# Predicting Procedure Time in Pediatric Dental Rehabilitation Under General Anesthesia: The Role of Preoperative Factors and Age‐Based Models

## TL;DR

This study finds that a child's age is the best predictor of dental procedure time under general anesthesia, leading to a new model that improves scheduling accuracy.

## Contribution

The study introduces an age-based predictive equation that outperforms existing systems like EPIC's analytics for pediatric dental rehabilitation under general anesthesia.

## Key findings

- Age was the strongest predictor of procedure duration, with an R² of 50.73%.
- The age-based model improved prediction accuracy by 42% and 114% in the 3–5 and 13–18 age groups compared to EPIC's analytics.
- Variables like weight, BMI, and ASA classification had minimal influence on procedure time.

## Abstract

Dental rehabilitation under general anesthesia (GA) is often required for children who are unable to cooperate during standard dental procedures. Accurately estimating the duration of these cases is challenging, particularly when preoperative X‐rays are unavailable. Efficient scheduling and optimal operating room (OR) utilization rely on precise time predictions; however, existing predictive models, including EPIC's analytics, frequently overlook patient‐ and case‐specific factors, resulting in suboptimal OR efficiency.

This study aimed to identify preoperative, patient‐specific factors that influence the duration of pediatric dental rehabilitation under GA and to develop an age‐based predictive equation to improve procedure time estimation.

A retrospective review was conducted on 255 dental rehabilitation cases performed under general anesthesia (GA) between January 2022 and December 2023. Collected data included patient demographics, treatment details, availability of radiographs, and operating room (OR) time metrics. Statistical analysis was performed to assess the influence of preoperative factors on procedure duration. An age‐based fitted equation was developed, and its predictive accuracy compared with that of EPIC's analytics system.

Age was the strongest patient‐specific predictor of procedure duration (p < 0.001, R
2 = 50.73%), correlating with both dentition type and the extent of dental restoration required. The age‐based fitted equation substantially outperformed EPIC's analytics, particularly in the 3–5 and 13–18 age groups, improving prediction accuracy by 42% and 114%, respectively. The fitted equation was Y = 84–4.5X + 0.6X2, where Y represents procedure time and X represents age. Other patient‐specific variables, including weight, BMI, and ASA classification, demonstrated minimal influence.

Developing an age‐specific fitted equation based on site‐specific operating room (OR) data improves procedure time prediction for pediatric dental rehabilitation under GA. This model supports more precise scheduling, better resource allocation, and improved patient access to care, providing a valuable framework for efficiency in the OR.