The integration of artificial intelligence (AI), particularly deep learning models, has transformed the landscape of medical technology, especially in the field of diagnosis using imaging and physiological data. In otolaryngology, AI has shown promise in image classification for middle ear diseases. However, existing models often lack patient-specific data and clinical context, limiting their universal applicability. The emergence of GPT-4 Vision (GPT-4V) has enabled a multimodal diagnostic approach, integrating language processing with image analysis.
In this study, we investigated the effectiveness of GPT-4V in diagnosing middle ear diseases by integrating patient-specific data with otoscopic images of the tympanic membrane.
The design of this study was divided into two phases: (1) establishing a model with appropriate prompts and (2) validating the ability of the optimal prompt model to classify images. In total, 305 otoscopic images of 4 middle ear diseases (acute otitis media, middle ear cholesteatoma, chronic otitis media, and otitis media with effusion) were obtained from patients who visited Shinshu University or Jichi Medical University between April 2010 and December 2023. The optimized GPT-4V settings were established using prompts and patients\' data, and the model created with the optimal prompt was used to verify the diagnostic accuracy of GPT-4V on 190 images. To compare the diagnostic accuracy of GPT-4V with that of physicians, 30 clinicians completed a web-based questionnaire consisting of 190 images.
The multimodal AI approach achieved an accuracy of 82.1%, which is superior to that of certified pediatricians at 70.6%, but trailing behind that of otolaryngologists at more than 95%. The model\'s disease-specific accuracy rates were 89.2% for acute otitis media, 76.5% for chronic otitis media, 79.3% for middle ear cholesteatoma, and 85.7% for otitis media with effusion, which highlights the need for disease-specific optimization. Comparisons with physicians revealed promising results, suggesting the potential of GPT-4V to augment clinical decision-making.
Despite its advantages, challenges such as data privacy and ethical considerations must be addressed. Overall, this study underscores the potential of multimodal AI for enhancing diagnostic accuracy and improving patient care in otolaryngology. Further research is warranted to optimize and validate this approach in diverse clinical settings.

This study aimed to determine the prevalence of hearing loss and ear problems in Pacific children, and investigate current and past demographic, health and social factors potentially associated with hearing and ear problems.
A cross-sectional observational study design nested within a birth cohort was employed.
Nine-hundred-twenty Pacific children aged 11 years were audiologically assessed. Using average hearing thresholds at 500, 1k and 2k Hz, 162 (18%) right and 197 (21%) left ears had ≥20 dB hearing loss. Hearing loss was mild (20-39 dB) in most cases; 2% of ears had moderate to moderate-severe (40-69 dB) hearing loss. However, only 101 (11%) children had normal peripheral hearing defined by passing hearing threshold, tympanogram and distortion product otoacoustic emission assessments. Those with confirmed middle ear disease at age 2 years had significantly increased odds of a non-Type A tympanogram (adjusted odds ratio: 2.00; 95% confidence interval: 1.56, 2.50) when re-assessed at age 11 years.
Hearing loss, abnormal tympanograms, and auditory processing difficulties were present in many Pacific children. Interventions are also urgently needed to mitigate the effect of the longstanding ear disease likely to be present for many Pacific children.

OBJECTIVE: It has been our clinical observation that active middle ear disease (MED) temporally corresponds to a transient decrease in cochlear implant (CI) function, specifically at the apical electrodes. This is non-intuitive as CI function is thought to be independent of middle ear aeration and inflammation. The purpose of this case study is to demonstrate how active MED negatively affects both subjective hearing complaints and objective impedance measures in a CI patient.
RESULTS: Subjective hearing decreased and impedances levels increased significantly when the patient was experiencing active MED. No significant changes in these measures occurred when there was no active MED.
CONCLUSIONS: MED may affect CI function in some patients requiring adjustments in programing at times of involvement.