Stenzel, Jake G

ABSTRACTObjectivesTransnasal endoscopic sphenopalatine artery ligation (TESPAL) has been proposed as a first‐line therapy for intractable epistaxis before utilizing posterior nasal packing and embolization. A specific procedure code for TESPAL was newly introduced in 2018, adding to two prior codes for procedural control of epistaxis. This study compares all‐time utilization of the TESPAL CPT code in Medicare beneficiaries with alternative procedural codes for epistaxis management.MethodsThe publicly available data from the Centers for Medicare and Medicaid Services in the 2013–2022 period was analyzed for the reporting of TESPAL (31241), transcatheter permanent occlusion or embolization of noncentral nervous system, head, or neck (61626), and endoscopic control of epistaxis (31238) codes. Welch two sample t‐test and linear regression were used to characterize CPT code utilization.ResultsFrom 2018 to 2022, TESPAL CPT code reporting averaged 378 instances annually, with a stable utilization trend (p = 0.432). CPT codes 61626 and 31238 averaged 1429 and 3779 instances annually, respectively. CPT 31238 showed a significant decline (p < 0.001), and CPT 61626 showed a stable trend (p = 0.082). There was a significant decline in CPT code 31238 use after 2018 (p < 0.01). CPT 61626 showed a significant increase in usage post‐2018 (t = 2.90, p = 0.044).ConclusionAfter an initial increase in 2019, TESPAL reporting flattened, while CPT 61626 (which includes all embolization in head and neck vessels) significantly increased post‐2018. As recent studies show significant advantages of TESPAL over embolization, these findings warrant further attention and study.Level of Evidence3.

AbstractObjectivesThe study aimed to extract online comments of otolaryngologists in the 20 most populated cities in the United States from healthgrades.com, develop and validate a natural language processing (NLP) logistic regression algorithm for automated text classification of reviews into 10 categories, and compare 1‐ and 5‐star reviews in directly‐physician‐related and non‐physician‐related categories.Methods1977 1‐star and 12,682 5‐star reviews were collected. The primary investigator manually categorized a training dataset of 324 1‐star and 909 5‐star reviews, while a validation subset of 100 5‐star and 50 1‐star reviews underwent dual manual categorization. Using scikit‐learn, an NLP algorithm was trained and validated on the subsets, with F1 scores evaluating text classification accuracy against manual categorization. The algorithm was then applied to the entire dataset with comparison of review categorization according to 1‐ and 5‐star reviews.ResultsF1 scores for NLP validation ranged between 0.71 and 0.97. Significant associations emerged between 1‐star reviews and treatment plan, accessibility, wait time, office scheduling, billing, and facilities. 5‐star reviews were associated with surgery/procedure, bedside manner, and staff/mid‐levels.ConclusionThe study successfully validated an NLP text classification system for categorizing online physician reviews. Positive reviews were found to have an association with directly‐physician related context. 1‐star reviews were related to treatment plan, accessibility, wait time, office scheduling, billing, and facilities. This method of text classification effectively discerned the nuances of human‐written text, providing valuable insights into online healthcare feedback that is scalable.Level of evidence: Level 3