Assessing COPD severity using N-TidalTM, a novel fast-response capnometer (ID 470)
TidalSense Limited
Funding: NIHR (i4i grant), Innovate UK, SBRI Healthcare and Pfizer OpenAir.
Abstract
IntroductionThe GOLD recommends spirometry as the gold standard for measuring the severity of airflow limitation in COPD. However, there is a widespread shortage of staff accredited by the ARTP to perform quality assured spirometry and its use remains limited in areas due to the associated risk of an aerosol-generating cough. There is therefore a need for an alternative physiological marker of COPD severity. TidalSense has developed the N-TidalTM handheld capnometer which measures exhaled carbon dioxide during relaxed breathing. The aim was to develop an alternative severity index to FEV1% predicted which can be used to distinguish mild from severe COPD by using interpretable machine learning and the N-TidalTM device.
Methods
Participant records were drawn from five clinical studies (CBRS, CBRS2, GBRS, ABRS and CARES). A logistic regression model was trained to distinguish capnograms of participants with GOLD 1 disease from GOLD 4 disease on the basis of 82 features derived from capnography. The training dataset included 19 COPD GOLD 4 (very severe) and 37 COPD GOLD 1 (mild) participants, with model output defined as the probability of severe COPD. Performance metrics were generated from an unseen test set of 5 COPD GOLD 4, and 10 COPD GOLD 1 participants.
Results
The classification model achieved an AUROC of 0.985, a sensitivity of 0.957, a specificity of 0.985, a positive predictive value (PPV) of 0.985, and a negative predictive value (NPV) of 0.956 in distinguishing GOLD 1 and 4 participants. Figure 1 shows the correlation between the model’s output probabilities and FEV1% predicted for all participants’ spirometry readings.
Figure 1: FEV1 % Predicted vs. Severity Model Output Probabilities
Conclusion
The N-TidalTM device shows high diagnostic accuracy in distinguishing GOLD 1 from GOLD 4 COPD in near-real-time, providing a possible alternative to spirometry for disease monitoring.
Conflicts of interest: LT, ABS, MH, JCC, HB, RHL, GL, AXP are currently employed, or were employed/funded at the time of the research, by TidalSense Limited. GH is funded by the National Institute for Health Research (NIHR) Community Healthcare MedTech and In Vitro Diagnostics Co-operative at Oxford Health NHS Foundation Trust. All authors declare no competing interests. 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.
The conference has been instigated and organised by PCRS. We are grateful to sponsors and exhibitors who have contributed funding towards this event in return for exhibition space. Neither sponsors or exhibitors have had any input into the agenda or the selection of speakers with the exception of any sponsored satellite symposia which are clearly indicated. View the full list of sponsors.