Application of Machine Learning Based on fNIRS in Predicting Acupuncture's Efficacy in Treating Tinnitus

What this Trial Is About

Researchers are studying tinnitus, a condition involving ringing in the ears, to evaluate how well acupuncture works for patients using advanced brain imaging and machine learning. This study aims to build a model predicting acupuncture's clinical effects on patients with chronic subjective tinnitus by analyzing brain activity data collected through functional near-infrared spectroscopy (fNIRS). The research will involve 500 participants aged 18 to 60 who meet specific diagnostic criteria for tinnitus. Participants will receive acupuncture treatment three times a week for four weeks at specific acupoints, including TE17 (Yifeng), SI19 (Tinggong), and others. Brain imaging data will be collected from all detection channels using fNIRS before and after the acupuncture treatment. Based on their recovery status after treatment, participants will be grouped into "good prognosis" or "poor prognosis" categories. The collected data will be divided into training and test sets to develop the machine learning model. Throughout the study, researchers will assess changes in resting-state functional connectivity, hemoglobin signals, and tinnitus severity grading before and after treatment. Additional measures include the Tinnitus Handicap Inventory score and pure-tone hearing thresholds. Participants will be monitored for treatment response and safety during the 4-week acupuncture course, with data collected at baseline and post-treatment to evaluate outcomes and build predictive models.

Application of Machine Learning Based on fNIRS in Predicting Acupuncture's Efficacy in Treating Tinnitus