Diagnosis and Severity Assessment of COPD Using a Novel Fast-Response Capnometer and Interpretable Machine Learning

Abstract

Introduction

Spirometry is the gold standard for COPD diagnosis and severity determination, but is technique-dependent, nonspecific, and requires administration by a trained healthcare professional. There is a need for a fast, reliable, and precise alternative diagnostic test. This study’s aim was to use interpretable machine learning to diagnose COPD and assess severity using 75-second carbon dioxide (CO₂) breath records captured with TidalSense’s N-Tidal^TM capnometer.

Method

For COPD diagnosis, machine learning algorithms were trained and evaluated on 294 COPD (including GOLD stages 1–4) and 705 non-COPD participants. A logistic regression model was also trained to distinguish GOLD 1 from GOLD 4 COPD with the output probability used as an index of severity.

Results

The best diagnostic model achieved an AUROC of 0.890, sensitivity of 0.771, specificity of 0.850 and positive predictive value (PPV) of 0.834. Evaluating performance on all test capnograms that were confidently ruled in or out yielded PPV of 0.930 and NPV of 0.890. The severity determination model yielded an AUROC of 0.980, sensitivity of 0.958, specificity of 0.961 and PPV of 0.958 in distinguishing GOLD 1 from GOLD 4. Output probabilities from the severity determination model produced a correlation of 0.71 with percentage predicted FEV₁.

Conclusion

The N-Tidal^TM device could be used alongside interpretable machine learning as an accurate, point-of-care diagnostic test for COPD, particularly in primary care as a rapid rule-in or rule-out test. N-Tidal^TM also could be effective in monitoring disease progression, providing a possible alternative to spirometry for disease monitoring.

Keywords:

• Pulmonary Disease
• chronic obstructive
• machine learning
• diagnosis
• capnometry
• severity assessment

Ethics approval and consent to participate

All participants consented to participate. Further details can be found on the National Library of Medicine’s Clinical Trial website for CBRS (NCT02814253), GBRS (NCT03356288), CBRS2 (NCT03615365), ABRS (NCT04504838) and CARES (NCT04939558).

Availability of data and materials

The datasets generated during and/or analysed during the current study are not publicly available for data protection reasons.

Declaration of interest

LT, CD, ABS, JCC, HB, RHL, GL, AXP are currently employed, or were employed/funded at the time of the research, by TidalSense Limited. GH and HFA are funded by the National Institute for Health Research (NIHR) Community Healthcare MedTech and In Vitro Diagnostics Co-operative at Oxford Health NHS Foundation Trust. The views expressed in this publication are those of the author(s) and not necessarily those of the NHS, the NIHR or the Department of Health and Social Care.

Additional information

Funding

The studies which provided the data for this report were funded by NIHR (i4i grant), Innovate UK, and Pfizer OpenAir. The authors had sole responsibility for the study design, data collection, data analysis, data interpretation and report writing. The ABRS study was supported by the National Institute for Health Research Invention for Innovation (NIHR i4i) Programme (Grant Reference Number: II-LA-1117-20002), the GBRS study was supported by Innovate UK (Grant Reference Number: 102977), the CBRS study was supported by SBRI Healthcare, the CBRS2 study was supported by Pfizer OpenAir and the CARES study was supported by Innovate UK through two grants (Grant Reference Numbers: 133879 and 74355).