Correlating Predicted Admissions with Unscheduled Return Visits: Insights from a Machine Learning Model in Emergency
Wayne A Martini1, Rachelle Beste2, Andrej Urumov1
1Department of Emergency Medicine, Mayo Clinic, Phoenix, Arizona.
The Journal of Emergency Medicine
|October 24, 2025
Summary
Machine learning (ML) models predict hospital admissions in emergency departments (EDs). Higher predicted admission scores correlate with increased unscheduled return visits (URVs), suggesting ML can optimize ED operations.
Area of Science:
- Emergency medicine
- Health informatics
- Artificial intelligence in healthcare
Background:
- Emergency departments (EDs) increasingly use machine learning (ML) for predicting hospital admissions and managing patient flow.
- The relationship between ML-driven admission predictions and unscheduled return visits (URVs) requires further investigation.
Purpose of the Study:
- To evaluate the association between real-time ML-predicted admission likelihood and 72-hour URVs leading to hospital admission.
- To analyze this relationship across three tertiary care centers.
Main Methods:
- Analysis of 169,288 ED visits from January 1 to December 31, 2023.
- Utilized an internally developed ML model incorporating 47 clinical features extracted from electronic health records.
- Excluded expected return visits from the analysis.
Main Results:
- The ML model achieved an AUC of 0.88 for hospital admission prediction.
- A total of 1,996 URVs (1.18%) occurred within 72 hours, with 6.61% involving multiple returns.
- Higher predicted admission scores correlated with increased URV rates and subsequent hospital admissions, with the highest score group (AI Score >75%) showing a 4.86% URV rate and 76.54% admission on return.
Conclusions:
- Elevated predicted hospital admission scores are linked to a higher incidence of URVs and hospital admissions.
- ML models show potential for enhancing ED operations by identifying high-risk patients for timely intervention and improved resource allocation.
Related Concept Videos
01:11Residuals and Least-Squares Property
9.1K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
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...
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...
9.1K
01:18Steps in Outbreak Investigation
487
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
487
02:20Correlations
35.7K
Correlation means that there is a relationship between two or more variables (such as ice cream consumption and crime), but this relationship does not necessarily imply cause and effect. When two variables are correlated, it simply means that as one variable changes, so does the other. We can measure correlation by calculating a statistic known as a correlation coefficient. A correlation coefficient is a number from -1 to +1 that indicates the strength and direction of the relationship between...
35.7K
01:03Prediction Intervals
3.3K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
3.3K
01:15Receiver Operating Characteristic Plot
470
A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...
470
01:19Variation
7.7K
An important characteristic of any set of data is the variation in the data. In some data sets, the data values are concentrated closely near the mean; in other data sets, the data values are more widely spread out from the mean. The most common measure of variation, or spread, is the standard deviation, which is the square root of variance.
When independent and dependent variables are plotted on a scatter plot, the slope of a line is a value that describes the rate of change between the two...
When independent and dependent variables are plotted on a scatter plot, the slope of a line is a value that describes the rate of change between the two...
7.7K