A Multimodal Autonomic Sensing Framework for Objective Assessment of Patient Responses to Dental Pulp Stimulation
A multimodal model using ECG-derived and electrodermal signals classifies dental pulp-test responses in 49 patients.
Researchers recorded cold pulp tests from 49 patients under no-response, mild-response, and intense-response conditions. Temporal convolutional encoders with attention-based mid-level fusion combined ECG-derived skin nerve activity and R-R intervals with electrodermal activity, plus anxiety scores and biological sex. Binary classification of no response versus any response reached 80.2% balanced accuracy, 75.2% sensitivity, and 85.2% specificity. Three-class performance was 60.0% balanced accuracy and 58.8% macro F1, with electrodermal activity the strongest contributor and age associated with performance.
- Forty-nine patients produced no, mild, and intense cold-pulp responses
- Binary balanced accuracy was 80.2%, with 75.2% sensitivity and 85.2% specificity
- Three-class balanced accuracy was 60.0% and macro F1 was 58.8%
- EDA contributed most, then RRI; SKNA added about five accuracy points
Full article199 words · extracted from arxiv.org · click to collapse
Patient responses to dental pulp testing, ranging from no sensation to intense pain, provide important information for assessing pulp status in endodontic diagnosis. However, pain is a subjective sensory and emotional experience that varies considerably across individuals and can be difficult to communicate. We investigated whether complementary autonomic signals could support objective assessment of responses during dental examination. Forty-nine patients underwent cold pulp testing, yielding no-response, mild-response, and intense-response conditions. The framework integrated ECG-derived skin nerve activity (SKNA) and R-R intervals (RRI), together with electrodermal activity (EDA), using temporal convolutional network encoders with attention-based mid-level fusion. Individual baseline signals and subject-level covariates, including anxiety scores and biological sex, were also incorporated. The framework achieved 80.2% balanced accuracy, 75.2% sensitivity, and 85.2% specificity for binary classification of no response versus mild or intense response. For three-class classification, it achieved 60.0% balanced accuracy and a 58.8% macro-averaged F1 score. Ablation and attention-weight analyses indicated that EDA contributed most strongly to model performance, followed by RRI, while SKNA improved balanced accuracy by approximately five percentage points. Age was significantly associated with model performance. These findings support the feasibility of multimodal autonomic sensing for objective, non-invasive assessment of responses to dental pulp stimulation.
Text extracted automatically; images, tables and formatting may be missing. Original: https://arxiv.org/abs/2609.35121