The study evaluated the diagnostic accuracy of gastric filling ultrasound combined with body mass index (BMI) for the detection of gastroesophageal reflux disease (GERD) in symptomatic patients, using 24-hour pH impedance monitoring and esophagogastroduodenoscopy as reference methods. Patients with GERD had significant differences in age, BMI, His angle, and reflux metrics (p < 0.05). The BMI-based ultrasound composite score achieved an area under the curve of 0.826 with an optimal cutoff of 4.50, with scores of 6–8 defining GERD. Sensitivity was 83.75%, specificity 65.33%, positive predictive value 72.04%, negative predictive value 79.03%, and overall accuracy 74.84%. Cohen's kappa was 0.494, the calibration curve showed good agreement with a mean absolute error of 0.034. Decision curve analysis demonstrated a superior net benefit of the model over the “treat all” or “no treat” strategies in the range of 10–65% threshold probabilities. BMI-based gastric filling ultrasound is a promising auxiliary diagnostic tool for GERD with good correlation with reference methods.