A machine learning approach to predict extreme inactivity in COPD patients using non-activity-related clinical data.

Facilitating the identification of extreme inactivity (EI) has the potential to improve morbidity and mortality in COPD patients. Apart from patients with obvious EI, the identification of a such behavior during a real-life consultation is unreliable. We therefore describe a machine learning algorithm to screen for EI, as actimetry measurements are difficult to implement. Complete datasets for 1409 COPD patients were obtained from COLIBRI-COPD, a database of clinicopathological data submitted by French pulmonologists. Patient- and pulmonologist-reported estimates of PA quantity (daily walking time) and intensity (domestic, recreational, or fitness-directed) were first used to assign patients to one of four PA groups (extremely inactive [EI], overtly active [OA], intermediate [INT], inconclusive [INC]). The algorithm was developed by (i) using data from 80% of patients in the EI and OA groups to identify 'phenotype signatures' of non-PA-related clinical variables most closely associated with EI or OA; (ii) testing its predictive validity using data from the remaining 20% of EI and OA patients; and (iii) applying the algorithm to identify EI patients in the INT and INC groups. The algorithm's overall error for predicting EI status among EI and OA patients was 13.7%, with an area under the receiver operating characteristic curve of 0.84 (95% confidence intervals: 0.75-0.92). Of the 577 patients in the INT/INC groups, 306 (53%) were reclassified as EI by the algorithm. Patient- and physician- reported estimation may underestimate EI in a large proportion of COPD patients. This algorithm may assist physicians in identifying patients in urgent need of interventions to promote PA.

Are there specific clinical characteristics associated with physician's treatment choices in COPD?

BACKGROUND: The number of pharmacological agents and guidelines available for COPD has increased markedly but guidelines remain poorly followed. Understanding underlying clinical reasoning is challenging and could be informed by clinical characteristics associated with treatment prescriptions. METHODS: To determine whether COPD treatment choices by respiratory physicians correspond to specific patients' features, this study was performed in 1171 patients who had complete treatment and clinical characterisation data. Multiple statistical models were applied to explain five treatment categories: A: no COPD treatment or short-acting bronchodilator(s) only; B: one long-acting bronchodilator (beta2 agonist, LABA or anticholinergic agent, LAMA); C: LABA+LAMA; D: a LABA or LAMA + inhaled corticosteroid (ICS); E: triple therapy (LABA+LAMA+ICS). RESULTS: Mean FEV1 was 60% predicted. Triple therapy was prescribed to 32.9% (treatment category E) of patients and 29.8% received a combination of two treatments (treatment categories C or D); ICS-containing regimen were present for 44% of patients altogether. Single or dual bronchodilation were less frequently used (treatment categories B and C: 19% each). While lung function was associated with all treatment decisions, exacerbation history, scores of clinical impact and gender were associated with the prescription of > 1 maintenance treatment. Statistical models could predict treatment decisions with a < 35% error rate. CONCLUSION: In COPD, contrary to what has been previously reported in some studies, treatment choices by respiratory physicians appear rather rational since they can be largely explained by the patients' characteristics proposed to guide them in most recommendations.