Abstract: Computed tomography (CT) of the paranasal sinuses is essential in diagnosing odontogenic chronic rhinosinusitis. Treatment primarily targets the dental focus, with endoscopic sinus surgery (ESS) indicated when necessary. Assessing CT findings using the Lund–Mackay score (LMS) may guide therapeutic decisions. This study retrospectively compared LMS, dental pathology type, and reported symptoms with treatment choices in patients treated for odontogenic chronic rhinosinusitis between 2012 and 2022 at a tertiary otorhinolaryngology center. From 2067 chronic rhinosinusitis patients, 61 had an odontogenic cause. LMS was determined in 57 patients and correlated with treatment strategy. Dental pathology subtypes and presenting symptoms were also analyzed. A control group of 25 patients with localized, non-odontogenic chronic rhinosinusitis was included. Fifteen patients not undergoing ESS had lower LMS values (median 1), while 42 surgical patients had higher scores (median 6). Periapical pathology (47.4%) and oroantral fistula (26.3%) were the most common causes. Nasal discharge and pain were the most frequent symptoms. Neither dental pathology type nor symptoms significantly influenced treatment decisions.The extent of CT-detected pathology, reflected by LMS, can serve as a key criterion in determining treatment for odontogenic chronic rhinosinusitis, independent of symptoms or specific dental pathology type.

Abstract: Background: Overprescription of antibiotics for pharyngitis—driven by diagnostic uncertainty and physician disagreement on ambiguous presentations—contributes significantly to antimicrobial resistance. Existing AI diagnostic models report aggregate accuracy metrics that obscure performance variability across cases with different levels of diagnostic certainty, limiting their clinical utility. Objective: To develop and validate a consensus-based evaluation framework for deep learning models in pharyngitis diagnosis, stratifying performance by physician agreement levels (High vs. Low Consensus), and to compare image-only, symptom-only, and multimodal fusion strategies for smartphone-based diagnosis. Methods: We curated a dataset of 742 multimodal cases (symptoms and throat images) independently evaluated by 4–9 physicians. After excluding 102 cases where physicians could not reach a clear majority, 640 cases were used for model training and evaluation. We compared six architectures: Image-Only (CNN, Vision Transformer), Symptoms-Only, and Multimodal Fusion (Late Fusion, Gated Fusion, Cross-Attention). Models were evaluated using 5-fold stratified cross-validation, with separate analysis for High-Consensus (N=199) and Low-Consensus (N=441) cases. Results: On High-Consensus cases, all image-based models achieved excellent accuracy (95–96%) with high specificity (>96%). On Low-Consensus cases, accuracy dropped to 76–78%, matching the inter-physician agreement rate. Vision Transformer demonstrated the best overall performance (84.84% accuracy, 70.5% AUC). Multimodal fusion provided minimal benefit over image-only approaches. All models maintained high specificity (>96%) but exhibited low sensitivity (2–15%) for bacterial pharyngitis, reflecting conservative prediction patterns suitable for rule-out screening but requiring human oversight for suspected bacterial cases. Conclusions: Our consensus-based evaluation framework reveals that AI models, like human physicians, perform reliably only on diagnostically clear pharyngitis cases. The high specificity (96–98%) suggests strong potential for reducing unnecessary antibiotic prescriptions through AI-assisted triage, while the low sensitivity (2–15%) necessitates physician review for suspected bacterial infections. This stratified approach provides clinically meaningful insights for safe AI deployment in antibiotic stewardship programs.

Abstract: The present exploratory, uncontrolled, open-label study investigated the effect of Ginkgo biloba extract EGb 761® in the management of chronic tinnitus, and whether comorbidities have an impact on the treatment outcome. The full analysis set comprised 170 patients with chronic tinnitus who took 120 mg EGb 761® twice daily for 24 weeks. Outcomes were assessed using the Tinnitus Questionnaire, Tinnitus Handicap Inventory, and 11-Point Box Scales for loudness and annoyance. Comorbidities were recorded with audiometry, the Hospital Anxiety and Depression Scale, and the Perceived Stress Questionnaire. The effectiveness was further examined in responder analyses (at least 30% score reduction in 3 out of 4 outcomes) and in subgroups defined by baseline anxiety, hearing impairment, stress and depression. At week 24, significant improvements were observed in all tinnitus-related outcomes compared to baseline (all p<0.0001). In subgroup analyses, patients with high baseline anxiety or stress as well as those with normacusis improved more whereas baseline depression had no influence. The overall response rate was 18.8%. The results of this exploratory study indicate that EGb 761® improved complaints in patients with chronic tinnitus. The therapy appears to be particularly beneficial for patients with normal hearing and/or concomitant anxiety and/or stress. Trial registration: The study was registered at ISRCTN (ISRCTN83863387, registration date October 14, 2016).

Abstract: Aim of this work is to deduce the position of the otoconial debris in lateral cupulo/canalolithiasis, as a function of two parameters: 1) the direction of the nystagmus that appears when the patient lies down (if present); 2) the positional nystagmus evoked by the supine roll test. The theoretical results are then compared with a population of 170 patients observed in the last ten years for vertigo due to paroxysmal positional vertigo of the horizontal canal. From the comparison between lying down and positional nystagmus, it is probably possible to identify the initial position of the fragments inside the lateral canal. This may be a useful clue for performing the correct liberatory maneuver. Instead, it is believed that to distinguish a jam located on the canal side of the cupula from a jam on the utricular side, one can only rely on the effective side of the liberatory maneuver. Background/Objectives: Aim of this work is to deduce the position of the otoconial debris in lateral cupulolithiasis or canalolithiasis based on two parameters: the direction of the nystagmus that appears when the patient lies down (if present) and the positional nystagmus evoked by the supine roll test. Methods: The theoretical results are then compared with a population of 170 patients observed in the last ten years for vertigo due to paroxysmal positional vertigo of the horizontal canal. Results: The study analyzed 170 cases of paroxysmal positional vertigo due to lateral canalolithiasis, comprising 141 geotropic and 29 apogeotropic forms. Among the geotropic cases, 80 showed no nystagmus in the supine position (GT0), 51 had supine nystagmus directed toward the healthy side (GT+, congruent), and 10 toward the affected side (GT−, incongruent). In the apogeotropic group, 10 had no supine nystagmus (AGT0), 16 exhibited nystagmus toward the affected side (AGT+, congruent), and only 1 toward the healthy side (AGT−, incongruent). Additionally, 2 cases showed monopositional apogeotropic nystagmus (mAGT), consistent with a “sieve-type” canal jam. Overall, 90 out of 170 patients (approximately 53%) had no nystagmus in the supine position: 80 out of 141 (≈57%) among geotropic forms and 10 out of 29 (≈34%) among apogeotropic forms. This difference was statistically significant (p = 0.0474, Yates correction), indicating that supine nystagmus is more frequent in geotropic than in apogeotropic variants. Conclusions: From the comparison between lying down and positional nystagmus, it is probably possible to identify the initial position of the fragments inside the lateral canal. This may be a useful clue for performing the correct liberatory maneuver. Instead, it is believed that to distinguish a jam located on the canal side of the cupula from a jam on the utricular side, one can only rely on the effective side of the liberatory maneuver.

Abstract: Cochlear homeostasis is critical for the preservation of hearing sensitivity by maintaining optimal cochlear fluid composition, sustaining electrochemical gradients, and supporting the function of sensory and supporting cells in the cochlea. Sensorineural hearing loss, resulting from the damage or loss of sensory hair cells, auditory neurons and other cochlear cells and structures, is intimately linked to disruptions in the homeostatic environment. In this narrative review, we explore the cellular and molecular pathways underpinning cochlear homeostasis in health and disease and examine the mechanisms by which failed homeostasis leads to sensorineural hearing loss. We further discuss current research avenues and emerging therapeutic strategies to restore or compensate for the loss of homeostatic balance. These interventions suggest a future where regenerative healing is possible, ultimately leading to permanent repair and functional recovery.

Abstract: Background. Differentiating Ménière’s disease (MD) from vestibular migraine (VM) remains difficult because current diagnostic frameworks are predominantly clinical and incorporate pure-tone thresholds, risking incorporation bias. We asked whether speech discrimination scores (SDS) alone can separate MD from VM at the patient level and whether adding a prespecified vestibular marker, the caloric–vHIT dissociation, pattern A (abnormal calorics with normal horizontal vHIT), improves performance. Methods. In a retrospective cohort (2015–2018) including definite MD (n=60) and definite VM (n=40) by Bárány/ICHD criteria, we trained patient-level logistic regression models with 5-fold out-of-fold validation and in-fold preprocessing. To avoid incorporation bias, PTA was excluded from all models. Predefined feature sets were: (1) SDS-only (bilateral SDS), (2) CalHiT-A-only (Yes/No; canal paresis ≥22% with horizontal-canal vHIT gain ≥0.80 in either ear), and (3) SDS+CalHiT-A. Discrimination was assessed by ROC–AUC with bootstrap 95% CIs; calibration and decision-curve analysis (DCA) are reported. An exploratory model encoded SDS as “affected/healthy.” Results. The SDS-only model achieved AUC 0.866 (95% CI 0.787–0.937). CalHiT-A-only yielded AUC 0.674 (0.561–0.778). Adding CalHiT-A to SDS did not improve discrimination (SDS+CalHiT-A AUC 0.844 [0.760–0.913]). The exploratory “affected/healthy” SDS encoding underperformed (AUC 0.801 [0.706–0.882]). CalHiT-A was significantly more prevalent in MD than in VM (56.7% [34/60] vs 17.5% [7/40]; Fisher’s exact p = 1.49×10⁻⁴). Calibration favored SDS-only, and DCA showed the highest net benefit for SDS-only across thresholds p=0.05–0.40. Conclusions. Bilateral SDS alone provides robust, well-calibrated discrimination between MD and VM and outperforms CalHiT-A and the affected/healthy SDS encoding. In this cohort, vestibular tests dissociation did not add diagnostic value beyond SDS at the patient level, supporting SDS-centered diagnostic workflows while reserving CalHiT-A for adjudication and phenotyping rather than primary classification.

Abstract: Background: Olfactory and taste disorders are associated with a variety of conditions, not only those directly affecting the nasal or oral cavity mucosa. In clinical practice, the acuity of the sense of smell is investigated subjectively using a variety of olfactory tests, both screening and diagnostic. The aim of this study was to develop an application that allows a patient to self-administer an olfactory and taste test at home. Methods: In the first stage, a literature review was carried out on the olfactory and taste tests available on the market. In the second stage, the best conditions for storing ST and TT were investigated. The third stage looked at how well patients of different ages and electronic literacy levels could per-form ST and TT independently. In the fourth stage, the feasibility of using STT for olfactory and taste screening was assessed. Results: The study used an olfactory test based on the ST and TT used in the Sensory Testing Capsule (STC), which can be used for olfactory and taste screening. Development of the app involved steps of registration, ordering, perform-ing the STT, and read-out of results. Simple instructions for performing the STT were cre-ated using graphics to illustrate the steps involved. Conclusions: The app could also be useful in the assessment of smell and taste by speech therapists before implementing multisensory therapy and used in occupational medicine to monitor the state of the sense of smell and taste in people who are occupationally exposed to toxic substances.

Abstract: Background: Parotid gland tumors pose diagnostic and surgical challenges due to their histological heterogeneity and proximity to the facial nerve. This study aimed to evaluate clinicopathological features and postoperative outcomes in a large cohort undergoing parotidectomy. Methods: This retrospective study included 314 patients who underwent parotidectomy between 2008 and 2024 at a tertiary center. Demographic data, tumor histology, and postoperative complications—particularly facial nerve paralysis—were analyzed. Histopathological features such as capsular, perineural, and lymphovascular invasion were also assessed. Results: Of all cases, 79% were benign, 14.6% malignant, and 6.4% non-neoplastic. Pleomorphic adenoma and Warthin tumor were the most common benign entities, while mucoepidermoid carcinoma was the most frequent malignancy. Malignant tumors were associated with higher rates of positive surgical margins (44.2%), capsular invasion (25%), and tumor necrosis (22%). Facial paralysis occurred in 4.4% of patients, more frequently among those with malignant tumors and extensive lymph node dissection. Capsular invasion and necrosis were rare in benign lesions but still observed, especially in pleomorphic adenoma. No significant differences in pathology were found based on place of birth. Conclusion: Most parotid tumors are benign, but certain histopathological features—such as necrosis, capsular and perineural invasion—are strong indicators of malignancy and should guide surgical planning and postoperative surveillance. These findings highlight the need for individualized, risk-adapted management strategies in parotid surgery to balance oncological safety with preservation of function.

Abstract: Background: In the present study, we focused on the periostin expression in Warthin’s tumor and malignant lymphomas, which require differentiation from these tumors. Objectives: we investigated the expression and the roles of periostin in the formation of parotid gland mass. Methods: Twenty-eight samples of parotid gland mass were investigate histopathologically and immunohistochemically. Result: Pathologically, tumors were diagnosed as Warthin’s tumors in 15 specimens and malignant lymphomas in 13 specimens. Increased periostin expression was observed in the stroma of Warthin's tumor and malignant lymphoma in 24 of 28 samples (12 Warthin's tumor, 12 malignant lymphoma) (85.7%). Periostin expression was observed in three different patterns: negative, superficial, and infiltrative. Statistically significant differences were found between the histological classification of the tumors　and periostin expression patterns. When periostin expression was examined in the same 28 specimens, increased periostin expression was observed in the tumor capsule in 13 specimens (46.4%). A statistically significant association was found between the presence or absence of periostin expression within the tumor capsule and the histology of parotid tumors. Conclusion and significance: Periostin may be involved in the development of Warthin's tumor and malignant lymphoma. Periostin may serve as a new biomarker for these diseases.

Abstract:

Background. Loss of smell can impair quality of life. Olfactory disorders (ODs) are often caused by viral infections, such as coronavirus disease 2019 (COVID-19). The aim of the study was to evaluate the effectiveness of olfactory training in patients with post-COVID OD. Materials and methods. The entire group consisted of 75 subjects (15 men and 60 women). They were randomly divided into two groups. Patients in both groups received pharmacological treatment (intranasal corticosteroids and vitamin A), salt irrigations, and elements of speech therapy olfactory training (SOT). Participants in the study group additionally carried out classical olfactory training (OT) using applicators with 4 scents twice a day. Olfactory function was assessed using the Sniffin Sticks' Test (SST). Results. For total SST score, the mean change before and after intervention in the study group was 7.9 points (p < 0.001). In the control group, the mean change was 2.8 points (p = 0.006). Conclusions. Classical OT appears to improve the recovery from post-COVID OD compared to pharmacological therapy with SOT elements alone. The use of intranasal corticosteroids, topical vitamin A, and saline nasal irrigation in our therapy seemed to help in improving olfaction. It is thought that the multidisciplinary team used here – doctor, speech therapist, and psychologist – may have also contributed to the effectiveness of the therapy.

Abstract: Otitis media is a common pediatric ear infection that, if left undiagnosed or misdiagnosed can lead to complications such as hearing loss. Traditional diagnostic methods rely on subjective clinical assessments which can result in variability in accuracy. The integration of artificial intelligence, particularly deep learning offers a promising approach for automated and objective diagnosis. This study reviews the application of deep learning algorithms in the automatic detection of otitis media using otoscopic images, with a focus on deep metric learning techniques and their diagnostic performance. An evaluation of deep learning-based models including convolutional neural networks (CNNs) and deep metric learning, was conducted. Performance metrics such as sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve (AUC-ROC) were analyzed. A comparative evaluation of traditional CNN-based models and deep metric learning techniques was done to assess their relative strengths in diagnostic accuracy and generalization to diverse datasets. The advantages of deep metric learning in improving model generalization and robustness were also discussed. AI-driven models demonstrated high accuracy in detecting otitis media, with deep metric learning enhancing feature differentiation and classification performance. Several studies reported sensitivity and specificity values exceeding 90% with AUC-ROC values approaching 1.0, indicating strong diagnostic capability. However, variations in dataset quality, image preprocessing, and model interpretability remain key challenges. Additionally, this review explores the clinical feasibility of AI-based otoscopic analysis by assessing the integration of AI into routine otolaryngological practice. Deep learning, particularly deep metric learning holds significant potential for enhancing the automated diagnosis of otitis media in pediatric patients. Future research should focus on dataset standardization, model transparency, and real-world clinical validation to ensure widespread adoption in healthcare settings.

Abstract: Backgrounds: Many reported rates of positive results by nicking enzyme amplification reaction (NEAR) applied together with the Abbott ID NOW™ COVID-19 (AIN) test and dry patient samples is lower than rates provided by other nucleic acid amplification tests. Few studies have used fresh samples, however. Methods: We conducted this retrospective study using fresh samples to determine the correlations among fever, associated symptoms, and the NEAR detection rate. Quarantined cases of suspected SARS-CoV-2 infection at Kunimoto ENT clinic (Jan 14, 2022–May 7, 2023) who had been in close contact with SARS-CoV-2-infected individuals were enrolled. Specimens were collected by the thin-diameter nasal sterile swab from the nasopharynx and examined immediately. We evaluated the positive-result rates, fever, and symptoms. Results: The total number of close-contact patients evaluated was 661 and AIN-positive cases was 427. The detection rate in the fever ≥37.4°C patients was 97% (257/266), significantly higher than the corresponding rate in the <37.4°C patients (170/395) (p<0.00001). The detection rate in the patients with ≤1 symptoms other than fever was 98% (394/402). Conclusions: These results suggest that the AIN results are sufficiently dependable when fresh samples are obtained from patients with a fever ≥37.4°C, and with more than one symptom.

Abstract: Hearing loss (HL) affects more than 1.5 billion people worldwide and remains a leading cause of disability across the lifespan. While genetic predispositions, otitis media (OM), and cholesteatoma are well-recognized contributors, Eustachian tube dysfunction (ETD) is an underappreciated but pivotal determinant of auditory morbidity. By impairing middle ear pressure (MEP) regulation, ETD drives conductive hearing loss (CHL) through stiffness and mass-loading effects, contributes to sensorineural hearing loss (SNHL) via altered window mechanics and vascular stress, and produces mixed hearing loss (MHL) when these pathways converge. A characteristic clinical trajectory emerges in which conductive deficits often resolve quickly with restored ventilation, whereas sensorineural impairment requires prolonged, physiology-restoring intervention, resulting in transient or persistent MHL. This review integrates mechanistic insights with clinical manifesta-tions, diagnostic approaches, and therapeutic options. Diagnostic frameworks that com-bine patient-reported outcomes with objective biomarkers such as wideband absorbance, tympanometry, and advanced imaging enable reproducible identification of ETD-related morbidity. Conventional treatments, including tympanostomy tubes and balloon dila-tion, offer short-term benefit but rarely normalize tubal physiology. In contrast, Eusta-chian tube catheterization (ETC) has emerged as a promising, mechanism-based inter-vention capable of reestablishing dynamic tubal opening and MEP regulation. Looking forward, integration of physiology-based frameworks with personalized diagnostics and advanced tools such as artificial intelligence (AI) may help prevent progression from reversible conductive deficits to irreversible SNHL or MHL.

Abstract: Background/Objectives: Tinnitus treatment is often based on coping strategies, as still no causal treatment is available. Based on our “Erlangen model” of tinnitus development and two pilot stud-ies, we treated tinnitus patients with individualized, non-masking low intensity noise (LIN) to reduce the tinnitus loudness. Methods: 72 adult patients with a tinnitus severity index below IV (tinnitus health question-naire, THQ), a hearing loss not exceeding 40 dB up to 6 kHz, and without experience in hearing aid (HA) usage were included in this study. Their audiograms, tinnitus pa-rameters, THQ scores and optimal LIN were determined individually. Patients were double-blinded assigned to a treatment only (TO) or placebo-and-treatment (PT) group. The TO patients received treatment for four weeks while the PT patients ini-tially received placebo (low intensity white noise) stimulation for two weeks and hereinafter treatment for four weeks. Every two weeks, the measurements listed above were repeated. Long term effects on THQ were assessed four weeks after the end of treatment. Data were analyzed by parametric and nonparametric statistics. Results: We identified a significant decrease in the THQ score already after two weeks of treatment that was still present four weeks after the end of treatment in the TO group. In individual cases, tinnitus could be suppressed completely by LINTS. The PT group did profit much less, as the initial placebo treatment seemed to counteract the LIN ef-fects. Conclusions: Individually fitted LIN treatment is able to suppress tinnitus. The optimal fitting of the LIN is crucial for treatment success.

Abstract: Background: Otitis Media with Effusion (OME) is characterized by persistent middle ear effusion without acute infection. Type2 inflammation, mediated by IL-4 and IL-13 signaling through the IL-4Rα receptor, has been implicated in the pathogenesis of chronic rhinosinusitis with nasal polyps, asthma, and possibly OME. Refractory OME in adults remains a therapeutic challenge, as conventional treatments often fail to provide long-term resolution. Targeted biologic therapies that modulate type 2 inflammation may offer a novel therapeutic option. Methods: A 60-year-old man with a 15-year history of allergic rhinitis and chronic rhinosinusitis with nasal polyps, as well as multiple asthma exacerbations, presented with recurrent bilateral aural fullness, hearing loss, and tinnitus. His symptoms persisted despite repeated tympanic punctures, insufflation, and corticosteroid treatment. Otoscopic examination revealed dull tympanic membranes with effusion. Audiometry showed conductive hearing loss with a B-type tympanogram on the left and an A-type curve on the right. Laboratory evaluation demonstrated mildly elevated peripheral eosinophils. Results: The patient was diagnosed with OME, likely secondary to type 2 inflammation. Treatment with Stapokibart (CM310), a humanized anti–IL-4Rα monoclonal antibody, was initiated in March 2025. After nine biweekly injections, the patient experienced complete resolution of aural fullness. Otoscopy and tympanometry normalized, and audiometric thresholds improved significantly. No recurrence of ear symptoms was observed during follow-up. Conclusions: This case illustrates that IL-4Rα blockade with Stapokibart may be effective in refractory OME associated with type 2 inflammation. Early recognition of type 2–driven mechanisms in chronic middle ear disease could facilitate targeted therapy, offering symptom resolution and improved quality of life in patients unresponsive to conventional treatment.ral fullness; otitis media with effusion; allergic rhinitis.

Abstract: Background: Dynamic whole-body (D-WB) FDG PET/CT is a novel technique that enables the direct reconstruction of multiparametric images representing the FDG metabolic uptake rate (MRFDG) and "free" FDG (DVFDG). Applying complementary parameters with distinct characteristics compared to static SUV images, the aims of this study are as follows: 1) to determine the threshold values of SUV, MRFDG, and DVFDG for malignant and benign lesions; 2) to compare the specificity of MRFDG and DVFDG images with static SUVbw images; 3) to assess whether any of the dynamic imaging parameters correlate more significantly with malignancy or non-malignancy in the examined lesions based on the measured values obtained from D-WB FDG PET/CT. Results: Patlak PET parameters (MRFDG, DVFDG) combined with mean SUVbw achieved the highest accuracy of 0.82 (F1-score = 0.90) for malignancy detection. Classification accuracy in tumors was 0.86 (F1 = 0.92), lymph nodes reached 0.81 (F1 = 0.89). Relative contribution analysis showed that DVFDG accounted for up to 65 % of classification weight. The ROC analysis demonstrated AUC values above 0.8 for all models, with optimal thresholds achieving sensitivities around 0.85 and specificities up to 0.93. Thresholds for malignancy detection were for mean values: SUVbw>5.8 g/mL, MRFDG>0.05 µmol/mL/min, DVFDG> 68 %; for maximal values: SUVbw> 8.7 g/mL, MRFDG> 0.11 µmol/mL/min, DVFDG> 202 %. Conclusions: The D-WB [¹⁸F]FDG PET/CT images in this study highlight the potential for improved differentiation between malignant and benign lesions compared to conventional SUVbw imaging in patients with locally advanced head and neck cancers presenting with cervical lymphadenopathy and carcinoma of unknown primary (CUP). This observation may be particularly relevant in common diagnostic dilemmas, especially in distinguishing residual or recurrent tumors from post-radiotherapy changes. Further validation in larger cohorts with histopathological confirmation is warranted.

Abstract: Background: Cholesteatoma is a destructive middle ear lesion that compromises hearing and quality of life, for which endoscopic ear surgery (EES) has emerged as a minimally invasive alternative to microscopic approaches. While recurrence and audiological outcomes are frequently reported, patient-centered evaluations using validated patient-reported outcome measures (PROMs) remain limited. Objective: This study aimed to assess postoperative quality of life in patients undergoing exclusive endoscopic cholesteatoma surgery, using validated patient-reported outcome measures. Methods: We conducted a prospective observational cohort study in a tertiary referral center, enrolling 41 patients who underwent exclusive endoscopic cholesteatoma surgery over 20 months. Pre- and postoperative QoL was assessed using the Chronic Otitis Media Questionnaire-12 (COMQ-12) and the Glasgow Benefit Inventory (GBI). Follow-up included assessments at 3, 6, and 12 months, complemented by non–echo–planar diffusion-weighted magnetic resonance imaging (DWI-MRI) to detect residual or recurrent disease. Results: COMQ-12 scores improved significantly from baseline (54.0 ± 4.2) to 12 months (10.2 ± 3.3; mean difference –43.8, 95% CI: –46.1 to –41.5; p < 0.001). GBI scores were consistently high, increasing from 82.6 ± 4.8 at 6 months to 84.1 ± 4.9 at 12 months (p < 0.001). Audiometric evaluation demonstrated a significant postoperative improvement, with the mean air–bone gap (ABG) decreasing from 52.1 ± 5.3 dB pre-operatively to 26.4 ± 4.7 dB postoperatively (p < 0.001), indicating substantial closure of the conductive gap. Conclusions: Exclusive endoscopic cholesteatoma surgery is associated with significant improvement in disease-specific and general QoL, favorable audiological outcomes, and low recurrence rates. These findings support EES as a safe, effective, and patient-centered alternative to microscopic techniques for the management of middle ear cholesteatoma.

Abstract: Surgical treatment is the only option for cholesteatoma; however, the recurrence rate is high, and the incidence of residual cholesteatoma recurrence largely depends on the surgeon's skill. Training deep neural network (DNN) models typically requires large datasets, but the prevalence of cholesteatoma is low (1 in 25,000 people). However, cholesteatoma remains difficult to treat. Developing analytical methods to improve ac-curacy with limited datasets remains a significant challenge in medical artificial intelli-gence (AI) research. This study introduces an AI-based system for detecting residual cholesteatoma in surgical field videos. A retrospective analysis was conducted on 144 cases from 88 patients who underwent surgery. The training dataset comprised videos of cholesteatoma lesions recorded during surgery and intact middle ear mucosa after lesion removal. These videos were captured using both endoscope and microscope for AI model development. The diagnostic accuracy was approximately 80% for both endoscopic and microscopic images. Although the diagnostic accuracy for microscopic images was slightly lower, focusing on the lesion center improved the accuracy to a level comparable to that of endoscopic images. This study demonstrates the diagnostic feasibility of AI-based cholesteatoma detection despite a limited sample size highlighting the value of proof-of-concept studies in clar-ifying technical requirements for future clinical systems and is the first AI study to use videos from both modalities.

Abstract: Background: As surgeons become more au fait with the strengths and limitations of the endoscope in middle ear surgery, the boundaries of same are being explored. What was once thought to be technically challenging has become the norm for some. One such important operative step is that of ossicular chain reconstruction (ossiculoplasty), a challenging task when operating single handedly. The reporting of outcomes in otological surgery remains somewhat ill-defined, but certainly the improvement of audiological thresholds when performing ossiculoplasty is a clear area of focus. Methods: A case report of a totally endoscopic ear surgery case (Cohens classification 3) and review of the literature. Results: Case report discusses a favourable audiological and surgical outcome despite a number of negative prognostic issues. The literature highlights the need for an individualised approach to each patient when considering the type and extent of defect, state of the middle ear mucosa and also in selecting the prosthesis and graft material. Conclusions: Results of endoscopic ossiculoplasty are extremely variable. There are a number of factors to be considered in order to achieve optimal outcomes.

Abstract: Chronic rhinosinusitis (CRS) is a prevalent inflammatory condition of the paranasal sinuses involving at least 12 weeks of persistent sinonasal inflammation, often with nasal obstruction, discharge, facial pressure, and hyposmia. While the burden of CRS on quality of life and respiratory health is well recognized, its potential impact on orbital structures is an area of growing clinical attention. Chronic sinus disease can therefore extend beyond the sinuses to involve the orbit, leading to ophthalmologic complications that range from subtle vision changes to severe, sight-threatening emergencies. Traditionally, orbital complications are more commonly associated with acute sinusitis (particularly in children), but contemporary evidence highlights that chronic rhinosinusitis and its sequelae – including mucoceles, chronic infections (bacterial or fungal), and protracted inflammation – can likewise produce significant orbital consequences. These manifestations underscore the need for vigilance and a multidisciplinary approach in managing CRS patients with ocular symptoms. This review aims give an updated understanding of this interdisciplinary topic to clinicians in both otolaryngology and ophthalmology, guiding prompt recognition and effective management of CRS patients with orbital involvement.