Neuroscience informatics最新文献

{"title":"Beyond the numbers: App-enabled stroke prediction system for high-risk individuals in imbalanced datasets","authors":"Abrar Faiaz Eram ,&nbsp;Aliva Sadnim Mahmud ,&nbsp;Marwan Mostafa Khadem ,&nbsp;Md Amimul Ihsan","doi":"10.1016/j.neuri.2025.100215","DOIUrl":"10.1016/j.neuri.2025.100215","url":null,"abstract":"<div><h3>Background:</h3><div>Brain stroke, characterized by interrupted blood flow to the brain, poses significant mortality risks and quality-of-life impacts. While machine learning approaches show promise in stroke prediction, current research often relies on synthetic data to address dataset imbalance, potentially compromising real-world model performance in clinical settings.</div></div><div><h3>Method:</h3><div>This research proposes an alternative approach focusing on recall as the primary evaluation metric for stroke prediction, specifically targeting the reduction of false negatives. In the context of stroke diagnosis, where missed detection can lead to severe consequences or fatality, recall is crucial for directly measuring the model's ability to identify actual stroke cases.</div></div><div><h3>Results:</h3><div>Three superior models were identified: Logistic Regression, an Ensemble using Soft Voting (combining Gaussian Naive Bayes and Logistic Regression), and customized Support Vector Machine. Exceptional stroke prediction was achieved with recall values of 92%, 92%, and 94%, respectively. Interpretability is enhanced through SHAP applied to the best one. While previous methods showed recall values between 5.6% and 40%, this approach outperformed these benchmarks (94%). Current research emphasizes accuracy metrics, relying on oversampling, being inappropriate for sensitive medical datasets. The pitfall is a slight increase in false positives, which is tolerable because the cost of misdiagnosing a stroke patient far outweighs the reverse scenario.</div></div><div><h3>Conclusions:</h3><div>The research demonstrates the effectiveness of focusing on recall as an evaluation metric for stroke prediction, minimizing false negative predictions. To facilitate practical implementation, a mobile application incorporating the best-performing model was included. A primary screening which can supplement doctors in stroke diagnosis and prediction was proposed.</div></div>","PeriodicalId":74295,"journal":{"name":"Neuroscience informatics","volume":"5 3","pages":"Article 100215"},"PeriodicalIF":0.0,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144338309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting stroke with machine learning techniques in a sub-Saharan African population","authors":"Benjamin Segun Aribisala ,&nbsp;Deirdre Edward ,&nbsp;Godwin Ogbole ,&nbsp;Onoja M. Akpa ,&nbsp;Segun Ayilara ,&nbsp;Fred Sarfo ,&nbsp;Olusola Olabanjo ,&nbsp;Adekunle Fakunle ,&nbsp;Babafemi Oluropo Macaulay ,&nbsp;Joseph Yaria ,&nbsp;Joshua Akinyemi ,&nbsp;Albert Akpalu ,&nbsp;Kolawole Wahab ,&nbsp;Reginald Obiako ,&nbsp;Morenikeji Komolafe ,&nbsp;Lukman Owolabi ,&nbsp;Godwin Osaigbovo ,&nbsp;Akinkunmi Paul Okekunle ,&nbsp;Arti Singh ,&nbsp;Philip Ibinaye ,&nbsp;Mayowa Owolabi","doi":"10.1016/j.neuri.2025.100216","DOIUrl":"10.1016/j.neuri.2025.100216","url":null,"abstract":"<div><h3>Background</h3><div>Stroke is the second leading cause of death and the third leading cause of disability globally, including Africa, which bears its largest burden. Accurate models are needed in Africa to predict and prevent stroke occurrence. The aim of this study was to identify the best machine learning (ML) algorithm for stroke prediction.</div></div><div><h3>Methods</h3><div>We assessed medical data of 4,236 subjects comprising 2,118 stroke patients and 2,118 controls from the SIREN database. Sixteen established vascular risk factors were evaluated in this study. These are addition of salt to food at table during eating, cardiac disease, diabetes mellitus, dyslipidemia, education, family history of cardiovascular disease, hypertension, income, low green leafy vegetable consumption, obesity, physical inactivity, regular meat consumption, regular sugar consumption, smoking, stress and use of tobacco. From these, we also selected the 11 topmost risk factors using Population-Attributable Risk ranking. Eleven ML models were built and empirically investigated using the 16 and the 11 risk factors.</div></div><div><h3>Results</h3><div>Our results showed that the 16 features-based classification (maximum AUC of 82.32%) had a slightly better performance than the 11 feature-based (maximum AUC 81.17%) algorithm. The result also showed that Artificial Neural Network (ANN) had the best performance amongst eleven algorithms investigated with AUC of 82.32%, sensitivity of 71.23%, specificity of 80.00%.</div></div><div><h3>Conclusion</h3><div>Machine Learning algorithms predicted stroke occurrence employing major risk factors in Sub-Saharan Africa better than regression models. Machine Learning, especially Artificial Neural Network, is recommended to enhance Afrocentric stroke prediction models for stroke risk factor quantification and control in Africa.</div></div>","PeriodicalId":74295,"journal":{"name":"Neuroscience informatics","volume":"5 3","pages":"Article 100216"},"PeriodicalIF":0.0,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144322809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring community pharmacist's psychological intentions to adopt generative artificial intelligence (GenAI) chatbots for patient information, education, and counseling","authors":"Hafidz Ihsan Hidayatullah ,&nbsp;Muhammad Taufiq Saifullah ,&nbsp;Muhammad Thesa Ghozali ,&nbsp;Ayesha Aziz","doi":"10.1016/j.neuri.2025.100213","DOIUrl":"10.1016/j.neuri.2025.100213","url":null,"abstract":"<div><div>Generative AI (GenAI) chatbots, driven by advanced machine learning algorithms, are emerging as transformative tools for enhancing patient education, information dissemination, and counseling (EIC) in healthcare. This study investigated the psychological determinants of community pharmacists' intentions to adopt GenAI chatbots using the Extended Technology Acceptance Model (ETAM). A cross-sectional survey of 240 licensed community pharmacists across several Indonesian provinces assessed key constructs, including self-efficacy (SE), perceived usefulness (PU), perceived ease of use (PEU), attitude toward technology (ATT), trust (TT), and behavioral intention (BI). Structural equation modeling revealed that SE significantly influenced PU (<span><math><mi>β</mi><mo>=</mo><mn>0.37</mn></math></span>) and PEU (<span><math><mi>β</mi><mo>=</mo><mn>0.57</mn></math></span>), indicating that confidence in using technology positively affects perceived utility and usability. PU further predicted ATT (<span><math><mi>β</mi><mo>=</mo><mn>0.39</mn></math></span>) and BI (<span><math><mi>β</mi><mo>=</mo><mn>0.236</mn></math></span>), emphasizing the motivational role of perceived benefits. Trust emerged as a crucial mediator, channeling favorable attitudes into actionable behavioral intentions (indirect <span><math><mi>β</mi><mo>=</mo><mn>0.148</mn></math></span>). The model demonstrated strong fit indices (<span><math><msup><mrow><mi>χ</mi></mrow><mrow><mn>2</mn></mrow></msup><mo>=</mo><mn>263.09</mn></math></span>, RMSEA = 0.019, GFI = 0.915, CFI = 0.991), supporting the psychological framework. These findings highlight the importance of fostering trust, improving perceived usability, and enhancing self-efficacy through targeted training to promote GenAI chatbot adoption. Future research should explore longitudinal behavioral changes and contextual influences to support sustainable AI integration in pharmacy practice.</div></div>","PeriodicalId":74295,"journal":{"name":"Neuroscience informatics","volume":"5 3","pages":"Article 100213"},"PeriodicalIF":0.0,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144272556","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unlocking transcranial FUS-EEG feature fusion for non-invasive sleep staging in next-gen clinical applications","authors":"Suneet Gupta ,&nbsp;Praveen Gupta ,&nbsp;Bechoo Lal ,&nbsp;Aniruddha Deka ,&nbsp;Hirakjyoti Sarma ,&nbsp;Sheifali Gupta","doi":"10.1016/j.neuri.2025.100209","DOIUrl":"10.1016/j.neuri.2025.100209","url":null,"abstract":"<div><div>Accurate and non-invasive sleep staging is essential for evaluating sleep quality and diagnosing neurological and sleep disorders. Addressing the variations in electroencephalogram (EEG) and electrooculogram (EOG) signals across different sleep stages, this study introduces a transcranial focused ultrasound (tFUS) based multimodal feature fusion deep learning model (MFDL) for automated sleep staging. The proposed framework integrates two one-dimensional convolutional neural networks (1D-CNNs) to extract sleep-relevant features from EEG and EOG signals, followed by an adaptive feature fusion module that dynamically assigns weights based on feature significance. By enhancing discriminative features and suppressing irrelevant ones, the model generates a robust multimodal representation of sleep information. Furthermore, a bidirectional long short-term memory (Bi-LSTM) network captures temporal dependencies in sleep stage transitions, improving classification accuracy. The effectiveness of MFDL is validated on the publicly available Sleep-EDF dataset, achieving 94.1% accuracy, 88.2% Kappa coefficient, and 81.9% MF1 score. Notably, the recall rates for the challenging N1 and REM sleep stages are significantly enhanced to 64.6% and 93.5%, respectively. These results highlight the potential of MFDL in enhancing tFUS-based neuromodulation by providing precise, data-driven sleep state monitoring, paving the way for advanced non-invasive brain stimulation technologies in next-gen clinical applications.</div></div>","PeriodicalId":74295,"journal":{"name":"Neuroscience informatics","volume":"5 2","pages":"Article 100209"},"PeriodicalIF":0.0,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144069541","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing seizure detection with hybrid XGBoost and recurrent neural networks","authors":"Santushti Santosh Betgeri ,&nbsp;Madhu Shukla ,&nbsp;Dinesh Kumar ,&nbsp;Surbhi B. Khan ,&nbsp;Muhammad Attique Khan ,&nbsp;Nora A. Alkhaldi","doi":"10.1016/j.neuri.2025.100206","DOIUrl":"10.1016/j.neuri.2025.100206","url":null,"abstract":"<div><div>Epileptic seizures are sudden and unpredictable, posing serious health risks and significantly affecting the quality of life of patients. An accurate and timely prediction system can help mitigate these risks by enabling preventive measures and improving patient safety. This study investigates machine learning and deep learning algorithms for seizure prediction, comparing their effectiveness on a large EEG dataset of epileptic patients. Signal processing techniques were applied to enhance data quality, and all models were trained on the same dataset for binary classification. Sixteen models were evaluated, including traditional classifiers such as Logistic Regression, K-Nearest Neighbors, Decision Trees, ensemble methods that include Random Forest, Gradient Boosting, and advanced techniques such as Extreme Gradient Boosting, Support Vector Machines, Gated Recurrent Units, and Long Short-Term Memory networks. Performance was assessed using multiple evaluation metrics on both training and validation datasets. While simpler models showed varied accuracy, ensemble and deep learning models performed significantly better, with hybrid approaches demonstrating strong generalization. Results show that whereas ensemble and deep learning models far exceeded simpler models, their accuracy varied. AUC of 0.995 and accuracy of 98.2% on validation data and 0.994 AUC with 96.8% accuracy on test data were obtained by the proposed hybrid Model integrating XGBoost with RNN-based architectures (LSTM and GRU). High recall (96.2%) shown by the Model guarantees minimal false negatives and is important for clinical uses. Furthermore, EEG signal preprocessing methods improved data quality, raising classification accuracy. This Model can be implemented for real-time monitoring using wearable devices, enabling continuous patient observation and remote healthcare applications.</div></div>","PeriodicalId":74295,"journal":{"name":"Neuroscience informatics","volume":"5 2","pages":"Article 100206"},"PeriodicalIF":0.0,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143916826","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Neuroimaging informatics framework for analyzing rare brain metastasis patterns in pleural mesothelioma using hybrid PET CT","authors":"Sumit Kumar Agrawal ,&nbsp;Indra Prakash Dubey ,&nbsp;Anoop Kumar Nair ,&nbsp;Anurag Jain ,&nbsp;Abhishek Mahato ,&nbsp;Rajeev Kumar","doi":"10.1016/j.neuri.2025.100207","DOIUrl":"10.1016/j.neuri.2025.100207","url":null,"abstract":"<div><div>A rare and hostile cancer mostly affecting the lungs, pleural mesothelioma has an exceedingly unusual but clinically relevant propagation to the brain. Their unusual appearance and low frequency make early diagnosis and accurate characterization of such uncommon brain metastases a diagnostic difficulty. The present research presents a neuroimaging informatics system using hybrid Positron Emission Tomography–Computed Tomography (PET-CT) imaging to examine and explain uncommon brain metastasis patterns in pleural mesothelioma patients. Our methodology combines sophisticated neuroinformatics technologies with AI-driven image processing algorithms to improve hybrid PET-CT scans' spatial and metabolic resolution. While a radiomics pipeline drives out quantitative characteristics like texture, intensity, and shape descriptors, a deep learning (DL)-based segmentation algorithm finds abnormal metabolic activity suggestive of metastatic lesions. Unsupervised clustering and anomaly detection resources help to examine these characteristics and find rare metastatic developments. To assist thorough case analysis, a clinical informatics layer links imaging results with patient demographics, histopathology data, and treatment history. Validated using retrospective PET-CT data from mesothelioma patients with verified brain involvement, the approach shows increased sensitivity and specificity in finding mysterious metastatic foci. This work emphasizes the need for hybrid imaging modalities in monitoring uncommon oncologic events and provides insightful analysis of the brain spread paths of pleural mesothelioma by providing a strong, AI-enhanced neuroimaging framework. The suggested method helps with early identification, and individualized treatment planning helps to clarify metastatic behavior in typical thoracic cancers.</div></div>","PeriodicalId":74295,"journal":{"name":"Neuroscience informatics","volume":"5 2","pages":"Article 100207"},"PeriodicalIF":0.0,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143923562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing transcranial focused ultrasound parameters: A methodological advancement in non-invasive brain stimulation for next-gen clinical applications","authors":"Sachin Gupta ,&nbsp;Mustafa Mudhafar ,&nbsp;Yogini Dilip Borole ,&nbsp;V. Mahalakshmi ,&nbsp;Janjhyam Venkata Naga Ramesh ,&nbsp;Muhammad Attique Khan","doi":"10.1016/j.neuri.2025.100204","DOIUrl":"10.1016/j.neuri.2025.100204","url":null,"abstract":"<div><div><strong>Background:</strong> Transcranial-focused ultrasound (FUS), a non-invasive neuromodulation method, is gaining popularity for treating neurological and psychiatric disorders. However, changing stimulation settings for precise brain targeting remains challenging.</div><div><strong>Methods:</strong> Existing techniques have spatial resolution, skull acoustic transmission, and parameter selection issues that reduce clinical efficacy. These problems reduce tFUS application repeatability and safety. To address these challenges, this research proposes a novel computational-experimental strategy that combines advanced computational modeling (IACM) with in vivo validation. The proposed design uses subject-specific skull acoustic simulations, Deep Learning (DL)-based parameter optimization, and real-time feedback to increase stimulation accuracy and efficacy.</div><div><strong>Results</strong>: The recommended approach allows customized transcutaneous electrical nerve stimulation (tFUS) by modifying frequency, intensity, and targeting. Neuromodulation becomes better while staying safe. It should be adaptable enough for research and clinical usage to create neurostimulation precision medicine.</div><div><strong>Comparative analysis:</strong> The study shows that the proposed framework improves spatial precision, skull transmission effect variability, and neuromodulation efficacy compared to existing methods.</div><div><strong>Conclusion:</strong> This approach enables the development next-generation non-invasive brain stimulation devices with more therapeutic uses. Non-invasive brain stimulation (NIBS) technologies, including tFUS, TMS, and tDCS, may now accurately affect neurological and psychiatric diseases. However, these approaches are susceptible to inter-subject variability, poor targeting, and skull deformities. Artificial intelligence-driven real-time optimization frameworks like the Integrating Advanced Computational Modeling (IACM) framework are needed to overcome these constraints.</div></div>","PeriodicalId":74295,"journal":{"name":"Neuroscience informatics","volume":"5 2","pages":"Article 100204"},"PeriodicalIF":0.0,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143923559","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MindLift: AI-powered mental health assessment for students","authors":"Shanky Goyal ,&nbsp;RishiRaj Dutta ,&nbsp;Saurabh Dev ,&nbsp;Kola Narasimha Raju ,&nbsp;Mohammed Wasim Bhatt","doi":"10.1016/j.neuri.2025.100208","DOIUrl":"10.1016/j.neuri.2025.100208","url":null,"abstract":"<div><div>This study introduces MindLift, a student-specific AI-powered mental health assessment and intervention platform. The goal of this research is to create a real-time, multimodal system that can assess mental health through the use of behavioral pattern tracking, audio tone analysis, facial expression recognition, and text sentiment interpretation. By integrating convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformer-based natural language processing (NLP) models, MindLift provides a comprehensive emotional analysis. Through evidence-based techniques like Cognitive Behavioral Therapy (CBT), an intelligent chatbot built into the system provides individualized mental health support. Responses and interventions are customized using important parameters like sentiment polarity, mood detection, and behavioral abnormalities. MindLift emphasizes ethical AI deployment, with strong safeguards for privacy, consent, and fairness. Preliminary studies show a notable increase in student engagement, emotional control, and willingness to seek help. Future developments include deeper personalization, wearable device integration, and wider deployment across educational institutions. The system is evaluated using metrics including accuracy, precision, recall, and F1-score across several modalities.</div></div>","PeriodicalId":74295,"journal":{"name":"Neuroscience informatics","volume":"5 2","pages":"Article 100208"},"PeriodicalIF":0.0,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143935135","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A MATLAB-based tool for converting fNIRS time-series data to Homer3-compatible formats","authors":"Chao Wang ,&nbsp;Xiaojun Cheng ,&nbsp;Shichao Liu","doi":"10.1016/j.neuri.2025.100205","DOIUrl":"10.1016/j.neuri.2025.100205","url":null,"abstract":"<div><div>Functional Near-Infrared Spectroscopy (fNIRS) is increasingly used in cognitive neuroscience and clinical research, yet preprocessing raw time-series data remains challenging. We introduce a lightweight MATLAB tool to automate the conversion of fNIRS data into Homer3-compatible “*.nirs” format. Our solution targets non-SNIRF raw data and offers a standardized, user-friendly method to streamline fNIRS data preparation. This Technical Note describes the tool's design, workflow, and potential improvements for future development.</div></div>","PeriodicalId":74295,"journal":{"name":"Neuroscience informatics","volume":"5 2","pages":"Article 100205"},"PeriodicalIF":0.0,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143906484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep learning-based multi-brain capsule network for Next-Gen Clinical Emotion recognition using EEG signals","authors":"Ritu Dahiya ,&nbsp;Mamatha G ,&nbsp;Shila Sumol Jawale ,&nbsp;Santanu Das ,&nbsp;Sagar Choudhary ,&nbsp;Vinod Motiram Rathod ,&nbsp;Bhawna Janghel Rajput","doi":"10.1016/j.neuri.2025.100203","DOIUrl":"10.1016/j.neuri.2025.100203","url":null,"abstract":"<div><div>Deep learning techniques are crucial for next-generation clinical applications, particularly in Next-Gen Clinical Emotion recognition. To enhance classification accuracy, we propose an Attention mechanism based Capsule Network Model (At-CapNet) for Multi-Brain Region. EEG-tNIRS signals were collected using Next-Gen Clinical Emotion-inducing visual stimuli to construct the TYUT3.0 dataset, from which EEG and tNIRS features were extracted and mapped into matrices. A multi-brain region attention mechanism was applied to integrate EEG and tNIRS features, assigning different weights to features from distinct brain regions to obtain high-quality primary capsules. Additionally, a capsule network module was introduced to optimize the number of capsules entering the dynamic routing mechanism, improving computational efficiency. Experimental validation on the TYUT3.0 Next-Gen Clinical Emotion dataset demonstrates that integrating EEG and tNIRS improves recognition accuracy by 1.53% and 14.35% compared to single-modality signals. Moreover, the At-CapNet model achieves an average accuracy improvement of 4.98% over the original CapsNet model and outperforms existing CapsNet-based Next-Gen Clinical Emotion recognition models by 1% to 5%. This research contributes to the advancement of non-invasive neurotechnology for precise Next-Gen Clinical Emotion recognition, with potential implications for next-generation clinical diagnostics and interventions.</div></div>","PeriodicalId":74295,"journal":{"name":"Neuroscience informatics","volume":"5 2","pages":"Article 100203"},"PeriodicalIF":0.0,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143916824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}