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.Abdominal Epilepsy and Foreign Body in the Abdomen - Dilemma in Diagnosis of Abdominal Pain.
Noor TOPNO ; Mahesh S GOPASETTY ; Annappa KUDVA ; B LOKESH
Yonsei Medical Journal 2005;46(6):870-873
There are many medical causes of abdominal pain; abdominal epilepsy is one of the rarer causes. It is a form of temporal lobe epilepsy presenting with abdominal aura. Temporal lobe epilepsy is often idiopathic, however it may be associated with mesial temporal lobe sclerosis, dysembryoplastic neuroepithelial tumors and other benign tumors, arterio-venous malformations, gliomas, neuronal migration defects or gliotic damage as a result of encephalitis. When associated with anatomical abnormality, abdominal epilepsy is difficult to control with medication alone. In such cases, appropriate neurosurgery can provide a cure or, at least, make this condition easier to treat with medication. Once all known intra-abdominal causes have been ruled out, many cases of abdominal pain are dubbed as functional. If clinicians are not aware of abdominal epilepsy, this diagnosis is easily missed, resulting in inappropriate treatment. We present a case report of a middle aged woman presenting with abdominal pain and episodes of unconsciousness. On evaluation she was found to have an intra-abdominal foreign body (needle). Nevertheless, the presence of this entity was insufficient to explain her episodes of unconsciousness. On detailed analysis of her medical history and after appropriate investigations, she was diagnosed with temporal lobe epilepsy which was treated with appropriate medications, and which resulted in her pain being relieved.
Radiography, Abdominal
;
Humans
;
Foreign Bodies/pathology/*radiography
;
Female
;
Epilepsy, Temporal Lobe/*diagnosis/drug therapy
;
Electroencephalography
;
Anticonvulsants/therapeutic use
;
Adult
;
Abdominal Pain/drug therapy/*etiology/*radiography
;
*Abdomen

Result Analysis
Print
Save
E-mail