Identifying patients at risk for severe exacerbations of asthma: development and external validation of a multivariable prediction model

Comorbid allergy and rhinitis and patient-related outcomes in asthma and COPD: a cross-sectional study

Introduction

The study aimed to compare prevalence of comorbid allergic manifestations and rhinitis, allergy testing and associations with patient-related outcomes in patients with asthma and COPD.

Methods

Cross-sectional study of randomly selected Swedish patients with a doctor's diagnosis of asthma (n = 1291) or COPD (n = 1329). Self-completion questionnaires from 2014 provided data on demographics, rhinitis, allergic symptoms at exposure to pollen or furry pets, exacerbations, self-assessed severity of disease and scores from the Asthma Control Test (ACT) and the COPD Assessment Test (CAT), and records were reviewed for allergy tests.

Results

Allergic manifestations were more common in asthma (75%) compared with COPD (38%). Rhinitis was reported in 70% of asthma and 58% of COPD patients. Allergy tests had been performed during the previous decade in 28% of patients with asthma and in 8% of patients with COPD.In patients with asthma; comorbid allergy and rhinitis were both independently associated with increased risk for poor asthma symptom control (ACT < 20) (OR [95% CI] 1.41 [1.05 to 1.87] and 2.13 [1.60 to 2.83]), exacerbations (1.58 [1.15 to 2.17] and 1.38 [1.02 to 1.86]), and self-assessed moderate/severe disease (1.64 [1.22 to 2.18] and 1.75 [1.33 to 2.30]). In patients with COPD, comorbid allergy and rhinitis were both independently associated with increased risk for low health status (CAT ≥ 10) (OR [95% CI] 1.46 [1.20 to 1.95] and 2.59 [1.97 to 3.41]) respectively, with exacerbations during the previous six months (1.91 [1.49 to 2.45] and 1.57 [1.23 to 2.01]), and with self-assessed moderate/severe disease (1.70 [1.31 to 2.22] and 2.13 [1.66 to 2.74]).

Conclusion

Allergic manifestations and rhinitis are more common in asthma than COPD but associated with worse outcomes in both diseases. This highlights the importance of examining and treating comorbid allergy and rhinitis, not only in asthma but also in COPD.

Therapeutic effect of long-acting muscarinic antagonist for treating uncontrolled asthma assessed using impulse oscillometry

BACKGROUND

In recent years, the incorporation of LAMAs into asthma therapy has been expected to enhance symptom control. However, a significant number of patients with asthma continue to experience poorly managed symptoms. There have been limited investigations on LAMA-induced airway alterations in asthma treatment employing IOS. In this study, we administered a LAMA to patients with poorly controlled asthma, evaluated clinical responses and respiratory function, and investigated airway changes facilitated by LAMA treatments using the IOS.

METHODS

Of a total of 1282 consecutive patients with asthma, 118 exhibited uncontrolled symptoms. Among them, 42 switched their treatment to high-dose fluticasone furoate/umeclidinium/vilanterol (FF/UMEC/VI) (ICS/LABA/LAMA). The patients were then assessed using AHQ-33 or LCQ and ACT. Spirometry parameters (such as FEV1 or MMEF) and IOS parameters (such as R20 or AX) were measured and compared before and after exacerbations and the addition of LAMA.

RESULTS

Of the 42 patients, 17 who switched to FF/UMEC/VI caused by dyspnea exhibited decreased pulmonary function between period 1 and baseline, followed by an increase in pulmonary function between baseline and period 2. Significant differences were observed in IOS parameters such as R20, R5-R20, Fres, or AX between period 1 and baseline as well as between baseline and period 2. Among the patients who switched to inhaler due to cough, 25 were classified as responders (n = 17) and nonresponders (n = 8) based on treatment outcomes. Among nonresponders, there were no significant differences in spirometry parameters such as FEV1 or PEF and IOS parameters such as R20 or AX between period 1 and baseline. However, among responders, significant differences were observed in all IOS parameters, though not in most spirometry parameters, between period 1 and baseline. Furthermore, significant differences were noted between baseline and period 2 in terms of FEV1, %MMEF, %PEF, and all IOS parameters.

CONCLUSION

ICS/LABA/LAMA demonstrates superiority over ICS/LABA in improving symptoms and lung function, which is primarily attributed to the addition of LAMA. Additionally, IOS revealed the effectiveness of LAMA across all airway segments, particularly in the periphery. Hence, LAMA can be effective against various asthma phenotypes characterized by airway inflammation, even in real-world cases.

Management of Chronic Asthma in Adults

Asthma is characterized by chronic inflammation and respiratory symptoms such as wheezing and coughing. In the United States, it affects 25 million people annually. Chronic smokers, poor adherence to medications, incorrect use of inhalers, and overall poor asthma control are known risk factors that lead to poorly controlled chronic asthmatics. Although asthma is traditionally categorized by severity, treatment by primary care providers is guided by the Global Initiative for Asthma or the National Asthma Education and Prevention Program. As more research is available, shared decision-making between health care providers and patients will lead to improved outcomes in managing chronic asthma.

A Roadmap for Using Causal Inference and Machine Learning to Personalize Asthma Medication Selection

Inhaled corticosteroid (ICS) is a mainstay treatment for controlling asthma and preventing exacerbations in patients with persistent asthma. Many types of ICS drugs are used, either alone or in combination with other controller medications. Despite the widespread use of ICSs, asthma control remains suboptimal in many people with asthma. Suboptimal control leads to recurrent exacerbations, causes frequent ER visits and inpatient stays, and is due to multiple factors. One such factor is the inappropriate ICS choice for the patient. While many interventions targeting other factors exist, less attention is given to inappropriate ICS choice. Asthma is a heterogeneous disease with variable underlying inflammations and biomarkers. Up to 50% of people with asthma exhibit some degree of resistance or insensitivity to certain ICSs due to genetic variations in ICS metabolizing enzymes, leading to variable responses to ICSs. Yet, ICS choice, especially in the primary care setting, is often not tailored to the patient's characteristics. Instead, ICS choice is largely by trial and error and often dictated by insurance reimbursement, organizational prescribing policies, or cost, leading to a one-size-fits-all approach with many patients not achieving optimal control. There is a pressing need for a decision support tool that can predict an effective ICS at the point of care and guide providers to select the ICS that will most likely and quickly ease patient symptoms and improve asthma control. To date, no such tool exists. Predicting which patient will respond well to which ICS is the first step toward developing such a tool. However, no study has predicted ICS response, forming a gap. While the biologic heterogeneity of asthma is vast, few, if any, biomarkers and genotypes can be used to systematically profile all patients with asthma and predict ICS response. As endotyping or genotyping all patients is infeasible, readily available electronic health record data collected during clinical care offer a low-cost, reliable, and more holistic way to profile all patients. In this paper, we point out the need for developing a decision support tool to guide ICS selection and the gap in fulfilling the need. Then we outline an approach to close this gap via creating a machine learning model and applying causal inference to predict a patient's ICS response in the next year based on the patient's characteristics. The model uses electronic health record data to characterize all patients and extract patterns that could mirror endotype or genotype. This paper supplies a roadmap for future research, with the eventual goal of shifting asthma care from one-size-fits-all to personalized care, improve outcomes, and save health care resources.

Primary Care Asthma Attack Prediction Models for Adults: A Systematic Review of Reported Methodologies and Outcomes

Prognostic models hold great potential for predicting asthma exacerbations, providing opportunities for early intervention, and are a popular area of current research. However, it is unclear how models should be compared and contrasted, given their differences in both design and performance, particularly with a view to potential implementation in routine practice. This systematic review aimed to identify novel predictive models of asthma attacks in adults and compare differences in construction related to populations, outcome definitions, prediction time horizons, algorithms, validation, and performance estimation. Twenty-five studies were identified for comparison, with varying definitions of asthma attacks and prediction event time horizons ranging from 15 days to 30 months. The most commonly used algorithm was logistic regression (20/25 studies); however, none of the six which tested multiple algorithms identified it as highest performing algorithm. The effect of various study design characteristics on performance was evaluated in order to provide context to the limitations of highly performing models. Models used a variety of constructs, which affected both their performance and their viability for implementation in routine practice. Consultation with stakeholders is necessary to identify priorities for model refinement and to create a benchmark of acceptable performance for implementation in clinical practice.

Predicting pediatric severe asthma exacerbations: an administrative claims-based predictive model

OBJECTIVE

Previous machine learning approaches fail to consider race and ethnicity and social determinants of health (SDOH) to predict childhood asthma exacerbations. A predictive model for asthma exacerbations in children is developed to explore the importance of race and ethnicity, rural-urban commuting area (RUCA) codes, the Child Opportunity Index (COI), and other ICD-10 SDOH in predicting asthma outcomes.

METHODS

Insurance and coverage claims data from the Arkansas All-Payer Claims Database were used to capture risk factors. We identified a cohort of 22,631 children with asthma aged 5-18 years with 2 years of continuous Medicaid enrollment and at least one asthma diagnosis in 2018. The goal was to predict asthma-related hospitalizations and asthma-related emergency department (ED) visits in 2019. The analytic sample was 59% age 5-11 years, 39% White, 33% Black, and 6% Hispanic. Conditional random forest models were used to train the model.

RESULTS

The model yielded an area under the curve (AUC) of 72%, sensitivity of 55% and specificity of 78% in the OOB samples and AUC of 73%, sensitivity of 58% and specificity of 77% in the training samples. Consistent with previous literature, asthma-related hospitalization or ED visits in the previous year (2018) were the two most important variables in predicting hospital or ED use in the following year (2019), followed by the total number of reliever and controller medications.

CONCLUSIONS

Predictive models for asthma-related exacerbation achieved moderate accuracy, but race and ethnicity, ICD-10 SDOH, RUCA codes, and COI measures were not important in improving model accuracy.

Novel Artificial Intelligence-Based Technology to Diagnose Asthma Using Methacholine Challenge Tests

PURPOSE

The methacholine challenge test (MCT) has high sensitivity but relatively low specificity for asthma diagnosis. This study aimed to develop and validate machine learning (ML) models to improve the diagnostic performance of MCT for asthma.

METHODS

Data from 1,501 patients with asthma symptoms who underwent MCT between 2015 and 2020 were analyzed. The patients were grouped as either the training (80%, n = 1,265) and test sets (20%, n = 236) depending on the time of referral. The conventional model (provocative concentration that causes a 20% decrease in forced expiratory volume in one second [FEV1]; PC20 ≤ 16 mg/mL) was compared with the prediction models derived from five ML methods: logistic regression, support vector machine, random forest, extreme gradient boosting, and artificial neural network. The area under the receiver operator characteristic curves (AUROC) and area under the precision-recall curves (AUPRC) of each model were compared. The prediction models were further analyzed using different input combinations of FEV1, forced vital capacity (FVC), and forced expiratory flow at 25%-75% of forced vital capacity (FEF25%-75%) values obtained during MCT.

RESULTS

In total, 545 patients (36.3%) were diagnosed with asthma. The AUROC of the conventional model was 0.856 (95% confidence interval [CI], 0.852-0.861), and the AUPRC was 0.759 (95% CI, 0.751-0.766). All the five ML prediction models had higher AUROC and AUPRC values than those of the conventional model, and random forest showed both highest AUROC (0.950; 95% CI, 0.948-0.952) and AUROC (0.909; 95% CI, 0.905-0.914) when FEV1, FVC, and FEF25%-75% were included as inputs.

CONCLUSIONS

Artificial intelligence-based models showed excellent performance in asthma prediction compared to using PC20 ≤ 16 mg/mL. The novel technology could be used to enhance the clinical diagnosis of asthma.

Asthma and COPD: A Focus on β-Agonists - Past, Present and Future

Asthma has been recognised as a respiratory disorder for millennia and the focus of targeted drug development for the last 120 years. Asthma is one of the most common chronic non-communicable diseases worldwide. Chronic obstructive pulmonary disease (COPD), a leading cause of morbidity and mortality worldwide, is caused by exposure to tobacco smoke and other noxious particles and exerts a substantial economic and social burden. This chapter reviews the development of the treatments of asthma and COPD particularly focussing on the β-agonists, from the isolation of adrenaline, through the development of generations of short- and long-acting β-agonists. It reviews asthma death epidemics, considers the intrinsic efficacy of clinical compounds, and charts the improvement in selectivity and duration of action that has led to our current medications. Important β2-agonist compounds no longer used are considered, including some with additional properties, and how the different pharmacological properties of current β2-agonists underpin their different places in treatment guidelines. Finally, it concludes with a look forward to future developments that could improve the β-agonists still further, including extending their availability to areas of the world with less readily accessible healthcare.

Development of a risk prediction model to predict the risk of hospitalization due to exacerbated asthma among adult asthma patients in a lower middle-income country

BACKGROUND

Asthma patients experience higher rates of hospitalizations due to exacerbations leaving a considerable clinical and economic burden on the healthcare system. The use of a simple, risk prediction tool offers a low-cost mechanism to identify these high-risk asthma patients for specialized care. The study aimed to develop and validate a risk prediction model to identify high-risk asthma patients for hospitalization due to exacerbations.

METHODS

Hospital-based, case-control study was carried out among 466 asthma patients aged ≥ 20 years recruited from four tertiary care hospitals in a district of Sri Lanka to identify risk factors for asthma-related hospitalizations. Patients (n = 116) hospitalized due to an exacerbation with respiratory rate > 30/min, pulse rate > 120 bpm, O2 saturation (on air) < 90% on admission, selected consecutively from medical wards; controls (n = 350;1:3 ratio) randomly selected from asthma/medical clinics. Data was collected via a pre-tested Interviewer-Administered Questionnaire (IAQ). Logistic Regression (LR) analyses were performed to develop the model with consensus from an expert panel. A second case-control study was carried out to assess the criterion validity of the new model recruiting 158 cases and 101 controls from the same hospitals. Data was collected using an IAQ based on the newly developed risk prediction model.

RESULTS

The developed model consisted of ten predictors with an Area Under the Curve (AUC) of 0.83 (95% CI: 0.78 to 0.88, P < 0.001), sensitivity 69.0%, specificity 86.1%, positive predictive value (PPV) 88.6%, negative predictive value (NPV) 63.9%. Positive and negative likelihood ratios were 4.9 and 0.3, respectively.

CONCLUSIONS

The newly developed model was proven valid to identify adult asthma patients who are at risk of hospitalization due to exacerbations. It is recommended as a simple, low-cost tool for identifying and prioritizing high-risk asthma patients for specialized care.

Promising treatment biomarkers in asthma

Asthma is a highly heterogenous disease which researchers over time have attempted to classify into different phenotypes and endotypes to improve diagnosis, prognosis and treatment. Earlier classifications based on reaction to environmental allergens, age, sex and lung function have evolved, and today, the use of precision medicine guided by biomarkers offers new perspectives on asthma management. Identifying biomarkers that may reveal the underlying pathophysiology of the disease will help to select the patients who will benefit most from specific treatments. This review explores the classification of asthma phenotypes and focuses on the most recent advances in using biomarkers to guide treatment.

Development of an Asthma Exacerbation Risk Prediction Model for Conversational Use by Adults in England

Background

Improving accurate risk assessment of asthma exacerbations, and reduction via relevant behaviour change among people with asthma could save lives and reduce health care costs. We developed a simple personalised risk prediction model for asthma exacerbations using factors collected in routine healthcare data for use in a risk modelling feature for automated conversational systems.

Methods

We used pseudonymised primary care electronic healthcare records from the Clinical Practice Research Datalink (CPRD) Aurum database in England. We combined variables for prediction of asthma exacerbations using logistic regression including age, gender, ethnicity, Index of Multiple Deprivation, geographical region and clinical variables related to asthma events.

Results

We included 1,203,741 patients divided into three cohorts to implement temporal validation: 898,763 (74.7%) in the training sample, 226,754 (18.8%) in the testing sample and 78,224 (6.5%) in the validation sample. The Area under the ROC curve (AUC) for the full model was 0.72 and for the restricted model was 0.71. Using a cut-off point of 0.1, approximately 27 asthma reviews by clinicians per 100 patients would be prevented compared with a strategy that all patients are regarded as high risk. Compared with patients without an exacerbation, patients who exacerbated were older, more likely to be female, prescribed more SABA and ICS in the preceding 12 months, have history of GORD, COPD, anxiety, depression, live in very deprived areas and have more severe disease.

Conclusion

Using information available from routinely collected electronic healthcare record data, we developed a model that has moderate ability to separate patients who had an asthma exacerbation within 3 months from their index date from patients who did not. When comparing this model with a simplified model with variables that can easily be self-reported through a WhatsApp chatbot, we have shown that the predictive performance of the model is not substantially different.

Management of Chronic Asthma in Adults

Asthma is characterized by chronic inflammation and respiratory symptoms such as wheezing and coughing. In the United States, it affects 25 million people annually. Chronic smokers, poor adherence to medications, incorrect use of inhalers, and overall poor asthma control are known risk factors that lead to poorly controlled chronic asthmatics. Although asthma is traditionally categorized by severity, treatment by primary care providers is guided by the Global Initiative for Asthma or the National Asthma Education and Prevention Program. As more research is available, shared decision-making between health care providers and patients will lead to improved outcomes in managing chronic asthma.

Asthma

Asthma is one of the most common chronic non-communicable diseases worldwide and is characterised by variable airflow obstruction, causing dyspnoea and wheezing. Highly effective therapies are available; asthma morbidity and mortality have vastly improved in the past 15 years, and most patients can attain good asthma control. However, undertreatment is still common, and improving patient and health-care provider understanding of when and how to adjust treatment is crucial. Asthma management consists of a cycle of assessment of asthma control and risk factors and adjustment of medications accordingly. With the introduction of biological therapies, management of severe asthma has entered the precision medicine era-a shift that is driving clinical ambitions towards disease remission. Patients with severe asthma often have co-existing conditions contributing to their symptoms, mandating a multidimensional management approach. In this Seminar, we provide a clinically focused overview of asthma; epidemiology, pathophysiology, diagnosis, and management in children and adults.

Symptom versus exacerbation control: an evolution in GINA guidelines?

The article traces the concept of asthma control within GINA guidelines over the past 25 years. In the first 15 years after 1995, the main objective of asthma management was to obtain the control of all clinical and functional characteristics of asthma. A landmark study (GOAL) showed for the first time that a good control of asthma is a reasonable outcome that can be achieved in a large proportion of asthmatics with a regular appropriate treatment. In the following years, more emphasis was placed on the role of exacerbations as critical manifestations of poor asthma control, whose frequency is associated with excessive FEV1 decline and increased risk of death. Accordingly, the 2014 GINA report makes a clear distinction between the control of the day-by-day symptoms and the reduction in the risk of severe exacerbations, stating that both conditions should be obtained. The 2019 update included a significant change in the management of mild asthma, prioritizing the prevention of exacerbations to that of mild symptoms. This view was repeated in the 2021 update, where the prevention of exacerbations, together with an acceptable symptom control with a minimal use of rescue medication, appeared to be the real main goal of asthma management. While a discrepancy between current symptoms and exacerbations may be present in mild asthma, a significant relationship between these two features is observed in moderate-severe asthma: a persistent poor symptom control is a major risk factor for exacerbations, whereas achieving symptom control through regular treatment is associated with a reduction in exacerbation rate. Thus, the opinion that frequent symptoms are not important in the absence of acute exacerbations should be discouraged, whereas education of patients to a good symptom perception and to improve adherence to regular treatment should be implemented. Furthermore, the persistence of risk factors, such as increased airway inflammation, even in a patient with minor daily symptoms, should be considered for optimizing treatment.

Acute severe asthma in emergency department: clinical characteristics, risk factors, and predictors for poor outcome

Background

Severe asthma exacerbation can be a frightening experience to the patient and physician. Despite continuous efforts to frame management guidelines and advances in treatment, severe exacerbations still occur. In order to prevent and judicious management of asthma exacerbations, we should predict them first. This study aims to evaluate distinct clinical trajectories and management outcome of patients with severe asthma exacerbations and also evaluate predictors for poor outcome.

Methods

Patients suffering from acute asthma exacerbation and presented to emergency room (forty patients) were grouped into 2 groups (groups A and B) according to severity of exacerbation. Assessment included full clinical history, laboratory investigations (including eosinophil cell count and serum IgE level), Beck’s anxiety and depression inventory scales, assessment of asthma medication adherence and control level, and peak expiratory flow measurement (at presentation, 1 and 6 h after).

Results

Fifty-five percent of patients suffered from severe and life-threatening asthma exacerbations, 63.6% of them were females. The most important predictors for severe exacerbations were SO2 < 90% at baseline (OR = 4.56; 95% CI = 3.45–7.56; P < 0.001), PEFR after 1 h (OR= 3.34; 95%CI = 1.90–4.90; P < 0.001), and uncontrolled asthma (OR= 3.33; 95%CI = 2.50–5.05; P < 0.001). Predictors for hospitalization were old age (OR = 1.11; 95%CI = 1.09–2.11; P < 0.001), uncontrolled asthma (OR = 2.34; 95%CI = 2.01–4.40; P < 0.001), PEFR after 1 h (OR= 4.44; 95%CI= 3.24–7.68; P < 0.001), and SO2 <90% at baseline (OR= 5.67; 95%CI= 3.98–8.50; P < 0.001).

Conclusions

Severe asthma exacerbations can be predicted by old age, previous history of mechanical ventilation, obstructive sleep apnea, overuse of SABA, uncontrolled asthma, moderate to severe depression, eosinophilia, SO2 <90%, and low peak expiratory flow rates.

Error and Timeliness Analysis for Using Machine Learning to Predict Asthma Hospital Visits: Retrospective Cohort Study

Background

Asthma hospital visits, including emergency department visits and inpatient stays, are a significant burden on health care. To leverage preventive care more effectively in managing asthma, we previously employed machine learning and data from the University of Washington Medicine (UWM) to build the world’s most accurate model to forecast which asthma patients will have asthma hospital visits during the following 12 months.

Objective

Currently, two questions remain regarding our model’s performance. First, for a patient who will have asthma hospital visits in the future, how far in advance can our model make an initial identification of risk? Second, if our model erroneously predicts a patient to have asthma hospital visits at the UWM during the following 12 months, how likely will the patient have ≥1 asthma hospital visit somewhere else or ≥1 surrogate indicator of a poor outcome? This work aims to answer these two questions.

Methods

Our patient cohort included every adult asthma patient who received care at the UWM between 2011 and 2018. Using the UWM data, our model made predictions on the asthma patients in 2018. For every such patient with ≥1 asthma hospital visit at the UWM in 2019, we computed the number of days in advance that our model gave an initial warning. For every such patient erroneously predicted to have ≥1 asthma hospital visit at the UWM in 2019, we used PreManage and the UWM data to check whether the patient had ≥1 asthma hospital visit outside of the UWM in 2019 or any surrogate indicators of poor outcomes. Such surrogate indicators included a prescription for systemic corticosteroids during the following 12 months, any type of visit for asthma exacerbation during the following 12 months, and asthma hospital visits between 13 and 24 months later.

Results

Among the 218 asthma patients in 2018 with asthma hospital visits at the UWM in 2019, 61.9% (135/218) were given initial warnings of such visits ≥3 months ahead by our model and 84.4% (184/218) were given initial warnings ≥1 day ahead. Among the 1310 asthma patients in 2018 who were erroneously predicted to have asthma hospital visits at the UWM in 2019, 29.01% (380/1310) had asthma hospital visits outside of the UWM in 2019 or surrogate indicators of poor outcomes.

Conclusions

Our model gave timely risk warnings for most asthma patients with poor outcomes. We found that 29.01% (380/1310) of asthma patients for whom our model gave false-positive predictions had asthma hospital visits somewhere else during the following 12 months or surrogate indicators of poor outcomes, and thus were reasonable candidates for preventive interventions. There is still significant room for improving our model to give more accurate and more timely risk warnings.

International Registered Report Identifier (IRRID)

RR2-10.2196/5039

Characteristics, phenotypes, mechanisms and management of severe asthma

ABSTRACT

Severe asthma is "asthma which requires treatment with high dose inhaled corticosteroids (ICS) plus a second controller (and/or systemic corticosteroids) to prevent it from becoming 'uncontrolled' or which remains 'uncontrolled' despite this therapy." The state of control was defined by symptoms, exacerbations and the degree of airflow obstruction. Therefore, for the diagnosis of severe asthma, it is important to have evidence for a diagnosis of asthma with an assessment of its severity, followed by a review of comorbidities, risk factors, triggers and an assessment of whether treatment is commensurate with severity, whether the prescribed treatments have been adhered to and whether inhaled therapy has been properly administered. Phenotyping of severe asthma has been introduced with the definition of a severe eosinophilic asthma phenotype characterized by recurrent exacerbations despite being on high dose ICS and sometimes oral corticosteroids, with a high blood eosinophil count and a raised level of nitric oxide in exhaled breath. This phenotype has been associated with a Type-2 (T2) inflammatory profile with expression of interleukin (IL)-4, IL-5, and IL-13. Molecular phenotyping has also revealed non-T2 inflammatory phenotypes such as Type-1 or Type-17 driven phenotypes. Antibody treatments targeted at the T2 targets such as anti-IL5, anti-IL5Rα, and anti-IL4Rα antibodies are now available for treating severe eosinophilic asthma, in addition to anti-immunoglobulin E antibody for severe allergic asthma. No targeted treatments are currently available for non-T2 inflammatory phenotypes. Long-term azithromycin and bronchial thermoplasty may be considered. The future lies with molecular phenotyping of the airway inflammatory process to refine asthma endotypes for precision medicine.

Blood eosinophils, fractional exhaled nitric oxide and the risk of asthma attacks in randomised controlled trials: protocol for a systemic review and control arm patient-level meta-analysis for clinical prediction modelling

INTRODUCTION

The reduction of the risk of asthma attacks is a major goal of guidelines. The fact that type-2 inflammatory biomarkers identify a higher risk, anti-inflammatory responsive phenotype is potentially relevant to this goal. We aim to quantify the relation between blood eosinophils, exhaled nitric oxide (FeNO) and the risk of severe asthma attacks.

METHODS AND ANALYSIS

A systematic review of randomised controlled trials (RCTs) will be conducted by searching MEDLINE from January 1993 to April 2021. We will include RCTs that investigated the effect of fixed treatment(s) regimen(s) on severe asthma exacerbation rates over at least 24 weeks and reported a baseline value for blood eosinophils and FeNO. Study selection will follow the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, and the methodological appraisal of the studies will be assessed by the Cochrane Risk-of-Bias Tool for RCTs. Study authors will be contacted to request anonymised individual participant data (IPD) for patients randomised to the trial's control arm. An IPD meta-analysis will be performed for multivariable prognostic modelling with performance assessment (calibration plots and the c-statistic) in a cross-validation by study procedure. The outcome to predict is the absolute number of severe asthma attacks to occur in the following 12 months if anti-inflammatory therapy is not changed (ie, annualised number of attacks requiring ≥3 days of systemic corticosteroids and/or hospitalisation if the patient was randomised to the control arm of an RCT). A summary prognostic equation and risk stratification chart will be reported as a basis for further analyses of individualised treatment benefit.

ETHICS AND DISSEMINATION

The protocol has been reviewed by the relevant Oxford academic ethics committee and found to comprise fully anonymised data not requiring further ethical approbation. Results will be communicated in an international meeting and submitted to a peer-reviewed journal.

PROSPERO REGISTRATION NUMBER

CRD42021245337.

A Roadmap for Boosting Model Generalizability for Predicting Hospital Encounters for Asthma

In the United States, ~9% of people have asthma. Each year, asthma incurs high health care cost and many hospital encounters covering 1.8 million emergency room visits and 439,000 hospitalizations. A small percentage of patients with asthma use most health care resources. To improve outcomes and cut resource use, many health care systems use predictive models to prospectively find high-risk patients and enroll them in care management for preventive care. For maximal benefit from costly care management with limited service capacity, only patients at the highest risk should be enrolled. However, prior models built by others miss >50% of true highest-risk patients and mislabel many low-risk patients as high risk, leading to suboptimal care and wasted resources. To address this issue, 3 site-specific models were recently built to predict hospital encounters for asthma, gaining up to >11% better performance. However, these models do not generalize well across sites and patient subgroups, creating 2 gaps before translating these models into clinical use. This paper points out these 2 gaps and outlines 2 corresponding solutions: (1) a new machine learning technique to create cross-site generalizable predictive models to accurately find high-risk patients and (2) a new machine learning technique to automatically raise model performance for poorly performing subgroups while maintaining model performance on other subgroups. This gives a roadmap for future research.

Predicting Continuity of Asthma Care Using a Machine Learning Model: Retrospective Cohort Study

Continuity of care (COC) has been shown to possess numerous health benefits for chronic diseases. Specifically, the establishment of its level can facilitate clinical decision-making and enhanced allocation of healthcare resources. However, the use of a generalizable predictive methodology to determine the COC in patients has been underinvestigated. To fill this research gap, this study aimed to develop a machine learning model to predict the future COC of asthma patients and explore the associated factors. We included 31,724 adult outpatients with asthma who received care from the University of Washington Medicine between 2011 and 2018, and examined 138 features to build the machine learning model. Following the 10-fold cross-validations, the proposed model yielded an accuracy of 88.20%, an average area under the receiver operating characteristic curve of 0.96, and an average F1 score of 0.86. Further analysis revealed that the severity of asthma, comorbidities, insurance, and age were highly correlated with the COC of patients with asthma. This study used predictive methods to obtain the COC of patients, and our excellent modeling strategy achieved high performance. After further optimization, the model could facilitate future clinical decisions, hospital management, and improve outcomes.

Asthma Patients Benefit More Than Chronic Obstructive Pulmonary Disease Patients in the Coronavirus Disease 2019 Pandemic

Background: Coronavirus disease 2019 (COVID-19) has raised many questions about the role of underlying chronic diseases on disease outcomes. However, there is limited information about the effects of COVID-19 on chronic airway diseases. Therefore, we conducted the present study to investigate the impact of COVID-19 on patients with asthma or chronic obstructive pulmonary disease (COPD) and ascertain risk factors for acute exacerbations (AEs). Methods: This single-center observational study was conducted at the Second Xiangya Hospital of Central South University, involving asthma or COPD patients who had been treated with inhaled combination corticosteroids (ICSs), such as budesonide, and one long-acting beta-2-agonist (LABA), such as formoterol, for at least a year before the COVID-19 pandemic. We conducted telephone interviews to collect demographic information and clinical data between January 1, 2019, and December 31, 2020, focusing on respiratory and systemic symptoms, as well as times of exacerbations. Data for asthma and COPD were then compared, and the risk factors for AEs were identified using logistic regression analysis. Results: A total of 251 patients were enrolled, comprising 162 (64.5%) who had asthma and 89 who had COPD, with none having COPD/asthma overlap. Frequency of AEs among asthma patients was significantly lower in 2020 than in 2019 (0.82 ± 3.33 vs. 1.00 ± 3.16; P < 0.05). Moreover, these patients visited the clinic less (0.37 ± 0.93 vs. 0.49 ± 0.94; P < 0.05) and used emergency drugs less (0.01 ± 0.11 vs. 007 ± 0.38; P < 0.05) during the COVID-19 pandemic. In contrast, among COPD patients, there were no significant differences in AE frequency, clinic visits, or emergency drug use. Furthermore, asthma patients visited clinics less frequently during the pandemic than those with COPD. Logistic regression analysis also showed that a history of at least one AE within the last 12 months was associated with increased AE odds for both asthma and COPD during the COVID-19 pandemic (odds ratio: 13.73, 95% CI: 7.04-26.77; P < 0.01). Conclusion: During the COVID-19 pandemic, patients with asthma showed better disease control than before, whereas patients with COPD may not have benefited from the pandemic. For both diseases, at least one AE within the previous 12 months was a risk factor for AEs during the pandemic. Particularly, among asthma patients, the risk factors for AE during the COVID-19 pandemic were urban environment, smoking, and lower asthma control test scores.

Ranking Rule-Based Automatic Explanations for Machine Learning Predictions on Asthma Hospital Encounters in Patients With Asthma: Retrospective Cohort Study

Background

Asthma hospital encounters impose a heavy burden on the health care system. To improve preventive care and outcomes for patients with asthma, we recently developed a black-box machine learning model to predict whether a patient with asthma will have one or more asthma hospital encounters in the succeeding 12 months. Our model is more accurate than previous models. However, black-box machine learning models do not explain their predictions, which forms a barrier to widespread clinical adoption. To solve this issue, we previously developed a method to automatically provide rule-based explanations for the model’s predictions and to suggest tailored interventions without sacrificing model performance. For an average patient correctly predicted by our model to have future asthma hospital encounters, our explanation method generated over 5000 rule-based explanations, if any. However, the user of the automated explanation function, often a busy clinician, will want to quickly obtain the most useful information for a patient by viewing only the top few explanations. Therefore, a methodology is required to appropriately rank the explanations generated for a patient. However, this is currently an open problem.

Objective

The aim of this study is to develop a method to appropriately rank the rule-based explanations that our automated explanation method generates for a patient.

Methods

We developed a ranking method that struck a balance among multiple factors. Through a secondary analysis of 82,888 data instances of adults with asthma from the University of Washington Medicine between 2011 and 2018, we demonstrated our ranking method on the test case of predicting asthma hospital encounters in patients with asthma.

Results

For each patient predicted to have asthma hospital encounters in the succeeding 12 months, the top few explanations returned by our ranking method typically have high quality and low redundancy. Many top-ranked explanations provide useful insights on the various aspects of the patient’s situation, which cannot be easily obtained by viewing the patient’s data in the current electronic health record system.

Conclusions

The explanation ranking module is an essential component of the automated explanation function, and it addresses the interpretability issue that deters the widespread adoption of machine learning predictive models in clinical practice. In the next few years, we plan to test our explanation ranking method on predictive modeling problems addressing other diseases as well as on data from other health care systems.

International Registered Report Identifier (IRRID)

RR2-10.2196/5039

Developing a short-term prediction model for asthma exacerbations from Swedish primary care patients' data using machine learning - Based on the ARCTIC study

OBJECTIVE

The ability to predict impending asthma exacerbations may allow better utilization of healthcare resources, prevention of hospitalization and improve patient outcomes. We aimed to develop models using machine learning to predict risk of exacerbations.

METHODS

Data from 29,396 asthma patients was collected from electronic medical records and national registers covering clinical and epidemiological factors (e.g. comorbidities, health care contacts), between 2000 and 2013. Machine-learning classifiers were used to create models to predict exacerbations within the next 15 days. Model selection was done using the mean cross validation score of area under precision-recall curve (AUPRC).

RESULTS

The most important predictors of exacerbation were comorbidity burden and previous exacerbations. Model validation on test data yielded an AUPRC = 0.007 (95% CI: ± 0.0002), indicating that historic clinical information alone may not be sufficient to predict a near future risk of asthma exacerbation.

CONCLUSIONS

Supplementation with additional data on environmental triggers, (e.g. weather, pollen count, air quality) and from wearables, might be necessary to improve performance of the short-term predictive model to develop a more clinically useful tool.

Using Computational Methods to Improve Integrated Disease Management for Asthma and Chronic Obstructive Pulmonary Disease: Protocol for a Secondary Analysis

Background

Asthma and chronic obstructive pulmonary disease (COPD) impose a heavy burden on health care. Approximately one-fourth of patients with asthma and patients with COPD are prone to exacerbations, which can be greatly reduced by preventive care via integrated disease management that has a limited service capacity. To do this well, a predictive model for proneness to exacerbation is required, but no such model exists. It would be suboptimal to build such models using the current model building approach for asthma and COPD, which has 2 gaps due to rarely factoring in temporal features showing early health changes and general directions. First, existing models for other asthma and COPD outcomes rarely use more advanced temporal features, such as the slope of the number of days to albuterol refill, and are inaccurate. Second, existing models seldom show the reason a patient is deemed high risk and the potential interventions to reduce the risk, making already occupied clinicians expend more time on chart review and overlook suitable interventions. Regular automatic explanation methods cannot deal with temporal data and address this issue well.

Objective

To enable more patients with asthma and patients with COPD to obtain suitable and timely care to avoid exacerbations, we aim to implement comprehensible computational methods to accurately predict proneness to exacerbation and recommend customized interventions.

Methods

We will use temporal features to accurately predict proneness to exacerbation, automatically find modifiable temporal risk factors for every high-risk patient, and assess the impact of actionable warnings on clinicians’ decisions to use integrated disease management to prevent proneness to exacerbation.

Results

We have obtained most of the clinical and administrative data of patients with asthma from 3 prominent American health care systems. We are retrieving other clinical and administrative data, mostly of patients with COPD, needed for the study. We intend to complete the study in 6 years.

Conclusions

Our results will help make asthma and COPD care more proactive, effective, and efficient, improving outcomes and saving resources.

International Registered Report Identifier (IRRID)

PRR1-10.2196/27065

Forecasting Future Asthma Hospital Encounters of Patients With Asthma in an Academic Health Care System: Predictive Model Development and Secondary Analysis Study

Background

Asthma affects a large proportion of the population and leads to many hospital encounters involving both hospitalizations and emergency department visits every year. To lower the number of such encounters, many health care systems and health plans deploy predictive models to prospectively identify patients at high risk and offer them care management services for preventive care. However, the previous models do not have sufficient accuracy for serving this purpose well. Embracing the modeling strategy of examining many candidate features, we built a new machine learning model to forecast future asthma hospital encounters of patients with asthma at Intermountain Healthcare, a nonacademic health care system. This model is more accurate than the previously published models. However, it is unclear how well our modeling strategy generalizes to academic health care systems, whose patient composition differs from that of Intermountain Healthcare.

Objective

This study aims to evaluate the generalizability of our modeling strategy to the University of Washington Medicine (UWM), an academic health care system.

Methods

All adult patients with asthma who visited UWM facilities between 2011 and 2018 served as the patient cohort. We considered 234 candidate features. Through a secondary analysis of 82,888 UWM data instances from 2011 to 2018, we built a machine learning model to forecast asthma hospital encounters of patients with asthma in the subsequent 12 months.

Results

Our UWM model yielded an area under the receiver operating characteristic curve (AUC) of 0.902. When placing the cutoff point for making binary classification at the top 10% (1464/14,644) of patients with asthma with the largest forecasted risk, our UWM model yielded an accuracy of 90.6% (13,268/14,644), a sensitivity of 70.2% (153/218), and a specificity of 90.91% (13,115/14,426).

Conclusions

Our modeling strategy showed excellent generalizability to the UWM, leading to a model with an AUC that is higher than all of the AUCs previously reported in the literature for forecasting asthma hospital encounters. After further optimization, our model could be used to facilitate the efficient and effective allocation of asthma care management resources to improve outcomes.

International Registered Report Identifier (IRRID)

RR2-10.2196/resprot.5039

Generalizability of an Automatic Explanation Method for Machine Learning Prediction Results on Asthma-Related Hospital Visits in Patients With Asthma: Quantitative Analysis

Background

Asthma exerts a substantial burden on patients and health care systems. To facilitate preventive care for asthma management and improve patient outcomes, we recently developed two machine learning models, one on Intermountain Healthcare data and the other on Kaiser Permanente Southern California (KPSC) data, to forecast asthma-related hospital visits, including emergency department visits and hospitalizations, in the succeeding 12 months among patients with asthma. As is typical for machine learning approaches, these two models do not explain their forecasting results. To address the interpretability issue of black-box models, we designed an automatic method to offer rule format explanations for the forecasting results of any machine learning model on imbalanced tabular data and to suggest customized interventions with no accuracy loss. Our method worked well for explaining the forecasting results of our Intermountain Healthcare model, but its generalizability to other health care systems remains unknown.

Objective

The objective of this study is to evaluate the generalizability of our automatic explanation method to KPSC for forecasting asthma-related hospital visits.

Methods

Through a secondary analysis of 987,506 data instances from 2012 to 2017 at KPSC, we used our method to explain the forecasting results of our KPSC model and to suggest customized interventions. The patient cohort covered a random sample of 70% of patients with asthma who had a KPSC health plan for any period between 2015 and 2018.

Results

Our method explained the forecasting results for 97.57% (2204/2259) of the patients with asthma who were correctly forecasted to undergo asthma-related hospital visits in the succeeding 12 months.

Conclusions

For forecasting asthma-related hospital visits, our automatic explanation method exhibited an acceptable generalizability to KPSC.

International Registered Report Identifier (IRRID)

RR2-10.2196/resprot.5039

Fractional exhaled nitric oxide as a determinant for the clinical course of asthma: a systematic review

Background: Precision medicine means linking the right patient to the right management strategy including best possible pharmacological therapy, considering the individual variability of the disease characteristics, type of inflammation, genes, environment, and lifestyle. For heterogenous diseases such as asthma, reliable biomarkers are needed to facilitate the best possible disease control and reduce the risk of side effects. The present review examines fractional exhaled nitric oxide (FeNO) as a guide for the management strategy of asthma and predictor of its clinical course.

Method: The literature included was identified by searching the PubMed database using specific key words and MeSH terms. Studies were not excluded based on their design alone. The search resulted in 212 hits, of which 35 articles were included in this review.

Results: Several studies support a potential role for high FeNO levels as a prognostic biomarker for accelerated lung function decline in adults with newly diagnosed asthma. Furthermore, studies report an association between high FeNO levels and excess decline in FEV₁ in adults with long-standing moderate to severe asthma despite optimised therapy, whereas the findings for patients with less severe disease are conflicting. Applying a FeNO-based management algorithm reduces the exacerbation rate in adults with asthma. Similar observations are seen in children, though based on fewer studies. The available studies provide evidence that the level of FeNO may be useful as a predictor of subsequent loss of asthma control in adults, though the evidence is somewhat conflicting in children and young adults.

Conclusion: The present review provides evidence of the prognostic value of FeNO as a surrogate biomarker for type 2 inflammation in the airways. FeNO is likely to emerge as an important biomarker in monitoring and tailoring modern asthma treatment, either alone or in combination with other biomarkers.

The impact of comorbidities on severe asthma

PURPOSE OF REVIEW

Severe asthma is often associated with numerous comorbidities that complicate disease management and affect patient's outcomes. They contribute to poor disease control and mimic asthma symptoms. Although some comorbidities such as obstructive sleep apnea, bronchiectasis, and chronic obstructive pulmonary disease are generally well recognized, many other may remain undiagnosed but may be detected in an expert specialist setting. The management of comorbidities seems to improve asthma outcomes, and optimizes therapy by avoiding overtreatment. The present review provides recent knowledge regarding the most common comorbidities which are associated with severe asthma.

RECENT FINDINGS

Comorbidities are more prevalent in severe asthma than in mild-to-moderate disease or in the general population. They can be grouped into two large domains: the pulmonary domain and the extrapulmonary domain. Pulmonary comorbidities include upper respiratory tract disorders (obstructive sleep apnea, allergic and nonallergic rhinitis, chronic rhinosinusitis, nasal polyposis) and middle/lower respiratory tract disorders (chronic obstructive pulmonary disease, allergic bronchopulmonary aspergillosis and fungal sensitization, bronchiectasis, dysfunctional breathing). Extrapulmonary comorbidities include anxiety, depression, gastro-esophageal reflux disease, obesity, cardiovascular, and metabolic diseases.

SUMMARY

The identification of comorbidities via multidimensional approach is needed to initiate appropriate multidisciplinary management of patients with severe asthma.

Novel Machine Learning Can Predict Acute Asthma Exacerbation

BACKGROUND

Asthma exacerbations result in significant health and economic burden, but are difficult to predict.

RESEARCH QUESTION

Can machine learning (ML) models with large-scale outpatient data predict asthma exacerbations?

STUDY DESIGN AND METHODS

We analyzed data extracted from electronic health records (EHRs) of asthma patients treated at the Cleveland Clinic from 2010 through 2018. Demographic information, comorbidities, laboratory values, and asthma medications were included as covariates. Three different models were built with logistic regression, random forests, and a gradient boosting decision tree to predict: (1) nonsevere asthma exacerbation requiring oral glucocorticoid burst, (2) ED visits, and (3) hospitalizations.

RESULTS

Of 60,302 patients, 19,772 (32.8%) had at least one nonsevere exacerbation requiring oral glucocorticoid burst, 1,748 (2.9%) requiring and ED visit and 902 (1.5%) requiring hospitalization. Nonsevere exacerbation, ED visit, and hospitalization were predicted best by light gradient boosting machine, an algorithm used in ML to fit predictive analytic models, and had an area under the receiver operating characteristic curve of 0.71 (95% CI, 0.70-0.72), 0.88 (95% CI, 0.86-0.89), and 0.85 (95% CI, 0.82-0.88), respectively. Risk factors for all three outcomes included age, long-acting β agonist, high-dose inhaled glucocorticoid, or chronic oral glucocorticoid therapy. In subgroup analysis of 9,448 patients with spirometry data, low FEV₁ and FEV₁ to FVC ratio were identified as top risk factors for asthma exacerbation, ED visits, and hospitalization. However, adding pulmonary function tests did not improve models' prediction performance.

INTERPRETATION

Models built with an ML algorithm from real-world outpatient EHR data accurately predicted asthma exacerbation and can be incorporated into clinical decision tools to enhance outpatient care and to prevent adverse outcomes.

Automatically Explaining Machine Learning Prediction Results on Asthma Hospital Visits in Patients With Asthma: Secondary Analysis

Background

Asthma is a major chronic disease that poses a heavy burden on health care. To facilitate the allocation of care management resources aimed at improving outcomes for high-risk patients with asthma, we recently built a machine learning model to predict asthma hospital visits in the subsequent year in patients with asthma. Our model is more accurate than previous models. However, like most machine learning models, it offers no explanation of its prediction results. This creates a barrier for use in care management, where interpretability is desired.

Objective

This study aims to develop a method to automatically explain the prediction results of the model and recommend tailored interventions without lowering the performance measures of the model.

Methods

Our data were imbalanced, with only a small portion of data instances linking to future asthma hospital visits. To handle imbalanced data, we extended our previous method of automatically offering rule-formed explanations for the prediction results of any machine learning model on tabular data without lowering the model’s performance measures. In a secondary analysis of the 334,564 data instances from Intermountain Healthcare between 2005 and 2018 used to form our model, we employed the extended method to automatically explain the prediction results of our model and recommend tailored interventions. The patient cohort consisted of all patients with asthma who received care at Intermountain Healthcare between 2005 and 2018, and resided in Utah or Idaho as recorded at the visit.

Results

Our method explained the prediction results for 89.7% (391/436) of the patients with asthma who, per our model’s correct prediction, were likely to incur asthma hospital visits in the subsequent year.

Conclusions

This study is the first to demonstrate the feasibility of automatically offering rule-formed explanations for the prediction results of any machine learning model on imbalanced tabular data without lowering the performance measures of the model. After further improvement, our asthma outcome prediction model coupled with the automatic explanation function could be used by clinicians to guide the allocation of limited asthma care management resources and the identification of appropriate interventions.

Developing a Predictive Model for Asthma-Related Hospital Encounters in Patients With Asthma in a Large, Integrated Health Care System: Secondary Analysis

Background

Asthma causes numerous hospital encounters annually, including emergency department visits and hospitalizations. To improve patient outcomes and reduce the number of these encounters, predictive models are widely used to prospectively pinpoint high-risk patients with asthma for preventive care via care management. However, previous models do not have adequate accuracy to achieve this goal well. Adopting the modeling guideline for checking extensive candidate features, we recently constructed a machine learning model on Intermountain Healthcare data to predict asthma-related hospital encounters in patients with asthma. Although this model is more accurate than the previous models, whether our modeling guideline is generalizable to other health care systems remains unknown.

Objective

This study aims to assess the generalizability of our modeling guideline to Kaiser Permanente Southern California (KPSC).

Methods

The patient cohort included a random sample of 70.00% (397,858/568,369) of patients with asthma who were enrolled in a KPSC health plan for any duration between 2015 and 2018. We produced a machine learning model via a secondary analysis of 987,506 KPSC data instances from 2012 to 2017 and by checking 337 candidate features to project asthma-related hospital encounters in the following 12-month period in patients with asthma.

Results

Our model reached an area under the receiver operating characteristic curve of 0.820. When the cutoff point for binary classification was placed at the top 10.00% (20,474/204,744) of patients with asthma having the largest predicted risk, our model achieved an accuracy of 90.08% (184,435/204,744), a sensitivity of 51.90% (2259/4353), and a specificity of 90.91% (182,176/200,391).

Conclusions

Our modeling guideline exhibited acceptable generalizability to KPSC and resulted in a model that is more accurate than those formerly built by others. After further enhancement, our model could be used to guide asthma care management.

International Registered Report Identifier (IRRID)

RR2-10.2196/resprot.5039

Testing the Generalizability of an Automated Method for Explaining Machine Learning Predictions on Asthma Patients' Asthma Hospital Visits to an Academic Healthcare System

Asthma puts a tremendous overhead on healthcare. To enable effective preventive care to improve outcomes in managing asthma, we recently created two machine learning models, one using University of Washington Medicine data and the other using Intermountain Healthcare data, to predict asthma hospital visits in the next 12 months in asthma patients. As is common in machine learning, neither model supplies explanations for its predictions. To tackle this interpretability issue of black-box models, we developed an automated method to produce rule-style explanations for any machine learning model's predictions made on imbalanced tabular data and to recommend customized interventions without lowering the prediction accuracy. Our method exhibited good performance in explaining our Intermountain Healthcare model's predictions. Yet, it stays unknown how well our method generalizes to academic healthcare systems, whose patient composition differs from that of Intermountain Healthcare. This study evaluates our automated explaining method's generalizability to the academic healthcare system University of Washington Medicine on predicting asthma hospital visits. We did a secondary analysis on 82,888 University of Washington Medicine data instances of asthmatic adults between 2011 and 2018, using our method to explain our University of Washington Medicine model's predictions and to recommend customized interventions. Our results showed that for predicting asthma hospital visits, our automated explaining method had satisfactory generalizability to University of Washington Medicine. In particular, our method explained the predictions for 87.6% of the asthma patients whom our University of Washington Medicine model accurately predicted to experience asthma hospital visits in the next 12 months.

Towards a personalised treatment approach for asthma attacks

Asthma attacks (exacerbations) are common, accounting for over 90 000 UK hospital admissions per annum. They kill nearly 1500 people per year in the UK, have significant associated direct and indirect costs and lead to accelerated and permanent loss of lung function. The recognition of asthma as a heterogeneous condition with multiple phenotypes has revolutionised the approach to the long-term management of the condition, with greater emphasis on personalised treatment and the introduction of the treatable traits concept. In contrast asthma attacks are poorly defined and understood and our treatment approach consists of bronchodilators and systemic corticosteroids. This review aims to explore the current limitations in the description, assessment and management of asthma attacks. We will outline the risk factors for attacks, strategies to modify this risk and describe the recognised characteristics of attacks as a first step towards the development of an approach for phenotyping and personalising the treatment of these critically important events. By doing this, we hope to gradually improve asthma attack treatment and reduce the adverse effects associated with recurrent courses of corticosteroids.

Asthma Exacerbation Prediction and Risk Factor Analysis Based on a Time-Sensitive, Attentive Neural Network: Retrospective Cohort Study

BACKGROUND

Asthma exacerbation is an acute or subacute episode of progressive worsening of asthma symptoms and can have a significant impact on patients' quality of life. However, efficient methods that can help identify personalized risk factors and make early predictions are lacking.

OBJECTIVE

This study aims to use advanced deep learning models to better predict the risk of asthma exacerbations and to explore potential risk factors involved in progressive asthma.

METHODS

We proposed a novel time-sensitive, attentive neural network to predict asthma exacerbation using clinical variables from large electronic health records. The clinical variables were collected from the Cerner Health Facts database between 1992 and 2015, including 31,433 adult patients with asthma. Interpretations on both patient and cohort levels were investigated based on the model parameters.

RESULTS

The proposed model obtained an area under the curve value of 0.7003 through a five-fold cross-validation, which outperformed the baseline methods. The results also demonstrated that the addition of elapsed time embeddings considerably improved the prediction performance. Further analysis observed diverse distributions of contributing factors across patients as well as some possible cohort-level risk factors, which could be found supporting evidence from peer-reviewed literature such as respiratory diseases and esophageal reflux.

CONCLUSIONS

The proposed neural network model performed better than previous methods for the prediction of asthma exacerbation. We believe that personalized risk scores and analyses of contributing factors can help clinicians better assess the individual's level of disease progression and afford the opportunity to adjust treatment, prevent exacerbation, and improve outcomes.

On the aggregation of published prognostic scores for causal inference in observational studies

As real world evidence on drug efficacy involves nonrandomized studies, statistical methods adjusting for confounding are needed. In this context, prognostic score (PGS) analysis has recently been proposed as a method for causal inference. It aims to restore balance across the different treatment groups by identifying subjects with a similar prognosis for a given reference exposure ("control"). This requires the development of a multivariable prognostic model in the control arm of the study sample, which is then extrapolated to the different treatment arms. Unfortunately, large cohorts for developing prognostic models are not always available. Prognostic models are therefore subject to a dilemma between overfitting and parsimony; the latter being prone to a violation of the assumption of no unmeasured confounders when important covariates are ignored. Although it is possible to limit overfitting by using penalization strategies, an alternative approach is to adopt evidence synthesis. Aggregating previously published prognostic models may improve the generalizability of PGS, while taking account of a large set of covariates-even when limited individual participant data are available. In this article, we extend a method for prediction model aggregation to PGS analysis in nonrandomized studies. We conduct extensive simulations to assess the validity of model aggregation, compared with other methods of PGS analysis for estimating marginal treatment effects. We show that aggregating existing PGS into a "meta-score" is robust to misspecification, even when elementary scores wrongfully omit confounders or focus on different outcomes. We illustrate our methods in a setting of treatments for asthma.

A systematic review of methodology used in the development of prediction models for future asthma exacerbation

Background

Clinical prediction models are widely used to guide medical advice and therapeutic interventions. Asthma is one of the most common chronic diseases globally and is characterised by acute deteriorations. These exacerbations are largely preventable, so there is interest in using clinical prediction models in this area. The objective of this review was to identify studies which have developed such models, determine whether consistent and appropriate methodology was used and whether statistically reliable prognostic models exist.

Methods

We searched online databases MEDLINE (1948 onwards), CINAHL Plus (1937 onwards), The Cochrane Library, Web of Science (1898 onwards) and ClinicalTrials.gov, using index terms relating to asthma and prognosis. Data was extracted and assessment of quality was based on GRADE and an early version of PROBAST (Prediction study Risk of Bias Assessment Tool). A meta-analysis of the discrimination and calibration measures was carried out to determine overall performance across models.

Results

Ten unique prognostic models were identified. GRADE identified moderate risk of bias in two of the studies, but more detailed quality assessment via PROBAST highlighted that most models were developed using highly selected and small datasets, incompletely recorded predictors and outcomes, and incomplete methodology. None of the identified models modelled recurrent exacerbations, instead favouring either presence/absence of an event, or time to first or specified event. Preferred methodologies were logistic regression and Cox proportional hazards regression.

The overall pooled c-statistic was 0.77 (95% confidence interval 0.73 to 0.80), though individually some models performed no better than chance. The meta-analysis had an I² value of 99.75% indicating a high amount of heterogeneity between studies. The majority of studies were small and did not include internal or external validation, therefore the individual performance measures are likely to be optimistic.

Conclusions

Current prognostic models for asthma exacerbations are heterogeneous in methodology, but reported c-statistics suggest a clinically useful model could be created. Studies were consistent in lacking robust validation and in not modelling serial events. Further research is required with respect to incorporating recurrent events, and to externally validate tools in large representative populations to demonstrate the generalizability of published results.

Developing a Model to Predict Hospital Encounters for Asthma in Asthmatic Patients: Secondary Analysis

Background

As a major chronic disease, asthma causes many emergency department (ED) visits and hospitalizations each year. Predictive modeling is a key technology to prospectively identify high-risk asthmatic patients and enroll them in care management for preventive care to reduce future hospital encounters, including inpatient stays and ED visits. However, existing models for predicting hospital encounters in asthmatic patients are inaccurate. Usually, they miss over half of the patients who will incur future hospital encounters and incorrectly classify many others who will not. This makes it difficult to match the limited resources of care management to the patients who will incur future hospital encounters, increasing health care costs and degrading patient outcomes.

Objective

The goal of this study was to develop a more accurate model for predicting hospital encounters in asthmatic patients.

Methods

Secondary analysis of 334,564 data instances from Intermountain Healthcare from 2005 to 2018 was conducted to build a machine learning classification model to predict the hospital encounters for asthma in the following year in asthmatic patients. The patient cohort included all asthmatic patients who resided in Utah or Idaho and visited Intermountain Healthcare facilities during 2005 to 2018. A total of 235 candidate features were considered for model building.

Results

The model achieved an area under the receiver operating characteristic curve of 0.859 (95% CI 0.846-0.871). When the cutoff threshold for conducting binary classification was set at the top 10.00% (1926/19,256) of asthmatic patients with the highest predicted risk, the model reached an accuracy of 90.31% (17,391/19,256; 95% CI 89.86-90.70), a sensitivity of 53.7% (436/812; 95% CI 50.12-57.18), and a specificity of 91.93% (16,955/18,444; 95% CI 91.54-92.31). To steer future research on this topic, we pinpointed several potential improvements to our model.

Conclusions

Our model improves the state of the art for predicting hospital encounters for asthma in asthmatic patients. After further refinement, the model could be integrated into a decision support tool to guide asthma care management allocation.

International Registered Report Identifier (IRRID)

RR2-10.2196/resprot.5039

ERS/EAACI statement on severe exacerbations in asthma in adults: facts, priorities and key research questions

Despite the use of effective medications to control asthma, severe exacerbations in asthma are still a major health risk and require urgent action on the part of the patient and physician to prevent serious outcomes such as hospitalisation or death. Moreover, severe exacerbations are associated with substantial healthcare costs and psychological burden, including anxiety and fear for patients and their families. The European Academy of Allergy and Clinical Immunology (EAACI) and the European Respiratory Society (ERS) set up a task force to search for a clear definition of severe exacerbations, and to also define research questions and priorities. The statement includes comments from patients who were members of the task force.

Development and validation of an asthma exacerbation prediction model using electronic health record (EHR) data

Objective: Asthma exacerbations are associated with significant morbidity, mortality, and cost. Accurately identifying asthma patients at risk for exacerbation is essential. We sought to develop a risk prediction tool based on routinely collected data from electronic health records (EHRs).Methods: From a repository of EHRs data, we extracted structured data for gender, race, ethnicity, smoking status, use of asthma medications, environmental allergy testing BMI status, and Asthma Control Test scores (ACT). A subgroup of this population of patients with asthma that had available prescription fill data was identified, which formed the primary population for analysis. Asthma exacerbation was defined as asthma-related hospitalization, urgent/emergent visit or oral steroid use over a 12-month period. Univariable and multivariable statistical analysis was completed to identify factors associated with exacerbation. We developed and tested a risk prediction model based on the multivariable analysis.Results: We identified 37,675 patients with asthma. Of those, 1,787 patients with asthma and fill data were identified, and 979 (54.8%) of them experienced an exacerbation. In the multivariable analysis, smoking (OR = 1.69, CI: 1.08-2.64), allergy testing (OR = 2.40, CI: 1.54-3.73), obesity (OR = 1.66, CI: 1.29-2.12), and ACT score reflecting uncontrolled asthma (OR = 1.66, CI: 1.10-2.29) were associated with increased risk of exacerbation. The area-under-the-curve (AUC) of our model in a combined derivation and validation cohort was 0.67.Conclusion: Despite use of rigorous methodology, we were unable to produce a predictive model with an acceptable degree of accuracy and AUC to be clinically useful.

Predicting asthma attacks in primary care: protocol for developing a machine learning-based prediction model

INTRODUCTION

Asthma is a long-term condition with rapid onset worsening of symptoms ('attacks') which can be unpredictable and may prove fatal. Models predicting asthma attacks require high sensitivity to minimise mortality risk, and high specificity to avoid unnecessary prescribing of preventative medications that carry an associated risk of adverse events. We aim to create a risk score to predict asthma attacks in primary care using a statistical learning approach trained on routinely collected electronic health record data.

METHODS AND ANALYSIS

We will employ machine-learning classifiers (naïve Bayes, support vector machines, and random forests) to create an asthma attack risk prediction model, using the Asthma Learning Health System (ALHS) study patient registry comprising 500 000 individuals across 75 Scottish general practices, with linked longitudinal primary care prescribing records, primary care Read codes, accident and emergency records, hospital admissions and deaths. Models will be compared on a partition of the dataset reserved for validation, and the final model will be tested in both an unseen partition of the derivation dataset and an external dataset from the Seasonal Influenza Vaccination Effectiveness II (SIVE II) study.

ETHICS AND DISSEMINATION

Permissions for the ALHS project were obtained from the South East Scotland Research Ethics Committee 02 [16/SS/0130] and the Public Benefit and Privacy Panel for Health and Social Care (1516-0489). Permissions for the SIVE II project were obtained from the Privacy Advisory Committee (National Services NHS Scotland) [68/14] and the National Research Ethics Committee West Midlands-Edgbaston [15/WM/0035]. The subsequent research paper will be submitted for publication to a peer-reviewed journal and code scripts used for all components of the data cleaning, compiling, and analysis will be made available in the open source GitHub website (https://github.com/hollytibble).

Future Risks in Patients With Severe Asthma

A major burden of severe asthma is the future risk of adverse health outcomes. Patients with severe asthma are prone to serious exacerbation and deterioration of lung function and may experience side effects of medications such as oral corticosteroids (OCSs). However, such future risk is not easily measurable in daily clinical practice. In particular, currently available tools to measure asthma control and asthma-related quality of life incompletely predict the future risk of medication-related morbidity. This is a significant issue in asthma management. This review summarizes the current evidence of future risk in patients with severe asthma. As future risk is poorly perceived by controlled asthmatics, our review focuses on the risk in patients with ‘controlled’ severe asthma. Of note, it is likely that long-term OCS therapy may not prevent future asthma progression, including lung function decline. In addition, the risk of drug side effects increases even during low-dose OCS therapy. Thus, novel treatments are highly desirable for reducing future risks without any loss of asthma control.

Diagnosis and Treatment of Asthma in Nonpregnant Women

Asthma is a common condition affecting 8.3% of the adult population in the United States. The disease is characterized by chronic airway inflammation that leads to airway hyperresponsiveness and obstruction that results in coughing, wheezing, shortness of breath, and a feeling of chest tightness. The diagnosis and classification of asthma is based on reported symptoms, physical examination findings, and spirometry. Pharmacologic therapy is prescribed using a stepwise approach that begins with inhaled short-acting beta₂ -agonists for intermittent asthma with the addition of daily inhaled corticosteroids for more persistent cases. Individuals with asthma are reevaluated on a regular basis to monitor symptoms, and pharmacologic treatments are adjusted as needed. Familiarity with the stepwise approach for asthma management and confidence in the efficacy and safety profiles of inhaled medications will assist clinicians in successful management of asthma in the primary care setting.

Performance of database-derived severe exacerbations and asthma control measures in asthma: responsiveness and predictive utility in a UK primary care database with linked questionnaire data

BACKGROUND

Observational research is essential to evaluate the real-life effectiveness of asthma treatments and can now make use of outcomes derived from electronic medical records.

AIM

The aim of this study was to investigate the utility of several database outcome measures in asthma.

METHODS

This study identified cohorts of patients with active asthma from a UK primary care database - Optimum Patient Care Research Database - approximately 10% of which was prospectively supplemented with questionnaire data. The "Questionnaire cohort" included patients aged 18-60 years with valid questionnaire data and 1 year of continuous primary care data. Separate "ICS initiation" and "ICS step-up" cohorts included patients aged 5-60 years initiated on inhaled corticosteroids (ICSs), who had 1 year of continuous primary care data before, and after, this index visit. Database measures of asthma symptom control and exacerbations were identified in the Optimum Patient Care Research Database and cross-tabulated with corresponding patient-reported (questionnaire) data. Responsiveness of the database outcomes was analyzed, using McNemar's and Wilcoxon's signed rank tests, and Poisson regression was used to estimate the association between database outcomes and future risk of database exacerbations, in the ICS initiation cohort.

RESULTS

The final study included 2,366 Questionnaire cohort patients and 51,404 ICS initiation patients. Agreement between patient-reported and database-recorded exacerbations was fair (kappa 0.35). Following the initiation of ICS, database risk domain asthma control (based on exacerbations) improved (proportion of patients with uncontrolled asthma decreased from 24.9% to 18.6%; P<0.001) and mean number of database exacerbations decreased from 0.09 to 0.08 per patient per year (P=0.001). However, another measure of asthma control which includes short-acting beta-agonist prescription as part of the definition did not show this improvement. Patients with prior exacerbations had a higher risk of future exacerbation (rate ratio [95% confidence interval], 3.23 [3.03-3.57]).

CONCLUSION

Asthma control and exacerbations derived from primary care databases were responsive, with the exception of short-acting beta-agonist prescriptions, and useful for risk prediction.

Comorbid "treatable traits" in difficult asthma: Current evidence and clinical evaluation

The care of patients with difficult-to-control asthma ("difficult asthma") is challenging and costly. Despite high-intensity asthma treatment, these patients experience poor asthma control and face the greatest risk of asthma morbidity and mortality. Poor asthma control is often driven by severe asthma biology, which has appropriately been the focus of intense research and phenotype-driven therapies. However, it is increasingly apparent that extra-pulmonary comorbidities also contribute substantially to poor asthma control and a heightened disease burden. These comorbidities have been proposed as "treatable traits" in chronic airways disease, adding impetus to their evaluation and management in difficult asthma. In this review, eight major asthma-related comorbidities are discussed: rhinitis, chronic rhinosinusitis, gastroesophageal reflux, obstructive sleep apnoea, vocal cord dysfunction, obesity, dysfunctional breathing and anxiety/depression. We describe the prevalence, impact and treatment effects of these comorbidities in the difficult asthma population, emphasizing gaps in the current literature. We examine the associations between individual comorbidities and highlight the potential for comorbidity clusters to exert combined effects on asthma outcomes. We conclude by outlining a pragmatic clinical approach to assess comorbidities in difficult asthma.

Development and Validation of Personalized Prediction to Estimate Future Risk of Severe Exacerbations and Uncontrolled Asthma in Patients with Asthma, Using Clinical Parameters and Early Treatment Response

BACKGROUND

Current level of asthma control can be easily assessed by validated instruments, but it is currently difficult to assess individuals' level of future risk.

OBJECTIVE

Develop, and validate, a risk prediction score for level of future risk, including patient characteristics and information on early treatment response.

METHODS

We used data of 304 adult patients with asthma from a 12-month primary care randomized controlled trial with 3-monthly assessments. With logistic regression we modeled the association between the level of future risk and patient characteristics including early treatment response. Future risk was defined as Asthma Control Questionnaire (ACQ) score of 1.5 or more at 12 months or the experience of at least 1 exacerbation during the final 6 months. We developed a risk prediction score on the basis of regression coefficients.

RESULTS

Performance of the risk prediction score improved, taking into account data on early treatment response (area under receiver-operating curve [AUROC] = 0.84) compared with a model containing only baseline characteristics (AUROC = 0.78). The score includes 6 easy-to-obtain predictors: sex, ACQ score and exacerbations in the previous year at baseline and at first follow-up, and smoking status and exacerbations in the previous 3 months (indicating early treatment response). External validation yielded an AUROC of 0.77. The risk prediction score classified patients into 3 risk groups: low (absolute risk, 11.7%), intermediate (47.0%), and high (72.7%).

CONCLUSIONS

We developed and externally validated a risk prediction score, quantifying both level of current asthma control and the guideline-defined future risk. Patients' individual risk can now be estimated in an easy way, as proposed but not specified, by asthma management guidelines.