Neuroimage-Based Stroke Identification: A Machine Learning Approach DOI Open Access

Ms. Priyanka V Dhurve,

Prof. N. R. Wankhade

International Journal of Advanced Research in Science Communication and Technology, Год журнала: 2024, Номер unknown, С. 268 - 273

Опубликована: Ноя. 11, 2024

Stroke diagnosis is a time-critical process that requires rapid and accurate identification to ensure timely treatment. This study proposes machine learning-based diagnostic model for stroke using neuro images. Early intervention are critical improving outcomes patients, but current techniques, such as CT MRI scans, often require time-consuming expert analysis. These delays can limit the effectiveness of treatment, particularly in acute cases where every minute counts. The problem lies need faster, more reliable tools analyze neuroimaging data with high accuracy minimal human intervention. Machine learning, specifically deep offers promising solution address this gap by automating detection. We employed comprehensive approach, utilizing Inceptionv3, MobileNet, Convolutional Neural Network (CNN) algorithms neuroimages predict occurrence. research neuroimages, leveraging power Networks (CNN), Inception V3 MobileNet architectures. V3, known its ability capture intricate image features through convolutional layers, optimized efficiency speed, were large datasets brain scans. was trained on these distinguish between healthy tissues those affected stroke. combination two architectures allows both detailed analysis fast processing, making adaptable clinical settings. results showed achieved rate identification, demonstrating potential assist healthcare professionals diagnosing faster accurately. By integrating learning into existing workflows, it could significantly reduce time diagnosis, enabling earlier treatment ultimately patient outcomes. Our has enhance economic burden advanced aims compared traditional methods

Язык: Английский

Innovations in Stroke Identification: A Machine Learning-Based Diagnostic Model Using Neuroimages DOI Creative Commons
Muhammad Asim Saleem, Ashir Javeed,

Wasan Akarathanawat

и другие.

IEEE Access, Год журнала: 2024, Номер 12, С. 35754 - 35764

Опубликована: Янв. 1, 2024

Cerebrovascular diseases such as stroke are among the most common causes of death and disability worldwide preventable treatable. Early detection strokes their rapid intervention play an important role in reducing burden disease improving clinical outcomes. In recent years, machine learning methods have attracted a lot attention they can be used to detect strokes. The aim this study is identify reliable methods, algorithms, features that help medical professionals make informed decisions about treatment prevention. To achieve goal, we developed early system based on CT images brain coupled with genetic algorithm bidirectional long short-term Memory (BiLSTM) at very stage. For image classification, approach neural networks select relevant for classification. BiLSTM model then fed these features. Cross-validation was evaluate accuracy diagnostic system, precision, recall, F1 score, ROC (Receiver Operating Characteristic Curve), AUC (Area Under Curve). All metrics were determine system's overall effectiveness. proposed achieved 96.5%. We also compared performance Logistic Regression, Decision Trees, Random Forests, Naive Bayes, Support Vector Machines. With diagnosis physicians decision stroke.

Язык: Английский

Процитировано

13
A novel integrated logistic regression model enhanced with recursive feature elimination and explainable artificial intelligence for dementia prediction DOI Creative Commons
Rasel Ahmed, Nafiz Fahad, M. Saef Ullah Miah

и другие.

Healthcare Analytics, Год журнала: 2024, Номер unknown, С. 100362 - 100362

Опубликована: Сен. 1, 2024

Язык: Английский

Процитировано

6
AI-driven early diagnosis of specific mental disorders: a comprehensive study DOI Creative Commons
Firuze Damla Eryılmaz Baran, Meriç Çetin

Cognitive Neurodynamics, Год журнала: 2025, Номер 19(1)

Опубликована: Май 5, 2025

Abstract One of the areas where artificial intelligence (AI) technologies are used is detection and diagnosis mental disorders. AI approaches, including machine learning deep models, can identify early signs bipolar disorder, schizophrenia, autism spectrum depression, suicidality, dementia by analyzing speech patterns, behaviors, physiological data. These approaches increase diagnostic accuracy enable timely intervention, which crucial for effective treatment. This paper presents a comprehensive literature review applied to disorder using various data sources, such as survey, Electroencephalography (EEG) signal, text image. Applications include predicting anxiety depression levels in online games, detecting schizophrenia from EEG signals, text-based indicators suicidality diagnosing magnetic resonance imaging images. eXtreme Gradient Boosting (XGBoost), light gradient-boosting (LightGBM), random forest (RF), support vector (SVM), K-nearest neighbor were designed convolutional neural networks (CNN), long short-term memory (LSTM) gated recurrent unit (GRU) models suitable dataset models. Data preprocessing techniques wavelet transforms, normalization, clustering optimize model performances, hyperparameter optimization feature extraction performed. While LightGBM technique had highest performance with 96% prediction, optimized SVM stood out 97% accuracy. Autism classification reached 98% XGBoost, RF LightGBM. The LSTM achieved high 83% diagnosis. GRU showed best 93% suicide detection. In dementia, have demonstrated their effectiveness analysis reaching 99% findings study highlight sequential applicability medical or natural language processing. XGBoost noted be highly accurate ML tools clinical diagnoses. addition, advanced pre-processing confirmed significantly improve performance. results obtained this revealed potential decision systems disorders AI, facilitating personalized treatment strategies.

Язык: Английский

Процитировано

0
Optimizing Depression Prediction in Older Adults: A Comparative Study of Feature Extraction and Machine Learning Models DOI
Ashir Javeed, Peter Anderberg, Ahmad Nauman Ghazi

и другие.

Опубликована: Май 15, 2024

Depression emerged as a major public health concern in older adults, and timely prediction of depression has become difficult problem medical informatics. The latest studies have attentiveed on feature transformation selection for better prediction. In this study, we assess the performance various extraction algorithms, including principal component analysis (PCA), independent (ICA), locally linear Embedding (LLE), t-distributed stochastic neighbor embedding (TSNE). These algorithms are combined with machine learning (ML) classifier such Gaussian Naive Bayes (GNB), Logistic Regression (LR), K-nearest-neighbor (KNN), Decision Tree (DT) to enhance total, sixteen automated integrated systems constructed based above-mentioned methods ML classifiers. all these models is assessed using data from Swedish National Study Aging Care (SNAC). According experimental results, PCA algorithm (LR) model provides 89.04% classification accuracy. As result, it demonstrated that more suitable method than ICA, LLE, TSNE.

Язык: Английский

Процитировано

2
An intelligent learning system based on electronic health records for unbiased stroke prediction DOI Creative Commons
Muhammad Asim Saleem, Ashir Javeed,

Wasan Akarathanawat

и другие.

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Окт. 4, 2024

Язык: Английский

Процитировано

0
Machine learning-based personalized composite score dissects risk and protective factors for cognitive and motor function in older participants DOI Creative Commons
Ann‐Kathrin Schalkamp, Stefanie Lerche, Isabel Wurster

и другие.

Frontiers in Aging Neuroscience, Год журнала: 2024, Номер 16

Опубликована: Окт. 15, 2024

Introduction With age, sensory, cognitive, and motor abilities decline, the risk for neurodegenerative disorders increases. These impairments influence quality of life increase need care, thus putting a high burden on society, economy, healthcare system. Therefore, it is important to identify factors that healthy aging, particularly ones are potentially modifiable through lifestyle choices. However, large-scale studies investigating multi-modal global description aging measured by multiple clinical assessments sparse. Methods We propose machine learning model simultaneously predicts cognitive outcome measurements personalized level recorded from one learned composite score. This score derived large set components TREND cohort, including genetic, biofluid, clinical, demographic, factors. Results found based single was able predict almost as well classical flexible regression specifically trained each In contrast model, our globally motoric scores. The identified several protective recovered physical exercise major, modifiable, factor. Discussion conclude low parametric modeling approach successfully known while providing an interpretable suggest validating this in other cohorts.

Язык: Английский

Процитировано

0
Neuroimage-Based Stroke Identification: A Machine Learning Approach DOI Open Access

Ms. Priyanka V Dhurve,

Prof. N. R. Wankhade

International Journal of Advanced Research in Science Communication and Technology, Год журнала: 2024, Номер unknown, С. 268 - 273

Опубликована: Ноя. 11, 2024

Stroke diagnosis is a time-critical process that requires rapid and accurate identification to ensure timely treatment. This study proposes machine learning-based diagnostic model for stroke using neuro images. Early intervention are critical improving outcomes patients, but current techniques, such as CT MRI scans, often require time-consuming expert analysis. These delays can limit the effectiveness of treatment, particularly in acute cases where every minute counts. The problem lies need faster, more reliable tools analyze neuroimaging data with high accuracy minimal human intervention. Machine learning, specifically deep offers promising solution address this gap by automating detection. We employed comprehensive approach, utilizing Inceptionv3, MobileNet, Convolutional Neural Network (CNN) algorithms neuroimages predict occurrence. research neuroimages, leveraging power Networks (CNN), Inception V3 MobileNet architectures. V3, known its ability capture intricate image features through convolutional layers, optimized efficiency speed, were large datasets brain scans. was trained on these distinguish between healthy tissues those affected stroke. combination two architectures allows both detailed analysis fast processing, making adaptable clinical settings. results showed achieved rate identification, demonstrating potential assist healthcare professionals diagnosing faster accurately. By integrating learning into existing workflows, it could significantly reduce time diagnosis, enabling earlier treatment ultimately patient outcomes. Our has enhance economic burden advanced aims compared traditional methods

Язык: Английский

Процитировано

0