Introduction: Drumbeat.AI is a deep learning classification algorithm for analyzing otoscopic images, primarily trained on images from Australian Indigenous children. Given higher risk of middle ear disease among Māori and Pasifika populations in New Zealand (NZ), this study assesses the algorithm's generalizability in a novel population of NZ ears. Methods: Otoscopic images, tympanometry, and audiometry data from urban NZ children (3-12yo) were collected at an audiology clinic. 3 otolaryngologists labeled images into four categories: Normal, Acute Otitis Media (AOM), Middle Ear Effusion (MEE), and perforation. Images lacking consensus or showing tympanic membrane retraction were discarded. Remaining images were split into training (100) and testing (50) datasets. AI was retrained using the training set, and diagnostic performance evaluated for accuracy, sensitivity, specificity Results: From 200 datasets, 150 were retained after exclusions. Overall accuracy reached 82%. After retraining with 100 NZ images, binary classification accuracy (normal vs. abnormal) improved to 84%, and disease-specific accuracy (normalvs.MEEvs.perforation) reached 82%. Initial testing had 11 misclassifications (7 MEE), reduced to 9 after retraining (5 MEE). Misclassifications of normal ears as MEE were more common in NZ children of European descent.Conclusions: AI demonstrated improved diagnostic performance after retraining with local NZ images. While overall accuracy increased, specific classes showed variable improvement: MEE classifications and perforations improved significantly, whereas misclassifications for normal ears remained a concern. Future research with larger NZ-based training datasets would enhance the model’s performance and address the observed misclassifications.