information. Crucially, the system is based on a generative model, which allows for relatively straightforward re-parameterization to reflect local disease and risk factor burden in diverse regions and population segments. This is an appealing property, particularly when considering the potential of AI systems to improve the provision of healthcare on a global scale in many regions and for both developing and developed countries. We performed a prospective validation study of the accuracy and safety of the AI system and human doctors. Importantly, we assessed the accuracy and safety of both the AI and human doctors independently against identical clinical cases and, unlike previous studies, also accounted for the information gathering process of both agents. Overall, we found that the AI system is able to provide patients with triage and diagnostic information with a level of clinical accuracy and safety comparable to that of human doctors. Through this approach and study, we hope to start building trust in AI-powered systems by directly comparing their performance to human doctors, who do not always agree with each other on the cause of patients’ symptoms or the most appropriate triage recommendation.
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
Evaluating Digital Health Interventions
Murray, E., Hekler, E. B., Andersson, G., Collins, L. M., Doherty, A., Hollis, C., Rivera, D. E., West, R., & Wyatt, J. C. (2016) · American Journal of Preventive Medicine · doi:10.1016/j.amepre.2016.06.008 · Cited by 847
Wahl, B., Cossy-Gantner, A., Germann, S., & Schwalbe, N. R. (2018) · BMJ Global Health · doi:10.1136/bmjgh-2018-000798 · Cited by 796 · cited 1×
“In low-income countries their impact may be even greater since, although access to human healthcare experts may be limited, many developing countries have seen a rapid expansion of mobile phones and wireless technology which has enabled opportunities to deliver mHealth technologies (Wahl et al., 2018).”
The incidence of diagnostic error in medicine
Graber, M. L. (2013) · BMJ Quality & Safety · doi:10.1136/bmjqs-2012-001615 · Cited by 626
Evaluation of symptom checkers for self diagnosis and triage: audit study
Semigran, H. L., Linder, J. A., Gidengil, C., & Mehrotra, A. (2015) · BMJ · doi:10.1136/bmj.h3480 · Cited by 489 · cited 3×
“In particular, (Semigran et al., 2015) assessed 23 commercial symptom checker apps and highlighted signi fi cant variation in terms of clinical accuracy.”
What is the clinical value of mHealth for patients?
Rowland, S. P., Fitzgerald, J. E., Holme, T., Powell, J., & McGregor, A. (2020) · npj Digital Medicine · doi:10.1038/s41746-019-0206-x · Cited by 454
The Application of Medical Artificial Intelligence Technology in Rural Areas of Developing Countries
Guo, J., & Li, B. (2018) · Health Equity · doi:10.1089/heq.2018.0037 · Cited by 401
Chambers, D., Cantrell, A. J., Johnson, M., Preston, L., Baxter, S. K., Booth, A., & Turner, J. (2019) · BMJ Open · doi:10.1136/bmjopen-2018-027743 · Cited by 218 · cited 1×
“Previous work has investigated the diagnostic and triage accuracy of symptom checkers (Semigran et al., 2015; Millenson et al., 2018; Chambers et al., 2019; Yu et al., 2019).”
Comparison of Physician and Computer Diagnostic Accuracy
Semigran, H. L., Levine, D. M., Nundy, S., & Mehrotra, A. (2016) · JAMA Internal Medicine · doi:10.1001/jamainternmed.2016.6001 · Cited by 145 · cited 1×
“This was assessed in a follow-up study, where the authors noted that doctors signi fi cantly outperform symptom checkers, providing a valuable contribution to our understanding of comparative diagnostic performance (Semigran et al., 2016).”
Beyond Dr. Google: the evidence on consumer-facing digital tools for diagnosis
Millenson, M. L., Baldwin, J. L., Zipperer, L., & Singh, H. (2018) · Diagnosis · doi:10.1515/dx-2018-0009 · Cited by 91 · cited 3×
“AI virtual assistants (symptom checkers) are a convenient and valuable resource for users to better understand the underlying cause(s) of their symptoms and to receive advice on the most appropriate point of care (Millenson et al., 2018; Rowland et al., 2020).”
A fairer way forward for AI in health care
Nordling, L. (2019) · Nature · doi:10.1038/d41586-019-02872-2 · Cited by 90 · cited 1×
“In particular, lack of diversity in medical datasets has the potential to result in biased algorithms which could widen healthcare inequality (Nordling, 2019).”
Research works printed but not linked: 16
- Berry, 2020, Symptom checkers versus doctors: a prospective, head‐to‐head comparison for cough, Clin. Res. J, 14, 413, 10.1111/crj.13135 · DOI
- Bulacan, 2019, Gp at hand: a digital revolution for health care provision?, Lancet, 394, 457, 10.1016/s0140-6736(19)31802-1 · DOI
- Cheng, 2000, AIS-BN: an adaptive importance sampling algorithm for evidential reasoning in large Bayesian networks, J. Artif. Intell. Res., 13, 10264, 10.1613/jair.764 · DOI
- Fraser, 2018, Safety of patient-facing digital symptom checkers, Lancet, 392, 2263, 10.1016/s0140-6736(18)32819-8 · DOI · Paper page
- Gu, 2015, Neural adaptive sequential Monte Carlo, Adv. Neural Inf. Process. Syst., 28, 2611
- Heckerman, 1990, A tractable inference algorithm for diagnosing multiple diseases, Mach. Intell. Patt. Recog., 10, 163, 10.1016/B978-0-444-88738-2.50020-8 · DOI
- Jutel, 2015, Digitizing diagnosis: a review of mobile applications in the diagnostic process, Diagnosis, 2, 89, 10.1515/dx-2014-0068 · DOI · Paper page
- Koller, 2009, Probabilistic graphical models: principles and techniques, 1270
- Meyer, 2013, Physicians’ diagnostic accuracy, confidence, and resource requests, JAMA Intern Med, 173, 1952, 10.1001/jamainternmed.2013.10081 · DOI · Paper page
- O’Cathain, 2003, NHS direct: consistency of triage outcomes, Emerg. Med. J., 20, 289, 10.1136/emj.20.3.289 · DOI · Paper page
- Stead, 1994, Designing medical informatics research and library--resource projects to increase what is learned, J. Am. Med. Inf. Assoc., 1, 28, 10.1136/jamia.1994.95236134 · DOI · Paper page
- Talmon, 2009, STARE-HI-Statement on reporting of evaluation studies in Health Informatics, Int. J. Med. Inf., 78, 1, 10.1016/j.ijmedinf.2008.09.002 · DOI · Paper page
- Van Veen, 2019, Potential of mobile health technology to reduce health disparities in underserved communities, West. J. Emerg. Med., 20, 799, 10.5811/westjem.2019.6.41911 · DOI
- Wainwright, 2008, Graphical models, exponential families, and variational inference, Found. Trends Mach. Learn., 1, 1, 10.1561/2200000001 · DOI · Paper page
- Wiegand, 2019, Who and itu establish benchmarking process for artificial intelligence in health, Lancet, 394, 9, 10.1016/s0140-6736(19)30762-7 · DOI · Paper page
- Yu, 2019, Triage accuracy of online symptom checkers for accident and emergency department patients, Hong Kong J. Emerg. Med., 27, 217, 10.1177/1024907919842486 · DOI · Paper page
Cited by
ChatGPT: the future of discharge summaries?
Patel, S. B., & Lam, K. (2023) · The Lancet Digital Health · doi:10.1016/s2589-7500(23)00021-3 · Cited by 728
Conversational Agents in Health Care: Scoping Review and Conceptual Analysis
Tudor Car, L., Dhinagaran, D. A., Kyaw, B. M., Kowatsch, T., Joty, S., Theng, Y.-L., & Atun, R. (2020) · Journal of Medical Internet Research · doi:10.2196/17158 · Cited by 553
Improving the accuracy of medical diagnosis with causal machine learning
Richens, J. G., Lee, C. M., & Johri, S. (2020) · Nature Communications · doi:10.1038/s41467-020-17419-7 · Cited by 598
Self-citationArtificially intelligent chatbots in digital mental health interventions: a review
Boucher, E. M., Harake, N. R., Ward, H. E., Stoeckl, S. E., Vargas, J., Minkel, J., Parks, A. C., & Zilca, R. (2021) · Expert Review of Medical Devices · doi:10.1080/17434440.2021.2013200 · Cited by 440
“For example, some chatbots using NLP can simulate a therapeutic conversational style that implements and teaches users about various therapeutic techniques (see Fitzpatrick et al., 2017, for a discussion) [51].”
BackgroundChatGPT in healthcare: A taxonomy and systematic review
Li, J., Dada, A., Puladi, B., Kleesiek, J., & Egger, J. (2024) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2024.108013 · Cited by 452
Metadata
- Authors
- Baker, A., Perov, Y., Middleton, K., Baxter, J., Mullarkey, D., Sangar, D., Butt, M., DoRosario, A., & Johri, S.
- Venue
- Frontiers in Artificial Intelligence
- Publisher
- Frontiers Media SA
- Published
- 2020-11-30
- Volume
- 3
- Pages
- 543405-543405
- ISSN
- 2624-8212 (ISSN-L)
- OpenAlex
- W3108779652
- Cited by
- 157
- References
- 10
- FWCI
- 3.75
- 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: A Comparison of Artificial Intelligence and Human Doctors for the Purpose of Triage and Diagnosis. https://app.cochat.ai/papers/10.3389/frai.2020.543405
- The paper
- Baker, A., Perov, Y., Middleton, K., Baxter, J., Mullarkey, D., Sangar, D., Butt, M., DoRosario, A., & Johri, S. (2020). A Comparison of Artificial Intelligence and Human Doctors for the Purpose of Triage and Diagnosis. Frontiers in Artificial Intelligence. https://doi.org/10.3389/frai.2020.543405
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.