Related Experiment Video
Updated: Jul 2, 2025
Signal Acquisition, Score Interpretation, and Economics of a Non-Invasive Point-of-Care Test for Coronary Artery Disease
Published on: August 9, 2024
Predictive Value of LACE Scores for Pediatric Readmissions
Jelena Douillard1, Sarah Lentz2, Shaina Ganjian2
1Southern California Permanente Medical Group, Los Angeles, CA, USA.
Insights
The LACE score, a tool for predicting hospital readmissions, showed poor predictive capability in children. Further research is needed to develop effective models for reducing pediatric readmissions.
Area of Science:
- Pediatric healthcare research
- Health services research
- Predictive modeling in medicine
Background:
- Hospital readmissions represent a significant personal and economic burden.
- The LACE score (Length of stay, Acuity of admission, Comorbidities, Emergency Department visits) is used to predict readmissions.
- Limited research exists on LACE score efficacy in pediatric populations.
Purpose of the Study:
- To investigate the predictive capability of the LACE score for pediatric hospital readmissions.
- To develop a predictive model for pediatric readmissions using LACE scores and other factors.
- To identify strategies for reducing pediatric readmission rates.
Main Methods:
- Analysis of 25,616 pediatric hospitalizations from electronic medical records.
- Inclusion of LACE scores, age, gender, race/ethnicity, income, and medical center data.
- Utilized regression modeling and Area Under the Curve (AUC) to assess predictive capability for 7, 14, and 30-day readmissions.
Main Results:
- Only age and LACE score were statistically significant predictors of 30-day readmission.
- The combined predictive model achieved an AUC of 0.69.
- The model demonstrated poor predictive capability for pediatric readmissions.
Conclusions:
- LACE scores, along with other examined factors, exhibited poor predictive capability for pediatric readmissions.
- The current predictive model is insufficient for accurately identifying children at high risk for readmission.
- Further investigation is required to enhance predictive models for pediatric readmission reduction.
Introduction:
Hospital readmissions are recognized as a prevalent, yet potentially preventable, personal and economic burden. Length of stay, Acuity of admission, Comorbidities, and number of Emergency Department visits in the preceding 6 months can be quantified into one score, the LACE score. LACE scores have previously been identified to correlate with hospital readmissions within 30 days of discharge, but research specific to the pediatric population is scant. The objective of the present study was to investigate if LACE scores, in addition to other factors, can be utilized to create a predictive pediatric hospital readmission model that may ultimately be used to decrease readmission rates.
Methods:
This study included 25,616 hospitalizations of patients under the age of 18 years. Data were extracted from a hospital network electronic medical record. Demographics included LACE scores, age, gender, race/ethnicity, median household income, and medical centers. The primary exposure variable was LACE score. The main outcome measures were readmissions within 7, 14, and 30 days. The area under the curve (AUC) was used to assess the predictive capability of the regression model on patient 30-day admission.
Results:
LACE scores, age, gender, race/ethnicity, median household income, and medical centers were examined in a multivariable model to assess patient risk of a 30-day readmission. Only age and LACE score were observed to be statistically significant. The AUC for the combined model was 0.69.
Discussion:
As only age and LACE score were observed to be statistically significant and the AUC for the combined model was 0.69, this model is considered to have poor predictive capability.
Conclusions:
In this study, LACE scores, as well the other factors, had a poor predictive capability for pediatric readmissions.
More Related Videos
Related Concept Videos
01:15Receiver Operating Characteristic Plot
01:13Sensitivity, Specificity, and Predicted Value
Sensitivity is the...
01:11Residuals and Least-Squares Property
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
01:52Regression Toward the Mean
01:17z Scores and Area Under the Curve
01:12Coefficient of Correlation
If you suspect a linear relationship between x and y, then r can measure how strong the linear relationship is.
What the VALUE of r tells us:
The value of r is always between –1 and +1: –1 ≤ r ≤ 1.
The size of the correlation r indicates the...