Objective To explore an epileptic seizure prediction method for patients with refractory epilepsy to improve the classification and prediction efficiency of epileptic electroencephalogram(EEG)signals.Methods The study used the long-term EEG database of patients with intractable epilepsy from Children's Hospital Boston(CHB-MIT).The EEG features of epileptic seizures and preictal periods were extracted from multiple dimensions such as EEG synchronization,complexity,and energy distribution,and then these features were input into the artificial neural network model for classification and identification,thereby achieving accurate prediction of epilepsy.The performance were optimized by adjusting the model parameters,and a comparative evaluation was conducted with existing deep learning models.Results The model proposed in this study showed an accuracy rate of 99.29％,a precision of 91.44％,a sensitivity of 96.46％,and a specificity of 99.46％.Compared with current epilepsy seizure prediction studies based on machine learning or deep learning frameworks,the model in this study improved its classification prediction capabilities and demonstrated higher prediction accuracy.Conclusion An effective prediction of epileptic seizures was achieved by manually extracting epileptic EEG features and constructing an artificial neural network model.The model demonstrated high accuracy and stability,providing reliable technique to support clinical treatment and prevention of epilepsy.

Objective To explore an epileptic seizure prediction method for patients with refractory epilepsy to improve the classification and prediction efficiency of epileptic electroencephalogram(EEG)signals.Methods The study used the long-term EEG database of patients with intractable epilepsy from Children's Hospital Boston(CHB-MIT).The EEG features of epileptic seizures and preictal periods were extracted from multiple dimensions such as EEG synchronization,complexity,and energy distribution,and then these features were input into the artificial neural network model for classification and identification,thereby achieving accurate prediction of epilepsy.The performance were optimized by adjusting the model parameters,and a comparative evaluation was conducted with existing deep learning models.Results The model proposed in this study showed an accuracy rate of 99.29％,a precision of 91.44％,a sensitivity of 96.46％,and a specificity of 99.46％.Compared with current epilepsy seizure prediction studies based on machine learning or deep learning frameworks,the model in this study improved its classification prediction capabilities and demonstrated higher prediction accuracy.Conclusion An effective prediction of epileptic seizures was achieved by manually extracting epileptic EEG features and constructing an artificial neural network model.The model demonstrated high accuracy and stability,providing reliable technique to support clinical treatment and prevention of epilepsy.

Objective : To explore the expression of chemokine CXCL1 in proliferative infantile hemangioma (IH) , and to study the effect of exogenous CXCL1 on hemangioma stem cells (HemSCs) . Methods : Immunohistochemistry was used to explore the expression of CXCL1 in proliferative IH specimens.Primary HemSCs were isolated from IH tissues by CD133 magnetic beads.5 groups of CXCL1 with different concentrations(0,10,20,50 and 100 ng/ml) were co-cultured with HemSCs, and the effects of exogenous CXCL1 on HemSCs were studied by cell viability and migration experiments. Results : CXCL1 was expressed in the interstitial tissues of proliferative IH.The overall expression of CXCL1 in proliferative IH was low, but the expression of CXCL1 in the proliferative IH interstitial tissues was higher than that of the adjacent interstitial tissues.The CXCL1 positive area rate was(0.773±0.101)% in the tumor compared with(0.268±0.081)% in the adjacent tumor, and the difference was statistically significant(t=7.843,P<0.001).Exogenous CXCL1 promoted the proliferation of HemSCs, and there were statistical differences after adding different concentrations of CXCL1 to HemSCs for 24,48,and 72 h(F=14.610,P<0.001;F=14.430,P<0.001;F=5.388,P<0.01).But the exogenous CXCL1 did not affect the migration ability of HemSCs. Conclusion The expression of CXCL1 in proliferative IH interstitial tissues is higher than that in adjacent interstitial tissues, and exogenous CXCL1 promotes the proliferation of HemSCs.