EUVIMEDEUVIMED entdecken
Randomisierte kontrollierte Studie

AI-Assisted Spirometry Interpretation in Primary Care: A Randomized Controlled Trial

Gillian Doe iD, Winston Banya iD, George Edwards iD, Marko Topalovic iD, Ethaar El-Emir iD, Rachael A Evans iD, Richard Russell iD, Elena Smets iD, Karolien Van Orshoven iD, Karl P Sylvester iD, Anthony P Sunjaya iD, David A Scott iD und 14 weitere

NEJM AI · 2025

DOI: 10.1056/aioa2400804 ↗

Kurz gefasst

Randomisierte kontrollierte Studie in der Zeitschrift NEJM AI, 2025. Verfasst von Gillian Doe und 25 weiteren Autor:innen. Beteiligte Einrichtung: NIHR Biomedical Research Centre Leicester, Department of Respiratory Science, University of Leicester, Glenfield Hospital, UK. Hauptthemen laut MEDLINE: Spirometry, Artificial Intelligence, Pulmonary Disease, Chronic Obstructive, Decision Support Systems, Clinical. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 46 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Spirometry quality and confidence in spirometry interpretation are highly variable in primary care, contributing to underdiagnosis, overdiagnosis, and misdiagnosis of chronic respiratory diseases worldwide. Artificial intelligence (AI) decision support software has been shown to improve the accuracy of lung function interpretation in specialist care, but its applicability to primary care remains unknown. METHODS: We conducted a parallel-group, randomized, controlled superiority trial to evaluate whether AI decision support software improves spirometry interpretation performance by primary care clinicians. Clinicians working in primary care who refer for, perform, or interpret spirometry assessed 50 real-world patient spirometry records, providing the most likely diagnosis ("preferred diagnosis") through an online platform either with (intervention) or without (control) AI decision support software. The primary outcome was the preferred diagnosis prediction performance, measured as the percentage of cases in which the preferred diagnosis agreed with the reference diagnosis predetermined by expert pulmonologists. A planned subgroup analysis focused on cases with a diagnosis of chronic obstructive pulmonary disease (COPD). Secondary outcomes were performance in differential diagnosis prediction, technical quality assessment, pattern interpretation, and self-rated confidence in interpretation. RESULTS: Out of 400 clinicians assessed for eligibility, 234 were randomly assigned, with 133 (57%) completing the assessment (intervention, n=67; control, n=66) - 73% female, 42% general practitioners, and 50% nurses. Compared with the control group, the addition of AI decision support software led to improvements in preferred diagnosis prediction performance in all cases (mean difference, 9.0; 95% confidence interval [CI], 4.5 to 13.3%; P=0.001) and in COPD cases (15.9; 95% CI, 9.0 to 22.7%; P

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SpirometryArtificial IntelligencePulmonary Disease, Chronic ObstructiveDecision Support Systems, ClinicalHumansPrimary Health CareFemaleMaleMiddle AgedAgedSoftware

Autor:innen und Institutionen

  • NIHR Biomedical Research Centre Leicester, Department of Respiratory Science, University of Leicester, Glenfield Hospital, UK.
  • Medical Statistics, Research and Development, Royal Brompton and Harefield Hospitals, Guy's and St Thomas' NHS Foundation Trust, London.
  • Harefield Respiratory Research Group, Guy's and St Thomas' NHS Foundation Trust, London.
  • ArtiQ, a Clario Company, Leuven, Belgium.
  • King's Centre for Lung Health, Faculty of Life Sciences and Medicine, King's College London.
  • Royal Papworth Hospital NHS Foundation Trust, Cambridge, UK.

ORCID-Profile: Gillian Doe, Winston Banya, George Edwards, Marko Topalovic, Ethaar El-Emir, Rachael A Evans, Richard Russell, Elena Smets, Karolien Van Orshoven, Karl P Sylvester, Anthony P Sunjaya, David A Scott, Maarten De Vos, Ahmed Elmahy, Stephanie J C Taylor, Ann Hutchinson, Nicholas S Hopkinson, Michael Morgan, Samantha S Kon, Suhani Patel, Ian Jarrold, Erika Kennington, Satesh Sehdev, Nannette Spain, A Toby Prevost, William D-C Man

Zitieren

APA

Doe, G., Banya, W., Edwards, G., Topalovic, M., El-Emir, E., Evans, R. A., Russell, R., Smets, E., Van Orshoven, K., Sylvester, K. P., Sunjaya, A. P., Scott, D. A., De Vos, M., Elmahy, A., Taylor, S. J. C., Hutchinson, A., Hopkinson, N. S., Morgan, M., Kon, S. S., …, & Man, W. D. (2025). AI-Assisted Spirometry Interpretation in Primary Care: A Randomized Controlled Trial. NEJM AI. https://doi.org/10.1056/aioa2400804

Vancouver

Doe G, Banya W, Edwards G, Topalovic M, El-Emir E, Evans RA, et al. AI-Assisted Spirometry Interpretation in Primary Care: A Randomized Controlled Trial. NEJM AI. 2025. doi:10.1056/aioa2400804

BibTeX
@article{Doe2025,
  author = {Doe, Gillian and Banya, Winston and Edwards, George and Topalovic, Marko and El-Emir, Ethaar and Evans, Rachael A and Russell, Richard and Smets, Elena and Van Orshoven, Karolien and Sylvester, Karl P and Sunjaya, Anthony P and Scott, David A and De Vos, Maarten and Elmahy, Ahmed and Taylor, Stephanie J C and Hutchinson, Ann and Hopkinson, Nicholas S and Morgan, Michael and Kon, Samantha S and Patel, Suhani and Jarrold, Ian and Kennington, Erika and Sehdev, Satesh and Spain, Nannette and Toby Prevost, A and Man, William D-C},
  title = {AI-Assisted Spirometry Interpretation in Primary Care: A Randomized Controlled Trial},
  journal = {NEJM AI},
  year = {2025},
  doi = {10.1056/aioa2400804}
}
Kostenlos starten →