Linking e-health records, patient-reported symptoms and environmental exposure data to characterise and model COPD exacerbations: protocol for the COPE study

Estimating exposure to pollutants generated from indoor and outdoor sources within vulnerable populations using personal air quality monitors: A London case study

Personal exposure to air pollution can originate from indoor or outdoor sources, depending on location and activity. This study aimed to quantify personal exposure from each source separately, allowing comparison of the associated epidemiological estimates from each source type. We utilised 12,901 participant-day personal measurements of exposure to multiple pollutants collected from 344 London dwelling participants of four panel studies conducted between 2015 and 2019. A four-step process was applied to personal measurements incorporating 1) GPS spatial analysis including address identification and location tagging; 2) estimating outdoor home pollutant levels from matched fixed ambient monitors; 3) calculation of infiltration efficiency when participants were at home; and 4) indoor and outdoor source separation for personal exposure measurements. From the results, our participants with Chronic Obstructive Pulmonary Disease (COPD) dataset had an average (SD) personal exposure from outdoor sources of 4.0 (1.3) μg/m3 for NO2 and 5.1 (3.0) μg/m3 for PM2.5, the school children's average (SD) personal exposure to PM2.5 from outdoor sources was 5.5 (4.3) μg/m3, the professional drivers' average (SD) personal exposure to black carbon from outdoor sources was 1.7 (1.0) μg/m3, and the healthy young adults' average (SD) personal exposure to black carbon from outdoor sources was 1.2 (0.5) μg/m3. Compared to the average total personal exposures, outdoor sources accounted for 49 % of NO2 exposure, 41 % to 55 % of PM2.5, and 60 % to 85 % of black carbon, dependent on the panel study - demonstrating a strong influence from outdoor sources for personal exposures to air pollution in London. Our findings highlighted that endeavours should continue to be made towards reducing pollution from both outdoor and indoor sources. The between-panel and within-panel exposure differences, derived from our novel partitioning methodology, can contribute to the estimation of health effects from indoor and outdoor sources and inform targeted interventions for vulnerable groups.

A machine learning framework for short-term prediction of chronic obstructive pulmonary disease exacerbations using personal air quality monitors and lifestyle data

Chronic Obstructive Pulmonary Disease (COPD) is a heterogeneous disease with a variety of symptoms including, persistent coughing and mucus production, shortness of breath, wheezing, and chest tightness. As the disease advances, exacerbations, i.e. acute worsening of respiratory symptoms, may increase in frequency, leading to potentially life-threatening complications. Exposure to air pollutants may trigger COPD exacerbations. Literature predictive models for COPD exacerbations, while promising, may be constrained by their reliance on fixed air quality sensor data that may not fully capture individuals' dynamic exposure to air pollution. To address this, we designed a machine learning (ML) framework that leverages data from personal air quality monitors, health records, lifestyle, and living condition information to build models that perform short-term prediction of COPD exacerbations. The framework employs (i) k-means clustering to uncover potentially distinct patient sub-types, (ii) supervised ML techniques (Logistic Regression, Random Forest, and eXtreme Gradient Boosting) to train and test predictive models for each patient sub-type and (iii) an explainable artificial intelligence technique (SHAP) to interpret the final models. The framework was tested on data collected in 101 COPD patients monitored for up to 6 months with occurrence of exacerbation in 10.7% of total samples. Two different patient sub-types have been identified, characterised by different disease severity. The best performing models were Random Forest in cluster 1, with area under the receiver operating characteristic curve (AUC) of 0.90, and area under the precision/recall curve (AUPRC) of 0.7; and Random Forest model in cluster 2, with AUC of 0.82 and AUPRC of 0.56. The model interpretability analysis identified previous symptoms and cumulative pollutant exposure as key predictors of exacerbations. The results of our study set a premise for a predictive framework in COPD exacerbations, particularly investigating the potential influence of environmental features. The SHAP analysis revealed that the contribution of environmental features is not uniform across all subjects. For instance, cumulative exposure to pollutants demonstrated greater predictive power in cluster 1. The SHAP analysis also shown that overall clinical factors and individual symptomatology play the most significant role in this setup to determine exacerbation risk.

Air pollution and respiratory health in patients with COPD: should we focus on indoor or outdoor sources?

INTRODUCTION

While associations between ambient air pollution and respiratory health in chronic obstructive pulmonary disease (COPD) patients are well studied, little is known about individuals' personal exposure to pollution and associated health effects by source.

AIM

To separate measured total personal exposure into indoor-generated and outdoor-generated pollution and use these improved metrics in health models for establishing more reliable associations with exacerbations and respiratory symptoms.

METHODS

We enrolled a panel of 76 patients with COPD and continuously measured their personal exposure to particles and gaseous pollutants and location with portable monitors for 134 days on average. We collected daily health information related to respiratory symptoms through diary cards and peak expiratory flow (PEF). Mixed-effects models were applied to quantify the relationship between total, indoor-generated and outdoor-generated personal exposures to pollutants with exacerbation and symptoms occurrence and PEF.

RESULTS

Exposure to nitrogen dioxide from both indoor and outdoor sources was associated with exacerbations and respiratory symptoms. We observed an increase of 33% (22%-45%), 19% (12%-18%) and 12% (5%-20%) in the odds of exacerbation for an IQR increase in total, indoor-generated and outdoor-generated exposures. For carbon monoxide, health effects were mainly attributed to indoor-generated pollution. While no associations were observed for particulate matter2.5 with COPD exacerbations, indoor-generated particles were associated with a significant decrease in PEF.

CONCLUSIONS

Indoor-generated and outdoor-generated pollution can deteriorate COPD patients' health. Policy-makers, physicians and patients with COPD should note the importance of decreasing exposure equally to both source types to decrease risk of exacerbation.

Early detection of COPD patients' symptoms with personal environmental sensors: a remote sensing framework using probabilistic latent component analysis with linear dynamic systems

In this study, we present a cohort study involving 106 COPD patients using portable environmental sensor nodes with attached air pollution sensors and activity-related sensors, as well as daily symptom records and peak flow measurements to monitor patients' activity and personal exposure to air pollution. This is the first study which attempts to predict COPD symptoms based on personal air pollution exposure. We developed a system that can detect COPD patients' symptoms one day in advance of symptoms appearing. We proposed using the Probabilistic Latent Component Analysis (PLCA) model based on 3-dimensional and 4-dimensional spectral dictionary tensors for personalised and population monitoring, respectively. The model is combined with Linear Dynamic Systems (LDS) to track the patients' symptoms. We compared the performance of PLCA and PLCA-LDS models against Random Forest models in the identification of COPD patients' symptoms, since tree-based classifiers were used for remote monitoring of COPD patients in the literature. We found that there was a significant difference between the classifiers, symptoms and the personalised versus population factors. Our results show that the proposed PLCA-LDS-3D model outperformed the PLCA and the RF models between 4 and 20% on average. When we used only air pollutants as input, the PLCA-LDS-3D forecasting results in personalised and population models were 48.67 and 36.33% accuracy for worsening of lung capacity and 38.67 and 19% accuracy for exacerbation of COPD patients' symptoms, respectively. We have shown that indicators of the quality of an individual's environment, specifically air pollutants, are as good predictors of the worsening of respiratory symptoms in COPD patients as a direct measurement.

Automated classification of time-activity-location patterns for improved estimation of personal exposure to air pollution

BACKGROUND

Air pollution epidemiology has primarily relied on measurements from fixed outdoor air quality monitoring stations to derive population-scale exposure. Characterisation of individual time-activity-location patterns is critical for accurate estimations of personal exposure and dose because pollutant concentrations and inhalation rates vary significantly by location and activity.

METHODS

We developed and evaluated an automated model to classify major exposure-related microenvironments (home, work, other static, in-transit) and separated them into indoor and outdoor locations, sleeping activity and five modes of transport (walking, cycling, car, bus, metro/train) with multidisciplinary methods from the fields of movement ecology and artificial intelligence. As input parameters, we used GPS coordinates, accelerometry, and noise, collected at 1 min intervals with a validated Personal Air quality Monitor (PAM) carried by 35 volunteers for one week each. The model classifications were then evaluated against manual time-activity logs kept by participants.

RESULTS

Overall, the model performed reliably in classifying home, work, and other indoor microenvironments (F1-score>0.70) but only moderately well for sleeping and visits to outdoor microenvironments (F1-score=0.57 and 0.3 respectively). Random forest approaches performed very well in classifying modes of transport (F1-score>0.91). We found that the performance of the automated methods significantly surpassed those of manual logs.

CONCLUSIONS

Automated models for time-activity classification can markedly improve exposure metrics. Such models can be developed in many programming languages, and if well formulated can have general applicability in large-scale health studies, providing a comprehensive picture of environmental health risks during daily life with readily gathered parameters from smartphone technologies.

Environmental effects on acute exacerbations of respiratory diseases: A real-world big data study

BACKGROUND

The effects of weather periods, race/ethnicity, and sex on environmental triggers for respiratory exacerbations are not well understood. This study linked the OneFlorida network (~15 million patients) with an external exposome database to analyze environmental triggers for asthma, bronchitis, and COPD exacerbations while accounting for seasonality, sex, and race/ethnicity.

METHODS

This is a case-crossover study of OneFlorida database from 2012 to 2017 examining associations of asthma, bronchitis, and COPD exacerbations with exposures to heat index, PM 2.5 and O 3. We spatiotemporally linked exposures using patients' residential addresses to generate average exposures during hazard and control periods, with each case serving as its own control. We considered age, sex, race/ethnicity, and neighborhood deprivation index as potential effect modifiers in conditional logistic regression models.

RESULTS

A total of 1,148,506 exacerbations among 533,446 patients were included. Across all three conditions, hotter heat indices conferred increasing exacerbation odds, except during November to March, where the opposite was seen. There were significant differences when stratified by race/ethnicity (e.g., for asthma in April, May, and October, heat index quartile 4, odds were 1.49 (95% confidence interval (CI) 1.42-1.57) for Non-Hispanic Blacks and 2.04 (95% CI 1.92-2.17) for Hispanics compared to 1.27 (95% CI 1.19-1.36) for Non-Hispanic Whites). Pediatric patients' odds of asthma and bronchitis exacerbations were significantly lower than adults in certain circumstances (e.g., for asthma during June - September, pediatric odds 0.71 (95% CI 0.68-0.74) and adult odds 0.82 (95% CI 0.79-0.85) for the highest quartile of PM 2.5).

CONCLUSION

This study of acute exacerbations of asthma, bronchitis, and COPD found exacerbation risk after exposure to heat index, PM 2.5 and O 3 varies by weather period, age, and race/ethnicity. Future work can build upon these results to alert vulnerable populations to exacerbation triggers.

Digital Healthcare for Airway Diseases from Personal Environmental Exposure

Digital technologies have emerged in various dimensions of human life, ranging from education to professional services to well-being. In particular, health products and services have expanded by the use and development of artificial intelligence, mobile health applications, and wearable electronic devices. Such advancements have enabled accurate and updated tracking and modeling of health conditions. For instance, digital health technologies are capable of measuring environmental pollution and predicting its adverse health effects. Several health conditions, including chronic airway diseases such as asthma and chronic obstructive pulmonary disease, can be exacerbated by pollution. These diseases impose substantial health burdens with high morbidity and mortality. Recently, efforts have been made to develop digital technologies to alleviate such conditions. Moreover, the COVID-19 pandemic has facilitated the application of telemedicine and telemonitoring for patients with chronic airway diseases. This article reviews current trends and studies in digital technology utilization for investigating and managing environmental exposure and chronic airway diseases. First, we discussed the recent progression of digital technologies in general environmental healthcare. Then, we summarized the capacity of digital technologies in predicting exacerbation and self-management of airway diseases. Concluding these reviews, we provided suggestions to improve digital health technologies' abilities to reduce the adverse effects of environmental exposure in chronic airway diseases, based on personal exposure-response modeling.

Personal exposure to air pollution and respiratory health of COPD patients in London

Previous studies have investigated the effects of air pollution on chronic obstructive pulmonary disease (COPD) patients using either fixed-site measurements or a limited number of personal measurements, usually for one pollutant and a short time period. These limitations may introduce bias and distort the epidemiological associations as they do not account for all the potential sources or the temporal variability of pollution.

We used detailed information on individuals’ exposure to various pollutants measured at fine spatiotemporal scale to obtain more reliable effect estimates. A panel of 115 patients was followed up for an average continuous period of 128 days carrying a personal monitor specifically designed for this project that measured temperature, nitrogen dioxide (NO₂), ozone (O₃), nitric oxide (NO), carbon monoxide (CO), and particulate matter with aerodynamic diameter <2.5 and <10 μm at 1-min time resolution. Each patient recorded daily information on respiratory symptoms and measured peak expiratory flow (PEF). A pulmonologist combined related data to define a binary variable denoting an “exacerbation”. The exposure–response associations were assessed with mixed effects models.

We found that gaseous pollutants were associated with a deterioration in patients’ health. We observed an increase of 16.4% (95% CI 8.6–24.6%), 9.4% (95% CI 5.4–13.6%) and 7.6% (95% CI 3.0–12.4%) in the odds of exacerbation for an interquartile range increase in NO₂, NO and CO, respectively. Similar results were obtained for cough and sputum. O₃ was found to have adverse associations with PEF and breathlessness. No association was observed between particulate matter and any outcome.

Our findings suggest that, when considering total personal exposure to air pollutants, mainly the gaseous pollutants affect COPD patients’ health.

Significant adverse associations were found between the respiratory health of COPD patients and their personal exposure to gaseous pollutants measured using portable sensors over 6 months. No significant associations were found for particulate pollutants.https://bit.ly/3aqMT6O

Advances in Comprehensive Exposure Assessment: Opportunities for the US Military

OBJECTIVE

Review advances in exposure assessment offered by the exposome concept and new -omics and sensor technologies.

METHODS

Narrative review of advances, including current efforts and potential future applications by the US military.

RESULTS

Exposure assessment methods from both bottom-up and top-down exposomics approaches are advancing at a rapid pace, and the US military is engaged in developing both approaches. Top-down approaches employ various -omics technologies to identify biomarkers of internal exposure and biological effect. Bottom-up approaches use new sensor technology to better measure external dose. Key challenges of both approaches are largely centered around how to integrate, analyze, and interpret large datasets that are multidimensional and disparate.

CONCLUSIONS

Advances in -omics and sensor technologies may dramatically enhance exposure assessment and improve our ability to characterize health risks related to occupational and environmental exposures, including for the US military.

Characterising low-cost sensors in highly portable platforms to quantify personal exposure in diverse environments

The inaccurate quantification of personal exposure to air pollution introduces error and bias in health estimations, severely limiting causal inference in epidemiological research worldwide. Rapid advancements in affordable, miniaturised air pollution sensor technologies offer the potential to address this limitation by capturing the high variability of personal exposure during daily life in large-scale studies with unprecedented spatial and temporal resolution. However, concerns remain regarding the suitability of novel sensing technologies for scientific and policy purposes. In this paper we characterise the performance of a portable personal air quality monitor (PAM) that integrates multiple miniaturised sensors for nitrogen oxides (NO x ), carbon monoxide (CO), ozone (O3) and particulate matter (PM) measurements along with temperature, relative humidity, acceleration, noise and GPS sensors. Overall, the air pollution sensors showed high reproducibility (meanR ¯ 2 = 0.93, min-max: 0.80-1.00) and excellent agreement with standard instrumentation (meanR ¯ 2 = 0.82, min-max: 0.54-0.99) in outdoor, indoor and commuting microenvironments across seasons and different geographical settings. An important outcome of this study is that the error of the PAM is significantly smaller than the error introduced when estimating personal exposure based on sparsely distributed outdoor fixed monitoring stations. Hence, novel sensing technologies such as the ones demonstrated here can revolutionise health studies by providing highly resolved reliable exposure metrics at a large scale to investigate the underlying mechanisms of the effects of air pollution on health.

Personalized medicine for patients with COPD: where are we?

Chronic airflow limitation is the common denominator of patients with chronic obstructive pulmonary disease (COPD). However, it is not possible to predict morbidity and mortality of individual patients based on the degree of lung function impairment, nor does the degree of airflow limitation allow guidance regarding therapies. Over the last decades, understanding of the factors contributing to the heterogeneity of disease trajectories, clinical presentation, and response to existing therapies has greatly advanced. Indeed, diagnostic assessment and treatment algorithms for COPD have become more personalized. In addition to the pulmonary abnormalities and inhaler therapies, extra-pulmonary features and comorbidities have been studied and are considered essential components of comprehensive disease management, including lifestyle interventions. Despite these advances, predicting and/or modifying the course of the disease remains currently impossible, and selection of patients with a beneficial response to specific interventions is unsatisfactory. Consequently, non-response to pharmacologic and non-pharmacologic treatments is common, and many patients have refractory symptoms. Thus, there is an ongoing urgency for a more targeted and holistic management of the disease, incorporating the basic principles of P4 medicine (predictive, preventive, personalized, and participatory). This review describes the current status and unmet needs regarding personalized medicine for patients with COPD. Also, it proposes a systems medicine approach, integrating genetic, environmental, (micro)biological, and clinical factors in experimental and computational models in order to decipher the multilevel complexity of COPD. Ultimately, the acquired insights will enable the development of clinical decision support systems and advance personalized medicine for patients with COPD.

Associations between daily air quality and hospitalisations for acute exacerbation of chronic obstructive pulmonary disease in Beijing, 2013-17: an ecological analysis

BACKGROUND

Air pollution in Beijing has been improving through implementation of the Air Pollution Prevention and Control Action Plan (2013-17), but its implications for respiratory morbidity have not been directly investigated. We aimed to assess the potential effects of air-quality improvements on respiratory health by investigating the number of cases of acute exacerbations of chronic obstructive pulmonary disease (COPD) advanced by air pollution each year.

METHODS

Daily city-wide concentrations of PM10, PM2·5, PMcoarse (particulate matter >2·5-10 μm diameter), nitrogen dioxide (NO2), sulphur dioxide (SO2), carbon monoxide (CO), and ozone (O3) in 2013-17 were averaged from 35 monitoring stations across Beijing. A generalised additive Poisson time-series model was applied to estimate the relative risks (RRs) and 95% CIs for hospitalisation for acute exacerbation of COPD associated with pollutant concentrations.

FINDINGS

From Jan 18, 2013, to Dec 31, 2017, 161 613 hospitalisations for acute exacerbation of COPD were recorded. Mean ambient concentrations of SO2 decreased by 68% and PM2·5 decreased by 33% over this 5-year period. For each IQR increase in pollutant concentration, RRs for same-day hospitalisation for acute exacerbation of COPD were 1·029 (95% CI 1·023-1·035) for PM10, 1·028 (1·021-1·034) for PM2·5, 1·018 (1·013-1·022) for PMcoarse, 1·036 (1·028-1·044) for NO2, 1·019 (1·013-1·024) for SO2, 1·024 (1·018-1·029) for CO, and 1·027 (1·010-1·044) for O3 in the warm season (May to October). Women and patients aged 65 years or older were more susceptible to the effects of these pollutants on hospitalisation risk than were men and patients younger than 65 years. In 2013, there were 12 679 acute exacerbations of COPD cases that were advanced by PM2·5 pollution above the expected number of cases if daily PM2·5 concentrations had not exceeded the WHO target (25 μg/m3), whereas the respective figure in 2017 was 7377 cases.

INTERPRETATION

Despite improvement in overall air quality, increased acute air pollution episodes were significantly associated with increased hospitalisations for acute exacerbations of COPD in Beijing. Stringent air pollution control policies are important and effective for reducing COPD morbidity, and long-term multidimensional policies to safeguard public health are indicated.

FUNDING

UK Medical Research Council.

Limitations for health research with restricted data collection from UK primary care

Purpose

UK primary care provides a rich data source for research. The impact of proposed data collection restrictions is unknown. This study aimed to assess the impact of restricting the scope of electronic health record (EHR) data collection on the ability to conduct research. The study estimated the consequences of restricted data collection on published Clinical Practice Research Datalink studies from high impact journals or referenced in clinical guidelines.

Methods

A structured form was used to systematically analyse the extent to which individual studies would have been possible using a database with data collection restrictions in place: (1) retrospective collection of specified diseases only; (2) retrospective collection restricted to a 6‐ or 12‐year period; (3) prospective and retrospective collection restricted to non‐sensitive data. Outcomes were categorised as unfeasible (not reproducible without major bias); compromised (feasible with design modification); or unaffected.

Results

Overall, 91% studies were compromised with all restrictions in place; 56% studies were unfeasible even with design modification. With restrictions on diseases alone, 74% studies were compromised; 51% were unfeasible. Restricting collection to 6/12 years had a major impact, with 67 and 22% of studies compromised, respectively. Restricting collection of sensitive data had a lesser but marked impact with 10% studies compromised.

Conclusion

EHR data collection restrictions can profoundly reduce the capacity for public health research that underpins evidence‐based medicine and clinical guidance. National initiatives seeking to collect EHRs should consider the implications of restricting data collection on the ability to address vital public health questions.

Recruitment of patients with Chronic Obstructive Pulmonary Disease (COPD) from the Clinical Practice Research Datalink (CPRD) for research

Databases of electronic health records (EHR) are not only a valuable source of data for health research but have also recently been used as a medium through which potential study participants can be screened, located and approached to take part in research. The aim was to assess whether it is feasible and practical to screen, locate and approach patients to take part in research through the Clinical Practice Research Datalink (CPRD). This is a cohort study in primary care. The CPRD anonymised EHR database was searched to screen patients with Chronic Obstructive Pulmonary Disease (COPD) to take part in a research study. The potential participants were contacted via their General Practitioner (GP) who confirmed their eligibility. Eighty two practices across Greater London were invited to the study. Twenty-six (31.7%) practices consented to participate resulting in a pre-screened list of 988 patients. Of these, 632 (63.7%) were confirmed as eligible following the GP review. Two hundred twenty seven (36%) response forms were received by the study team; 79 (34.8%) responded ‘yes’ (i.e., they wanted to be contacted by the research assistant for more information and to talk about enrolling in the study), and 148 (65.2%) declined participation. This study has shown that it is possible to use EHR databases such as CPRD to screen, locate and recruit participants for research. This method provides access to a cohort of patients while minimising input needed by GPs and allows researchers to examine healthcare usage and disease burden in more detail and in real-life settings.

Screening anonymized electronic health records could prove a valuable, time-saving method for identifying patient cohorts for research projects. Jennifer Quint at Imperial College, London, and co-workers used primary care databases provided by doctors’ surgeries in London to find suitable patients for a study monitoring daily chronic obstructive pulmonary disease (COPD) symptoms. Using carefully-designed algorithms, the researchers identified 988 COPD patients who met eligibility criteria and lived within defined localities. Quint’s team then asked the patients’ doctors to review and approve the list for their own practice, thus limiting the doctors’ workload for selecting patients. The researchers approached 632 patients to invite them to participate in the research; 66 were enrolled. This provided an adequate number for the study, though the team highlight a need to improve strategies that encourage patients to take part in research.

How Sensors Might Help Define the External Exposome

The advent of the exposome concept, the advancement of mobile technology, sensors, and the “internet of things” bring exciting opportunities to exposure science. Smartphone apps, wireless devices, the downsizing of monitoring technologies, along with lower costs for such equipment makes it possible for various aspects of exposure to be measured more easily and frequently. We discuss possibilities and lay out several criteria for using smart technologies for external exposome studies. Smart technologies are evolving quickly, and while they provide great promise for advancing exposure science, many are still in developmental stages and their use in epidemiology and risk studies must be carefully considered. The most useable technologies for exposure studies at this time relate to gathering exposure-factor data, such as location and activities. Development of some environmental sensors (e.g., for some air pollutants, noise, UV) is moving towards making the use of these more reliable and accessible to research studies. The possibility of accessing such an unprecedented amount of personal data also comes with various limitations and challenges, which are discussed. The advantage of improving the collection of long term exposure factor data is that this can be combined with more “traditional” measurement data to model exposures to numerous environmental factors.