Rationale: The decades-long progression of chronic obstructive pulmonary disease (COPD) renders identifying different trajectories of disease progression challenging. Objectives: To identify subtypes of patients with COPD with distinct longitudinal progression patterns using a novel machine-learning tool called “Subtype and Stage Inference” (SuStaIn) and to evaluate the utility of SuStaIn for patient stratification in COPD. Methods: We applied SuStaIn to cross-sectional computed tomography imaging markers in 3,698 Global Initiative for Chronic Obstructive Lung Disease (GOLD) 1–4 patients and 3,479 controls from the COPDGene (COPD Genetic Epidemiology) study to identify subtypes of patients with COPD. We confirmed the identified subtypes and progression patterns using ECLIPSE (Evaluation of COPD Longitudinally to Identify Predictive Surrogate Endpoints) data. We assessed the utility of SuStaIn for patient stratification by comparing SuStaIn subtypes and stages at baseline with longitudinal follow-up data. Measurements and Main Results: We identified two trajectories of disease progression in COPD: a “Tissue→Airway” subtype (n = 2,354, 70.4%), in which small airway dysfunction and emphysema precede large airway wall abnormalities, and an “Airway→Tissue” subtype (n = 988, 29.6%), in which large airway wall abnormalities precede emphysema and small airway dysfunction. Subtypes were reproducible in ECLIPSE. Baseline stage in both subtypes correlated with future FEV₁/FVC decline (r = −0.16 [P < 0.001] in the Tissue→Airway group; r = −0.14 [P = 0.011] in the Airway→Tissue group). SuStaIn placed 30% of smokers with normal lung function at elevated stages, suggesting imaging changes consistent with early COPD. Individuals with early changes were 2.5 times more likely to meet COPD diagnostic criteria at follow-up. Conclusions: We demonstrate two distinct patterns of disease progression in COPD using SuStaIn, likely representing different endotypes. One third of healthy smokers have detectable imaging changes, suggesting a new biomarker of “early COPD.”

Exacerbations of chronic obstructive pulmonary disease (COPD) are currently diagnosed based on changes in respiratory symptoms. Characterizing the imaging manifestation of exacerbations could be useful for objective diagnosis of exacerbations in the clinic and clinical trials, as well as provide a mechanism for monitoring exacerbation treatment and recovery. In this systematic review, we employed a comprehensive search across three databases (Medline, EMBASE, Web of Science) to identify studies that performed imaging of the thorax at COPD exacerbation. We included 51 from a total of 5,047 articles which met all our inclusion criteria. We used an adapted version of the Modified Newcastle-Ottawa Quality Assessment Scale for cohort studies to assess the quality of the included studies. Conclusions were weighted towards higher-quality articles. We identified a total of 36 thoracic imaging features studied at exacerbation of COPD. Studies were generally heterogeneous in their measurements and focus. Nevertheless, considering studies which performed consecutive imaging at stable state and exacerbation, which scored highest for quality, we identified salient imaging biomarkers of exacerbations. An exacerbation is characterized by airway wall and airway calibre changes, hyperinflation, pulmonary vasoconstriction and imaging features suggestive of pulmonary arterial hypertension. Most information was gained from CT studies. We present the first ever composite imaging signature of COPD exacerbations. While imaging during an exacerbation is comparatively new and not comprehensively studied, it may uncover important insights into the acute pathophysiologic changes in the cardiorespiratory system during exacerbations of COPD, providing objective confirmation of events and a biomarker of recovery and treatment response.

Small Airways Disease (SAD) is a recognised part of the pathology in Chronic Obstructive Pulmonary Disease (COPD) and contributes to the symptom burden in the disease. Upper airway symptoms in COPD is an emerging field of study, and in this study, we sought to examine the co-existence of SAD and upper airways symptoms in a cohort of COPD patients METHODS: We investigated a cohort of patients with COPD for the presence of SAD with three different modalities. We performed High-Resolution CT (HRCT) with Parametric Response Mapping (PRM) analysis and recorded distribution of emphysema (PRM^Emph) and functional Small Airways Disease (PRM^fSAD). We measured central and peripheral lung resistance using Impulse Oscillometry (IOS) and recorded R5Hz, R20Hz, R5-R20Hz, X5, Fres and Ax. Static lung function parameters were obtained using Body Plethysmography. Data on upper and lower airway symptoms were evaluated using the Upper Airway subdomain of the 22 items Sino Nasal Outcome Test (SNOT22_nasal) and the COPD Assessment Test (CAT), respectively. We recruited a total of 112 patients. (female sex: 58%, Age 68 (±8) years, FEV1%predicted: 53% (±16%), GOLD stage: A: 23%, B: 55%, C:1% D: 21%). Forty-five (40%) were classified as having high upper airway symptoms (UAS), defined as SNOT22_nasal ≥6. Eighty-seven per cent showed signs of SAD using IOS (R5-R20Hz > 0.07 kPa/L/s). No significant differences were found between UAS groups in IOS, PRM or Body Plethysmography parameters. In patients with COPD, the prevalence of small airways disease was very high, but no association between upper airway symptoms and small airways disease was demonstrated.

The COVID-19 pandemic has been a great challenge to healthcare systems worldwide. It highlighted the need for robust predictive models which can be readily deployed to uncover heterogeneities in disease course, aid decision-making and prioritise treatment. We adapted an unsupervised data-driven model—SuStaIn, to be utilised for short-term infectious disease like COVID-19, based on 11 commonly recorded clinical measures. We used 1344 patients from the National COVID-19 Chest Imaging Database (NCCID), hospitalised for RT-PCR confirmed COVID-19 disease, splitting them equally into a training and an independent validation cohort. We discovered three COVID-19 subtypes (General Haemodynamic, Renal and Immunological) and introduced disease severity stages, both of which were predictive of distinct risks of in-hospital mortality or escalation of treatment, when analysed using Cox Proportional Hazards models. A low-risk Normal-appearing subtype was also discovered. The model and our full pipeline are available online and can be adapted for future outbreaks of COVID-19 or other infectious disease.