Related Experiment Video
Updated: Jan 20, 2026
Dosage-Adjusted Resistance Training in Mice with a Reduced Risk of Muscle Damage
Published on: August 31, 2022
Prediction of 30-day pediatric unplanned hospitalizations using the Johns Hopkins Adjusted Clinical Groups risk
Mitchell G Maltenfort1, Yong Chen2, Christopher B Forrest1
1Applied Clinical Research Center, Roberts Center for Pediatric Research, Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, United States of America.
Insights
The Johns Hopkins ACG System effectively predicts pediatric unplanned hospitalizations using electronic health records. This tool aids in identifying high-risk children for targeted care management and population health initiatives.
Area of Science:
- Health Services Research
- Pediatric Healthcare
- Predictive Analytics
Background:
- The Johns Hopkins ACG System is a widely utilized tool for predicting healthcare service utilization and costs, primarily in adult populations.
- Existing applications of the ACG System have largely concentrated on adult patient cohorts.
- This study investigates the efficacy of the ACG System in predicting unplanned pediatric hospital admissions.
Purpose of the Study:
- To evaluate the predictive performance of the Johns Hopkins ACG System for pediatric unplanned hospitalizations.
- To assess the utility of the ACG System using electronic health record (EHR) data for predicting monthly hospital admissions in children.
- To determine the model's applicability in population health and care management strategies for pediatric patients.
Main Methods:
- Utilized EHR data from 920,051 pediatric patients across a multi-state integrated delivery system (2009-2016).
- Employed a generalized linear mixed model (GLMM) on a 70% training sample to derive regression coefficients for demographic and clinical predictors from the ACG System, including prior hospitalizations.
- Applied the developed model to a 30% test sample to generate risk scores and assess predictive accuracy using the area under the receiver operator characteristic curve (AUC).
Main Results:
- The predictive model achieved an excellent area under the receiver operator characteristic curve (AUC) of 0.82 for predicting pediatric unplanned hospitalizations.
- Excluding prior hospitalization data decreased the AUC to 0.80 and led to under-estimation of risk in high-risk groups.
- The top 5% of patients identified by risk scores accounted for 43% of all unplanned hospitalizations, with the top 1% accounting for 20%.
Conclusions:
- A 12-month predictive model using the ACG System demonstrates strong performance in identifying children at risk for unplanned hospitalization.
- The developed model shows potential for use in population health and care management initiatives targeting high-risk pediatric populations.
- External validation across different institutions is recommended to confirm the generalizability of these findings.
Background:
The Johns Hopkins ACG System is widely used to predict patient healthcare service use and costs. Most applications have focused on adult populations. In this study, we evaluated the use of the ACG software to predict pediatric unplanned hospital admission in a given month, based on the past year's clinical information captured by electronic health records (EHRs).
Methods And Findings:
EHR data from a multi-state pediatric integrated delivery system were obtained for 920,051 patients with at least one physician visit during January 2009 to December 2016. Over this interval an average of 0.36% of patients each month had an unplanned hospitalization. In a 70% training sample, we used the generalized linear mixed model (GLMM) to generate regression coefficients for demographic, clinical predictors derived from the ACG system, and prior year hospitalizations. Applying these coefficients to a 30% test sample to generate risk scores, we found that the area under the receiver operator characteristic curve (AUC) was 0.82. Omitting prior hospitalizations decreased the AUC from 0.82 to 0.80, and increased under-estimation of hospitalizations at the greater risk levels. Patients in the top 5% of risk scores accounted for 43% and the top 1% of risk scores accounted for 20% of all unplanned hospitalizations.
Conclusions:
A predictive model based on 12-months of demographic and clinical data using the ACG system has excellent predictive performance for 30-day pediatric unplanned hospitalization. This model may be useful in population health and care management applications targeting patients likely to be hospitalized. External validation at other institutions should be done to confirm our results.
Related Concept Videos
01:12Adjusting a Traverse
01:25The Anchoring-and-Adjustment Heuristic
01:11Renal Failure: Dose Adjustments
Reduced renal clearance and elimination rate are common outcomes of renal impairment. These alterations lead to a prolonged elimination half-life and an altered apparent volume of distribution for drugs. As a result, dosage adjustments are typically necessary to maintain optimal drug levels in the body.
However, dosage adjustments...
01:08Effect of Hepatic Disease on Pharmacokinetics: Dose Adjustments Due to Hepatic Impairment
00:59Hospitals-II
Nurses that work in...
01:28Hospitals-I