A Statistical-Learning Model for Unplanned 7-Day Readmission in Pediatrics

Abstract

The rate of pediatric 7-day unplanned readmissions is often seen as a measure of quality of care, with high rates indicative of the need for improvement of quality of care. In this study, we used machine learning on electronic health records to study predictors of pediatric 7-day readmissions. We ranked predictors by clinical significance, as determined by the magnitude of the least absolute shrinkage and selection operator regression coefficients.METHODS: Data consisting of 50 241 inpatient and observation encounters at a single tertiary pediatric hospital were retrieved; 50% of these patients' data were used for building a least absolute shrinkage and selection operator regression model, whereas the other half of the data were used for evaluating model performance. The categories of variables included were demographics, social determinants of health, severity of illness and acuity, resource use, diagnoses, medications, psychosocial factors, and other variables such as primary care no show.RESULTS: Previous hospitalizations and readmissions, medications, multiple comorbidities, longer current and previous lengths of stay, certain diagnoses, and previous emergency department use were the most significant predictors modifying a patient's risk of 7-day pediatric readmission. The model achieved an area under the curve of 0.778 (95% confidence interval 0.763-0.793).CONCLUSIONS: Predictors such as medications, previous and current health care resource use, history of readmissions, severity of illness and acuity, and certain psychosocial factors modified the risk of unplanned 7-day readmissions. These predictors are mostly unmodifiable, indicating that intervention plans on high-risk patients may be developed through discussions with patients and parents to identify underlying modifiable causal factors of readmissions.

A multicenter mixed-effects model for inference and prediction of 72-h return visits to the emergency department for adult patients with trauma-related diagnoses

“…We assessed multicollinearity by estimating the generalized variance inflation factor [28,29] (GVIF) of the variables. In a stepwise process, we excluded the variable with the highest GVIF and reassessed multicollinearity until the GVIF of all variables kept is below 4-a rule of thumb threshold based on the previous studies [23]. We randomly split the data into two: 50% for model and the other 50% for evaluating model performance.…”

“…We provide an assessment of model performance with recommendations on the potential implementation of the corresponding predictive models in the ED. The new variables we considered include several measures of current and past healthcare resource utilization that have been found to be associated with the related problem of hospital readmission [22][23][24].…”

Predictors of pediatric readmissions among patients with neurological conditions

“…Previous studies on unplanned readmission among patients with neurological conditions have indicated multiple anti-epilepsy drugs, pediatric intensive care unit admission, seizure with major complication or comorbidity, and presence of a major complication or comorbidity irrespective of diagnosis as factors associated with higher risk of unplanned readmission [3,8]. In this study, we aimed to identify novel factors that may predict a higher risk of unplanned readmission in pediatric neurology and provide a prediction model that may be useful to clinicians in their efforts to reduce readmission rates [9,10]. Previous studies were limited by sample size and only included a single center.…”

Contributions to Variable Selection in Complexly Sampled Case-control Models, Epidemiology of 72-hour Emergency Department Readmission, and Out-of-site Migration Rate Estimation Using Pseudo-tagged Longitudinal Data

“…In addition, we retrieved available data on demographics (age, sex, and race/ethnicity), proxies for socioeconomic status (health insurance payer), and health care utilization variables. The health care utilization variables we retrieved were informed by findings in hospital readmission [58][59][60], for which we hypothesized will have shared risk factors with return visits to the ED. These include utilization in the prior 6 months of the index ED visit for previous ED visits and the maximum length of stay of the visits, and hospitalizations.…”

“…We introduced two related variables not to be confused with the outcome variable: a variable counting the history of return visits within the prior 6 months (not counting the index ED visit), and another variable checking to see if the index visit was a return visit of an earlier encounter. The selection of these variables were again informed by previous findings [58,59] in the related problem of hospital readmissions.…”