Wednesday, January 15, 2025
1/15/2025
Project Summary We propose to diagnose and differentiate dental pain from stress using a wearable electrodermal activity (EDA) device. Dental caries is one of the major causes of endodontic infection in the pulp or soft tissues of the tooth, causing hypersensitivity, severe pain, and even death. It is estimated that at least 2 billion adults and 520 million children suffer from dental caries worldwide. EDA has shown the capability to objectively assess dental pain since it measures the electrical conductance of the skin due to innervation of the sympathetic nervous system (SNS). However, EDA has two fundamental issues. First, stress can also elicit an EDA response via the SNS, and stress commonly presents in dental clinics due to pain anticipation and previous experience. Second, EDA analysis relies on knowing the onset and end timepoints of a stimulus and when the subject feels pain on the affected teeth, which is difficult to obtain from patients with communication issues. Skin nerve activity (SKNA), recorded via ECG at high sampling rates (>4 kHz), has been shown to represent the dynamics of the SNS with precise start and end times of nerve firing, which can be used to align events in the EDA signal for subsequent EDA analysis. Therefore, we propose to use the skin nerve activity (SKNA) signal, derived from the ECG, to precisely locate the onset and end of noxious stimuli. We will also apply and validate a machine learning model to detect and differentiate EDA segments affected by stress from pain during pulpal diagnosis. As both pain and stress increase amplitudes of EDA signals, albeit less with the latter, it is crucial to develop a quantitative approach to differentiate stress from pain in EDA signals. Therefore, we will investigate SKNA and EDA signals from datasets collected during dental examination to separate stress from pain response so that more accurate assessment of pain due to noxious stimuli during dental examination can be made. Our approach combining SKNA and EDA will allow autonomous and more accurate segmentation of the data that are specific to pain and stress, which will be especially useful for patients with communication issues, and ultimately will lead to more accurate assessment of pain.
HHS’ Tracking Accountability in Government Grants System (TAGGS) website provides access to detailed descriptions of grants, loans, aggregated direct payments and other types of financial assistance awarded by the HHS Operating Divisions (OPDIVs) and the Office of the Secretary Staff Divisions (STAFFDIVs).