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

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-TidalTM 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-TidalTM 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-TidalTM also could be effective in monitoring disease progression, providing a possible alternative to spirometry for disease monitoring.

Machine diagnosis of chronic obstructive pulmonary disease using a novel fast-response capnometer.

BACKGROUND: Although currently most widely used in mechanical ventilation and cardiopulmonary resuscitation, features of the carbon dioxide (CO2) waveform produced through capnometry have been shown to correlate with V/Q mismatch, dead space volume, type of breathing pattern, and small airway obstruction. This study applied feature engineering and machine learning techniques to capnography data collected by the N-Tidal™ device across four clinical studies to build a classifier that could distinguish CO2 recordings (capnograms) of patients with COPD from those without COPD. METHODS: Capnography data from four longitudinal observational studies (CBRS, GBRS, CBRS2 and ABRS) was analysed from 295 patients, generating a total of 88,186 capnograms. CO2 sensor data was processed using TidalSense's regulated cloud platform, performing real-time geometric analysis on CO2 waveforms to generate 82 physiologic features per capnogram. These features were used to train machine learning classifiers to discriminate COPD from 'non-COPD' (a group that included healthy participants and those with other cardiorespiratory conditions); model performance was validated on independent test sets. RESULTS: The best machine learning model (XGBoost) performance provided a class-balanced AUROC of 0.985 ± 0.013, positive predictive value (PPV) of 0.914 ± 0.039 and sensitivity of 0.915 ± 0.066 for a diagnosis of COPD. The waveform features that are most important for driving classification are related to the alpha angle and expiratory plateau regions. These features correlated with spirometry readings, supporting their proposed properties as markers of COPD. CONCLUSION: The N-Tidal™ device can be used to accurately diagnose COPD in near-real-time, lending support to future use in a clinical setting. TRIAL REGISTRATION: Please see NCT03615365, NCT02814253, NCT04504838 and NCT03356288.

Continental data on cave-dwelling spider communities across Europe (Arachnida: Araneae).

BACKGROUND: Spiders (Arachnida: Araneae) are widespread in subterranean ecosystems worldwide and represent an important component of subterranean trophic webs. Yet, global-scale diversity patterns of subterranean spiders are still mostly unknown. In the frame of the CAWEB project, a European joint network of cave arachnologists, we collected data on cave-dwelling spider communities across Europe in order to explore their continental diversity patterns. Two main datasets were compiled: one listing all subterranean spider species recorded in numerous subterranean localities across Europe and another with high resolution data about the subterranean habitat in which they were collected. From these two datasets, we further generated a third dataset with individual geo-referenced occurrence records for all these species. NEW INFORMATION: Data from 475 geo-referenced subterranean localities (caves, mines and other artificial subterranean sites, interstitial habitats) are herein made available. For each subterranean locality, information about the composition of the spider community is provided, along with local geomorphological and habitat features. Altogether, these communities account for > 300 unique taxonomic entities and 2,091 unique geo-referenced occurrence records, that are made available via the Global Biodiversity Information Facility (GBIF) (Mammola and Cardoso 2019). This dataset is unique in that it covers both a large geographic extent (from 35° south to 67° north) and contains high-resolution local data on geomorphological and habitat features. Given that this kind of high-resolution data are rarely associated with broad-scale datasets used in macroecology, this dataset has high potential for helping researchers in tackling a range of biogeographical and macroecological questions, not necessarily uniquely related to arachnology or subterranean biology.

Local- versus broad-scale environmental drivers of continental ß-diversity patterns in subterranean spider communities across Europe.

Macroecologists seek to identify drivers of community turnover (ß-diversity) through broad spatial scales. However, the influence of local habitat features in driving broad-scale ß-diversity patterns remains largely untested, owing to the objective challenges of associating local-scale variables to continental-framed datasets. We examined the relative contribution of local- versus broad-scale drivers of continental ß-diversity patterns, using a uniquely suited dataset of cave-dwelling spider communities across Europe (35-70° latitude). Generalized dissimilarity modelling showed that geographical distance, mean annual temperature and size of the karst area in which caves occurred drove most of ß-diversity, with differential contributions of each factor according to the level of subterranean specialization. Highly specialized communities were mostly influenced by geographical distance, while less specialized communities were mostly driven by mean annual temperature. Conversely, local-scale habitat features turned out to be meaningless predictors of community change, which emphasizes the idea of caves as the human accessible fraction of the extended network of fissures that more properly represents the elective habitat of the subterranean fauna. To the extent that the effect of local features turned to be inconspicuous, caves emerge as experimental model systems in which to study broad biological patterns without the confounding effect of local habitat features.