Abstract: Objective To explore the diagnostic efficacy of augmented reality navigation and traditional bronchoscopic-guided alveolar lavage in the diagnosis of smear-negative pulmonary tuberculosis.Provide a reference basis for optimizing diagnostic and therapeutic strategies for this patient population in clinical practice. Method A prospective study was conducted to screen 200 suspected smear-negative pulmonary tuberculosis patients who were admitted to Xi'an Chest Hospital from January 2024 to June 2025. The patients were randomly divided into a control group and an experimental group using a random number table, with 100 cases in each group. Among them, the patients in the control group only underwent diagnosis using the traditional bronchoscopy alveolar lavage technique; while the patients in the experimental group underwent diagnosis using the augmented reality navigation bronchoscopy-guided alveolar lavage technique. The study compared the positive detection rates and diagnostic efficacy between the two groups. Result The average recovery rate of bronchoalveolar lavage fluid was (68.5%±10.2%) in the experimental group and (61.3%±12.4%) in the control group. In the experimental group, the success rate of specimen acquisition under AR navigation guidance was 94.0%., which was significantly higher than 82.0% in the control group, with a statistically significant difference (P<0.05). The positive detection rate of smear-negative pulmonary tuberculosis in the experimental group was 67.00%, also significantly higher than 53.00% in the control group (P<0.05).Receiver operating characteristic (ROC) curve analysis revealed that the augmented reality-guided bronchoscopic bronchoalveolar lavage yielded higher sensitivity (0.834), specificity (0.691) and area under the curve (AUC) (0.811) for the diagnosis of smear-negative pulmonary tuberculosis compared with conventional bronchoscopic bronchoalveolar lavage, and the difference was statistically significant (P<0.05). There were no significant differences in operation time, intraoperative minor bleeding volume and postoperative pneumothorax incidence between the two groups (P>0.05). Conclusion Augmented reality navigation-guided bronchoalveolar lavage demonstrates superior diagnostic efficacy for smear-negative pulmonary tuberculosis compared with conventional bronchoscopy, with favorable safety and clinical application value.

Key words: Augmented reality navigation, Bronchoscopy, Smear-negative pulmonary tuberculosis, Bronchoalveolar lavage, Diagnostic efficacy