Advanced search
1 file | 573.36 KB Add to list

Artificial intelligence outperforms pulmonologists in the interpretation of pulmonary function tests

Author
Organization
Abstract
The interpretation of pulmonary function tests (PFTs) to diagnose respiratory diseases is built on expert opinion which relies on the recognition of patterns and clinical context for the detection of specific diseases. In the study, we aimed to explore the accuracy and inter-rater variability of pulmonologists when interpreting PFTs and compared it against that of artificial intelligence (AI)-based software which was developed and validated in more than 1500 historical patient cases. 120 pulmonologists from 16 European hospitals evaluated 50 cases comprising with PFT and clinical information resulting in 6000 independent interpretations. AI software examined the same data. ATS/ERS 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 inter-rater variability of 0.67 (kappa) pointed to a common agreement. Pulmonologists made correct diagnoses in 44.6% (±8.7) of the cases (range: 24-62%) with a large inter-rater variability (kappa= 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.
Keywords
DIAGNOSIS, PERFORMANCE, STRATEGIES, GUIDELINES

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 573.36 KB

Citation

Please use this url to cite or link to this publication:

MLA
Topalovic, Marko, et al. “Artificial Intelligence Outperforms Pulmonologists in the Interpretation of Pulmonary Function Tests.” EUROPEAN RESPIRATORY JOURNAL, vol. 53, no. 4, 2019.
APA
Topalovic, M., Das, N., Burgel, P.-R., Daenen, M., Derom, E., Haenebalcke, C., … Janssens, W. (2019). Artificial intelligence outperforms pulmonologists in the interpretation of pulmonary function tests. EUROPEAN RESPIRATORY JOURNAL, 53(4).
Chicago author-date
Topalovic, Marko, Nalakash Das, Pierre-Régis Burgel, Marc Daenen, Eric Derom, Christel Haenebalcke, Rob Janssen, et al. 2019. “Artificial Intelligence Outperforms Pulmonologists in the Interpretation of Pulmonary Function Tests.” EUROPEAN RESPIRATORY JOURNAL 53 (4).
Chicago author-date (all authors)
Topalovic, Marko, Nalakash Das, Pierre-Régis Burgel, Marc Daenen, Eric Derom, Christel Haenebalcke, Rob Janssen, Huib AM Kerstjens, Giuseppe Liistro, Renaud Louis, Vincent Ninane, Christophe Pison, Marc Schlesser, Piet Vercauter, Claus F Vogelmeier, Emiel Wouters, Jokke Wynants, and Wim Janssens. 2019. “Artificial Intelligence Outperforms Pulmonologists in the Interpretation of Pulmonary Function Tests.” EUROPEAN RESPIRATORY JOURNAL 53 (4).
Vancouver
1.
Topalovic M, Das N, Burgel P-R, Daenen M, Derom E, Haenebalcke C, et al. Artificial intelligence outperforms pulmonologists in the interpretation of pulmonary function tests. EUROPEAN RESPIRATORY JOURNAL. 2019;53(4).
IEEE
[1]
M. Topalovic et al., “Artificial intelligence outperforms pulmonologists in the interpretation of pulmonary function tests,” EUROPEAN RESPIRATORY JOURNAL, vol. 53, no. 4, 2019.
@article{8610500,
  abstract     = {The interpretation of pulmonary function tests (PFTs) to diagnose respiratory diseases is built on expert opinion which relies on the recognition of patterns and clinical context for the detection of specific diseases. In the study, we aimed to explore the accuracy and inter-rater variability of pulmonologists when interpreting PFTs and compared it against that of artificial intelligence (AI)-based software which was developed and validated in more than 1500 historical patient cases.
120 pulmonologists from 16 European hospitals evaluated 50 cases comprising with PFT and clinical information resulting in 6000 independent interpretations. AI software examined the same data. ATS/ERS 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 inter-rater variability of 0.67 (kappa) pointed to a common agreement. Pulmonologists made correct diagnoses in 44.6% (±8.7) of the cases (range: 24-62%) with a large inter-rater variability (kappa= 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.},
  articleno    = {01660-2018},
  author       = {Topalovic, Marko and Das, Nalakash and Burgel, Pierre-Régis and Daenen, Marc and Derom, Eric and Haenebalcke, Christel and Janssen, Rob and Kerstjens, Huib AM and Liistro, Giuseppe and Louis, Renaud and Ninane, Vincent and Pison, Christophe and Schlesser, Marc and Vercauter, Piet and Vogelmeier, Claus F and Wouters, Emiel and Wynants, Jokke and Janssens, Wim},
  issn         = {0903-1936},
  journal      = {EUROPEAN RESPIRATORY JOURNAL},
  keywords     = {DIAGNOSIS,PERFORMANCE,STRATEGIES,GUIDELINES},
  language     = {eng},
  number       = {4},
  pages        = {11},
  title        = {Artificial intelligence outperforms pulmonologists in the interpretation of pulmonary function tests},
  url          = {http://dx.doi.org/10.1183/13993003.01660-2018},
  volume       = {53},
  year         = {2019},
}

Altmetric
View in Altmetric
Web of Science
Times cited: