Background/Objectives: Studies attempting to predict the development of severe respiratory failure in patients with a COVID-19 infection using machine learning algorithms have yielded different results due to differences in variable selection. We aimed to predict the development of severe respiratory failure, defined as the need for high-flow oxygen support, continuous positive airway pressure, or mechanical ventilation, in patients with COVID-19, using machine learning algorithms to identify the most important variables in achieving this prediction. Methods: This retrospective, cross-sectional study included COVID-19 patients with mild respiratory failure (mostly receiving oxygen through a mask or nasal cannula). We used XGBoost, support vector machines, multi-layer perceptron, k-nearest neighbor, random forests, decision trees, logistic regression, and naïve Bayes methods to accurately predict severe respiratory failure in these patients. Results: A total of 320 patients (62.1% male; average age, 54.67 ± 15.82 years) were included in this study. During the follow-ups of these cases, 114 patients (35.6%) required high-level oxygen support, 67 (20.9%) required intensive care unit admission, and 43 (13.4%) died. The machine learning algorithms with the highest accuracy values were XGBoost, support vector machines, k-nearest neighbor, logistic regression, and multi-layer perceptron (0.7395, 0.7395, 0.7291, 0.7187, and 0.75, respectively). The method that obtained the highest ROC-AUC value was logistic regression (ROC-AUC = 0.7274). The best predictors of severe respiratory failure were a low lymphocyte count, a high computed tomography score in the right and left upper lung zones, an elevated neutrophil count, a small decrease in CRP levels on the third day of admission, a high Charlson comorbidity index score, and a high serum procalcitonin level. Conclusions: The development of severe respiratory failure in patients with COVID-19 could be successfully predicted using machine learning methods, especially logistic regression, and the best predictors of severe respiratory failure were the lymphocyte count and the degree of upper lung zone involvement.

Background/Objectives: NPC is a radiosensitive malignancy with high recurrence rates despite therapeutic advances. This study aimed to identify radiologic and metabolic predictors of recurrence in newly diagnosed NPC by integrating MRI and ¹⁸F-FDG PET/CT parameters. Methods: Fifty-two patients with biopsy-proven, previously untreated NPC who underwent pre-treatment MRI and ¹⁸F-FDG PET/CT were retrospectively analyzed. Local tumor features, nodal status, and response patterns were evaluated using MRI and PET/CT-derived metrics: SUVmax, SUVmean, SUVpeak, MTV, and TLG. The post-treatment MRI response was categorized into six patterns. Univariate and multivariate analyses were performed to identify independent predictors. Results: Recurrence occurred in 27% of patients. Based on the multivariate analysis, PNI, extensive PPS invasion, GTV, and metastatic LN count were identified as independent predictors of recurrence (PNI: OR = 1.60, p = 0.029; PPS: OR = 1.23, p = 0.027; GTV: OR = 1.08, p = 0.042; LN count: OR = 1.20, p = 0.031). PNI and PPS invasion were significantly associated with local failure (HR = 8.21, p = 0.008 and HR = 3.52, p = 0.043, respectively). GTV was independently associated with an increased risk of local (HR = 1.14, p = 0.021) and distant recurrence (HR = 1.19, p = 0.024). The presence of metastatic disease at diagnosis (HR = 6.27, p = 0.027) and a higher LN count (HR = 1.17, p = 0.028) were also linked to distant failure. Conclusions: Imaging-derived predictors including GTV, PNI, LN burden, and MRI-based response patterns demonstrate prognostic value for disease recurrence in NPC and may guide risk-adapted treatment strategies.

Objective: This study aimed to characterize computed tomography (CT) imaging features of adult intussusception, identify underlying lead points, and correlate morphological findings (segment length, transverse diameter) with clinical presentation. Materials and Methods: Nineteen surgically confirmed adult intussusception cases were retrospectively analyzed. Demographic data, CT findings, intussuscepted segment length, transverse diameter, presence of a lead point, and obstruction status were recorded. Results: The mean patient age was 57.1 ± 14.1 years. The ileum was the most commonly affected segment (57.9%). A lead point was identified on CT in 94.7% of cases, with lipoma being the most frequent lesion. Malignant lesions were found in 21.1% of patients, consistent with the literature. Transverse diameter was significantly greater in cases with obstruction (p = 0.002). Although segment length was higher in the obstruction group, the difference was not statistically significant (p = 0.052). Conclusion: CT is not only effective in diagnosing adult intussusception but also provides valuable information on its etiology and severity through parameters such as lead point detection and signs of obstruction. CT-derived measurements like transverse diameter and segment length may have predictive value in clinical decision-making. Further large-scale, prospective studies are needed to validate these findings.

Background/Objectives: Advancements in molecular diagnostics and targeted therapies have significantly transformed the management of non-small cell lung cancer (NSCLC). Rare MET rearrangements, including novel fusions such as HLA-DRB1-MET and HLA-DQB2-MET, represent actionable genetic alterations with critical therapeutic implications. This review synthesizes findings from multiple case reports to highlight the efficacy of MET tyrosine kinase inhibitors (TKIs) in MET-driven oncogenesis. Methods: A systematic review of published case reports and studies on MET rearrangements in NSCLC was conducted. Data were analyzed to assess the clinical outcomes of patients treated with MET TKIs, such as crizotinib and tepotinib. Additionally, our case report demonstrates the utility of comprehensive next-generation sequencing (NGS) in identifying rare MET fusions and guiding personalized treatment strategies.Results: Our case illustrates the potential of NGS in detecting rare MET fusions and achieving durable disease control with crizotinib. Comparative analyses indicate the necessity of individualized treatment approaches, particularly in cases involving central nervous system (CNS) involvement and prior treatment history. The review further emphasizes that MET alterations are more frequently identified in never-smoking female patients, where driver mutation detection rates exceed 60%. Conclusions: Precision oncology plays a pivotal role in addressing rare MET rearrangements in NSCLC. Despite advancements, challenges persist in early identification, therapeutic sequencing, and access to advanced diagnostics. Collaborative efforts among researchers, clinicians, and policymakers are crucial to refining treatment strategies and improving patient outcomes.