Motion Tracking-Based Dental Posture Training: Heuristic-Based Assessment and a Comparative Feasibility Study

Accurate dental working posture is essential for clinical performance and patient safety, yet objective and consistent posture training remains challenging. We present a motion-recognition-based posture assessment approach for dental clinical training that computes posture features from skeletal motion data and applies a rule-based (heuristic) posture assessment module based on predefined clinical criteria to generate posture scores, penalty counts, and warning counts. We conducted a comparative feasibility study with five dental residents (40 sessions total; eight procedure states per participant, 5 min/session). Heuristic-based assessment outputs were compared with specialist video-based ratings using paired nonparametric tests and Bland–Altman analysis. Across pooled sessions (n = 40), the heuristic method yielded lower posture scores than the video-based assessment (89.38 ± 5.21 vs. 97.38 ± 2.99) and higher penalty and warning counts (2.13 ± 1.04 vs. 0.53 ± 0.60; 7.23 ± 3.10 vs. 2.48 ± 1.54). Between-method differences were significant (p < 0.001), and Bland–Altman analysis showed a mean bias of 8.00 points (95% limits of agreement: −1.36 to 17.36), indicating limited session-level interchangeability. The proposed approach shows practical feasibility for quantitative posture recording and training support, but larger validation studies and calibration strategies are needed to improve agreement with reference assessments.