Kumar, Nitish

ABSTRACT Background Optimizing access to cost‐effective care in capacity‐constrained health systems is a contemporary imperative. We evaluated whether machine learning (ML) models using patient‐reported data could optimize access for patients requiring surgical care in rhinology clinics, without need for CT imaging. The outcome was defined as any rhinologic surgery within 90 days of initial evaluation. Methods A de‐identified electronic dataset from patients seen at five distinct sites within an integrated healthcare system between 2018 and 2025 was used to train models. Demographic data and 22‐item Sinonasal Outcome Test (SNOT‐22) responses were studied. Models were trained using stratified 5‐fold cross‐validation with an 80% development cohort and validated in a 20% held‐out validation cohort. Hyperparameters were optimized with Optuna. The primary outcome was performance of any rhinologic surgical intervention within 90 days of initial SNOT‐22. Results Data from 35,170 patients were evaluated. Item‐level responses outperformed use of total SNOT‐22 score in the models. Among models, XGBoost demonstrated best discrimination with AUC of 0.70 (95% CI, 0.69–0.71), outperforming logistic regression (0.66), random forest (0.63), and TabNet (0.66) (all p < 0.001). At optimal threshold, XGBoost achieved 66% sensitivity, 64% specificity, 28% PPV, and 90% NPV. Top predictors for surgery were age, nasal blockage, facial pain or pressure, and decreased sense of smell or taste. Validation on the held‐out cohort remained stable (AUC 0.70), with strong discrimination across sites despite surgical rates ranging from 11.5% to 27.4%. Conclusions Demographics and item‐level SNOT‐22 responses were successful in developing an ML model that demonstrated moderate discrimination and high NPV (90%) for performance of surgery within next 90 days. ML models balanced with human oversight may accelerate triage and optimize surgical yield for rhinology clinics.

ABSTRACT Objective Odontogenic sinusitis (ODS) ranges from isolated maxillary disease to pansinusitis. We compared patient characteristics, microbial and histopathological features, and symptom outcomes following endoscopic sinus surgery (ESS) between low and high radiographic burden ODS patients. Methods ODS patients undergoing ESS between 01/2013 and 08/2024 were reviewed. Preoperative CT scans were used to classify patients into high radiographic burden [with ostiomeatal complex (OMC) opacification] and low radiographic burden ODS [clear OMC]. Demographic, microbiological, and histopathological data were analyzed. Symptom improvement was assessed using pre‐ and post‐operative SNOT‐22 scores. Results Eighty‐seven patients were identified (high CT burden: 70; low CT burden: 17). High CT burden ODS was associated with older age ( p = 0.014), higher overall degree of inflammation ( p = 0.002), hyperplastic/papillary epithelial changes ( p = 0.034), and neutrophil infiltration ( p = 0.003). Culture of classic ODS bacteria ( Fusobacterium spp., Prevotella spp., mixed anaerobes, Streptococcus anginosus group) did not correlate with CT disease burden ( p = 0.110). No independent predictors of radiographic high‐burden disease were identified. Post‐ESS, significant reduction in total and rhinologic SNOT‐22 scores was only observed in the radiographic high‐burden ODS group ( n = 39; median reductions: 23 and 12 respectively; p < 0.001). Conclusion High radiographic burden was associated with older patients and with tissue inflammation level. Classic ODS bacterial profile did not associate with increased CT burden. While these findings remain exploratory, the observed differences in inflammatory and symptomatic profiles between groups suggest that radiographic burden warrants further study as a potential factor in ODS clinical decision‐making. Level of Evidence 3.

ABSTRACT Objective Surgical repair and 3D‐printed customized septal prosthesis (3D‐PCSP) are options for septal perforation treatment. We performed a study to compare the clinical outcomes of surgery and 3D‐PCSP using the NOSE‐Perf Scale (NPfS). Methods A chart review was performed on patients undergoing surgical repair or 3D‐PCSP placement between January 2018 and July 2024. The change in NPfS was used as primary endpoint. Demographics, ASA score, perforation size, etiology, and follow‐up duration were reported. Results Thirty‐five patients, 23 for surgical repairs and 12 for 3D‐PCSP, were included in this review [median (IQR)]. In the surgical repair group, perforation length and height measured 12 (10–18) mm and 10 (8–15) mm, respectively. Baseline NPfS was 24 (16–32), and this decreased to 8 (6–13) following surgical repair ( p < 0.001). Follow‐up time was 12 (5–21) months. In the 3D‐PCSP group, septal perforation length and height measured 25 (15–30) mm and 17 (15–20) mm, respectively. The baseline NPfS was 17 (3–24.5), and this decreased to 9.5 (7–13) following 3D‐PCSP placement ( p = 0.001). The follow‐up was 18.4 (16–23) months. NPfS reduction was greater for surgical repair ( p = 0.018). Conclusions Surgery and 3D‐PCSP offer meaningful symptom relief for NSP patients. Treatment decisions should be individualized through shared decision‐making that considers patient comorbidities, preferences, surgeon experience, and risk tolerance. In this cohort, surgical repair was associated with greater NPfS reduction compared with 3D‐PCSP placement. Level of Evidence 3.

ABSTRACT Objectives We evaluated the impact of teprotumumab therapy ( TT ) introduction on orbital decompression ( OD ) utilization for thyroid eye disease ( TED ) and compared rates of significant exophthalmos reduction ( SER ) and diplopia between TT and OD . Methods Newly diagnosed TED patients treated pre (2015–2020) and post teprotumumab (2020–2025) FDA approval were identified from the EHR . Utilization trends, diplopia rates, and immediate (≤ 6 weeks post‐intervention) and long‐term follow‐up SER (≥ 2 mm reduction) were studied. Results Of 406 TED patients, 53 (36.8%) underwent OD in the pre‐ TT cohort ( n = 144). Post‐teprotumumab approval ( n = 262), primary OD was performed in 29 (11.1%), of which 3 (10.3%) were subsequently placed on TT ; primary TT was used in 68/262 (25.9%) with subsequent OD performed in 9 (13.2%). The remaining patients used other treatments (corticosteroids, orbital radiation, rituximab, tocilizumab, etc.). In the overall cohort, immediate SER was achieved in 94.4% of OD versus 83.8% of TT patients ( p = 0.028), with greater median reduction in the OD group (5 vs. 4 mm; p = 0.001). At long‐term follow‐up (median 13 vs. 12 months), SER was sustained in 85.4% of OD and 62.9% of TT patients ( p = 0.042). Pre‐therapy diplopia was more prevalent in TT vs. OD patients (79.4% vs. 59.7%; p = 0.019). New‐onset posttreatment diplopia was higher in the OD group (20.7% vs. 5.9%; p = 0.008). Conclusions Rates of OD surgery declined following FDA approval of teprotumumab. OD achieved sustained and greater exophthalmos reduction but carried a higher risk of diplopia. Contemporaneous OD indications may have evolved to use in TT‐recalcitrant TED or those in need of urgent decompression. Level of Evidence 4.

Background Mepolizumab blocks IL-5, targeting eosinophilic type-2 inflammation. Due to existing phenotype driven patient selection, evidence of its effectiveness in primary diffuse CRS and CRS without nasal polyps (CRSsNP) and in real-world populations is limited. Our objective was to evaluate the real-world effectiveness of mepolizumab in patients with primary diffuse CRS, regardless of nasal polyp status, and to assess outcomes across CRS phenotypes and prior surgical history. Methods Adults with primary diffuse CRS treated with mepolizumab for ≥6 months were identified. Pre- and post-therapy outcomes included serum eosinophil counts, Lund-Mackay CT scores, Lund-Kennedy endoscopic scores, and SNOT-22 symptom scores. Subgroup analyses were performed by CRS phenotype (CRSwNP vs . CRSsNP) and prior endoscopic sinus surgery (ESS). Biologic switching and discontinuation were recorded. Results Among 277 patients (mean age 60.8 ± 14.7 years; 54.9% female), 93.5% had type-2 comorbidities, 29.6% had CRSsNP, and 27.8% were ESS-naïve. The median duration of mepolizumab therapy was 31 months. Mepolizumab therapy significantly reduced serum eosinophils (median 0.57 to 0.07 ×10 9 /L, p&lt;0.001) and Lund-Mackay scores (median 14 to 10, p&lt;0.001), which was consistent across all subgroups. Improvements in SNOT-22 and endoscopic scores were modest and not consistently significant. CRSwNP patients were more likely to undergo ESS during therapy, but time to first post-therapy ESS was longer than in CRSsNP. There were no differences in likelihood of undergoing ESS during therapy, time to subsequent ESS, or oral corticosteroid use between prior ESS and ESS-naïve patients. Biologic switching occurred in 24.9%, and discontinuation in 16.6%, primarily due to disease recalcitrance. Conclusion Mepolizumab effectively reduced systemic eosinophilia and radiographic disease burden in primary diffuse CRS, independent of phenotype or prior ESS. Symptom improvement was variable, highlighting the heterogeneity of clinical response. These findings support an endotype-driven approach to biologic therapy and suggest that IL-5 blockade may benefit selected CRSsNP patients.

Key Points Contemporary aspirin exacerbated respiratory disorder (AERD) therapy commonly includes aspirin desensitization (55%) and biologics (48%). Aspirin desensitization therapy has higher discontinuation rates than biologics. Patients receiving biologics are younger, and ∼25% of the patients switch to other agents.