Bronchiolitis is the most common illness leading to hospitalization in young children. For children under agetwo, bronchiolitis incurs an annual total inpatient cost of $1.73 billion. Each year in the U.S., 287,000emergency department (ED) visits occur because of bronchiolitis, with a hospital admission rate of 32-40%.Due to a lack of evidence and objective criteria for managing bronchiolitis, ED disposition decisions (hospitaladmission or discharge to home) are often made subjectively resulting in significant practice variation. Studiesreviewing admission need suggest that up to 29% of admissions from the ED are unnecessary. About 6% of EDdischarges for bronchiolitis result in ED returns with admission. These inappropriate dispositions waste limitedhealthcare resources, increase patient and parental distress, expose patients to iatrogenic risks, and worsenoutcomes. Clinical guidelines are designed to reduce practice variation and improve clinicians? decision making. Existingguidelines for bronchiolitis offer limited improvement in patient outcomes. Methodological shortcomings includethat the guidelines provide no specific thresholds for ED decisions to admit or to discharge, have an insufficientlevel of detail, and do not account for differences in patient and illness characteristics including co-morbidities. Predictive models are frequently used to complement clinical guidelines, reduce practice variation, andimprove clinicians? decision making. Used in real time, predictive models can present objective criteria supportedby historical data for an individualized disease management plan and guide admission decisions. However,existing predictive models for bronchiolitis patients in the ED have limitations, including low accuracy and theassumption that the actual ED disposition decision was appropriate. To date, no operational definition ofappropriate admission exists. No model has been built based on appropriate admissions, which include bothactual admissions that were necessary and actual ED discharges that were unsafe. To fill the gap, the proposed project will: (1) Develop an operational definition of appropriate hospitaladmission for bronchiolitis patients in the ED. (2) Develop and test the accuracy of a new model to predictappropriate hospital admission for a bronchiolitis patient in the ED. (3) Conduct simulations to estimate theimpact of using the model on bronchiolitis outcomes. The project will produce a new predictive model that can beoperationalized to guide and improve disposition decisions for bronchiolitis patients in the ED. Broad use of themodel would reduce iatrogenic risk, patient and parental distress, healthcare use, and costs and improveoutcomes for bronchiolitis patients. If the model proves to be accurate and associated with improved outcomes,future study will test the impact of using it in a randomized controlled trial following its implementation into anexisting electronic medical record to facilitate real-time decision making.
Each year; many young children present to the emergency department (ED) because of bronchiolitis; but areinappropriately disposed. The new predictive model will standardize hospital admission practice and guide andimprove disposition decisions for bronchiolitis patients in the ED. Broad use of the model will reduce EDreturns; hospital admissions; and costs and increase safe discharges.
| Luo, Gang; Johnson, Michael D; Nkoy, Flory L et al. (2018) Appropriateness of Hospital Admission for Emergency Department Patients with Bronchiolitis: Secondary Analysis. JMIR Med Inform 6:e10498 |
| Luo, Gang (2017) Toward a Progress Indicator for Machine Learning Model Building and Data Mining Algorithm Execution: A Position Paper. SIGKDD Explor 19:13-24 |
| Luo, Gang; Sward, Katherine (2017) A Roadmap for Optimizing Asthma Care Management via Computational Approaches. JMIR Med Inform 5:e32 |
