Rationale: While American Thoracic Society (ATS)/European Respiratory Society (ERS) quality control criteria for spirometry include several quantitative limits, it also requires manual visual inspection. The current approach is time consuming and leads to high intertechnician variability. We propose a deep-learning approach called convolutional neural network (CNN), to standardise spirometric manoeuvre acceptability and usability.Methods and methods: In 36 873 curves from the National Health and Nutritional Examination Survey USA 2011–2012, technicians labelled 54% of curves as meeting ATS/ERS 2005 acceptability criteria with satisfactory start and end of test, but identified 93% of curves with a usable forced expiratory volume in 1 s. We processed raw data into images of maximal expiratory flow–volume curve (MEFVC), calculated ATS/ERS quantifiable criteria and developed CNNs to determine manoeuvre acceptability and usability on 90% of the curves. The models were tested on the remaining 10% of curves. We calculated Shapley values to interpret the models.Results: In the test set (n=3738), CNN showed an accuracy of 87% for acceptability and 92% for usability, with the latter demonstrating a high sensitivity (92%) and specificity (96%). They were significantly superior (p<0.0001) to ATS/ERS quantifiable rule-based models. Shapley interpretation revealed MEFVC<1 s (MEFVC pattern within first second of exhalation) and plateau in volume–time were most important in determining acceptability, while MEFVC<1 s entirely determined usability.Conclusion: The CNNs identified relevant attributes in spirometric curves to standardise ATS/ERS manoeuvre acceptability and usability recommendations, and further provides individual manoeuvre feedback. Our algorithm combines the visual experience of skilled technicians and ATS/ERS quantitative rules in automating the critical phase of spirometry quality control.

Rationale Estimating the causal effect of an intervention at individual level, also called individual treatment effect (ITE), may help in identifying response prior to the intervention. Objectives We aimed to develop machine learning (ML) models which estimate ITE of an intervention using data from randomised controlled trials and illustrate this approach with prediction of ITE on annual chronic obstructive pulmonary disease (COPD) exacerbation rates. Methods We used data from 8151 patients with COPD of the Study to Understand Mortality and MorbidITy in COPD (SUMMIT) trial (NCT01313676) to address the ITE of fluticasone furoate/vilanterol (FF/VI) versus control (placebo) on exacerbation rate and developed a novel metric, Q-score, for assessing the power of causal inference models. We then validated the methodology on 5990 subjects from the InforMing the PAthway of COPD Treatment (IMPACT) trial (NCT02164513) to estimate the ITE of FF/umeclidinium/VI (FF/UMEC/VI) versus UMEC/VI on exacerbation rate. We used Causal Forest as causal inference model. Results In SUMMIT, Causal Forest was optimised on the training set (n=5705) and tested on 2446 subjects (Q-score 0.61). In IMPACT, Causal Forest was optimised on 4193 subjects in the training set and tested on 1797 individuals (Q-score 0.21). In both trials, the quantiles of patients with the strongest ITE consistently demonstrated the largest reductions in observed exacerbations rates (0.54 and 0.53, p<0.001). Poor lung function and blood eosinophils, respectively, were the strongest predictors of ITE. Conclusions This study shows that ML models for causal inference can be used to identify individual response to different COPD treatments and highlight treatment traits. Such models could become clinically useful tools for individual treatment decisions in COPD.

Background and aims: Pulmonary hypertension due to left heart disease (PH-LHD) is the most frequent form of PH. As differential diagnosis with pulmonary arterial hypertension (PAH) has therapeutic implications, it is important to accurately and noninvasively differentiate PH-LHD from PAH before referral to PH centres. The aim was to develop and validate a machine learning (ML) model to improve prediction of PH-LHD in a population of PAH and PH-LHD patients.Methods: Noninvasive PH-LHD predictors from 172 PAH and 172 PH-LHD patients from the PH centre database at the University Hospitals of Leuven (Leuven, Belgium) were used to develop an ML model. The Jacobs score was used as performance benchmark. The dataset was split into a training and test set (70:30) and the best model was selected after 10-fold cross-validation on the training dataset (n=240). The final model was externally validated using 165 patients (91 PAH, 74 PH-LHD) from Erasme Hospital (Brussels, Belgium).Results: In the internal test dataset (n=104), a random forest-based model correctly diagnosed 70% of PH-LHD patients (sensitivity: n=35/50), with 100% positive predicted value, 78% negative predicted value and 100% specificity. The model outperformed the Jacobs score, which identified 18% (n=9/50) of the patients with PH-LHD without false positives. In external validation, the model had 64% sensitivity at 100% specificity, while the Jacobs score had a sensitivity of 3% for no false positives.Conclusions: ML significantly improves the sensitivity of PH-LHD prediction at 100% specificity. Such a model may substantially reduce the number of patients referred for invasive diagnostics without missing PAH diagnoses.

Spirometry is the gold standard to detect airflow limitation, but it does not measure airway resistance, which is one of the physiological factors behind airflow limitation. In this study, we describe the dynamics of forced expiration in spirometry using a deflating balloon and using this model. We propose a methodology to estimate ζ (zeta), a dimensionless and effort-independent parameter quantifying airway resistance. In N = 462 (65 ± 8 years), we showed that ζ is significantly (p < 0.0001) greater in COPD (2.59 ± 0.99) than healthy smokers (1.64 ± 0.18), it increased significantly (p < 0.0001) with the severity of airflow limitation and it correlated significantly (p < 0.0001) with airway resistance (r = 0.55) and specific conductance (r = −0.60) obtained from body-plethysmography. ζ also showed significant associations (p < 0.001) with diffusion capacity (r = −0.64), air-trapping (r = 0.68), and CT densitometry of emphysema (r = 0.40 against % below −950 HU and r = −0.34 against 15th percentile HU). Moreover, simulation studies demonstrated that an increase in ζ resulted in lower airflows from baseline. Therefore, we conclude that ζ quantifies airway resistance from forced expiration in spirometry—a method that is more abundantly available in primary care than traditional but expensive methods of measuring airway resistance such as body-plethysmography and forced oscillation technique.

Objective Long-term azithromycin treatment effectively prevents acute exacerbations of chronic obstructive pulmonary disease (COPD). However, patients would benefit from better identification of responders and non-responders to minimise unnecessary exposure. We aimed to assess treatment effect heterogeneity and estimate individual treatment effects (ITEs) to distinguish patients most likely to benefit from prophylactic treatment. Methods We used data from 1025 patients of the MACRO trial to assess the ITE of azithromycin on annual exacerbation rate. A Causal Forest was used as a causal machine learning model. We independently validated our findings using data from 83 patients of the COLUMBUS trial. Results The tertile of patients with the best predicted ITE within MACRO and within the COLUMBUS independent validation cohort showed significant and substantially greater reductions in annual exacerbation rates (in MACRO −0.50, rate ratio 0.70, p=0.01, in COLUMBUS: −2.28, rate ratio 0.43, p<0.001) compared with the average treatment effect across the entire cohort (MACRO −0.35, rate ratio 0.83, p=0.01 and COLUMBUS −1.28, rate ratio 0.58, p=0.001). Conversely, no significant treatment effect was observed in the remaining two-thirds of patients. Primary determinants of ITE included respiratory symptoms, white blood cell count, haemoglobin, C-reactive protein and forced vital capacity. Smoking status did not emerge as a significant predictor. Conclusion Based on five easily obtainable parameters to predict ITE, we identified treatment effect heterogeneity in COPD subjects treated with azithromycin maintenance therapy and found a small subgroup of responders driving the average reduction in exacerbations reported in previous trials.