AI Article Synopsis

  • Spirometry and plethysmography are crucial pulmonary function tests, but relying solely on spirometry can result in missed lung disease diagnoses, especially for restrictive conditions.
  • Researchers developed a deep learning model using data from 748 patients to enhance the interpretation of spirometry results without plethysmography.
  • The model demonstrated significantly better accuracy (94.67%) in diagnosing lung conditions compared to trained pulmonologists (66.67%) and decision trees (75.61%), suggesting that deep learning can effectively improve lung disease diagnostics.

Article Abstract

Rationale: Spirometry and plethysmography are the gold standard pulmonary function tests (PFT) for diagnosis and management of lung disease. Due to the inaccessibility of plethysmography, spirometry is often used alone but this leads to missed or misdiagnoses as spirometry cannot identify restrictive disease without plethysmography. We aimed to develop a deep learning model to improve interpretation of spirometry alone.

Methods: We built a multilayer perceptron model using full PFTs from 748 patients, interpreted according to international guidelines. Inputs included spirometry (forced vital capacity, forced expiratory volume in 1 s, forced mid-expiratory flow), plethysmography (total lung capacity, residual volume) and biometrics (sex, age, height). The model was developed with 2582 PFTs from 477 patients, randomly divided into training (80%), validation (10%) and test (10%) sets, and refined using 1245 previously unseen PFTs from 271 patients, split 50/50 as validation (136 patients) and test (135 patients) sets. Only one test per patient was used for each of 10 experiments conducted for each input combination. The final model was compared with interpretation of 82 spirometry tests by 6 trained pulmonologists and a decision tree.

Results: Accuracies from the first 477 patients were similar when inputs included biometrics+spirometry+plethysmography (95%±3%) vs biometrics+spirometry (90%±2%). Model refinement with the next 271 patients improved accuracies with biometrics+pirometry (95%±2%) but no change for biometrics+spirometry+plethysmography (95%±2%). The final model significantly outperformed (94.67%±2.63%, p<0.01 for both) interpretation of 82 spirometry tests by the decision tree (75.61%±0.00%) and pulmonologists (66.67%±14.63%).

Conclusions: Deep learning improves the diagnostic acumen of spirometry and classifies lung physiology better than pulmonologists with accuracies comparable to full PFTs.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9806081PMC
http://dx.doi.org/10.1136/bmjresp-2022-001396DOI Listing

Publication Analysis

Top Keywords

deep learning
8
interpretation spirometry
8
inputs included
8
477 patients
8
271 patients
8
final model
8
spirometry
7
patients
7
model
6
learning multilayer
4

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!