# Performance Evaluation of Rapid Entire Body Assessment Using AI-Assisted Ergonomic Analysis in Dentistry

## TL;DR

This study uses AI to automate ergonomic assessments for dentists, aiming to reduce musculoskeletal risks and improve accuracy.

## Contribution

AI-assisted REBA using MediaPipe and RSM modeling to optimize ergonomic scores in dentistry.

## Key findings

- 83% of dentists are at high risk, and 17% at very high risk for musculoskeletal disorders.
- The RSM model achieved R2 = 0.9055, showing strong predictive accuracy for REBA scores.
- Contour graphs and a linear regression equation guide ergonomic improvements for dental practice.

## Abstract

This study seeks to automate the Rapid Entire Body Assessment (REBA) in dentistry with Artificial Intelligence (AI) technologies, notably MediaPipe, to improve accuracy and obviate the necessity for expert judgment. This research utilizes time-synchronized videos and averages across frames to mitigate mistakes resulting from visual occlusion and over- or underestimation, respectively. The REBA scores of the observed dentists were evaluated and compared with the conventional single image-based method. Among the evaluated dentists, 83% of dentists are at high risk, and the other 17% of dentists are at very high risk, requiring solutions to lower their REBA scores and prevent musculoskeletal disorders (MSDs). The individual REBA point profiles differed, necessitating a collective study through response surface methodology (RSM) utilizing Design Expert software. The RSM model exhibited substantial results, as indicated by R2 = 0.9055 and p = < 0.0001 values. A linear regression equation was established, and contour graphs depicted the relative variation of REBA points. The optimized REBA score profile establishes a maximum attainable threshold for dentists, directing them towards the lower scores. This streamlined contour functions as a design restriction for creating ergonomic solutions in dental practice.