International Journal of Neuroscience最新文献

{"title":"Modulation of the HMGB1/TLR4 pathway by montelukast in PTZ-induced epilepsy: alleviating neuroinflammatory oxidative stress and seizure severity.","authors":"Aysha Bano, Nidhi, Mohammed Samim, Mohd Ashif Khan","doi":"10.1080/00207454.2026.2633644","DOIUrl":"10.1080/00207454.2026.2633644","url":null,"abstract":"<p><p><b>Background:</b> Epilepsy is a multifactorial neurological disorder often associated with neuroinflammatory processes that contribute to the persistence of recurrent seizures. Conventional antiepileptic drugs (AEDs) frequently fail to achieve complete seizure control, highlighting the urgent need for alternative therapeutic strategies. Recent studies have explored the potential of montelukast, a leukotriene receptor antagonist, in the management of neurological disorders, including epilepsy.</p><p><p><b>Methods</b>: In the present study, the neuroprotective and antiepileptic effects of montelukast were evaluated using a pentylenetetrazol (PTZ)-induced kindling model in mice. A total of six groups were established, each consisting of nine mice, and animals were randomly assigned to the groups. PTZ (25 mg/kg, i.p.) was administered on alternate days for six weeks to induce kindling. Montelukast (MTK) was tested at three dose levels (5, 10, and 20 mg/kg, i.p.), while levetiracetam (30 mg/kg, i.p.) served as the standard comparator.</p><p><p><b>Results</b>: Montelukast (20 mg/kg) significantly reduced seizure severity, as indicated by lower Racine scale scores, and improved cognitive performance in both the elevated plus maze and passive avoidance tests. Biochemical analyses demonstrated increased catalase activity, reduced glutamate levels, and elevated γ-aminobutyric acid (GABA) concentrations. Furthermore, montelukast significantly decreased pro-inflammatory cytokines, including interleukin-1β (IL-1β), interleukin-6 (IL-6), and tumor necrosis factor-α (TNF-α), as well as other mediators of neuroinflammation such as high-mobility group box-1 (HMGB1), transforming growth factor-β (TGF-β), matrix metalloproteinase-9 (MMP-9), and toll-like receptor-4 (TLR-4). Histopathological findings confirmed that montelukast administration preserved cortical and hippocampal integrity by reducing neuronal damage.</p><p><p><b>Conclusion</b>: Collectively, these findings indicate that montelukast exhibits significant anticonvulsant and neuroprotective effects in a PTZ-induced epilepsy model, supporting its potential as a therapeutic candidate for epilepsy and warranting further investigation.</p>","PeriodicalId":14161,"journal":{"name":"International Journal of Neuroscience","volume":" ","pages":"793-807"},"PeriodicalIF":1.7,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147369437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Rising mortality and post-COVID shifts due to stroke in adults with dyslipidemia in the U.S. from 1999 to 2023: analysis of the CDC WONDER database.","authors":"Maryam Saghir, Muhammad Affan, Abdullah Masood Ahmed, Hozefa Mateen, Nida Shoaib, Rayyan Nabi, Mahtab Zafar, Sima Rawal, Yasar Sattar, Raheel Ahmed, Syeed Mahmud Nishat","doi":"10.1080/00207454.2026.2639360","DOIUrl":"10.1080/00207454.2026.2639360","url":null,"abstract":"<p><strong>Introduction: </strong>Stroke is a leading cause of mortality and long-term disability in the U.S. and worldwide. Among its key modifiable risk factors, dyslipidemia plays a significant role by accelerating atherosclerosis and impairing cerebrovascular health, thereby substantially increasing stroke incidence.</p><p><strong>Methods: </strong>We analyzed stroke (ICD-10 codes: I60-I69)-related mortality in patients with dyslipidemia (ICD-10 code: E78), using the CDC-WONDER database from 1999 to 2023. Age-Adjusted Mortality Rates (AAMR) per 100,000 were calculated and categorized by demographics and region. Joinpoint regression was used to estimate Annual Percent Change (APC) and Average Annual Percent Change (AAPC).</p><p><strong>Results: </strong>A total of 94,118 stroke-related deaths in individuals with dyslipidemia were recorded aged ≥25 years. The AAMR observed a significantly steep incline from 0.5 in 1999 to 2.97 in 2023 (AAPC: 7.47; 95% CI: 6.54 to 8.40, <i>p</i> < 0.01). Men observed higher overall AAMR (1.64) than women (1.54). Among different races and ethnicities, Non-Hispanic Black population had the highest overall AAMR (1.79). Regionally, the highest overall AAMR was recorded by the West (1.98). Non-metropolitan areas had lower AAMR than metropolitan areas (1.7 vs 1.45).</p><p><strong>Conclusion: </strong>Stroke-related mortality among individuals with dyslipidemia has risen markedly in the U.S., despite the overall national decline in stroke mortality. This likely reflects the increasing prevalence of metabolic risk factors, an aging population, genetic predisposition, and inadequate lipid management in high-risk groups.</p>","PeriodicalId":14161,"journal":{"name":"International Journal of Neuroscience","volume":" ","pages":"808-822"},"PeriodicalIF":1.7,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147344114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Summary of the best evidence for frailty management in patients with ischemic stroke during the rehabilitation period.","authors":"Shuting Liu, Xiaokang Wang, Zhe Zhang","doi":"10.1080/00207454.2026.2643316","DOIUrl":"10.1080/00207454.2026.2643316","url":null,"abstract":"<p><strong>Background: </strong>To retrieve and summarize the best evidence for frailty management in patients with ischemic stroke during the rehabilitation period, providing reference for clinical practice.</p><p><strong>Methods: </strong>The system searches for literature on stroke frailty management in domestic and foreign databases and guideline websites, with a search period from the establishment of the database to November 2024. Two researchers independently evaluated the quality of the literature and organized and summarized the evidence.</p><p><strong>Results: </strong>A total of 22 articles were included, 4 guidelines, 1 expert consensus, 7 systematic reviews, 1 evidence summary, 1 quasi-experimental study and 8 randomized controlled trials. Finally, 31 pieces of evidence were summarized from six aspects: frailty assessment, team building, exercise intervention, nutritional support, psychosocial support and health education.</p><p><strong>Conclusions: </strong>The best evidence summary for frailty management in stroke patients is comprehensive, and medical staff should combine clinical application evidence to effectively improve patient frailty.</p>","PeriodicalId":14161,"journal":{"name":"International Journal of Neuroscience","volume":" ","pages":"879-887"},"PeriodicalIF":1.7,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147443592","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The correlation between <i>YTHDF1</i> gene polymorphism and cognitive dysfunction after radiotherapy for glioma.","authors":"Huanfeng Zhu, Xiyun Shi, Dan Zong, Xia He","doi":"10.1080/00207454.2026.2630961","DOIUrl":"10.1080/00207454.2026.2630961","url":null,"abstract":"<p><strong>Background: </strong>Gliomas are the most common primary malignant tumors of the central nervous system. Mounting evidence highlights the crucial role of YTH N6-methyladenosine RNA binding protein 1 (YTHDF1) in glioma treatment response. This study aimed to investigate the association between single-nucleotide polymorphisms (SNPs) of YTHDF1 and cognitive dysfunction (CD) following radiotherapy for glioma.</p><p><strong>Methods: </strong>A total of 323 glioma patients were enrolled pre-radiotherapy and followed up for 3 months post-radiotherapy. They were categorized into glioma patients with CD (group, <i>n</i> = 202) and glioma patients without CD (non-CD group, <i>n</i> = 121). YTHDF1 mRNA expression was measured in peripheral blood samples collected before radiotherapy using RT-qPCR. Four YTHDF1 SNPs (rs6011668, rs6090311, rs68041888 and rs6122103) were genotyped <i>via</i> PCR-RFLP. Multivariate logistic regression was further performed to verify the association between YTHDF1 polymorphisms and post-radiotherapy CD.</p><p><strong>Results: </strong>YTHDF1 mRNA expression was significantly higher in the CD group than in the non-CD group. Among the four analyzed SNPs, only rs6090311 exhibited significant differences in both genotype and allele frequencies between the two groups, while rs6011668, rs68041888 and rs6122103 showed no significant variations. After controlling for potential confounders, including WHO grade, tumor volume, BDNF levels, and radiotherapy dose, carriers of the G allele (A/G + G/G genotypes) at rs6090311 demonstrated a significantly lower risk of developing post-radiotherapy CD (OR = 0.319, 95% CI: 0.111-0.916).</p><p><strong>Conclusions: </strong>YTHDF1 overexpression is associated with post-radiotherapy CD in glioma patients, and the rs6090311 G allele may act as a protective genetic marker for this complication.</p>","PeriodicalId":14161,"journal":{"name":"International Journal of Neuroscience","volume":" ","pages":"783-792"},"PeriodicalIF":1.7,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146194592","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Insulin resistance increases stroke risk: a cross-sectional study from NHANES 1999-2018 and a Mendelian randomization study.","authors":"Yaxian Hu, Fei Zou, Zhen Zhou, Wei Lu","doi":"10.1080/00207454.2026.2641049","DOIUrl":"10.1080/00207454.2026.2641049","url":null,"abstract":"<p><strong>Background: </strong>Existing evidence suggested a relevance between insulin resistance (IR) and stroke, but further confirmation is needed. Research priorities encompass large sample size, stratified analysis, advanced IR index, stroke subtype characterization, and analysis of potential mechanisms.</p><p><strong>Methods: </strong>We applied multivariable logistic regression using data from National Health and Nutrition Examination Survey 1999-2018 to estimate the correlation between two IR indexes: metabolic score for insulin resistance (METS-IR) and homeostasis model assessment of insulin resistance (HOMA-IR), and stroke. We also performed a two-sample Mendelian randomization (MR) study to detect the causal relationship between IR phenotype, METS-IR, and HOMA-IR as exposures, and stroke as well as its ischemic subtypes as outcomes.</p><p><strong>Results: </strong>A total of 15,016 participants representing 147,325,838 individuals after weighting were enrolled. Both METS-IR and HOMA-IR were not significantly correlated with stroke after strict adjustment, but METS-IR was strongly related to stroke in individuals aged 20-40 in the stratification analysis. The MR analysis showed robust causal associations between IR phenotype and any stroke (AS) as well as ischemic stroke (IS). Besides AS and IS, METS-IR also had a causal effect on large artery stroke and small vessel stroke.</p><p><strong>Conclusion: </strong>IR was associated with an increased risk of stroke in young adults.</p>","PeriodicalId":14161,"journal":{"name":"International Journal of Neuroscience","volume":" ","pages":"849-862"},"PeriodicalIF":1.7,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147354902","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A systems biology framework uncovers multi-level genetic regulation of dizziness/vertigo through eQTL-GWAS integration and single-cell analysis.","authors":"Dingduo Shan, Shuo Li, Lili Zhang, Jiaqi Bai, Henglin Wang","doi":"10.1080/00207454.2026.2627258","DOIUrl":"10.1080/00207454.2026.2627258","url":null,"abstract":"<p><strong>Background: </strong>Dizziness/vertigo is a multifactorial neurological disorder with complex ge-netic and cellular bases, yet its molecular mechanisms remain unclear. Understanding how gene regulation contributes to dizziness/vertigo may reveal novel neurobiological and therapeutic insights.</p><p><strong>Methods: </strong>We established a multi-omics integrative framework combining genome-wide association study (GWAS) data with expression quantitative trait loci (eQTL) from brain single-cell types, CD4⁺ T cells, oneK1K immune cells, and plasma. Two-sample Mendelian randomization (MR) and colocalization analyses were applied to identify causal genes. Single-cell RNA sequencing (scRNA-seq) of the auditory nerve was used to as-sess cell type-specific expression, intercellular communication, and pseudotime dynam-ics. Gene-gene interaction and drug-target networks were further constructed to identify potential therapeutic candidates.</p><p><strong>Results: </strong>Six key genes-Activin A Receptor Type 2 A (<i>ACVR2A</i>), Phospholipid Transfer Protein (<i>PLTP</i>), Androgen Dependent TFPI Regulating Protein (<i>ADTRP</i>), Methylenetetrahydrofolate Dehydrogenase (NADP+ Dependent) 1 Like (<i>MTHFD1L</i>), Collagen Type VII Alpha 1 Chain (<i>COL7A1</i>), and Pantothenate Kinase 4 (<i>PANK4</i>)-showed strong causal and colocalization evidence for dizziness/vertigo. Single-cell analysis revealed distinct cell type-specific expression, with fibroblasts and adipocytes playing central roles in signaling and gene regulation. Pseudo-time trajectories indicated coordinated upregulation of <i>ACVR2A</i>, <i>MTHFD1L</i>, <i>PANK4</i>, and <i>PLTP</i> during later developmental stages. Interaction network analysis positioned these genes as major hubs, and DrugBank screening identified Sotatercept as a promising candidate targeting <i>ACVR2A</i>.</p><p><strong>Conclusion: </strong>This integrative analysis links gene expres-sion regulation to dizziness/vertigo across neuroimmune and metabolic systems. The findings uncover coordinated molecular pathways underlying disease susceptibility and highlight novel therapeutic targets, providing a foundation for precision treatment strate-gies.</p>","PeriodicalId":14161,"journal":{"name":"International Journal of Neuroscience","volume":" ","pages":"756-766"},"PeriodicalIF":1.7,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146118948","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating the efficacy and safety of Edaravone-Dexborneol in acute ischemic stroke: an updated systematic review and meta-analysis of 7,846 Chinese patients.","authors":"Haneen Sabet, Abdallah Abbas, Mohamed Ahmed Zanaty, Ziyad Elyamany, Mohamed El-Moslemani, Maria Antonia Oliveira Machado Pereira, Jude Al-Mufti, Ramy Abdelnaby, Mohamed Elfil","doi":"10.1080/00207454.2026.2628832","DOIUrl":"10.1080/00207454.2026.2628832","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate the safety and efficacy of Edaravone-Dexborneol (EDB) as a neuroprotective agent in patients with acute ischemic stroke (AIS).</p><p><strong>Methods: </strong>We conducted a comprehensive search in PubMed, Scopus, Web of Science, and Cochrane CENTRAL until January 22, 2026, including clinical trials and observational studies comparing EDB with edaravone monotherapy, standard treatment, and placebo. Data on functional recovery (Modified Rankin Scale [mRS], National Institutes of Health Stroke Scale [NIHSS], Barthel Index [BI]), safety outcomes, and mortality were extracted. A random effects model was used for statistical analysis.</p><p><strong>Results: </strong>Overall, 13 studies (5 cohort studies and 8 randomized controlled trials) involving 7,846 patients were included, demonstrating that EDB significantly improved 90-day mRS scores (0-1) compared with edaravone alone (RD: 0.08, 95% CI: [0.03, 0.13], <i>p</i> = 0.001). When compared with standard treatment, NIHSS scores were significantly lower in the EDB group (MD: -2.18, 95% CI: [-3.75, -0.62], <i>p</i> = 0.006), and no significant difference was observed in mRS (0-1) or the risk of symptomatic intracranial hemorrhage (sICH). Safety outcomes showed a possible dose-dependent adverse event (AE), including hyperhomocysteinemia and hypokalemia.</p><p><strong>Conclusion: </strong>EDB might be an effective treatment for improving functional recovery in patients with AIS and appears to have a relatively favorable safety profile. However, careful dosing is necessary to minimize AEs. Future research should focus on large-scale trials, long-term outcomes, and mechanistic studies to optimize treatment protocols.</p>","PeriodicalId":14161,"journal":{"name":"International Journal of Neuroscience","volume":" ","pages":"767-782"},"PeriodicalIF":1.7,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146137330","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Genetically predicted artificial sweeteners and stroke susceptibility: a multivariable Mendelian randomization study.","authors":"Zurong Song, Hua Li, Yan Zhang","doi":"10.1080/00207454.2026.2627251","DOIUrl":"10.1080/00207454.2026.2627251","url":null,"abstract":"<p><strong>Aims: </strong>The present study investigated the causal associations of artificial sweetener consumption on the risk of stroke.</p><p><strong>Methods: </strong>We applied a two-sample Mendelian randomization (MR) design using genome-wide association study (GWAS) summary data for artificial sweetener intake (added to coffee, tea, and cereal) and stroke. The primary inverse variance weighted (IVW) analysis was complemented by sensitivity tests (Cochran's Q-test, MR-Egger, MR-PRESSO, and leave-one-out analysis) and multivariate MR (MVMR) to address heterogeneity, pleiotropy, and potential confounding.</p><p><strong>Results: </strong>Artificial sweeteners added to tea nominally increased small vessel stroke risk (OR = 3.01, 95%CI: 1.28-7.07, <i>p</i> = 0.0115, P-FDR = 0.20). Low-calorie drink intake (OR = 1.71, 95%CI: 1.12-2.63, <i>p</i> = 0.014, P-FDR = 0.20) and sucralose metabolite levels (OR = 1.14, 95%CI: 1.02-1.27, <i>p</i> = 0.029, P-FDR = 0.20) were nominally associated with cardioembolic stroke. MVMR analysis revealed that after adjusting for coffee intake, the association between intake of artificial sweeteners added to tea and small vessel stroke (OR = 2.90, <i>p</i> = 0.024) remained statistically significant. And after adjusting for blood glucose levels, the association between sucralose metabolite levels and cardioembolic stroke reversed direction and remained statistically significant (OR = 0.73, <i>p</i> = 0.024).</p><p><strong>Conclusion: </strong>This MR study indicated that artificial sweeteners, particularly those added to tea and sucralose metabolites, were associated with small vessel and cardioembolic stroke, respectively. However, these associations were attenuated after adjusting for BMI or tea consumption, indicating potential confounding by adiposity or beverage habits. Findings should be interpreted cautiously and warrant further investigation.</p>","PeriodicalId":14161,"journal":{"name":"International Journal of Neuroscience","volume":" ","pages":"745-755"},"PeriodicalIF":1.7,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146118992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Genetic evidence for the causal relationship between cerebrospinal fluid metabolites and intracranial aneurysms: a bidirectional two-sample Mendelian randomization study.","authors":"Rong Xiao, Wen Zhang","doi":"10.1080/00207454.2025.2611329","DOIUrl":"10.1080/00207454.2025.2611329","url":null,"abstract":"<p><strong>Background: </strong>Intracranial Aneurysms (IA) are life-threatening cerebrovascular diseases, and their pathogenesis remains not fully understood. This study aims to systematically evaluate the causal relationship between cerebrospinal fluid (CSF) metabolites and IA through bidirectional two-sample Mendelian randomization (MR) analysis to identify potential biomarkers and therapeutic targets.</p><p><strong>Methods: </strong>Using genome-wide association study data from public databases, the primary analysis was conducted with inverse variance weighting, supplemented by MR-Egger regression, weighted median, weighted mode, and simple mode. Sensitivity analyses were performed using heterogeneity tests, horizontal pleiotropy tests, and leave-one-out analyses to ensure the stability of the results.</p><p><strong>Results: </strong>Forward MR analysis revealed that 1-arachidonoyl-gpc (20:4n6), 2'-deoxyuridine, 3-hydroxystachydrine, 5-hydroxyhexanoate, isobutyrylcarnitine (C4), phenylacetylglutamine, and X-10457 were protective factors for IA. In contrast, 2-hydroxybutyrate/2-hydroxyisobutyrate, arabonate/xylonate, argininosuccinate, citrate, cysteinylglycine disulfide, and isovalerate were identified as risk factors for IA. Reverse MR analysis showed a significant causal relationship between IA and changes in the concentrations of 14 CSF metabolites. Sensitivity analyses indicated the robustness of these findings.</p><p><strong>Conclusions: </strong>This study, through bidirectional MR analysis, uncovered the causal relationship between CSF metabolites and IA, highlighting the significant roles of various amino acids and lipid metabolites in the pathophysiology of IA. These metabolites not only provide new insights into the mechanisms underlying IA but also present potential biomarkers and therapeutic targets, offering theoretical support for early intervention and prevention strategies for the disease.</p>","PeriodicalId":14161,"journal":{"name":"International Journal of Neuroscience","volume":" ","pages":"618-628"},"PeriodicalIF":1.5,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145862451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep learning-based epileptic seizure detection from EEG signals and PPG signals using LSTM and CNN models.","authors":"Aruna Devi B","doi":"10.1080/00207454.2026.2621855","DOIUrl":"10.1080/00207454.2026.2621855","url":null,"abstract":"<p><p>Epilepsy is a chronic neurological disorder characterized by recurrent and unpredictable seizures that significantly affect patients' health and quality of life. Conventional diagnosis relies heavily on continuous electroencephalogram (EEG) monitoring, which requires clinical expertise and is not well suited for real-time detection. To address these challenges, this article presents a hybrid deep learning framework that integrates convolutional neural networks (CNNs) and long short-term memory (LSTM) models for automated epileptic seizure (ESD) detection using multimodal EEG and Photoplethysmogram (PPG) signals. Unlike EEG-only approaches, the inclusion of PPG provides complementary physiological information, such as autonomic fluctuations, seizure-induced heart rate variability (HRV) changes and peripheral vascular responses - which strengthens the model's discriminative capability, particularly in cases where EEG signatures alone are subtle or ambiguous. In the proposed framework, CNNs effectively extract spatial patterns from the preprocessed biosignals, while LSTMs capture temporal dependencies associated with seizure evolution. Data preprocessing steps including filtering, normalization, segmentation and augmentation are applied to enhance signal quality and model generalization. The hybrid CNN-LSTM model is evaluated on benchmark EEG-PPG datasets using accuracy, precision, recall, F1-score, Cohen's Kappa, Matthews Correlation Coefficient (MCC) and Critical Success Index (CSI). Comparative analysis with existing state-of-the-art models demonstrates superior performance and robustness. Overall, the proposed multimodal deep learning system offers a reliable and efficient solution for real-time seizure detection, with strong potential for deployment in wearable and clinical healthcare platforms.</p>","PeriodicalId":14161,"journal":{"name":"International Journal of Neuroscience","volume":" ","pages":"695-709"},"PeriodicalIF":1.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146165376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}