This study aims to explore the value of a machine learning (ML) model based on radiomics features and clinical features in predicting the outcome of spontaneous supratentorial intracerebral hemorrhage (sICH) 90 days after surgery. A total of 348 patients with sICH underwent craniotomy evacuation of hematoma from three medical centers. One hundred and eight radiomics features were extracted from sICH lesions on baseline CT. Radiomics features were screened using 12 feature selection algorithms. Clinical features included age, gender, admission Glasgow Coma Scale (GCS), intraventricular hemorrhage (IVH), midline shift (MLS), and deep ICH. Nine ML models were constructed based on clinical feature, and clinical features + radiomics features, respectively. Grid search was performed on different combinations of feature selection and ML model for parameter tuning. The averaged receiver operating characteristics (ROC) area under curve (AUC) was calculated and the model with the largest AUC was selected. It was then tested using multicenter data. The combination of lasso regression feature selection and logistic regression model based on clinical features + radiomics features had the best performance (AUC: 0.87). The best model predicted an AUC of 0.85 (95%CI, 0.75–0.94) on the internal test set and 0.81 (95%CI, 0.64–0.99) and 0.83 (95%CI, 0.68–0.97) on the two external test sets, respectively. Twenty-two radiomics features were selected by lasso regression. The second-order feature gray level non-uniformity normalized was the most important radiomics feature. Age is the feature with the greatest contribution to prediction. The combination of clinical features and radiomics features using logistic regression models can improve the outcome prediction of patients with sICH 90 days after surgery.
Aortoesophageal fistula (AEF) is a relatively rare and potentially fatal disease. Secondary AEF is rare but is associated with serious complications and high mortality. There are rare cases of esophageal mediastinal fistula after descending aortic aneurysm stent implantation. We report the case of a 76-year-old man who had upper abdominal distension, without obvious inducement, for 3 months and felt fullness after a meal, accompanied by anorexia. A chest computer tomography (CT) examination of the abdomen was performed with the outside hospital. Descending thoracic aortic aneurysm was discovered and was treated with stent implantation. The patient was transferred to our hospital to continue treatment, mainly because of an esophageal mediastinal fistula. Finally, the thoracic aortic aneurysm was diagnosed as AEF after stent implantation, combined with the diagnosis of upper gastrointestinal bleeding. We hope that, through this case, we can explain the possible causes of bronchial mediastinal fistula after stent implantation of descending aortic aneurysm and the mechanism of upper gastrointestinal bleeding.
25 September 2025 in Journal of Central Nervous System Disease
Purpose: This study aimed to evaluate the influence of the triglyceride-glucose index (TyG index) on clinical outcomes and to develop nomogram models for predicting early neurological deterioration (END) and long-term prognosis in acute ischemic stroke (AIS) patients following intravenous thrombolytic (IVT) therapy. Methods: We conducted a multi-center retrospective cohort study involving 333 AIS patients treated with IVT. The short-term and long-term outcomes were defined as the occurrence of END and 90-day prognosis. Multivariate logistic regression was used to develop nomogram models for forecasting these clinical outcomes. Results: Patients in the high-TyG group exhibited significantly higher risks of END ( P = 0.0010) and poor 90-day outcomes ( P = 0.0012). Independent risk factors for END included a lower baseline NIHSS score, delayed door-to-needle time (DNT), reduced ASPECTS score, elevated TyG index, higher potassium (K+) levels, and incomplete Willis artery. Additionally, a higher initial NIHSS, increased TyG levels, presence of END, and a history of hypertension were predictors of poor prognosis. Based on the identified risk factors, two nomogram models yielded AUC values of 0.746 and 0.849 for predicting END and poor prognosis, respectively. NIHSS scores, TyG index, and admission glucose levels (Glu) emerged as prognostic indicators across all patients, while higher mean platelet volume (MPV) and history of stroke were identified as novel risk factors for poor prognosis in NO-END group. Conclusion: A higher TyG index correlates with poor clinical outcomes in AIS patients post-IVT. The nomograms combining the TyG index with various factors enhanced risk prediction for END and poor prognosis.