野田 昌生

The intricate distribution of the facial nerve within the temporal bone is crucial in otological surgery. Anomalous facial nerve pathways are occasionally observed in middle ear malformations, although intra-tympanic bifurcation of the facial nerve is rare. When managing ossicular malformations with atypical facial nerve trajectories, hearing reconstruction should be prioritized based on the trajectory pattern and presence of the oval window. In this case, stapes surgery was performed due to facial nerve bifurcation within the tympanic cavity. In this case report, a 15-year-old female underwent stapes surgery due to gradually worsening conductive hearing loss. She was monitored at another hospital because of left-sided hearing loss at birth screening using automated auditory brainstem response. Her left ear initially had mild hearing loss, while her right ear remained within normal limits. However, her hearing deteriorated progressively, leading to significant daily challenges by age seven, prompting referral to our hospital. Intraoperatively, findings included defects in the incus-long process and stapes head, along with facial nerve bifurcation around the oval window, and the stapes footplate had poor flexibility. Stapedotomy was performed cautiously to preserve the facial nerve, utilizing a Teflon piston wire for sound transmission reconstruction. Postoperatively, the patient experienced no complications or facial nerve palsy, with hearing improving to 28.8 dB. Understanding the precise pathophysiology of middle ear anomalies is crucial for selecting appropriate surgical approaches. Even though the anomalies could not be evaluated prior to surgery, surgeons must carefully consider the risk of facial nerve injury and choose the optimal technique and reconstruction method tailored to each case, as predicting outcomes solely from preoperative evaluations can be challenging.

OBJECTIVE: Pediatric obstructive sleep apnea (OSA) caused by adenoids or an enlarged palatine tonsil has a negative impact on physical and mental growth. Surgical removal of the tissue is effective but entails a life-threatening risk of postoperative bleeding, which is up to 30 times higher in chronic pediatric disease cases. However, endoscopes and resection devices provide safe, reliable surgical methods. Here, we report the efficacy and safety of endoscopic powered intracapsular tonsillectomy and adenoidectomy (PITA) for pediatric OSA in patients with high-risk comorbidities. METHODS: This retrospective case series included pediatric patients with OSA who underwent PITA at a single tertiary medical center between April 2017 and May 2023. Ten patients (three males and seven females; mean age 6.4 years, range 2-12 years) were included; all met the Japanese criteria for complex chronic pediatric conditions. RESULTS: The average operative time was 61 min; a microdebrider was used in eight cases and a coblator in two cases. Although there was no postoperative bleeding, one case experienced regrowth. CONCLUSIONS: Our data show that an endoscopic PITA approach could reduce the risk of severe bleeding and relieve the sleeping conditions of pediatric patients with complex chronic OSA.

BACKGROUND: 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. OBJECTIVE: 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. METHODS: 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. RESULTS: 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. CONCLUSIONS: 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.