Kim K, et al. Yonsei Med J. 2019 May;60(5):474-480. https://doi.org/10.3349/ymj.2019.60.5.474

Objectives: The aim of this study was to investigate the preoperative clinical and hematologic variables, including the neutrophil-to-lymphocyte ratio (NLR), that can be used to predict malignancy in patients with atypia of undetermined significance (AUS) thyroid nodules; we further aimed to develop a machine learning-based prediction model. Methods: We enrolled 280 patients who underwent surgery for AUS nodules at the Wonju Severance Christian Hospital between 2018 and 2022. A logistic regression-based model was trained and tested using cross-validation, with the performance evaluated using metrics such as the area under the receiver operating characteristic curve (AUROC). Results: Among the 280 patients, 116 (41.4%) were confirmed to have thyroid malignancies. Independent predictors of malignancy included age, tumor size, and the Korean Thyroid Imaging Reporting and Data System (K-TIRADS) classification, particularly in patients under 55 years of age. The addition of NLR to these predictors significantly improved the malignancy prediction accuracy in this subgroup. Conclusions: Incorporating NLR into preoperative assessments provides a cost-effective, accessible tool for refining surgical decision making in younger patients with AUS nodules.

Intra-abdominal infection is a common, serious complication in patients undergoing emergency abdominal surgery following blunt abdominal trauma. Infectious conditions increase the incidence of autoimmune hemolytic anemia (AIHA), but reports of AIHA occurring after abdominal trauma surgery are rare. Therefore, we report a case of sepsis due to fasciitis and AIHA after abdominal trauma surgery which was successfully managed following the appropriate treatment of both conditions.

Purpose: This study aimed to investigate useful preoperative clinical and hematologic variables in predicting malignancy in patients with the atypia of undetermined significance (AUS) nodules, and to suggest a machine learning-based prediction model. Methods: We enrolled 280 patients who underwent surgery for the AUS nodules at Wonju Severance Christian Hospital between 2018 and 2022. We evaluated preoperative hematologic indices, including Delta Neutrophil Index (DNI), Neutrophil-to-Lymphocyte Ratio (NLR), and Platelet-to-Lymphocyte Ratio (PLR), as well as preoperatively identifiable clinical variables such as age and sex at diagnosis, history of radiation exposure, familial history of thyroid cancer, primary tumor size, and the 2016 Korean Thyroid Imaging Reporting and Data System (K-TIRADS) classification. Results: A total of 116 patients (41.4%) were finally diagnosed with various types of thyroid malignancy, excluding 32 patients (11.4%) with thyroid cancer incidentally identified. Age at diagnosis (p = 0.012), primary tumor size (p = 0.048), and the K-TIRADS classification (p = 0.003) were independent risk factors to predict the diagnosis of malignancy in patients with AUS nodules younger than 55 years, not in those aged of 55 years or older. Adding the NLR to these risk factors significantly improved the predictability for malignancy in the same patient group (p < 0.001). Conclusions: The inclusion of NLR in the ma-lignancy prediction model enhances the predictive accuracy for malignancy in younger patients with AUS nodules. This finding suggests that incorporating NLR into preoperative assessment could refine management strategies and improve decision-making for surgical interventions.