1.Prediction of Pharmacoresistance in Drug-Naïve Temporal Lobe Epilepsy Using Ictal EEGs Based on Convolutional Neural Network.
Yiwei GONG ; Zheng ZHANG ; Yuanzhi YANG ; Shuo ZHANG ; Ruifeng ZHENG ; Xin LI ; Xiaoyun QIU ; Yang ZHENG ; Shuang WANG ; Wenyu LIU ; Fan FEI ; Heming CHENG ; Yi WANG ; Dong ZHOU ; Kejie HUANG ; Zhong CHEN ; Cenglin XU
Neuroscience Bulletin 2025;41(5):790-804
Approximately 30%-40% of epilepsy patients do not respond well to adequate anti-seizure medications (ASMs), a condition known as pharmacoresistant epilepsy. The management of pharmacoresistant epilepsy remains an intractable issue in the clinic. Its early prediction is important for prevention and diagnosis. However, it still lacks effective predictors and approaches. Here, a classical model of pharmacoresistant temporal lobe epilepsy (TLE) was established to screen pharmacoresistant and pharmaco-responsive individuals by applying phenytoin to amygdaloid-kindled rats. Ictal electroencephalograms (EEGs) recorded before phenytoin treatment were analyzed. Based on ictal EEGs from pharmacoresistant and pharmaco-responsive rats, a convolutional neural network predictive model was constructed to predict pharmacoresistance, and achieved 78% prediction accuracy. We further found the ictal EEGs from pharmacoresistant rats have a lower gamma-band power, which was verified in seizure EEGs from pharmacoresistant TLE patients. Prospectively, therapies targeting the subiculum in those predicted as "pharmacoresistant" individual rats significantly reduced the subsequent occurrence of pharmacoresistance. These results demonstrate a new methodology to predict whether TLE individuals become resistant to ASMs in a classic pharmacoresistant TLE model. This may be of translational importance for the precise management of pharmacoresistant TLE.
Epilepsy, Temporal Lobe/diagnosis*
;
Animals
;
Drug Resistant Epilepsy/drug therapy*
;
Electroencephalography/methods*
;
Rats
;
Anticonvulsants/pharmacology*
;
Neural Networks, Computer
;
Male
;
Humans
;
Phenytoin/pharmacology*
;
Adult
;
Disease Models, Animal
;
Female
;
Rats, Sprague-Dawley
;
Young Adult
;
Convolutional Neural Networks
2.A study on the relationship between intrauterine infection and early-onset neonatal sepsis
Yuanzhi ZHONG ; Jinhu WANG ; Yuxia CHEN ; Yuqin YAN ; Tihai XIAO ; Ling LIU ; Zhen HE ; Wei SONG ; Guoqing HUANG ; Huayan LIU ; Benqing WU
Chinese Journal of Neonatology 2017;32(4):246-249
Objective To study the relationship between intrauterine infection and early neonatal sepsis.Method From October 2015 to September 2016,the clinical data of pregnant mothers and their newborns in Shenzhen Longhua District Central Hospital were collected,and data of Shenzhen People's Hospital from January 2016 to June 2016 were collected.100 pairs of pregnant mothers and their newborns with confirmed or suspected intrauterine infection were selected as the observation group,and another 100 pairs without intrauterine infection during the same period as the control group.The ratio of term infants vs.premature infants was 1∶ 1.The complete blood count (CBC),CD64,procalcitonin (PCT) and C-reactive protein (CRP) were measured in peripheral blood of all mothers on the day of delivery.The CBC,CD64,CRP,PCT,blood culture of both umbilical venous blood and peripheral blood in neonates were examined and the pathological examination of placenta was performed.Result The positive rate of placental pathology and umbilical cord blood culture in observation group were significantly higher than that in the control and the positive rate in preterms was higher than the terms in observation group (P < 0.05).No significant differences existed between term and premature newborns on the positive rate of peripheral blood culture (P > 0.05).The positive rate of blood culture from umbilical cord blood was higher than peripheral blood in observation group (P < 0.05),but no significant difference in control group (P > 0.05).The incidence of septicemia in term and premature newborns in observation group was significantly higher than the control group (P< 0.05).The CD64,PCT in mother's peripheral blood and umbilical cord blood,and CRP in mother's blood were all higher than the control group,the differences were statistically significant (P < 0.05),but CRP in umbilical cord blood in both group were similar (P > 0.05).The area under ROC curve of CD64 and PCT in mother's peripheral blood,CD64 and PCT in umbilical cord blood to diagnose early-onset septicemia in newborns was 0.755,0.793,0.852 and 0.811,respectively.Conclusion The risk of neonatal infections is significantly increased because of intrauterine infection.Combination of peripheral and umbilical blood cultures can increase the accuracy of sepsis diagnosis.Both CD64 and PCT in umbilical cord blood and maternal blood can be used as indicators of intrauterine infection with a predictive value in the diagnosis of early-onset neonatal sepsis.
3.No mutation was detected in the LMNA gene among sporadic Charcot-Marie-Tooth patients
Shujuan SONG ; Yuanzhi ZHANG ; Biao CHEN ; Manjie WANG ; Yueying WANG ; Yuanjin ZHANG ; Ming YAN ; Nanbert ZHONG
Journal of Peking University(Health Sciences) 2006;38(1):78-79
Objective: To intensively investigate sporadic CMT patients, we have analyzed the LMNA gene in this study in a series of 32 unrelated CMT patients. Methods: Twelve exons of the LMNA gene were amplified from genetomic DNA. PCR products of each exon were analyzed by single strand conformational polymorphism (SSCP). Results: No abnormal SSCP pattern, suggesting no mutation in our CMT patients, was detected. Conclusion: The CMT diseases resulted from the mutations of LMNA gene were rare.

Result Analysis
Print
Save
E-mail