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

Luo, Gang; He, Shan; Stone, Bryan L.; Nkoy, Flory L.; Johnson, Michael D.

doi:10.2196/16080

Cited by 44 publications

(90 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For predicting asthma hospital visits, our UWM model [24] reached a higher area under the receiver operating characteristic curve on UWM data than our Intermountain Healthcare model on Intermountain Healthcare data [23]. Our prior automated explanation paper [25] points out that the harder the outcome is to predict, the smaller the lower limit of commonality needs to be.…”

Section: G Parameter Settingmentioning

confidence: 99%

See 1 more Smart Citation

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

2020

Self Cite

View full text Add to dashboard Cite

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. INDEX TERMS Asthma, automated explanation, extreme gradient boosting, machine learning, patient care management, predictive model. LIST OF ABBREVIATIONS ED Emergency department. ICD-9 International Classification of Diseases, Ninth Revision. ICD-10 International Classification of Diseases, Tenth Revision.

show abstract

Section: G Parameter Settingmentioning

confidence: 99%

“…Both models were more accurate than the prior published models. One model was built on Intermountain Healthcare data [23]. The other was built on University of Washington Medicine (UWM) data [24].…”

Section: Introductionmentioning

confidence: 99%

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

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…1 Prediction of asthma exacerbations and patterns of health care service utilization for individuals and across populations is within technical and clinical reach. 2 In particular, ML algorithms can find these patterns by mining and aggregating repositories of data (including EHR, environmental, continuous physiologic data captured via remote telemonitoring, even social media feeds). 3 Ram et al 4 used multiple external data sources to help predict emergency department utilization in asthma in near real time with 70% precision.…”

mentioning

confidence: 99%

“…Finkelstein and Jeong 3 pioneered the use of home-based telemonitoring data to predict asthma exacerbations within a 7-day window, building on similar ML studies in asthma exacerbation prediction that have yielded potentially actionable sensitivity. 2,5 As depicted in Fig 1, the current and near-future application of ML and AI to currently inaccessible Big Data (including patient, population, and environmental sources) can drastically improve our diagnosis, management, and mechanistic understanding of asthma.…”

mentioning

confidence: 99%

“…3 Clinical prediction tools for asthma exacerbation or asthma hospitalization, even those that use ML, have a limited window of prediction and insufficient sensitivity and specificity. 2 To address these limitations, the inclusion of more variables, increased population size, novel physiologic measures (eg, heart rate variability and actigraphy), and environmental or epidemiologic data (eg, air quality, season, and viral infection rates) may help.…”

mentioning

confidence: 99%

See 1 more Smart Citation

The doctor will see you now: How machine learning and artificial intelligence can extend our understanding and treatment of asthma

Messinger

Luo

Deterding

2020

Journal of Allergy and Clinical Immunology

Self Cite

View full text Add to dashboard Cite

Composite predictive models for asthma exacerbations or asthma deterioration in pediatric asthmatic patients: A systematic review of the literature

Rodríguez‐Martínez

Sossa-Briceño

Forno

2023

Pediatric Pulmonology

View full text Add to dashboard Cite

A variety of factors have shown to be useful in predicting which children are at high risk for future asthma exacerbations, some of them combined into composite predictive models. The objective of the present review was to systematically identify all the available published composite predictive models developed for predicting which children are at high risk for future asthma exacerbations or asthma deterioration. A systematic search of the literature was performed to identify studies in which a composite predictive model developed for predicting which children are at high risk for future asthma exacerbations or asthma deterioration was described. Methodological quality assessment was performed using accepted criteria for prediction rules and prognostic models. A total of 18 articles, describing a total of 17 composite predictive models were identified and included in the review. The number of predictors included in the models ranged from 2–149. Upon analyzing the content of the models, use of healthcare services for asthma and prescribed or dispensed asthma medications were the most frequently used items (in 8/17, 47.0% of the models). Seven (41.2%) models fulfilled all the quality criteria considered in our evaluation. The identified models may help clinicians dealing with asthmatic children to identify which children are at a higher risk for future asthma exacerbations or asthma deterioration, therefore targeting and/or reinforcing specific interventions for these children in an attempt to prevent exacerbations or deterioration of the disease.

show abstract

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

Cited by 44 publications

References 47 publications

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

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

The doctor will see you now: How machine learning and artificial intelligence can extend our understanding and treatment of asthma

Composite predictive models for asthma exacerbations or asthma deterioration in pediatric asthmatic patients: A systematic review of the literature

Contact Info

Product

Resources

About