Artificial intelligence outperforms pulmonologists in the interpretation of pulmonary function tests
Open accessAbstract
The interpretation of pulmonary function tests (PFTs) to diagnose respiratory diseases is built on expert opinion that relies on the recognition of patterns and the clinical context for detection of specific diseases. In this study, we aimed to explore the accuracy and interrater variability of pulmonologists when interpreting PFTs compared with artificial intelligence (AI)-based software that was developed and validated in more than 1500 historical patient cases. 120 pulmonologists from 16 European hospitals evaluated 50 cases with PFT and clinical information, resulting in 6000 independent interpretations. The AI software examined the same data. American Thoracic Society/European Respiratory Society guidelines were used as the gold standard for PFT pattern interpretation. The gold standard for diagnosis was derived from clinical history, PFT and all additional tests. The pattern recognition of PFTs by pulmonologists (senior 73%, junior 27%) matched the guidelines in 74.4±5.9% of the cases (range 56–88%). The interrater variability of κ=0.67 pointed to a common agreement. Pulmonologists made correct diagnoses in 44.6±8.7% of the cases (range 24–62%) with a large interrater variability (κ=0.35). The AI-based software perfectly matched the PFT pattern interpretations (100%) and assigned a correct diagnosis in 82% of all cases (p<0.0001 for both measures). The interpretation of PFTs by pulmonologists leads to marked variations and errors. AI-based software provides more accurate interpretations and may serve as a powerful decision support tool to improve clinical practice.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
AI-based software provides more accurate interpretation and serves as a decision support tool in interpreting pulmonary function tests.
“A recent study (25) reported how AI-based software provides more accurate interpretation and serves as a decision support tool in the case on interpreting results from pulmonary function tests.”
From Artificial Intelligence in Medicine: Today and Tomorrow (2020) · cites this paper as [25]
The comparison with the AI software reports 82% diagnostic accuracy versus 44.6% for pulmonologists, supporting the greater-accuracy claim. The Abstract and Discussion say the software *may* serve as a decision-support tool; they do not establish that it already serves in that role. (LLM, conf=0.88)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 33 · Cited by 238
Research works printed but not linked: 1
- [18]18. Topalovic M, Das N, Troosters T, Decramer M, Janssens W. Late Breaking Abstract -Applying artificial intelligence on pulmonary function tests improves the diagnostic accuracy. European Respiratory Journal 2017: 50(suppl 61).
- Authors
- Topalovic, M., Das, N., Burgel, P.-R., Daenen, M., Derom, E., Haenebalcke, C., Janssen, R., Kerstjens, H. A. M., Liistro, G., Louis, R., Ninane, V., Pison, C., Schlesser, M., Vercauter, P., Vogelmeier, C. F., Wouters, E., Wynants, J., & Janssens, W.
- Affiliations
- KU Leuven (BE)
- Sorbonne Paris Cité (FR)
- Ziekenhuis Oost-Limburg (BE)
- Ghent University Hospital (BE)
- AZ Sint-Jan (BE)
- Canisius-Wilhelmina Ziekenhuis (NL)
- University Medical Center Groningen (NL)
- Cliniques Universitaires Saint-Luc (BE)
- Centre Hospitalier Universitaire de Liège (BE)
- Université Libre de Bruxelles (BE)
- Centre Hospitalier Universitaire de Grenoble (FR)
- Centre Hospitalier de Luxembourg (LU)
- Onze Lieve Vrouwziekenhuis Hospital (BE)
- Universitätsklinikum Gießen und Marburg (DE)
- Maastricht University Medical Centre (NL)
- Jessa Hospital (BE)
- ORCID
- Venue
- European Respiratory Journal
- Publisher
- European Respiratory Society (ERS)
- Published
- 2019-02-14
- Volume
- 53
- Issue
- 4
- Pages
- 1801660
- ISSN
- 0903-1936 (ISSN-L)
- 1399-3003
- OpenAlex
- W2913204420
- Cited by
- 238
- References
- 33
- Citations by year
- 2026: 32 · 2025: 37 · 2024: 39 · 2023: 41 · 2022: 37 · 2021: 19 · 2020: 24 · 2019: 9
- FWCI
- 16.36
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- European Respiratory Journal (publishedVersion)
- PubMed (publishedVersion)
- Ghent University Academic Bibliography (Ghent University) (publishedVersion)
- Research Publications (Maastricht University) (publishedVersion, other-oa)
- University of Groningen research database (University of Groningen / Centre for Information Technology) (publishedVersion, other-oa)
- HAL (submittedVersion)
- Ghent University Academic Bibliography (Ghent University) (submittedVersion)
- DIAL (Catholic University of Leuven) (submittedVersion, other-oa)
- Digital Access to Libraries (Université catholique de Louvain (UCL), l'Université de Namur (UNamur) and the Université Saint-Louis (USL-B)) (submittedVersion, other-oa)
- Dépôt institutionnel de l'Université libre de Bruxelles (Université Libre de Bruxelles) (submittedVersion)
- Document Server@UHasselt (UHasselt) (submittedVersion)
- Lirias (KU Leuven) (submittedVersion, other-oa)
- ORBi (University of Liège) (submittedVersion, other-oa)
- University of Groningen research database (University of Groningen / Centre for Information Technology) (submittedVersion)
- University of Groningen research database (University of Groningen / Centre for Information Technology) (submittedVersion, other-oa)
- Research Publications (Maastricht University) (submittedVersion, other-oa)
- Funders
- Vlaams Agentschap Innoveren & Ondernemen - VLAIO (IWT150747)
- Topics
- Health Sciences › Medicine › Pulmonary and Respiratory Medicine › Chronic Obstructive Pulmonary Disease (COPD) Research
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- pulmonary function tests, artificial intelligence, interobserver variability, diagnostic accuracy, clinical decision support, respiratory disease diagnosis
- MeSH terms
- Adult, Aged, Aged, 80 and over, Artificial Intelligence, Female, Humans, Male, Middle Aged, Prospective Studies, Respiratory Function Tests, Software, Pulmonary Medicine
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
