Innovations in Stroke Identification: A Machine Learning-Based Diagnostic Model Using Neuroimages

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

---

Breaking barriers: a statistical and machine learning-based hybrid system for predicting dementia

Frontiers in Bioengineering and Biotechnology, Год журнала: 2024, Номер 11

Опубликована: Янв. 8, 2024

Dementia is a condition (a collection of related signs and symptoms) that causes continuing deterioration in cognitive function, millions people are impacted by dementia every year as the world population continues to rise. Conventional approaches for determining rely primarily on clinical examinations, analyzing medical records, administering neuropsychological testing. However, these methods time-consuming costly terms treatment. Therefore, this study aims present noninvasive method early prediction so preventive steps should be taken avoid dementia.

Язык: Английский

---

Application of the Random Forest Algorithm for Accurate Bipolar Disorder Classification

Life, Год журнала: 2025, Номер 15(3), С. 394 - 394

Опубликована: Март 3, 2025

Bipolar disorder (BD) is a complex psychiatric condition characterized by alternating episodes of mania and depression, posing significant challenges for accurate timely diagnosis. This study explores the use Random Forest (RF) algorithm as machine learning approach to classify patients with BD healthy controls based on electroencephalogram (EEG) data. A total 330 participants, including euthymic controls, were analyzed. EEG recordings processed extract key features, power in frequency bands complexity metrics such Hurst Exponent, which measures persistence or randomness time series, Higuchi’s Fractal Dimension, used quantify irregularity brain signals. The RF model demonstrated robust performance, achieving an average accuracy 93.41%, recall specificity exceeding 93%. These results highlight algorithm’s capacity handle complex, noisy datasets while identifying features relevant classification. Importantly, provided interpretable insights into physiological markers associated BD, reinforcing clinical value diagnostic tool. findings suggest that reliable accessible method supporting diagnosis complementing traditional practices. Its ability reduce delays, improve classification accuracy, optimize resource allocation make it promising tool integrating artificial intelligence care. represents step toward precision psychiatry, leveraging technology understanding management mental health disorders.

Язык: Английский

---

A novel integrated logistic regression model enhanced with recursive feature elimination and explainable artificial intelligence for dementia prediction

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

Опубликована: Сен. 1, 2024

Язык: Английский

---

Customer Shopping Behavior Analysis Using RFID and Machine Learning Models

Information, Год журнала: 2023, Номер 14(10), С. 551 - 551

Опубликована: Окт. 8, 2023

Analyzing customer shopping habits in physical stores is crucial for enhancing the retailer–customer relationship and increasing business revenue. However, it can be challenging to gather data on browsing activities as compared online stores. This study suggests using RFID technology store shelves machine learning models analyze activity retail The uses tags track product movement collects behavior receive signal strength (RSS) of tags. time-domain features were then extracted from RSS utilized classify different activities. We proposed integration iForest Outlier Detection, ADASYN balancing Multilayer Perceptron (MLP). results indicate that model performed better than other supervised models, with improvements up 97.778% accuracy, 98.008% precision, 98.333% specificity, recall, 97.750% f1-score. Finally, we showcased this trained into a web-based application. result assist managers understanding preferences aid placement, promotions, recommendations.

Язык: Английский

---

Agglomeration of deep learning networks for classifying binary and multiclass classifications using 3D MRI images for early diagnosis of Alzheimer’s disease: a feature-node approach

International Journal of Systems Assurance Engineering and Management, Год журнала: 2023, Номер 15(3), С. 931 - 949

Опубликована: Окт. 10, 2023

Язык: Английский

---

Machine and deep learning algorithms for classifying different types of dementia: A literature review

Applied Neuropsychology Adult, Год журнала: 2024, Номер unknown, С. 1 - 15

Опубликована: Авг. 1, 2024

The cognitive impairment known as dementia affects millions of individuals throughout the globe. use machine learning (ML) and deep (DL) algorithms has shown great promise a means early identification treatment dementia. Dementias such Alzheimer's Dementia, frontotemporal dementia, Lewy body vascular are all discussed in this article, along with literature review on using ML their diagnosis. Different algorithms, support vector machines, artificial neural networks, decision trees, random forests, compared contrasted, benefits drawbacks. As accurate models may be achieved by carefully considering feature selection data preparation. We also discuss how can predict disease progression patient responses to therapy. However, overreliance DL technologies should avoided without further proof. It's important note that these meant assist diagnosis but not used sole criteria for final research implies help increase precision which is diagnosed, especially its stages. efficacy clinical contexts must verified, ethical issues around personal addressed, requires more study.

Язык: Английский

---

Decision Support System for Predicting Mortality in Cardiac Patients Based on Machine Learning

Applied Sciences, Год журнала: 2023, Номер 13(8), С. 5188 - 5188

Опубликована: Апрель 21, 2023

Researchers have proposed several automated diagnostic systems based on machine learning and data mining techniques to predict heart failure. However, researchers not paid close attention predicting cardiac patient mortality. We developed a clinical decision support system for mortality in patients address this problem. The dataset collected the experimental purposes of model consisted 55 features with total 368 samples. found that classes were highly imbalanced. To avoid problem bias model, we used synthetic minority oversampling technique (SMOTE). After balancing dataset, newly employed χ2 statistical rank from dataset. highest-ranked fed into an optimized random forest (RF) classification. hyperparameters RF classifier using grid search algorithm. performance (χ2_RF) was validated evaluation measures, including accuracy, sensitivity, specificity, F1 score, receiver operating characteristic (ROC) curve. With only 10 χ2_RF achieved highest accuracy 94.59%. improved standard by 5.5%. Moreover, compared other state-of-the-art models. results show outperforms same feature selection module (χ2).

Язык: Английский

---

Evaluation of Machine Learning Models for the Prediction of Alzheimer's: In Search of the Best Performance

Brain Behavior & Immunity - Health, Год журнала: 2025, Номер 44, С. 100957 - 100957

Опубликована: Фев. 1, 2025

Alzheimer's is a progressive and degenerative disease affecting millions worldwide, incapacitating them physically cognitively. This study aims to perform comparative analysis of Machine Learning models determine the model with best performance in predicting disease. The used were Random Forest (RF), Adaptive Boosting (AdaBoost), Support Vector (SVM), K-nearest Neighbors (KNN), Logistic Regression (LR). Two datasets called OASIS train models, first one had total 436 records 12 variables, while second stored 373 15 variables. article's content divided into six main sections: introduction, literature review, methodological approach, results, discussions, conclusions. After processing pooling datasets, RF, SVM, LR proved predictors, achieving 96% accuracy, precision, sensitivity, F1 score. highlights efficacy disease, offering significant advance toward understanding management this which supports relevance implementing these future research clinical applications.

Язык: Английский

---

Species distribution modeling of Malva neglecta Wallr. weed using ten different machine learning algorithms: An approach to site-specific weed management (SSWM)

European Journal of Agronomy, Год журнала: 2025, Номер 167, С. 127579 - 127579

Опубликована: Март 5, 2025

Язык: Английский

---