This paper is in the following e-collection/theme issue:

Viewpoints on and Experiences with Digital Technologies in Health (64) Clinical Information and Decision Making (1314) Machine Learning (1370) Decision Support for Health Professionals (1127) Respiratory Medicine (59) Precision Medicine (63) Artificial Intelligence (1186)

Published on in Vol 12 (2024)

This is a member publication of University of Washington

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/56572, first published .
A Roadmap for Using Causal Inference and Machine Learning to Personalize Asthma Medication Selection

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

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

Authors of this article:

Flory L Nkoy1 Author Orcid Image ;   Bryan L Stone1 Author Orcid Image ;   Yue Zhang2, 3 Author Orcid Image ;   Gang Luo4 Author Orcid Image
Article Authors Cited by Tweetations (3) Metrics

    Viewpoint

    1Department of Pediatrics, University of Utah, Salt Lake City, UT, United States

    2Division of Epidemiology, Department of Internal Medicine, University of Utah, Salt Lake City, UT, United States

    3Division of Biostatistics, Department of Population Health Sciences, University of Utah, Salt Lake City, UT, United States

    4Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, WA, United States

    *these authors contributed equally

    Corresponding Author:

    Gang Luo, PhD

    Department of Biomedical Informatics and Medical Education

    University of Washington

    850 Republican Street, Building C

    Box 358047

    Seattle, WA, 98195

    United States

    Phone: 1 2062214596

    Fax:1 2062212671

    Email: gangluo@cs.wisc.edu


    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.

    JMIR Med Inform 2024;12:e56572

    doi:10.2196/56572

    Keywords

    asthma; causal inference; forecasting; machine learning; decision support; drug; drugs; pharmacy; pharmacies; pharmacology; pharmacotherapy; pharmaceutic; pharmaceutics; pharmaceuticals; pharmaceutical; medication; medications; medication selection; respiratory; pulmonary; forecast; ICS; inhaled corticosteroid; inhaler; inhaled; corticosteroid; corticosteroids; artificial intelligence; personalized; customized 


    Asthma is a chronic disease characterized by inflammation, narrowing, and hyperactivity of the airways causing shortness of breath, chest tightness, coughing, and wheezing [1]. Asthma affects about 25 million people in the United States [2]. In 2021, there were 9.8 million exacerbations of asthma symptoms (or asthma attacks) leading to over 980,000 emergency room (ER) visits and over 94,500 hospitalizations [2]. Asthma costs the US economy over US $80 billion in health care expenses each year, work and school absenteeism, and deaths [3].

    Inhaled corticosteroid (ICS) is a mainstay treatment for controlling asthma and preventing exacerbations in patients with persistent asthma [4] accounting for over 60% of people with asthma [5,6]. Many types of ICS drugs are used, either alone like fluticasone (Flovent, Arnuity, and Aller-flo), budesonide (Pulmicort, Entocort, and Rhinocort), mometasone (Asmanex), beclomethasone (Beclovent, Qvar, Vancenase, Beconase, Vanceril, and Qnasl), ciclesonide (Alvesco), and so forth, or in combination with a long-acting beta2 agonist like fluticasone/salmeterol (Advair), budesonide/formoterol (Symbicort), mometasone/formoterol (Dulera), and fluticasone/vilanterol (Breo), and so forth [4]. Regular use of appropriate ICSs improves asthma control and reduces airway inflammation, symptoms, exacerbations, ER visits, and inpatient stays [7-9].

    Despite the widespread use of ICSs, asthma control remains suboptimal in many people with asthma [10-13] including 44% of children and 60% of adults based on asthma exacerbations in the past year [14,15], 72% of patients based on asthma control test [10], 53% of children and 44% of adults based on asthma attacks in the past year [16], and 59% of children based on the 2007-2013 Medical Expenditure Panel Survey [17]. Suboptimal control leads to recurrent exacerbations, causes frequent ER visits and inpatient stays, and is projected to have an economic burden of US $963.5 billion over the next 20 years [18]. Suboptimal control is due to multiple factors [19-23] including (1) failure to recognize and act on early signs of declining control [24,25], (2) lack of self-management skills, (3) nonadherence to therapy [26], and (4) inappropriate ICS choice for the patient [27-32]. While interventions targeting other factors exist, less attention has been given to inappropriate ICS choice.

    Asthma is heterogeneous with variable profiles in terms of clinical presentations (phenotypes) and underlying mechanisms (endotypes) [33,34]. Molecular techniques have revealed a few phenotype and endotype relationships, allowing the categorization of asthma into two main groups (1) T-helper type 2 (Th2)-high (eg, atopic and late onset) and (2) Th2-low (eg, nonatopic, smoking-related, and obesity-related) [33,34]. It is known that within the 2 groups, there are many subgroups [33,35] with different biomarker expressions (eg, immunoglobulin E [IgE], fractional exhaled nitric oxide [FeNO], interleukin [IL]-4, IL-5, and IL-13) [36]. So far, only a few biomarkers have been characterized for use in clinical practice. Despite a few successes using biomarkers for targeted therapy, ICS choice, especially in the primary care setting, is largely by trial and error and many patients remain uncontrolled [37-42].

    Besides patient nonadherence and environmental factors, response to ICS treatment is affected by genetic variations in ICS metabolizing enzymes [43,44], regardless of whether the ICS is used alone or is combined with another asthma medication like a long-acting beta2 agonist. Single nucleotide polymorphisms in cap methyltransferase 1 (CMTR1), tripartite motif containing 24 (TRIM24), and membrane associated guanylate kinase, WW and PDZ domain containing 2 (MAGI2) genes were found to be associated with variability in asthma exacerbations [43]. Additional evidence supports that these genes also cause variability in ICS response [44]. Due to genetic variations in cytochrome P (CYP) 450 enzymes that metabolize over 80% of drugs including ICS, up to 50% of people with asthma have altered metabolism to certain ICSs [45-51] impacting asthma control [52,53]. CYP3A5*3/*3 and CYP3A4*22 genotypes were found to be linked to ICS response [54,55]. These studies provide evidence that genetic variations greatly affect ICS responsiveness, although the exact relationships between genetic variations and ICS response remain largely unknown [36,56,57]. Currently, many candidate genes are being studied, and pharmacogenetics has not yet reached routine clinical practice in asthma care.

    ICS choice for patients is often dictated by insurance reimbursement, organizational policies, or cost, leading to a one-size-fits-all approach [37-42]. Some insurers require patients to first fail on a cheaper ICS before authorizing a more expensive ICS [39]. Nonmedical switch due to preferred drug formulary change is common and leads to bad outcomes, with 70% of patients reporting more exacerbations after the switch [39]. Patients also often report that they tried a few different ICSs before ending up with the drug that gave them the most relief, with 60% reporting it was hard for their providers to find the effective drug [37-39]. Cycling through various ICSs delays the start of an effective ICS and is neither efficient nor cost-effective [39]. New strategies are needed to allow a faster and more efficient way to tailor ICS selection to each patient’s characteristics [36].

    While the biologic heterogeneity of asthma is vast, few, if any, biomarkers or genotypes can currently be used to systematically profile all patients with asthma and predict ICS response [36,58,59]. Readily available electronic health record (EHR) data collected during clinical care offer a low-cost, reliable, and more holistic way to profile all patients [36,60]. With a high accuracy of 87%-95% [36], machine learning models using EHR data have been used to profile patients in various areas, for example, to develop a phenotype for patients with Turner syndrome [61], identify low medication adherence profiles [62], find variable COVID-19 treatment response profiles [63], and predict hypertension treatment response [64]. Yet, while machine learning has helped find various asthma profiles [65-72], no prior study has predicted ICS response. Also, prior studies are mostly from single centers with small sample sizes and have not moved the needle of precision treatment for asthma [58,60].

    A decision support tool is greatly needed, especially in the primary care setting, to guide providers to select at the point of care the ICS that will most likely and quickly ease patient symptoms and improve asthma control. Forecasting which patient will respond well to which ICS is the first step toward creating this tool, but no prior study has predicted ICS response, forming a gap.

    To shift asthma care from one-size-fits-all to personalized care, improve outcomes, and save health care resources, we make three contributions in this paper, supplying a roadmap for future research: (1) we point out the above-mentioned need for creating a decision support tool to guide ICS selection; (2) we point out the above-mentioned gap in fulfilling this need; and (3) to close this gap, we outline an approach to create a machine learning model and apply causal inference to predict a patient’s ICS response in the next year based on the patient’s characteristics. We present the central ideas of this approach in the following sections.


    Overview of Our Approach

    We use EHR data from a large health care system to develop a machine learning model and apply casual inference to predict a patient’s ICS response based on the patient’s characteristics. As endotyping or genotyping all patients is infeasible, our model uses EHR data to characterize all patients and extract patterns that could mirror endotype or genotype. Our model is trained on historical data, and can then be applied to new patients to guide ICS selection during an initial or early encounter for asthma care. The optimal ICS choice identified by our approach can be either an ICS (generic name and dosage) alone or an ICS combined with another asthma medication like a long-acting beta2 agonist.

    Both pediatric and adult patients with asthma are treated by primary care providers (PCPs) who are mostly generalists and asthma specialists including allergists, immunologists, and pulmonologists. Large differences exist between PCPs and specialists in terms of knowledge, care patterns, and asthma outcomes, with asthma specialists adhering more often to guideline recommendations [73-76]. A greater difference exists between PCPs and specialists in controller medication use [76]. Compared to PCPs, asthma specialists tend to achieve better outcomes [77], including higher physical functioning [78], better patient-reported care [78], and fewer ER visits and inpatient stays [78-84]. As over 60% of people with asthma are cared for by PCPs [85], our machine learning model primarily targets PCPs, although asthma specialists could also benefit from this model.

    The asthma medication ratio (AMR) is the total number of units of asthma controller medications dispensed divided by the total number of units of asthma medications (controllers + relievers) dispensed [86,87]. Higher AMR (≥0.5) is associated with less oral corticosteroid use (a surrogate measure for asthma exacerbations), fewer ER visits and inpatient stays, and lower costs [87-89]. Lower AMR (<0.5) is associated with more exacerbations, ER visits, and inpatient stays [90,91]. Approved by Healthcare Effectiveness Data and Information Set (HEDIS) as a quality measure, AMR is widely used by health care systems [89]. AMR is a reliable reflection of asthma control and gives an accurate assessment of asthma exacerbation risk [92]. We use change in AMR as the prediction target of our model for predicting ICS response, as AMR can be calculated on all patients. In comparison, neither asthma control nor acute outcomes (eg, ER visits, inpatient stays, or oral corticosteroid use) is used as the prediction target, as the former is often missing in EHRs and the latter does not occur in all patients. An effective ICS will lead to less reliever use and increased AMR. An ineffective ICS will lead to more reliever use and reduced AMR. We formerly used EHR data to build accurate models to predict hospital use (ER visit or inpatient stay) for asthma [93-95]. We expect EHR data to have great predictive power for AMR, which is associated with hospital use for asthma [87-91]. Using the AMR can facilitate the dissemination of our approach across health care systems.

    We outline the individual steps of our approach in the following sections.

    Step 1: Building a Machine Learning Model to Predict a Patient’s ICS Response Defined by Changes in AMR

    We focus on patients with persistent asthma for whom ICSs are mainly used. We use the HEDIS case definition of persistent asthma [96,97], the already validated [98] and the most commonly used administrative data marker of persistent asthma [97]. A patient is deemed to have persistent asthma if in each of 2 consecutive years, the patient meets at least one of the following criteria: (1) at least 1 ER visit or inpatient stay with a principal diagnosis code of asthma (ICD-9 [International Classification of Diseases, Ninth Revision] 493.0x, 493.1x, 493.8x, 493.9x; ICD-10 [International Classification of Diseases, Tenth Revision] J45.x), (2) at least 2 asthma medication dispensing and at least 4 outpatient visits, each with a diagnosis code of asthma, and (3) at least 4 asthma medication dispensing. In the rest of this paper, we always use patients with asthma to refer to patients with persistent asthma. The prediction target or outcome is the amount of change in a patient’s AMR after 1 year. The AMR is computed over a 1-year period [86,87].

    We combine patient, air quality, and weather features computed on the raw variables to build the model to predict ICS response. Existing predictive models for asthma outcomes [93-95,99-110] rarely use air quality and weather variables, but these variables impact asthma outcomes [111-117] (eg, short-term exposure to air pollution, even if measured at the regional level, is associated with asthma exacerbations [113-117]). For each such variable, we examine multiple features (eg, mean, maximum, SD, and slope). We examine over 200 patient features listed in our papers’ [93-95] appendices and formerly used to predict hospital use for asthma, which is associated with AMR [87-91]. Several examples of these features are comorbidities, allergies, the number of the patient’s asthma-related ER visits in the prior 12 months, the total number of units of systemic corticosteroids ordered for the patient in the prior 12 months, and the number of primary or principal asthma diagnoses of the patient in the prior 12 months. We also use as features the patient’s current AMR computed over the prior 12 months [86,87], the generic name and the dosage of the ICS that the patient currently uses, and those of the long-acting beta2 agonist, leukotriene receptor antagonist, biologic or another asthma medication, if any, that is combined with the ICS.

    Step 2: Conducting Causal Machine Learning to Identify Optimal ICS Choice

    Our goal is to integrate machine learning and G-computation to develop a method to estimate the causal effects of various ICS choices on AMR for patients with specific characteristics. This causal machine learning method [118] processes large data sets by capturing complex nonlinear relationships between features, thereby revealing the cause-and-effect relationships between ICS choice and change in AMR. We use the machine learning model built in step 1. Using G-computation [119,120], an imputation-based causal inference method, we estimate the potential effects of hypothetical ICS choices with specific dosages on changes in AMR after 1 year. G-computation builds on the machine learning model of the outcome as a function of ICS indicators, ICS dosages, and other features to predict AMR outcomes under different counterfactual ICS choice scenarios. CIs are estimated through 10,000 bootstrap resampling with replacement [121].

    We apply causal machine learning to estimate the impact of ICS choices on patients with specific characteristics by averaging predicted AMR after 1 year for a given ICS and these characteristics across all participants. This estimation is contrasted with the averaged predicted outcome in the absence of any ICS choice. The ICS choice with the highest and statistically significant contrast estimation is identified as the optimal choice for patients with these characteristics. All hypotheses can be tested at a significance level of .05.

    Step 3: Assessing the Impact of Adding External Patient-Reported Asthma Control and ICS Use Adherence Data on the Model’s Predictions

    EHRs have limitations regarding patient-reported data with extra predictive power such as asthma control and ICS use adherence. For asthma, asthma control and ICS use adherence are critical variables, as (1) a patient’s asthma control fluctuates over time and drives the provider’s decision to prescribe or adjust ICSs and (2) ICS use adherence impacts the patient’s asthma control and helps assess whether the patient is actually responding to an ICS. However, despite their high predictive power for patient outcomes, these variables are not routinely collected or included in EHRs in clinical practice. At Intermountain Healthcare, the largest health care system in Utah, we pioneered the electronic AsthmaTracker, a mobile health (mHealth) app used weekly to assess, collect, and monitor patients’ asthma control and actual ICS use adherence [122]. Like most patient-reported data, these patient-reported variables have been collected on only a small proportion of patients with asthma. To date, 1380 patients with asthma have used the app and produced about 45,000 records of weekly asthma control scores and ICS use adherence data (eg, the ICS’ name and the number of days an ICS is actually used by the patient in that week). If we train a predictive model using EHR and patient-reported data limited to this small proportion of patients, the model will be inaccurate due to insufficient training data. Yet, for these patients, combining their patient-reported data with the outputs of a model built on all patients’ EHR data can help raise the prediction accuracy for them. To realize this, we propose the first method to combine external patient-reported data available on a small proportion of patients with the outputs of a model built on all patients’ EHR data to raise prediction accuracy for the small proportion of patients while maintaining prediction accuracy for the other patients.

    To illustrate how our method works, we consider the case that the model created in step 1 is built using Intermountain Healthcare EHR data. The weekly asthma control scores and ICS use adherence data collected from the 1380 patients with asthma are unused in step 1. Now we add features (eg, mean, SD, and slope) computed on patient-reported asthma control and ICS use adherence data to raise prediction accuracy for these patients. Among all patients with asthma, only 1% have asthma control and ICS use adherence data. We use the method shown in Figure 1 to combine the asthma control and ICS use adherence data from this small proportion of patients with the outputs of a model trained on EHR, air quality, and weather data of all patients with asthma. We start from the original model built in step 1. This model is reasonably accurate, as it is trained using EHR, air quality, and weather data of all patients with asthma and all features excluding those computed on asthma control and ICS use adherence data. For each patient with asthma control and ICS use adherence data, we apply the model to the patient, obtain a prediction result, and use this result as a feature. We then combine this new feature with the features computed on asthma control and ICS use adherence data to train a second model for these patients using their data. The second model is built upon and thus tends to be more accurate than the original model for these patients. The original model is used for the other patients. Our method is general, works for all kinds of features, and is not limited to any specific disease, prediction target, cohort, or health care system. Whenever a small proportion of patients have extra predictive variables, we could use this method to raise prediction accuracy for these patients while maintaining prediction accuracy for the other patients.

    For the patients with asthma control and ICS use adherence data, we compare the mean squared and the mean absolute prediction errors gained by the model built in step 1 and the second model built here. We expect adding asthma control and ICS use adherence data to the model to lower both prediction errors. The error drop rates help reveal the value of routinely collecting asthma control and ICS use adherence data in clinical care to lower prediction errors. Currently, such data are rarely collected.

    ‎
    Figure 1. Our method to raise prediction accuracy for the small proportion of patients with asthma and asthma control and ICS use adherence data while maintaining prediction accuracy for the other patients with asthma. EHR: electronic health record; ICS: inhaled corticosteroid.

    Principal Findings

    Besides the variables mentioned in the “Step 1: Building a machine learning model to predict a patient’s ICS response defined by changes in AMR” section, environmental variables beyond air quality and weather and many other factors can impact patient outcomes. Moreover, there are almost infinite possible features. For any first future study that one will do along the direction pointed out in this paper, a realistic goal is to show that using our methods can build decent models and improve asthma care rather than to exhaust all possible useful variables and features and obtain the theoretically highest possible model performance. Not accounting for all possible factors limits the generalizability of these models to medication selection for other diseases.

    We use the G-computation method to conduct causal inference. This method relies heavily on correctly specifying the predictive model for ICS response, including accurately identifying all relevant confounders and interactions and incorporating them into the model. Misspecification of the model can lead to biased estimated effects of various ICS choices on AMR. To address this issue, we can adopt several preventive strategies during model development. We engage with subject matter experts to ensure that the model includes all relevant variables and reflects the underlying process. To guide model development and help identify potential sources of bias, we construct a directed acyclic graph that lays out the relationships among the independent and dependent variables. We use machine learning techniques that provide flexible modeling approaches to capture complex relationships among variables. When reporting our findings, we keep transparent about the final model specification and the rationale behind our model building process. We believe using these strategies will mitigate the risk of model misspecification and strengthen the reliability of our estimated effects of various ICS choices on AMR.

    AMR is reported to be a reliable reflection of asthma control and of asthma exacerbation risk [92]. In a future study that we plan to do along the direction pointed out in this paper, we can use Intermountain Healthcare data to validate this relationship. Specifically, we use multivariable linear regression to assess the relationship between the AMR computed on EHR data and the patient’s asthma control level obtained from the external patient-reported data, while controlling for other factors. We expect to see a strong and positive association between the AMR and the patient’s asthma control level.

    When creating the model in step 1, we can include medication persistence measures computed on insurance claim data [123], such as the proportion of days covered for ICS, as features. However, this does not obviate the need to examine patient-reported ICS use adherence data in step 3. ICS persistence measures give information on the possession of ICS, but not on actual use of ICS. Each ICS persistence measure is computed at a coarse time granularity as an average value over a long period. In comparison, our patient-reported ICS use adherence data offer information on the actual use of ICS. The data are at a fine time granularity, with 1 set of values per week for a patient. This enables us to compute features on various patterns and trends that can be useful for making predictions.

    Conclusions

    In asthma care, ICS choice is largely by trial and error and often made by a one-size-fits-all approach with many patients not achieving optimal outcomes. In this paper, we point out the need for creating a decision support tool to guide ICS selection and a gap in fulfilling this 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. This supplies a roadmap for future research.

    Authors' Contributions

    FLN and GL are co-senior authors mainly responsible for the paper. They conceptualized the presentation approach, performed literature review, and wrote the paper. BLS provided feedback on various medical issues, contributed to conceptualizing the presentation, and revised the paper. YZ wrote the causal inference section. All authors read and approved the final paper.

    Conflicts of Interest

    GL is an editorial board member of JMIR AI. The other authors declare no conflicts of interest.

    1. Hashmi MF, Tariq M, Cataletto ME. Asthma. In: StatPearls. Treasure Island (FL). StatPearls Publishing; 2023.
    2. Most recent national asthma data. Centers for Disease Control and Prevention. 2023. URL: https://www.cdc.gov/asthma/most_recent_national_asthma_data.htm [accessed 2024-01-22]
    3. Nurmagambetov T, Kuwahara R, Garbe P. The economic burden of asthma in the United States, 2008-2013. Ann Am Thorac Soc. 2018;15(3):348-356. [FREE Full text] [CrossRef] [Medline]
    4. Inhaled corticosteroids. American Academy of Allergy, Asthma & Immunology. 2023. URL: https://www.aaaai.org/tools-for-the-public/drug-guide/inhaled-corticosteroids [accessed 2024-01-22]
    5. Asthma severity among children with current asthma. Centers for Disease Control and Prevention. 2023. URL: https://archive.cdc.gov/#/details?url=https://www.cdc.gov/asthma/asthma_stats/severity_child.htm [accessed 2024-01-22]
    6. Asthma severity among adults with current asthma. Centers for Disease Control and Prevention. 2023. URL: https://archive.cdc.gov/#/details?url=https://www.cdc.gov/asthma/asthma_stats/severity_adult.htm [accessed 2024-01-22]
    7. Averell CM, Laliberté F, Germain G, Duh MS, Rousculp MD, MacKnight SD, et al. Impact of adherence to treatment with inhaled corticosteroids/long-acting β-agonists on asthma outcomes in the United States. Ther Adv Respir Dis. 2022;16:17534666221116997. [FREE Full text] [CrossRef] [Medline]
    8. Cardet JC, Papi A, Reddel HK. "As-needed" inhaled corticosteroids for patients with asthma. J Allergy Clin Immunol Pract. 2023;11(3):726-734. [FREE Full text] [CrossRef] [Medline]
    9. Sadatsafavi M, Lynd LD, De Vera MA, Zafari Z, FitzGerald JM. One-year outcomes of inhaled controller therapies added to systemic corticosteroids after asthma-related hospital discharge. Respir Med. 2015;109(3):320-328. [FREE Full text] [CrossRef] [Medline]
    10. George M, Balantac Z, Gillette C, Farooqui N, Tervonen T, Thomas C, et al. Suboptimal control of asthma among diverse patients: a US mixed methods focus group study. J Asthma Allergy. 2022;15:1511-1526. [FREE Full text] [CrossRef] [Medline]
    11. Sullivan PW, Ghushchyan V, Kavati A, Navaratnam P, Friedman HS, Ortiz B. Trends in asthma control, treatment, health care utilization, and expenditures among children in the United States by place of residence: 2003-2014. J Allergy Clin Immunol Pract. 2019;7(6):1835-1842.e2. [CrossRef] [Medline]
    12. Zhang S, White J, Hunter AG, Hinds D, Fowler A, Gardiner F, et al. Suboptimally controlled asthma in patients treated with inhaled ICS/LABA: prevalence, risk factors, and outcomes. NPJ Prim Care Respir Med. 2023;33(1):19. [FREE Full text] [CrossRef] [Medline]
    13. Nurmagambetov TA, Krishnan JA. What will uncontrolled asthma cost in the United States? Am J Respir Crit Care Med. 2019;200(9):1077-1078. [FREE Full text] [CrossRef] [Medline]
    14. Uncontrolled asthma among children with current asthma, 2018-2020. Centers for Disease Control and Prevention. 2021. URL: https://tinyurl.com/ycdz2mp2 [accessed 2024-01-22]
    15. Uncontrolled asthma among adults, 2019. Centers for Disease Control and Prevention. 2020. URL: https:/​/archive.​cdc.gov/​#/​details?url=https:/​/www.​cdc.gov/​asthma/​asthma_stats/​uncontrolled-asthma-adults-2019.​htm [accessed 2024-01-22]
    16. Pate CA, Zahran HS, Qin X, Johnson C, Hummelman E, Malilay J. Asthma surveillance—United States, 2006-2018. MMWR Surveill Summ. 2021;70(5):1-32. [FREE Full text] [CrossRef] [Medline]
    17. Sullivan PW, Ghushchyan V, Navaratnam P, Friedman HS, Kavati A, Ortiz B, et al. National prevalence of poor asthma control and associated outcomes among school-aged children in the United States. J Allergy Clin Immunol Pract. 2018;6(2):536-544.e1. [CrossRef] [Medline]
    18. Yaghoubi M, Adibi A, Safari A, FitzGerald JM, Sadatsafavi M. The projected economic and health burden of uncontrolled asthma in the United States. Am J Respir Crit Care Med. 2019;200(9):1102-1112. [FREE Full text] [CrossRef] [Medline]
    19. Centers for Disease Control and Prevention (CDC). Asthma hospitalizations and readmissions among children and young adults--Wisconsin, 1991-1995. MMWR Morb Mortal Wkly Rep. 1997;46(31):726-729. [FREE Full text] [Medline]
    20. Li D, German D, Lulla S, Thomas RG, Wilson SR. Prospective study of hospitalization for asthma. A preliminary risk factor model. Am J Respir Crit Care Med. 1995;151(3 Pt 1):647-655. [CrossRef] [Medline]
    21. Crane J, Pearce N, Burgess C, Woodman K, Robson B, Beasley R. Markers of risk of asthma death or readmission in the 12 months following a hospital admission for asthma. Int J Epidemiol. 1992;21(4):737-744. [CrossRef] [Medline]
    22. Mitchell EA, Bland JM, Thompson JM. Risk factors for readmission to hospital for asthma in childhood. Thorax. 1994;49(1):33-36. [FREE Full text] [CrossRef] [Medline]
    23. Vargas PA, Perry TT, Robles E, Jo CH, Simpson PM, Magee JM, et al. Relationship of body mass index with asthma indicators in head start children. Ann Allergy Asthma Immunol. 2007;99(1):22-28. [CrossRef] [Medline]
    24. Barnes PJ. Achieving asthma control. Curr Med Res Opin. 2005;21(Suppl 4):S5-S9. [CrossRef] [Medline]
    25. Bloomberg GR, Banister C, Sterkel R, Epstein J, Bruns J, Swerczek L, et al. Socioeconomic, family, and pediatric practice factors that affect level of asthma control. Pediatrics. 2009;123(3):829-835. [FREE Full text] [CrossRef] [Medline]
    26. Bateman ED, Frith LF, Braunstein GL. Achieving guideline-based asthma control: does the patient benefit? Eur Respir J. 2002;20(3):588-595. [FREE Full text] [CrossRef] [Medline]
    27. Chapman KR, Boulet LP, Rea RM, Franssen E. Suboptimal asthma control: prevalence, detection and consequences in general practice. Eur Respir J. 2008;31(2):320-325. [FREE Full text] [CrossRef] [Medline]
    28. Rabe KF, Adachi M, Lai CK, Soriano JB, Vermeire PA, Weiss KB, et al. Worldwide severity and control of asthma in children and adults: the global asthma insights and reality surveys. J Allergy Clin Immunol. 2004;114(1):40-47. [FREE Full text] [CrossRef] [Medline]
    29. National Asthma Education and Prevention Program. Expert Panel Report 3 (EPR-3): guidelines for the diagnosis and management of asthma-summary report 2007. J Allergy Clin Immunol. 2007;120(Suppl 5):S94-S138. [CrossRef] [Medline]
    30. Stempel DA, McLaughin TP, Stanford RH, Fuhlbrigge AL. Patterns of asthma control: a 3-year analysis of patient claims. J Allergy Clin Immunol. 2005;115(5):935-939. [FREE Full text] [CrossRef] [Medline]
    31. Cukovic L, Sutherland E, Sein S, Fuentes D, Fatima H, Oshana A, et al. An evaluation of outpatient pediatric asthma prescribing patterns in the United States. Int J Sci Res Arch. 2023;9(1):344-349. [FREE Full text] [CrossRef]
    32. Belhassen M, Nibber A, Van Ganse E, Ryan D, Langlois C, Appiagyei F, et al. Inappropriate asthma therapy-a tale of two countries: a parallel population-based cohort study. NPJ Prim Care Respir Med. 2016;26:16076. [FREE Full text] [CrossRef] [Medline]
    33. McIntyre AP, Viswanathan RK. Phenotypes and endotypes in asthma. Adv Exp Med Biol. 2023;1426:119-142. [CrossRef] [Medline]
    34. Kuruvilla ME, Lee FE, Lee GB. Understanding asthma phenotypes, endotypes, and mechanisms of disease. Clin Rev Allergy Immunol. 2019;56(2):219-233. [FREE Full text] [CrossRef] [Medline]
    35. Salter B, Lacy P, Mukherjee M. Biologics in asthma: a molecular perspective to precision medicine. Front Pharmacol. 2021;12:793409. [FREE Full text] [CrossRef] [Medline]
    36. van der Burg N, Tufvesson E. Is asthma's heterogeneity too vast to use traditional phenotyping for modern biologic therapies? Respir Med. 2023;212:107211. [CrossRef] [Medline]
    37. A study of the qualitative impact of non-medical switching. Alliance for Patient Access. 2019. URL: https://tinyurl.com/2vxwks83 [accessed 2024-01-22]
    38. Cost-motivated treatment changes & non-medical switching: commercial health plans analysis. Alliance for Patient Access. 2017. URL: https://tinyurl.com/424dy3xz [accessed 2024-01-22]
    39. Collins S. Asthma meds, insurers, and the practice of non-medical drug switching. HealthCentral. 2023. URL: https://www.healthcentral.com/condition/asthma/what-you-need-to-know-about-asthma-meds [accessed 2024-01-22]
    40. Landhuis E. OTC budesonide-formoterol for asthma could save lives, money. Medscape Medical News. 2023. URL: https://www.medscape.com/viewarticle/989099 [accessed 2024-01-22]
    41. Modglin L. How much do inhalers cost? SingleCare. 2022. URL: https://www.singlecare.com/blog/asthma-inhalers-price-list [accessed 2024-01-22]
    42. Gibson PG, McDonald VM, Thomas D. Treatable traits, combination inhaler therapy and the future of asthma management. Respirology. 2023;28(9):828-840. [FREE Full text] [CrossRef] [Medline]
    43. Dahlin A, Denny J, Roden DM, Brilliant MH, Ingram C, Kitchner TE, et al. CMTR1 is associated with increased asthma exacerbations in patients taking inhaled corticosteroids. Immun Inflamm Dis. 2015;3(4):350-359. [FREE Full text] [CrossRef] [Medline]
    44. Keskin O, Farzan N, Birben E, Akel H, Karaaslan C, Maitland-van der Zee AH, et al. Genetic associations of the response to inhaled corticosteroids in asthma: a systematic review. Clin Transl Allergy. 2019;9:2. [FREE Full text] [CrossRef] [Medline]
    45. Delgado-Dolset MI, Obeso D, Rodríguez-Coira J, Tarin C, Tan G, Cumplido JA, et al. Understanding uncontrolled severe allergic asthma by integration of omic and clinical data. Allergy. 2022;77(6):1772-1785. [FREE Full text] [CrossRef] [Medline]
    46. Liu Q, Hua L, Bao C, Kong L, Hu J, Liu C, et al. Inhibition of spleen tyrosine kinase restores glucocorticoid sensitivity to improve steroid-resistant asthma. Front Pharmacol. 2022;13:885053. [FREE Full text] [CrossRef] [Medline]
    47. Cardoso-Vigueros C, von Blumenthal T, Rückert B, Rinaldi AO, Tan G, Dreher A, et al. Leukocyte redistribution as immunological biomarker of corticosteroid resistance in severe asthma. Clin Exp Allergy. 2022;52(10):1183-1194. [FREE Full text] [CrossRef] [Medline]
    48. Liang H, Zhang X, Ma Z, Sun Y, Shu C, Zhu Y, et al. Association of CYP3A5 gene polymorphisms and amlodipine-induced peripheral edema in Chinese Han patients with essential hypertension. Pharmgenomics Pers Med. 2021;14:189-197. [FREE Full text] [CrossRef] [Medline]
    49. Wang SB, Huang T. The early detection of asthma based on blood gene expression. Mol Biol Rep. 2019;46(1):217-223. [CrossRef] [Medline]
    50. Roberts JK, Moore CD, Romero EG, Ward RM, Yost GS, Reilly CA. Regulation of CYP3A genes by glucocorticoids in human lung cells. F1000Res. 2013;2:173. [FREE Full text] [CrossRef] [Medline]
    51. Moore CD, Roberts JK, Orton CR, Murai T, Fidler TP, Reilly CA, et al. Metabolic pathways of inhaled glucocorticoids by the CYP3A enzymes. Drug Metab Dispos. 2013;41(2):379-389. [FREE Full text] [CrossRef] [Medline]
    52. Roche N, Garcia G, de Larrard A, Cancalon C, Bénard S, Perez V, et al. Real-life impact of uncontrolled severe asthma on mortality and healthcare use in adolescents and adults: findings from the retrospective, observational RESONANCE study in France. BMJ Open. 2022;12(8):e060160. [FREE Full text] [CrossRef] [Medline]
    53. Munoz-Cano R, Torrego A, Bartra J, Sanchez-Lopez J, Palomino R, Picado C, et al. Follow-up of patients with uncontrolled asthma: clinical features of asthma patients according to the level of control achieved (the COAS study). Eur Respir J. 2017;49(3):1501885. [FREE Full text] [CrossRef] [Medline]
    54. Stockmann C, Reilly CA, Fassl B, Gaedigk R, Nkoy F, Stone B, et al. Effect of CYP3A5*3 on asthma control among children treated with inhaled beclomethasone. J Allergy Clin Immunol. 2015;136(2):505-507. [FREE Full text] [CrossRef] [Medline]
    55. Stockmann C, Fassl B, Gaedigk R, Nkoy F, Uchida DA, Monson S, et al. Fluticasone propionate pharmacogenetics: CYP3A4*22 polymorphism and pediatric asthma control. J Pediatr. 2013;162(6):1222-1227, 1227.e1-2. [FREE Full text] [CrossRef] [Medline]
    56. Smolnikova MV, Kasparov EW, Malinchik MA, Kopylova KV. Genetic markers of children asthma: predisposition to disease course variants. Vavilovskii Zhurnal Genet Selektsii. 2023;27(4):393-400. [FREE Full text] [CrossRef] [Medline]
    57. Kim HK, Kang JO, Lim JE, Ha TW, Jung HU, Lee WJ, et al. Genetic differences according to onset age and lung function in asthma: a cluster analysis. Clin Transl Allergy. 2023;13(7):e12282. [FREE Full text] [CrossRef] [Medline]
    58. Mohan A, Lugogo NL. Phenotyping, precision medicine, and asthma. Semin Respir Crit Care Med. 2022;43(5):739-751. [CrossRef] [Medline]
    59. Casanova S, Ahmed E, Bourdin A. Definition, phenotyping of severe asthma, including cluster analysis. Adv Exp Med Biol. 2023;1426:239-252. [CrossRef] [Medline]
    60. Singhal P, Tan ALM, Drivas TG, Johnson KB, Ritchie MD, Beaulieu-Jones BK. Opportunities and challenges for biomarker discovery using electronic health record data. Trends Mol Med. 2023;29(9):765-776. [CrossRef] [Medline]
    61. Huang SD, Bamba V, Bothwell S, Fechner PY, Furniss A, Ikomi C, et al. Development and validation of a computable phenotype for turner syndrome utilizing electronic health records from a national pediatric network. Am J Med Genet A. 2024;194(4):e63495. [CrossRef] [Medline]
    62. Blecker S, Schoenthaler A, Martinez TR, Belli HM, Zhao Y, Wong C, et al. Leveraging electronic health record technology and team care to address medication adherence: protocol for a cluster randomized controlled trial. JMIR Res Protoc. 2023;12:e47930. [FREE Full text] [CrossRef] [Medline]
    63. Verhoef PA, Spicer AB, Lopez-Espina C, Bhargava A, Schmalz L, Sims MD, et al. Analysis of protein biomarkers from hospitalized COVID-19 patients reveals severity-specific signatures and two distinct latent profiles with differential responses to corticosteroids. Crit Care Med. 2023;51(12):1697-1705. [CrossRef] [Medline]
    64. Hu Y, Huerta J, Cordella N, Mishuris RG, Paschalidis IC. Personalized hypertension treatment recommendations by a data-driven model. BMC Med Inform Decis Mak. 2023;23(1):44. [FREE Full text] [CrossRef] [Medline]
    65. Cottrill KA, Rad MG, Ripple MJ, Stephenson ST, Mohammad AF, Tidwell M, et al. Cluster analysis of plasma cytokines identifies two unique endotypes of children with asthma in the pediatric intensive care unit. Sci Rep. 2023;13(1):3521. [FREE Full text] [CrossRef] [Medline]
    66. Horne EMF, McLean S, Alsallakh MA, Davies GA, Price DB, Sheikh A, et al. Defining clinical subtypes of adult asthma using electronic health records: analysis of a large UK primary care database with external validation. Int J Med Inform. 2023;170:104942. [FREE Full text] [CrossRef] [Medline]
    67. Ilmarinen P, Julkunen-Iivari A, Lundberg M, Luukkainen A, Nuutinen M, Karjalainen J, et al. Cluster analysis of Finnish population-based adult-onset asthma patients. J Allergy Clin Immunol Pract. 2023;11(10):3086-3096. [FREE Full text] [CrossRef] [Medline]
    68. Imoto S, Suzukawa M, Fukutomi Y, Kobayashi N, Taniguchi M, Nagase T, et al. Phenotype characterization and biomarker evaluation in moderate to severe type 2-high asthma. Asian Pac J Allergy Immunol. 2023.:1-14. [FREE Full text] [CrossRef] [Medline]
    69. Kim MA, Shin SW, Park JS, Uh ST, Chang HS, Bae DJ, et al. Clinical characteristics of exacerbation-prone adult asthmatics identified by cluster analysis. Allergy Asthma Immunol Res. 2017;9(6):483-490. [FREE Full text] [CrossRef] [Medline]
    70. Matabuena M, Salgado FJ, Nieto-Fontarigo JJ, Álvarez-Puebla MJ, Arismendi E, Barranco P, et al. Identification of asthma phenotypes in the Spanish MEGA cohort study using cluster analysis. Arch Bronconeumol. 2023;59(4):223-231. [FREE Full text] [CrossRef] [Medline]
    71. Ngo SY, Venter C, Anderson WC3, Picket K, Zhang H, Arshad SH, et al. Clinical features and later prognosis of replicable early-life wheeze clusters from two birth cohorts 12 years apart. Pediatr Allergy Immunol. 2023;34(7):e13999. [FREE Full text] [CrossRef] [Medline]
    72. Zhan W, Wu F, Zhang Y, Lin L, Li W, Luo W, et al. Identification of cough-variant asthma phenotypes based on clinical and pathophysiologic data. J Allergy Clin Immunol. 2023;152(3):622-632. [CrossRef] [Medline]
    73. Cloutier MM, Akinbami LJ, Salo PM, Schatz M, Simoneau T, Wilkerson JC, et al. Use of national asthma guidelines by allergists and pulmonologists: a national survey. J Allergy Clin Immunol Pract. 2020;8(9):3011-3020.e2. [FREE Full text] [CrossRef] [Medline]
    74. Vollmer WM, O'Hollaren M, Ettinger KM, Stibolt T, Wilkins J, Buist AS, et al. Specialty differences in the management of asthma. A cross-sectional assessment of allergists' patients and generalists' patients in a large HMO. Arch Intern Med. 1997;157(11):1201-1208. [Medline]
    75. Cloutier MM, Salo PM, Akinbami LJ, Cohn RD, Wilkerson JC, Diette GB, et al. Clinician agreement, self-efficacy, and adherence with the guidelines for the diagnosis and management of asthma. J Allergy Clin Immunol Pract. 2018;6(3):886-894.e4. [FREE Full text] [CrossRef] [Medline]
    76. Diette GB, Skinner EA, Nguyen TT, Markson L, Clark BD, Wu AW. Comparison of quality of care by specialist and generalist physicians as usual source of asthma care for children. Pediatrics. 2001;108(2):432-437. [CrossRef] [Medline]
    77. Rosman Y, Hornik-Lurie T, Meir-Shafrir K, Lachover-Roth I, Cohen-Engler A, Confino-Cohen R. The effect of asthma specialist intervention on asthma control among adults. World Allergy Organ J. 2022;15(11):100712. [FREE Full text] [CrossRef] [Medline]
    78. Wu AW, Young Y, Skinner EA, Diette GB, Huber M, Peres A, et al. Quality of care and outcomes of adults with asthma treated by specialists and generalists in managed care. Arch Intern Med. 2001;161(21):2554-2560. [FREE Full text] [CrossRef] [Medline]
    79. Erickson S, Tolstykh I, Selby JV, Mendoza G, Iribarren C, Eisner MD. The impact of allergy and pulmonary specialist care on emergency asthma utilization in a large managed care organization. Health Serv Res. 2005;40(5 Pt 1):1443-1465. [FREE Full text] [CrossRef] [Medline]
    80. Zeiger RS, Heller S, Mellon MH, Wald J, Falkoff R, Schatz M. Facilitated referral to asthma specialist reduces relapses in asthma emergency room visits. J Allergy Clin Immunol. 1991;87(6):1160-1168. [CrossRef] [Medline]
    81. Mahr TA, Evans R3. Allergist influence on asthma care. Ann Allergy. 1993;71(2):115-120. [Medline]
    82. Schatz M, Zeiger RS, Mosen D, Apter AJ, Vollmer WM, Stibolt TB, et al. Improved asthma outcomes from allergy specialist care: a population-based cross-sectional analysis. J Allergy Clin Immunol. 2005;116(6):1307-1313. [FREE Full text] [CrossRef] [Medline]
    83. Wechsler ME. Managing asthma in primary care: putting new guideline recommendations into context. Mayo Clin Proc. 2009;84(8):707-717. [FREE Full text] [CrossRef] [Medline]
    84. Cooper S, Rahme E, Tse SM, Grad R, Dorais M, Li P. Are primary care and continuity of care associated with asthma-related acute outcomes amongst children? A retrospective population-based study. BMC Prim Care. 2022;23(1):5. [FREE Full text] [CrossRef] [Medline]
    85. Akinbami LJ, Salo PM, Cloutier MM, Wilkerson JC, Elward KS, Mazurek JM, et al. Primary care clinician adherence with asthma guidelines: the National Asthma Survey of Physicians. J Asthma. 2020;57(5):543-555. [FREE Full text] [CrossRef] [Medline]
    86. HEDIS measures and technical resources: asthma medication ratio (AMR). NCQA. 2023. URL: https:/​/www.​ncqa.org/​hedis/​measures/​medication-management-for-people-with-asthma-and-asthma-medication-ratio [accessed 2024-01-22]
    87. Schatz M, Zeiger RS, Vollmer WM, Mosen D, Mendoza G, Apter AJ, et al. The controller-to-total asthma medication ratio is associated with patient-centered as well as utilization outcomes. Chest. 2006;130(1):43-50. [CrossRef] [Medline]
    88. Kim Y, Parrish KM, Pirritano M, Moonie S. A higher asthma medication ratio (AMR) predicts a decrease in ED visits among African American and Hispanic children. J Asthma. 2023;60(7):1428-1437. [CrossRef] [Medline]
    89. Luskin AT, Antonova EN, Broder MS, Chang E, Raimundo K, Solari PG. Patient outcomes, health care resource use, and costs associated with high versus low HEDIS asthma medication ratio. J Manag Care Spec Pharm. 2017;23(11):1117-1124. [FREE Full text] [CrossRef] [Medline]
    90. Andrews AL, Simpson AN, Basco WTJ, Teufel RJ2. Asthma medication ratio predicts emergency department visits and hospitalizations in children with asthma. Medicare Medicaid Res Rev. 2013;3(4):mmrr.003.04.a05. [FREE Full text] [CrossRef] [Medline]
    91. Andrews AL, Brinton DL, Simpson KN, Simpson AN. A longitudinal examination of the asthma medication ratio in children with Medicaid. J Asthma. 2020;57(10):1083-1091. [FREE Full text] [CrossRef] [Medline]
    92. Andrews AL, Brinton D, Simpson KN, Simpson AN. A longitudinal examination of the asthma medication ratio in children. Am J Manag Care. 2018;24(6):294-300. [FREE Full text] [Medline]
    93. Tong Y, Messinger AI, Wilcox AB, Mooney SD, Davidson GH, Suri P, et al. Forecasting future asthma hospital encounters of patients with asthma in an academic health care system: predictive model development and secondary analysis study. J Med Internet Res. 2021;23(4):e22796. [FREE Full text] [CrossRef] [Medline]
    94. Luo G, He S, Stone BL, Nkoy FL, Johnson MD. Developing a model to predict hospital encounters for asthma in asthmatic patients: secondary analysis. JMIR Med Inform. 2020;8(1):e16080. [FREE Full text] [CrossRef] [Medline]
    95. Luo G, Nau CL, Crawford WW, Schatz M, Zeiger RS, Rozema E, et al. Developing a predictive model for asthma-related hospital encounters in patients with asthma in a large, integrated health care system: secondary analysis. JMIR Med Inform. 2020;8(11):e22689. [FREE Full text] [CrossRef] [Medline]
    96. Mosen DM, Macy E, Schatz M, Mendoza G, Stibolt TB, McGaw J, et al. How well do the HEDIS asthma inclusion criteria identify persistent asthma? Am J Manag Care. 2005;11(10):650-654. [FREE Full text] [Medline]
    97. Schatz M, Zeiger RS. Improving asthma outcomes in large populations. J Allergy Clin Immunol. 2011;128(2):273-277. [FREE Full text] [CrossRef] [Medline]
    98. Schatz M, Zeiger RS, Yang SJ, Chen W, Crawford WW, Sajjan SG, et al. Persistent asthma defined using HEDIS versus survey criteria. Am J Manag Care. 2010;16(11):e281-e288. [FREE Full text] [Medline]
    99. Schatz M, Nakahiro R, Jones CH, Roth RM, Joshua A, Petitti D. Asthma population management: development and validation of a practical 3-level risk stratification scheme. Am J Manag Care. 2004;10(1):25-32. [FREE Full text] [Medline]
    100. Schatz M, Cook EF, Joshua A, Petitti D. Risk factors for asthma hospitalizations in a managed care organization: development of a clinical prediction rule. Am J Manag Care. 2003;9(8):538-547. [FREE Full text] [Medline]
    101. Lieu TA, Quesenberry CP, Sorel ME, Mendoza GR, Leong AB. Computer-based models to identify high-risk children with asthma. Am J Respir Crit Care Med. 1998;157(4 Pt 1):1173-1180. [FREE Full text] [CrossRef] [Medline]
    102. Lieu TA, Capra AM, Quesenberry CP, Mendoza GR, Mazar M. Computer-based models to identify high-risk adults with asthma: is the glass half empty of half full? J Asthma. 1999;36(4):359-370. [CrossRef] [Medline]
    103. Forno E, Fuhlbrigge A, Soto-Quirós ME, Avila L, Raby BA, Brehm J, et al. Risk factors and predictive clinical scores for asthma exacerbations in childhood. Chest. 2010;138(5):1156-1165. [FREE Full text] [CrossRef] [Medline]
    104. Loymans RJB, Debray TPA, Honkoop PJ, Termeer EH, Snoeck-Stroband JB, Schermer TRJ, et al. Exacerbations in adults with asthma: a systematic review and external validation of prediction models. J Allergy Clin Immunol Pract. 2018;6(6):1942-1952.e15. [FREE Full text] [CrossRef] [Medline]
    105. Eisner MD, Yegin A, Trzaskoma B. Severity of asthma score predicts clinical outcomes in patients with moderate to severe persistent asthma. Chest. 2012;141(1):58-65. [CrossRef] [Medline]
    106. Sato R, Tomita K, Sano H, Ichihashi H, Yamagata S, Sano A, et al. The strategy for predicting future exacerbation of asthma using a combination of the asthma control test and lung function test. J Asthma. 2009;46(7):677-682. [CrossRef] [Medline]
    107. Yurk RA, Diette GB, Skinner EA, Dominici F, Clark RD, Steinwachs DM, et al. Predicting patient-reported asthma outcomes for adults in managed care. Am J Manag Care. 2004;10(5):321-328. [FREE Full text] [Medline]
    108. Xiang Y, Ji H, Zhou Y, Li F, Du J, Rasmy L, et al. Asthma exacerbation prediction and risk factor analysis based on a time-sensitive, attentive neural network: retrospective cohort study. J Med Internet Res. 2020;22(7):e16981. [FREE Full text] [CrossRef] [Medline]
    109. Miller MK, Lee JH, Blanc PD, Pasta DJ, Gujrathi S, Barron H, et al. TENOR risk score predicts healthcare in adults with severe or difficult-to-treat asthma. Eur Respir J. 2006;28(6):1145-1155. [FREE Full text] [CrossRef] [Medline]
    110. Loymans RJ, Honkoop PJ, Termeer EH, Snoeck-Stroband JB, Assendelft WJ, Schermer TR, et al. Identifying patients at risk for severe exacerbations of asthma: development and external validation of a multivariable prediction model. Thorax. 2016;71(9):838-846. [FREE Full text] [CrossRef] [Medline]
    111. Schatz M. Predictors of asthma control: what can we modify? Curr Opin Allergy Clin Immunol. 2012;12(3):263-268. [CrossRef] [Medline]
    112. Dick S, Doust E, Cowie H, Ayres JG, Turner S. Associations between environmental exposures and asthma control and exacerbations in young children: a systematic review. BMJ Open. 2014;4(2):e003827. [FREE Full text] [CrossRef] [Medline]
    113. Schwartz J, Slater D, Larson TV, Pierson WE, Koenig JQ. Particulate air pollution and hospital emergency room visits for asthma in Seattle. Am Rev Respir Dis. 1993;147(4):826-831. [CrossRef] [Medline]
    114. Romieu I, Meneses F, Sienra-Monge JJ, Huerta J, Ruiz Velasco S, White MC, et al. Effects of urban air pollutants on emergency visits for childhood asthma in Mexico City. Am J Epidemiol. 1995;141(6):546-553. [CrossRef] [Medline]
    115. Lu P, Zhang Y, Lin J, Xia G, Zhang W, Knibbs LD, et al. Multi-city study on air pollution and hospital outpatient visits for asthma in China. Environ Pollut. 2020;257:113638. [CrossRef] [Medline]
    116. Liu Y, Pan J, Zhang H, Shi C, Li G, Peng Z, et al. Short-term exposure to ambient air pollution and asthma mortality. Am J Respir Crit Care Med. 2019;200(1):24-32. [FREE Full text] [CrossRef] [Medline]
    117. Vagaggini B, Taccola M, Cianchetti S, Carnevali S, Bartoli ML, Bacci E, et al. Ozone exposure increases eosinophilic airway response induced by previous allergen challenge. Am J Respir Crit Care Med. 2002;166(8):1073-1077. [FREE Full text] [CrossRef] [Medline]
    118. Sanchez P, Voisey JP, Xia T, Watson HI, O'Neil AQ, Tsaftaris SA. Causal machine learning for healthcare and precision medicine. R Soc Open Sci. 2022;9(8):220638. [FREE Full text] [CrossRef] [Medline]
    119. Robins JM. A new approach to causal inference in mortality studies with a sustained exposure period—application to control of the healthy worker survivor effect. Math Model. 1986;7(9-12):1393-1512. [FREE Full text] [CrossRef]
    120. Snowden JM, Rose S, Mortimer KM. Implementation of G-computation on a simulated data set: demonstration of a causal inference technique. Am J Epidemiol. 2011;173(7):731-738. [FREE Full text] [CrossRef] [Medline]
    121. Efron B. Bootstrap methods: another look at the Jackknife. Ann Stat. 1979;7(1):1-26. [FREE Full text] [CrossRef]
    122. Nkoy FL, Stone BL, Fassl BA, Uchida DA, Koopmeiners K, Halbern S, et al. Longitudinal validation of a tool for asthma self-monitoring. Pediatrics. 2013;132(6):e1554-e1561. [FREE Full text] [CrossRef] [Medline]
    123. Anghel LA, Farcas AM, Oprean RN. An overview of the common methods used to measure treatment adherence. Med Pharm Rep. 2019;92(2):117-122. [FREE Full text] [CrossRef] [Medline]

    ‎
    AMR: asthma medication ratio
    CMTR1: cap methyltransferase 1
    CYP: cytochrome P
    EHR: electronic health record
    ER: emergency room
    FeNO: fractional exhaled nitric oxide
    HEDIS: Healthcare Effectiveness Data and Information Set
    ICD-9: International Classification of Diseases, Ninth Revision
    ICD-10: International Classification of Diseases, Tenth Revision
    ICS: inhaled corticosteroid
    IgE: immunoglobulin E
    IL: interleukin
    MAGI2: membrane associated guanylate kinase, WW and PDZ domain containing 2
    mHealth: mobile health
    PCP: primary care provider
    Th2: T-helper type 2
    TRIM24: tripartite motif containing 24

    Edited by A Benis; submitted 24.01.24; peer-reviewed by H Tibble, A Kaplan; comments to author 01.03.24; revised version received 12.03.24; accepted 25.03.24; published 17.04.24.

    Copyright

    ©Flory L Nkoy, Bryan L Stone, Yue Zhang, Gang Luo. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 17.04.2024.

    This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR Medical Informatics, is properly cited. The complete bibliographic information, a link to the original publication on https://medinform.jmir.org/, as well as this copyright and license information must be included.