Exacerbation predictive modelling using real-world data from the myCOPD app.

Background: Acute exacerbations of COPD (AECOPD) are episodes of breathlessness, cough and sputum which are associated with the risk of hospitalisation, progressive lung function decline and death. They are often missed or diagnosed late. Accurate timely intervention can improve these poor outcomes. Digital tools can be used to capture symptoms and other clinical data in COPD. This study aims to apply machine learning to the largest available real-world digital dataset to develop AECOPD Prediction tools which could be used to support early intervention and improve clinical outcomes. Objective: To create and validate a machine learning predictive model that forecasts exacerbations of COPD 1-8 days in advance. The model is based on routine patient-entered data from myCOPD self-management app. Method: Adaptations of the AdaBoost algorithm were employed as machine learning approaches. The dataset included 506 patients users between 2017 and 2021. 55,066 app records were available for stable COPD event labels and 1263 records of AECOPD event labels. The data used for training the model included COPD assessment test (CAT) scores, symptom scores, smoking history, and previous exacerbation frequency. All exacerbation records used in the model were confined to the 1-8 days preceding a self-reported exacerbation event. Results: TheEasyEnsemble Classifier resulted in a Sensitivity of 67.0 % and a Specificity of 65 % with a positive predictive value (PPV) of 5.0 % and a negative predictive value (NPV) of 98.9 %. An AdaBoost model with a cost-sensitive decision tree resulted in a a Sensitivity of 35.0 % and a Specificity of 89.0 % with a PPV of 7.08 % and NPV of 98.3 %. Conclusion: This preliminary analysis demonstrates that machine learning approaches to real-world data from a widely deployed digital therapeutic has the potential to predict AECOPD and can be used to confidently exclude the risk of exacerbations of COPD within the next 8 days.

A history of asthma may be associated with grandparents' exposures to stress and cigarette smoking.

Introduction: Within human epidemiological studies, associations have been demonstrated between grandparental exposures during childhood and grandchildren's outcomes. A few studies have assessed whether asthma has ancestral associations with exposure to cigarette smoking, but results have been mixed so far. Material and methods: In this study we used four generations: (F0 great-grandparents, F1 grandparents, F2 parents, F3 study children) of the Avon Longitudinal Study of Parents and Children (ALSPAC) to determine whether there is evidence of associations between asthma in generations F2 or F3 and exposures to severe trauma in childhood and/or active cigarette smoking during the adolescence of grandmothers and grandfathers in generations F0 and F1 respectively, or of a history of a F0 or F1 grandmother smoking during pregnancy. Results: We have shown that: a) stress exemplified by the death of a F1 grandparent's parent during the grandparents' childhood was associated with increased risk of asthma in generation F3, especially if the grandparent involved was the paternal grandmother; b) if the grandparents of generations F0 or F1 smoked during adolescence (i.e. < 17 years), their grandchildren in generations F2 and F3 were more likely to have a history of asthma; c) paternal F1 grandmother's smoking in pregnancy was associated with her F3 grandchild's asthma at age 7; d) There were differences between the results for the grandsons and granddaughters of the paternal grandmother with exposure to smoking in adolescence and with smoking in pregnancy. e) The addition of all of the individual exposure variables to the different analyses often provided a considerable increase in goodness of fit compared with only adding demographic factors associated with asthma at P < 0.10 such as social class; this was particularly true when all four exposure variables were combined in one model, suggesting possible synergistic effects between them. Discussion: We have shown associations between all four types of exposure to the grandparents to be associated with asthma in the grandchildren, such that the results both depended on whether the male or female line was involved, and the sex of the grandchildren. It was notable that the paternal grandmother was particularly involved in many of the associations. We emphasize that these are exploratory analyses, that asthma diagnostic criteria likely changed over time and may not be consistent between generations, and that the results should be tested in other cohorts.

Prevalence, risk factors, and clinical implications of preserved ratio impaired spirometry: a UK Biobank cohort analysis.

BACKGROUND: Preserved ratio impaired spirometry (PRISm) is defined as a FEV1 of less than 80% predicted and a FEV1/forced vital capacity (FVC) ratio of 0·70 or higher. Previous research has indicated that PRISm is associated with respiratory symptoms and is a precursor of chronic obstructive pulmonary disease (COPD). However, these findings are based on relatively small selective cohorts with short follow-up. We aimed to determine the prevalence, risk factors, clinical implications, and mortality of PRISm in a large adult general population. METHODS: For this cohort analysis, we used data from the UKBiobank to assess PRISm prevalence, risk factors and associated symptoms, and associated comorbidities in a large adult population. Participants with spirometry deemed acceptable by an investigator (best measure FEV1 and FVC values) at baseline were included. Participants were excluded if they did not have acceptable spirometry or were missing data on body-mass index or smoking status. Control spirometry was defined as a FEV1 of 80% or more predicted and a FEV1/FVC ratio of 0·70 or higher. Airflow obstruction was defined as a FEV1/FVC ratio of less than 0·70. We used multivariable regression to determine risk factors for PRISm and associated comorbidities. Individuals who lived within close proximity to an assessment centre were invited for follow-up, with repeat spirometry. Only participants who had been included at baseline were examined in follow-up. This allowed for a longitudinal analysis of PRISm over time and risk factors for transition to airflow obstruction. We also did the survival analysis for a 12-year period. FINDINGS: Participants were recruited by UK Biobank between Dec 19, 2006, and Oct 10, 2010. We included 351 874 UK Biobank participants (189 247 women and 162 627 men) in our study, with a median follow-up of 9·0 years (IQR 8·0-10·0). 38 639 (11·0%) of 351 874 participants had PRISm at baseline. After adjustment, PRISm was strongly associated with obesity (odds ratio [OR] 2·40 [2·26-2·55], p<0·0001), current smoking (1·48 [1·36-1·62], p<0·0001), and patient reported doctor-diagnosed asthma (1·76 [1·66-1·88], p<0·0001). Other risk factors identified included female sex, being overweight, trunk fat mass, and trunk fat percentage. PRISm was strongly associated with symptoms and comorbidity including increased risk of breathlessness (adjusted OR 2·0 [95% CI 1·91-2·14], p<0·0001) and cardiovascular disease (adjusted OR 1·71 [1·64-1·83], p<0·0001 for heart attack). Longitudinal analysis showed that 241 (12·2%) of 1973 participants who had PRISm at baseline had transitioned to airflow obstruction consistent with COPD. PRISm was associated with increased all-cause mortality (adjusted hazard ratio 1·61 [95% CI 1·53-1·69], p<0·0001) versus control participants. INTERPRETATION: PRISm was associated with breathlessness, multimorbidity, and increased risk of death, which does not seem to be explained by smoking, obesity, or existing lung disease. Although for many patients PRISm is transient, it is important to understand which individuals are at risk of progressive lung function abnormalities. Further research into the genetic, structural and functional pathophysiology of PRISm is warranted. FUNDING: UK Medical Research Council and University of Bristol.

Lung function and cardiovascular disease: a two-sample Mendelian randomisation study.

BACKGROUND: Observational studies suggest an association between reduced lung function and risk of coronary artery disease and ischaemic stroke, independent of shared cardiovascular risk factors such as cigarette smoking. We use the latest genetic epidemiological methods to determine whether impaired lung function is causally associated with an increased risk of cardiovascular disease. METHODS AND FINDINGS: Mendelian randomisation uses genetic variants as instrumental variables to investigate causation. Preliminary analysis used two-sample Mendelian randomisation with lung function single nucleotide polymorphisms. To avoid collider bias, the main analysis used single nucleotide polymorphisms for lung function identified from UKBiobank in a multivariable Mendelian randomisation model conditioning for height, body mass index and smoking.Multivariable Mendelian randomisation shows strong evidence that reduced forced vital capacity (FVC) causes increased risk of coronary artery disease (OR 1.32, 95% CI 1.19-1.46 per standard deviation). Reduced forced expiratory volume in 1 s (FEV1) is unlikely to cause increased risk of coronary artery disease, as evidence of its effect becomes weak after conditioning for height (OR 1.08, 95% CI 0.89-1.30). There is weak evidence that reduced lung function increases risk of ischaemic stroke. CONCLUSION: There is strong evidence that reduced FVC is independently and causally associated with coronary artery disease. Although the mechanism remains unclear, FVC could be taken into consideration when assessing cardiovascular risk and considered a potential target for reducing cardiovascular events. FEV1 and airflow obstruction do not appear to cause increased cardiovascular events; confounding and collider bias may explain previous findings of a causal association.

Contributions of cardiovascular risk and smoking to chronic obstructive pulmonary disease (COPD)-related changes in brain structure and function.

Background: Brain damage and cardiovascular disease are extra-pulmonary manifestations of chronic obstructive pulmonary disease (COPD). Cardiovascular risk factors and smoking are contributors to neurodegeneration. This study investigates whether there is a specific, COPD-related deterioration in brain structure and function independent of cardiovascular risk factors and smoking. Materials and methods: Neuroimaging and clinical markers of brain structure (micro- and macro-) and function (cognitive function and mood) were compared between 27 stable COPD patients (age: 63.0±9.1 years, 59.3% male, forced expiratory volume in 1 second [FEV1]: 58.1±18.0% pred.) and 23 non-COPD controls with >10 pack years smoking (age: 66.6±7.5 years, 52.2% male, FEV1: 100.6±19.1% pred.). Clinical relationships and group interactions with brain structure were also tested. All statistical analyses included correction for cardiovascular risk factors, smoking, and aortic stiffness. Results: COPD patients had significantly worse cognitive function (p=0.011), lower mood (p=0.046), and greater gray matter atrophy (p=0.020). In COPD patients, lower mood was associated with markers of white matter (WM) microstructural damage (p<0.001), and lower lung function (FEV1/forced vital capacity and FEV1) with markers of both WM macro (p=0.047) and microstructural damage (p=0.028). Conclusion: COPD is associated with both structural (gray matter atrophy) and functional (worse cognitive function and mood) brain changes that cannot be explained by measures of cardiovascular risk, aortic stiffness, or smoking history alone. These results have important implications to guide the development of new interventions to prevent or delay progression of neuropsychiatric comorbidities in COPD. Relationships found between mood and microstructural abnormalities suggest that in COPD, anxiety, and depression may occur secondary to WM damage. This could be used to better understand disabling symptoms such as breathlessness, improve health status, and reduce hospital admissions.

Disruption of white matter connectivity in chronic obstructive pulmonary disease.

BACKGROUND: Mild cognitive impairment is a common systemic manifestation of chronic obstructive pulmonary disease (COPD). However, its pathophysiological origins are not understood. Since, cognitive function relies on efficient communication between distributed cortical and subcortical regions, we investigated whether people with COPD have disruption in white matter connectivity. METHODS: Structural networks were constructed for 30 COPD patients (aged 54-84 years, 57% male, FEV1 52.5% pred.) and 23 controls (aged 51-81 years, 48% Male). Networks comprised 90 grey matter regions (nodes) interconnected by white mater fibre tracts traced using deterministic tractography (edges). Edges were weighted by the number of streamlines adjusted for a) streamline length and b) end-node volume. White matter connectivity was quantified using global and nodal graph metrics which characterised the networks connection density, connection strength, segregation, integration, nodal influence and small-worldness. Between-group differences in white matter connectivity and within-group associations with cognitive function and disease severity were tested. RESULTS: COPD patients' brain networks had significantly lower global connection strength (p = 0.03) and connection density (p = 0.04). There was a trend towards COPD patients having a reduction in nodal connection density and connection strength across the majority of network nodes but this only reached significance for connection density in the right superior temporal gyrus (p = 0.02) and did not survive correction for end-node volume. There were no other significant global or nodal network differences or within-group associations with disease severity or cognitive function. CONCLUSION: COPD brain networks show evidence of damage compared to controls with a reduced number and strength of connections. This loss of connectivity was not sufficient to disrupt the overall efficiency of network organisation, suggesting that it has redundant capacity that makes it resilient to damage, which may explain why cognitive dysfunction is not severe. This might also explain why no direct relationships could be found with cognitive measures. Smoking and hypertension are known to have deleterious effects on the brain. These confounding effects could not be excluded.

COPD patients hospitalized with exacerbations have greater cognitive impairment than patients hospitalized with decompensated heart failure.

PURPOSE: People with COPD have cognitive dysfunction, which is greater in those hospitalized for exacerbations than in stable outpatients. We tested the hypothesis that cognitive dysfunction at exacerbation is a disease-specific feature of COPD, rather than a nonspecific feature of hospitalization for acute illness, by comparing cognition between patients hospitalized for acute COPD exacerbations and those with worsening heart failure (HF). PATIENTS AND METHODS: A total of 40 hospital inpatients were recruited, 20 patients with COPD exacerbations and 20 patients with congestive or left-sided HF. Exclusion criteria included previous stroke, known neurological disease, and marked alcohol excess. Participants completed the Montreal cognitive assessment (MoCA) and Hospital Anxiety and Depression Scale (HADS) and underwent spirometry and review of clinical records. RESULTS: Age (mean±SD, COPD 73±10; HF 76±11 years), acute illness severity (Acute Physiology and Chronic Health Evaluation [APACHE]-II, COPD 15.4±3.5; HF 15.9±3.0), comorbidities (Charlson index, COPD 1.3±1.9; HF 1.6±1.5), and educational background were similar between COPD and HF groups. MoCA total was significantly lower in COPD than in HF (COPD 20.6±5.6; HF 24.8±3.5, P=0.007); however, significance was lost after correction for age, sex, and pack year smoking history. When compared with HF patients, the COPD cohort performed worse on the following domains of the MoCA: visuospatial function (median [IQR], COPD 0 [1]; HF 2 [1], P=0.003), executive function (COPD 2 [1]; HF 3 [1], P=0.035), and attention (COPD 4 [3]; HF 6 [2], P=0.020). Age (P=0.012) and random glucose concentration (P=0.041) were associated with cognitive function in whole group analysis, with pack year smoking history reaching borderline significance (P=0.050). CONCLUSION: Total MoCA score for COPD and HF indicated that both groups had mild cognitive impairment, although this was greater in people with COPD. Mechanisms underlying the observed cognitive dysfunction in COPD remain unclear but appear related to blood glucose concentrations and greater lifetime smoking load.

Visual rating assessment of cerebral atrophy and its relationship with cognitive function in chronic obstructive pulmonary disease.

INTRODUCTION: Widespread white matter damage and cognitive impairment have been demonstrated in chronic obstructive pulmonary disease (COPD). However, it remains unclear if brain atrophy is a global phenomenon or if specific subregions are differentially affected. The aims of this study are, first, to test a simple, validated visual analogue grading technique. Second, we hypothesised that frontal regions of the brains of patients with COPD will show greater signs of atrophy compared with control subjects. Third, any localised regions of atrophy would correlate with components of cognitive performance. Finally, the severity of cerebral atrophy would be associated with measures of respiratory disease severity. METHODS: We used a simple, validated visual analogue grading technique to assess the degree of regional atrophy in multiple brain regions from cerebral MR images in patients with stable non-hypoxaemic COPD (n=25) and age-matched control subjects (n=25). We also explored correlations between regional brain atrophy with demographics, cognitive performance measures and disease severity. Measures of cognitive performance focused on executive function, working memory, verbal memory, overall memory and processing speed. Measures of disease severity include lung function, gas exchange, health status and breathlessness questionnaires. RESULTS: The visual grading scale found that patients with COPD had significantly greater frontal atrophy than control subjects (p=0.02), independent of smoking history, comorbid depression or anxiety. Cognitive function was significantly worse in the COPD group for executive function (p<0.001), working memory (p=0.02), verbal memory (p=0.03) and processing speed (p=0.001). Group differences in atrophy did not appear to account for differences in cognitive function. We were unable to identify meaningful correlations between regional atrophy and disease severity or cognitive function. CONCLUSION: Further work is needed to identify causative mechanisms behind unexplained structural brain changes in COPD.

White matter lesions characterise brain involvement in moderate to severe chronic obstructive pulmonary disease, but cerebral atrophy does not.

BACKGROUND: Brain pathology is relatively unexplored in chronic obstructive pulmonary disease (COPD). This study is a comprehensive investigation of grey matter (GM) and white matter (WM) changes and how these relate to disease severity and cognitive function. METHODS: T1-weighted and fluid-attenuated inversion recovery images were acquired for 31 stable COPD patients (FEV1 52.1% pred., PaO2 10.1 kPa) and 24 age, gender-matched controls. T1-weighted images were segmented into GM, WM and cerebrospinal fluid (CSF) tissue classes using a semi-automated procedure optimised for use with this cohort. This procedure allows, cohort-specific anatomical features to be captured, white matter lesions (WMLs) to be identified and includes a tissue repair step to correct for misclassification caused by WMLs. Tissue volumes and cortical thickness were calculated from the resulting segmentations. Additionally, a fully-automated pipeline was used to calculate localised cortical surface and gyrification. WM and GM tissue volumes, the tissue volume ratio (indicator of atrophy), average cortical thickness, and the number, size, and volume of white matter lesions (WMLs) were analysed across the whole-brain and regionally - for each anatomical lobe and the deep-GM. The hippocampus was investigated as a region-of-interest. Localised (voxel-wise and vertex-wise) variations in cortical gyrification, GM density and cortical thickness, were also investigated. Statistical models controlling for age and gender were used to test for between-group differences and within-group correlations. Robust statistical approaches ensured the family-wise error rate was controlled in regional and local analyses. RESULTS: There were no significant differences in global, regional, or local measures of GM between patients and controls, however, patients had an increased volume (p = 0.02) and size (p = 0.04) of WMLs. In patients, greater normalised hippocampal volume positively correlated with exacerbation frequency (p = 0.04), and greater WML volume was associated with worse episodic memory (p = 0.05). A negative relationship between WML and FEV1 % pred. approached significance (p = 0.06). CONCLUSIONS: There was no evidence of cerebral atrophy within this cohort of stable COPD patients, with moderate airflow obstruction. However, there were indications of WM damage consistent with an ischaemic pathology. It cannot be concluded whether this represents a specific COPD, or smoking-related, effect.

Toward Respiratory Assessment Using Depth Measurements from a Time-of-Flight Sensor.

Introduction: There is increasing interest in technologies that may enable remote monitoring of respiratory disease. Traditional methods for assessing respiratory function such as spirometry can be expensive and require specialist training to perform and interpret. Remote, non-contact tracking of chest wall movement has been explored in the past using structured light, accelerometers and impedance pneumography, but these have often been costly and clinical utility remains to be defined. We present data from a 3-Dimensional time-of-flight camera (found in gaming consoles) used to estimate chest volume during routine spirometry maneuvres. Methods: Patients were recruited from a general respiratory physiology laboratory. Spirometry was performed according to international standards using an unmodified spirometer. A Microsoft Kinect V2 time-of-flight depth sensor was used to reconstruct 3-dimensional models of the subject's thorax to estimate volume-time and flow-time curves following the introduction of a scaling factor to transform measurements to volume estimates. The Bland-Altman method was used to assess agreement of model estimation with simultaneous recordings from the spirometer. Patient characteristics were used to assess predictors of error using regression analysis and to further explore the scaling factors. Results: The chest volume change estimated by the Kinect camera during spirometry tracked respiratory rate accurately and estimated forced vital capacity (FVC) and vital capacity to within ± <1%. Forced expiratory volume estimation did not demonstrate acceptable limits of agreement, with 61.9% of readings showing >150 ml difference. Linear regression including age, gender, height, weight, and pack years of smoking explained 37.0% of the variance in the scaling factor for volume estimation. This technique had a positive predictive value of 0.833 to detect obstructive spirometry. Conclusion: These data illustrate the potential of 3D time-of-flight cameras to remotely monitor respiratory rate. This is not a replacement for conventional spirometry and needs further refinement. Further algorithms are being developed to allow its independence from spirometry. Benefits include simplicity of set-up, no specialist training, and cost. This technique warrants further refinement and validation in larger cohorts.

Executive Function, Survival, and Hospitalization in Chronic Obstructive Pulmonary Disease. A Longitudinal Analysis of the National Emphysema Treatment Trial (NETT).

RATIONALE: Cognitive dysfunction has been demonstrated in chronic obstructive pulmonary disease (COPD), but studies are limited to cross-sectional analyses or incompletely characterized populations. OBJECTIVES: We examined longitudinal changes in sensitive measures of executive function in a well-characterized population of patients with severe COPD. METHODS: This study was performed on patients enrolled in the National Emphysema Treatment Trial. To assess executive function, we analyzed trail making (TM) A and B times at enrollment in the trial (2,128 patients), and at 12 (731 patients) and 24 months (593 patients) after enrollment, adjusted for surgery, marriage status, age, education, income, depression, PaO2, PaCO2, and smoking. Associations with survival and hospitalizations were examined using Cox regression and linear regression models. MEASUREMENTS AND MAIN RESULTS: The average age of the patients was 66.4 years, and the average FEV1 was 23.9% predicted. At the time of enrolment, 38% had executive dysfunction. Compared with those who did not, these patients were older, less educated, had higher oxygen use, higher PaCO2, worse quality of life as measured by the St. George's Respiratory Quotient, reduced well-being, and lower social function. There was no significant change over 2 years in TM A or B times after adjustment for covariables. Changes in TM B times were modestly associated with survival, but changes in TM B-A times were not. Changes in TM scores were not associated with frequency of hospitalization. Lung function, PaO2, smoking, survival, and hospitalizations were not significantly different in those with executive dysfunction. CONCLUSIONS: In this large population of patients with severe emphysema and heavy cigarette smoking exposure, there was no significant decline over 2 years in cognitive executive function as measured by TM tests. There was no association between executive function impairment and frequency of hospitalization, and there was a possible modest association with survival. It is plausible that cerebrovascular comorbidities explain previously described cognitive pathology in COPD.

Lung disease as a determinant of cognitive decline and dementia.

Almost 40 million people currently live with dementia but this is estimated to double over the next 20 years; despite this, research identifying modifiable risk factors is scarce. There is increasing evidence that cognitive impairment is more frequent in those with chronic lung disease than those without. Chronic obstructive pulmonary disease affects 210 million people, with cognitive impairment present in 60% of certain populations. Co-morbid cognitive dysfunction also appears to impact on important outcomes such as quality of life, hospitalisation and survival. This review summarises the evidence of an association between cognition, impaired lung function and obstructive lung disease. It goes on to examine the contribution of neuro-imaging to our understanding of the underlying pathophysiology. While the mechanisms of brain pathology and cognitive impairment are likely to be complex and multi-factorial, there is evidence to suggest a key role for occult cerebrovascular damage independent of traditional vascular risk factors, including smoking.

Brain structure and function in chronic obstructive pulmonary disease: a multimodal cranial magnetic resonance imaging study.

RATIONALE: Brain pathology is a poorly understood systemic manifestation of chronic obstructive pulmonary disease (COPD). Imaging techniques using magnetic resonance (MR) diffusion tensor imaging (DTI) and resting state functional MR imaging (rfMRI) provide measures of white matter microstructure and gray functional activation, respectively. OBJECTIVES: We hypothesized that patients with COPD would have reduced white matter integrity and that functional communication between gray matter resting-state networks would be significantly different to control subjects. In addition, we tested whether observed differences related to disease severity, cerebrovascular comorbidity, and cognitive dysfunction. METHODS: DTI and rfMRI were acquired in stable nonhypoxemic patients with COPD (n = 25) and compared with age-matched control subjects (n = 25). Demographic, disease severity, stroke risk, and neuropsychologic assessments were made. MEASUREMENTS AND MAIN RESULTS: Patients with COPD (mean age, 68; FEV(1) 53 ± 21% predicted) had widespread reduction in white matter integrity (46% of white matter tracts; P < 0.01). Six of the seven resting-state networks showed increased functional gray matter activation in COPD (P < 0.01). Differences in DTI, but not rfMRI, remained significant after controlling for stroke risk and smoking (P < 0.05). White matter integrity and gray matter activation seemed to account for difference in cognitive performance between patients with COPD and control subjects. CONCLUSIONS: In stable nonhypoxemic COPD there is reduced white matter integrity throughout the brain and widespread disturbance in functional activation of gray matter, which may contribute to cognitive dysfunction. White matter microstructural integrity but not gray matter functional activation is independent of smoking and cerebrovascular comorbidity. The mechanisms remain unclear, but may include cerebral small vessel disease caused by COPD.