ObjectiveTo explore the prognostic value of normal 24 hour video electroencephalography (VEEG) with different frequency on antiepileptic drugs (AEDs) withdrawal in cryptogenic epilepsy patients with three years seizure-free. MethodsA retrospective study was conducted in the Neurology outpatient and the Epilepsy Center of Xi Jing Hospital. The subject who had been seizure free more than 3 years were divided into continual normal twice group and once group according to the nomal frequence of 24 hour VEEG before discontinuation from January 2013 to December 2014, and then followed up to replase or to December 2015. The recurrence and cumulative recurrence rate of the two group after withdrawal AEDs were compared with chi-square or Fisher's exact test and Kaplan-Meier survival curve. A Cox proportional hazard model was used for multivariate analysis to identify the risk factors for seizure recurrence after univariate analysis. P value < 0.05 was considered significant, and all P values were two-tailed. Results95 epilepsy patients with cause unknown between 9 to 45 years old were recruited (63 in normal twice group and 32 in normal once group). The cumulated recurrence rates in continual two normal VEEG group vs one normal VEEG group were 4.8% vs 21.9% (P=0.028), 4.8% vs 25% (P=0.006) and 7.9% vs 25%(P=0.03) at 18 months, 24 months and endpoint following AEDs withdrawal and there was statistically difference between the two groups. Factors associated with increased risk were adolescent onset epilepsy (HR=2.404), history of withdrawal recurrence (HR=7.186) and abnormal VEEG (epileptic-form discharge) (HR=8.222) during or after withdrawal AEDs. The recurrence rate of each group in which abnormal VEEG vs unchanged VEEG during or after withdrawal AEDs was respectively 100% vs 4.92% (P=0.005), 80% vs 19.23%(P=0.009). ConclusionsContinual normal 24h VEEG twice before withdrawal AEDs had higher predicting value of seizure recurrence and it could guide physicians to make the withdrawal decision. Epileptic patients with adolescent onset epilepsy, history of seizure recurrence and abnormal VEEG (epileptic-form discharge) during or after withdrawal AEDs had high risk of replase, especially patients with the presence of VEEG abnormalities is associated with a high probability of seizures occurring. Discontinuate AEDs should be cautious.
ObjectiveTo investigate the value of a predictive model for sentinel lymph node (SLN) metastasis after neoadjuvant therapy (NAT) based on the radiomic features from multi-modality MRI in combination with clinicopathologic data. MethodsThe clinical data and MRI images of breast cancer patients (initially diagnosed with cN0, all underwent NAT and surgical treatment) from two hospitals (Affiliated Hospital of Southwest Medical University and Suining Central Hospital) from January 2018 to September 2024, were retrospectively collected. The radiomic features from the multi-modality images, including T2-weighted short tau inversion recovery (T2STIR), diffusion-weighted imaging (DWI), dynamic contrast-enhanced (DCE), were extracted and selected. The predictive models for SLN metastasis after NAT were constructed using four algorithms: LightGBM, XGBoost, support vector machine (SVM), and logistic regression (LR), in combination with clinicopathologic data. The models were evaluated for performance and interpretability using receiver operating characteristic (ROC) curves, calibration curves, decision curve analysis, and Shapley additive explanation (SHAP) analysis. ResultsA total of 236 breast cancer patients were enrolled in this study. Among them, 216 patients from the Southwest Medical University were subdivided in an 8:2 ratio into the training set (173) and internal validation set (43), while 20 patients from the Suining Central Hospital served as the external validation set. Among the clinical and pathological features, lymphovascular invasion (LVI) (P<0.001), perineural invasion (PNI) (P=0.002), and Ki-67(P<0.001) were identified as the risk factors for SLN metastasis after NAT. The predictive models utilizing multi-modality MRI and clinicopathologic data yielded area under the ROC curve (AUC) values for the internal and external validation sets of 0.750 [95%CI=(0.395, 1.000)]/0.625 [95%CI=(0.321, 0.926)] for LightGBM, 0.878 [95%CI=(0.707, 1.000)]/0.778 [95%CI=(0.525, 0.986)] for XGBoost, 0.641 [95%CI=(0.488, 0.795)]/0.681 [95%CI=(0.345, 1.000)] for SVM, and 0.667 [95%CI=(0.357, 0.945)]/0.583 [95%CI=(0.196, 0.969)] for LR. XGBoost demonstrated the best predictive performance. Further SHAP analysis revealed that LVI, the minimum value of first-order features from T2STIR-MRI, and platelet count were the key features influencing the predictions of the models. ConclusionThe XGBoost prediction model based on radiomic features derived from multiparametric MRI (T2STIR, DWI, and DCE) combined with clinicopathological data was able to predict SLN metastasis after NAT in breast cancer patients.