Citations

Clear

4 citation(s) found for "Sramek, Michael".

Prediction of Rhinologic Surgery Within 90 Days Using Item‐Level SNOT‐22 Responses: A Multisite Machine Learning Study of 35,170 Patients
Sramek, Michael , Kumar, Nitish , Patel, Shrinath, Miglani, Amar , Marino, Michael, Lal, Devyani , Kumar, Nitish , Lal, Devyani , Marino, Michael J.

Mayo Clinic

International Forum of Allergy & Rhinology | September 10, 2026 | Volume: No volume available | Issue: No issue available | Pages: No page available

10.1002/alr.70273 | PMID 42722008 Get It

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.
Transoral Robotic Resection of Glossopharyngeal Neurofibroma: A Case Report
Messick, Cody L. , Swisher, Austin R., Gibbs, Hannah M. , Sramek, Michael T. , Klusovsky, Laura, Entezami, Payam , Lewis, James S., Swisher, Austin R , Klusovsky, Laura E., Lewis, James S., Chang, Brent A.

Mayo Clinic

World Journal of Otorhinolaryngology - Head and Neck Surgery | July 7, 2026 | Volume: No volume available | Issue: No issue available | Pages: No page available

10.1002/wjo2.70123 | PMID 42500081 Get It

ABSTRACT This case highlights the diagnostic challenges posed by rare oropharyngeal neurofibromas, their potential to mimic other conditions, and the novel application of transoral robotic surgery (TORS) for the management of an oropharyngeal neurofibroma. A 47‐year‐old female presented with a 1‐year history of a left tonsillar mass. Clinical evaluation, imaging, and biopsy results were inconclusive but raised suspicion for a neoplasm. The patient underwent robotic‐assisted tonsillectomy and mass resection. Subsequent histopathological evaluation confirmed a benign spindle cell tumor consistent with neurofibroma. Oropharyngeal neurofibromas may present diagnostic challenges due to their resemblance to common tonsillar pathologies. Imaging and biopsies may not always provide definitive diagnoses, necessitating surgical excision for accurate characterization. This case demonstrates the utility of TORS, offering improved visualization and access while minimizing patient morbidity.
Distinguishing Inverted Sinonasal Papilloma and Respiratory Epithelial Adenomatoid Hamartoma: A Single Institution Case Series
Swisher, Austin R. , Razmi, Samuel E., Sramek, Michael T. , Gomes, Pedro L., Schmitt, Alessandra, Miglani, Amar , Lal, Devyani, Marino, Michael J. , Razmi, Samuel E. , Eells, Annica C. , Razmi, Samuel , Swisher, Austin R , Gomes, Pedro L., Schmitt, Alessandra, Lal, Devyani

Mayo Clinic

International Journal of Surgical Pathology | May 15, 2026 | Volume: No volume available | Issue: No issue available | Pages: No page available

10.1177/10668969261446657 | PMID 42135597 Get It

Inverted sinonasal papilloma (ISP) and respiratory epithelial adenomatoid hamartoma (REAH) are sinonasal lesions with overlapping clinical, radiographic, and histologic features, making accurate diagnosis challenging. ISP is a benign but aggressive tumor with a propensity for local destruction, recurrence, and malignant transformation, whereas REAH is a hamartomatous lesion often arising in the olfactory cleft. We present four patients with lesions initially suspected to be ISP based on intraoperative frozen section but ultimately diagnosed as REAH on permanent pathology. All patients had polypoid sinonasal masses, frequently involving or adjacent to the olfactory cleft. Intraoperative frozen sections were often inconclusive or favored ISP, reflecting the difficulty of distinguishing these entities. Histologic analysis revealed that epithelial thickness served as a key morphologic feature differentiating ISP from REAH, with REAH exhibiting ciliated glandular proliferation and ISP characterized by hyperplastic epithelium with features of columnar and squamous differentiation. These patients underscore the diagnostic pitfalls of small biopsies and frozen sections, and highlight the importance of permanent specimens and collaboration with experienced pathologists. Accurate differentiation is critical, as management strategies differ substantially: ISP requires aggressive resection and long-term surveillance, while REAH may be treated with limited excision and minimal follow-up.
Lymphoepithelial Carcinoma of the Salivary Gland: A Systematic Review and Single Institution Experience
Gibbs, Hannah M. , Sramek, Michael T. , Hintze, Justin M. , Gibbs, H G , Hintze, Justin , Vasudevan, Srivatsa Surya , Nathan, Cherie-Ann O , Chang, Brent A.

Mayo Clinic

Otolaryngology–Head and Neck Surgery | December 31, 2025 | Volume: 174 | Issue: 2 | Pages: 297-304

10.1002/ohn.70095 | PMID 41474179 Get It

Abstract Objective Lymphoepithelial carcinoma of the salivary gland (LECSG) is a rare malignancy. The purpose of this study is to evaluate the clinical features of LECSG with a focus on the role of Epstein‐Barr virus (EBV). Data Sources PubMed, Embase, Web of Science, institutional pathology Natural Language search tool. Review Methods Retrospective review of patients diagnosed with LECSG at a single institution and a systematic literature review. Full text articles in English were included. Results 285 cases of LECSG identified via literature review and an additional 10 within our institution. Most tumors were in the parotid gland (70.5%). Lymph node metastasis was observed in 28%. Most cases were in Asian or Inuit patients (70.5%). EBV association was positive in 52%, and 87.6% of these were in endemic populations. Treatment primarily involved surgical resection (65.8%), often combined with adjuvant therapy (50.2%). No significant differences in disease‐free survival (DFS) or disease‐specific survival (DSS) were observed by EBV status. Advanced tumor stage was associated with worse DFS ( P < .0001) and worse DSS ( P < .0001). Lymph node metastasis was also associated with reduced DSS ( P = .04). Independent predictors of poorer DFS and DSS included late tumor and endemic region of origin. Conclusion This comprehensive analysis of 295 salivary gland LEC cases provides valuable insights into the clinical behavior, pathological features, and treatment outcomes of this rare malignancy. The study highlights the potential role of EBV in tumor pathogenesis, particularly in endemic populations, and emphasizes the need for further research to establish optimal management strategies.