The Cockburn Aboriginal Ear Health Program is a collaboration between Cockburn Integrated Health, The Kids Research Institute Australia (TKRI), Moorditj Koort Aboriginal Corporation, TSH, Hearing Australia, Child and Adolescent Health Service, St John of God Health Care (Murdoch and Midland), South Metropolitan Health Service, Rockingham Hospital, Midvale Hub, Oseca Health, Prof Francis Lannigan, A/Prof George Sim, Dr Travis Leahy, Dr Phillip Sale, and Dr Aaron Esmaili to provide timely and culturally secure access to specialist care for Aboriginal children with middle ear disease. The program was initiated following research undertaken by TKRI through the Djaalinj Waakinj Urban Aboriginal Ear Health Program and the recognition that while there was a significant level of middle ear disease identified in the Aboriginal population, there were deficiencies in the service provision available resulting in a range of sequalae that have lifelong consequences for this population group. In consultation with Moorditj Koort Aboriginal Corporation and the Aboriginal Community Advisory Group which guided the Djaalinj Waakinj Program, a service model was put in place that brought together a range of service providers to establish an integrated service to meet community needs. The model includes access to specialist Ear Nose and Throat services, audiology, and surgical care where necessary, along with the cultural and practical support necessary to make the program a success. We present what we believe to be the first external, independent evaluation of such a program from Dr Frank Baughman, School of Population Health, Curtin University. The outcomes of the evaluation have been used to implement further service improvements. The success of the program is testament to the commitment of all service providers and surgeons involved to improve the health and wellbeing of the Aboriginal population.

Aims: To report utilisation rates and available audiological outcomes among Australian Indigenous cochlear implant (CI) recipients, and identify access barriers to CI and hearing rehabilitation. Method: Systematic search of Medline, Web of Science, Embase, CINAHL and grey literature (September 2025) yielded 855 records. Studies reporting utilisation, outcomes, complications, and follow-up/access to CI amongst Indigenous Australians were screened. Results: Only three studies met inclusion criteria; nine additional grey literature sources were identified. While a Western Australian paediatric CI cohorts showed Indigenous children comprised 3% of recipients (4/118), nationally, only 1.8% (145/8,200) of Indigenous hearing device users have CIs, despite 43% of Indigenous people aged 7+ having measured hearing loss. Critically, none of the included studies reported Indigenous-stratified CI outcomes. First hearing device fittings typically occur at 3–6 years in Indigenous children versus under 1 year in non-Indigenous children. Major access barriers identified included under-screening, geographic isolation from tertiary CI centres, fragmented care pathways, and concerns about cultural safety. The evidence suggests that barriers accumulate across the entire hearing-care continuum, rather than being confined to CI services. Adult Indigenous audiology services remain particularly underutilised despite high prevalence of hearing-related diseases. Conclusion: Indigenous-specific CI outcome data are essentially absent despite a documented substantial burden of severe and profound hearing loss in First Nations people. Indigenous-specific effectiveness evidence is needed to ensure equitable benefit of CI across all Australian population groups. Urgent priorities include Indigenous-led research, and data linkage to track outcomes. Strengthening ear-health services and routine screening is essential to ensure equitable CI access for Aboriginal and Torres Strait Islander peoples.

Introduction: Access to otolaryngology services in rural and remote Australia is limited by geography, workforce shortages, and prolonged waiting times for specialist review. Otoscopy is fundamental to the assessment of ear disease but is often limited by variable skill levels and limited access to specialist equipment in remote settings. Smartphone-assisted otoscopy has emerged as a potential tool to support remote assessment and telehealth models of care. Aim: To review the current evidence for smartphone-assisted otoscopy in remote ENT assessment and discuss its potential role in improving access to ENT surgical services in rural Australia. Methods: A narrative review of the literature was performed, focusing on studies evaluating smartphone-compatible otoscopes used in community, primary care, and remote settings. Outcomes of interest included diagnostic accuracy, feasibility for remote assessment, impact on referral pathways, and integration with telehealth services. Results: Smartphone-assisted otoscopy enables acquisition and transfer of high-quality otoscopy images from non-specialist settings, facilitating remote specialist review. Studies demonstrate improved diagnostic confidence and referral quality for common otological conditions, including otitis media and tympanic membrane pathology. These systems have been successfully integrated into telehealth pathways, supporting earlier identification of patients requiring surgical assessment. Discussion: Deployment of smartphone-assisted otoscopes in rural Australia may improve ENT service delivery by enabling remote assessment, optimising referral prioritisation, and reducing unnecessary patient travel. Challenges include device cost, training requirements, image quality variability, data governance, and medicolegal considerations. Conclusion: Smartphone-assisted otoscopy represents a practical adjunct for improving access to ENT assessment and surgical care in rural and remote Australia. Further evaluation of implementation models within the Australian healthcare system is warranted.

Purpose: Artificial intelligence (AI) image classification models can detect paediatric middle ear disease from otoscopic images. However, they are limited by the inability to interpret complementary tympanometry and audiometry. A fusion model, combining large language model (LLM) clinical data interpretation with image classification, can fill this gap and provide a more comprehensive diagnostic tool. Methodology: Otoscopic images, tympanometry and audiogram results were collected prospectively by nursing staff as part of routine primary care assessments. A cohort of 80 encounters was analysed. Tympanometry and audiograms were processed by four LLMs (GPT-4, Claude 3.5 Sonnet, Grok-4, DeepSeek), each paired with an otoscopic image-only classification algorithm, to establish a multi-modal fusion model. Diagnostic outputs from each LLM–image system were generated and compared against ground truth, defined by a panel of 13 otolaryngologists, for the multi-classification of normal, acute otitis media, otitis media with effusion, and chronic otitis media. Results: The image-only classifier achieved accuracy of 87.3%, AUC=0.959, and κ=0.83. When combined with LLMs, overall diagnostic performance improved across hybrid configurations. The top fusion model (with GPT-4) reached 92.6% accuracy (AUC=0.962, κ=0.90), followed by Claude 3.5 Sonnet (accuracy=92.5%, AUC=0.963, κ=0.90), AI Grok-4 (accuracy=92.4%, AUC=0.963, κ=0.90), and DeepSeek V2 (accuracy=88.9%, AUC=0.955, κ=0.85). All four hybrid fusion models showed significantly higher diagnostic accuracy and inter-rater agreement than the image-only classifier (p<0.05 for all comparisons). Conclusion: Multi-modal integration of LLM-interpreted tympanometry and audiograms with otoscopic image classification significantly improves diagnostic performance in middle ear disease. This marks a major step towards AI systems reflecting real world clinical reasoning, synthesising multiple tiers of imaging and clinical data.