A Logistic Regression and Decision Tree Based Hybrid Approach to Predict Alzheimer's Disease

2022 International Conference on Computational Intelligence and Sustainable Engineering Solutions (CISES), Journal Year: 2023, Volume and Issue: unknown, P. 722 - 726

Published: April 28, 2023

Alzheimer's disease is a degenerative neurological disorder that typically impacts individuals over the age of 65, causing damage to brain and resulting in challenges with memory, cognition, behavior. Although there currently no cure for this condition, various therapies medications exist manage symptoms slow progression disease. Individuals experience cognitive impairment, changes behavior, communication difficulties, often leading psychological behavioral issues like anxiety, aggression, depression. In research paper, novel approach predicting outcomes using MRI data sets from Open Access Series Imaging Studies (OASIS) proposed. The method involves exploration, preprocessing, development hybrid model utilizes both Logistic Regression Decision Tree algorithms. Through rigorous testing, proposed demonstrated superior accuracy compared existing models, achieving an overall rate 96%.

Language: Английский

---

A Transfer Learning Approach: Early Prediction of Alzheimer’s Disease on US Healthy Aging Dataset

Mathematics, Journal Year: 2024, Volume and Issue: 12(14), P. 2204 - 2204

Published: July 13, 2024

Alzheimer’s disease (AD) is a growing public health crisis, very global concern, and an irreversible progressive neurodegenerative disorder of the brain for which there still no cure. Globally, it accounts 60–80% dementia cases, thereby raising need accurate effective early classification. The proposed work used healthy aging dataset from USA focused on three transfer learning approaches: VGG16, VGG19, Alex Net. This leveraged how convolutional model pooling layers to improve reduce overfitting, despite challenges in training numerical dataset. VGG was preferably chosen as hidden layer has more diverse, deeper, simpler architecture with better performance when dealing larger datasets. It consumes less memory time. A comparative analysis performed using machine neural network algorithm techniques. Performance metrics such accuracy, error rate, precision, recall, F1 score, sensitivity, specificity, kappa statistics, ROC, RMSE were experimented compared. accuracy 100% VGG16 VGG19 98.20% precision 99.9% 96.6% Net; recall values all cases sensitivity metric 96.8% 97.9% 98.7% Net, outperformed compared existing approaches classification disease. research contributes advancement predictive knowledge, leading future empirical evaluation, experimentation, testing biomedical field.

Language: Английский

---

A machine learning model for Alzheimer's disease prediction

IET Cyber-Physical Systems Theory & Applications, Journal Year: 2024, Volume and Issue: 9(2), P. 125 - 134

Published: March 20, 2024

Abstract Alzheimer’s disease (AD) is a neurodegenerative disorder that mostly affects old aged people. Its symptoms are initially mild, but they get worse over time. Although this health has no cure, its early diagnosis can help to reduce impacts. A methodology SMOTE‐RF proposed for AD prediction. Alzheimer's predicted using machine learning algorithms. Performances of three algorithms decision tree, extreme gradient boosting (XGB), and random forest (RF) evaluated in Open Access Series Imaging Studies longitudinal dataset available on Kaggle used experiments. The balanced synthetic minority oversampling technique. Experiments done both imbalanced datasets. Decision tree obtained 73.38% accuracy, XGB 83.88% accuracy RF maximum 87.84% the dataset. 83.15% 91.05% 95.03% achieved with SMOTE‐RF.

Language: Английский

---

A Novel Light-Weight Convolutional Neural Network Model to Predict Alzheimer’s Disease Applying Weighted Loss Function

Deleted Journal, Journal Year: 2024, Volume and Issue: 3(4)

Published: April 18, 2024

Alzheimer’s disease (AD) is a progressive neurological disorder that presents significant public health concern. Early detection of has the potential to greatly improve patient care and treatment. Artificial intelligence (AI) revolutionize healthcare by improving outcomes empowering providers. In recent years, breakthroughs in medical diagnosis have occurred, thanks use AI, particularly through application deep learning (DL) techniques. These advancements outcomes. Several proposals been developed utilizing DL techniques identify AD. This study proposes model classify individuals with AD using magnetic resonance imaging images. The aims evaluate DL’s effectiveness predicting proposed used custom-weighted loss function, resulting 99.24% training accuracy, 96.95% test Cohen’s kappa score 0.931, weighted average precision 97%. evaluated against several pre-trained models. Regarding accuracy findings score, suggested performs better than others.

Language: Английский

---

Harnessing the potentials of machine learning models in Alzheimer's disease prediction and detection

Elsevier eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 259 - 267

Published: Jan. 1, 2025

Language: Английский

---

Ensemble Model for Diagnostic Classification of Alzheimer’s Disease Based on Brain Anatomical Magnetic Resonance Imaging

Diagnostics, Journal Year: 2022, Volume and Issue: 12(12), P. 3193 - 3193

Published: Dec. 16, 2022

Alzheimer’s is one of the fast-growing diseases among people worldwide leading to brain atrophy. Neuroimaging reveals extensive information about brain’s anatomy and enables identification diagnostic features. Artificial intelligence (AI) in neuroimaging has potential significantly enhance treatment process for disease (AD). The objective this study two-fold: (1) compare existing Machine Learning (ML) algorithms classification AD. (2) To propose an effective ensemble-based model same perform its comparative analysis. In study, data from Diseases Initiative (ADNI), online repository, utilized experimentation consisting 2125 neuroimages (n = 975), mild cognitive impairment 538) normal 612). For classification, framework incorporates a Decision Tree (DT), Random Forest (RF), Naïve Bayes (NB), K-Nearest Neighbor (K-NN) followed by some variations Support Vector (SVM), such as SVM (RBF kernel), (Polynomial Kernel), (Sigmoid well Gradient Boost (GB), Extreme Boosting (XGB) Multi-layer Perceptron Neural Network (MLP-NN). Afterwards, Ensemble Based Generic Kernel presented where Master-Slave architecture combined attain better performance. proposed ensemble Boosting, SVM_Polynomial kernel (XGB + DT SVM). At last, method evaluated using cross-validation statistical techniques along with other ML models. SVM) outperformed state-of-the-art accuracy 89.77%. efficiency all models was optimized Grid-based tuning, results obtained after showed significant improvement. XGB parameters 95.75%. implication learning approach clearly shows best compared This experimental analysis improved understanding above-defined methods enhanced their scope significance early detection disease.

Language: Английский

---

SNSVM: SqueezeNet-Guided SVM for Breast Cancer Diagnosis

Computers, materials & continua/Computers, materials & continua (Print), Journal Year: 2023, Volume and Issue: 76(2), P. 2201 - 2216

Published: Jan. 1, 2023

Breast cancer is a major public health concern that affects women worldwide. It leading cause of cancer-related deaths among women, and early detection crucial for successful treatment. Unfortunately, breast can often go undetected until it has reached advanced stages, making more difficult to treat. Therefore, there pressing need accurate efficient diagnostic tools detect at an stage. The proposed approach utilizes SqueezeNet with fire modules complex bypass extract informative features from mammography images. extracted are then utilized train support vector machine (SVM) image classification. SqueezeNet-guided SVM model, known as SNSVM, achieved promising results, accuracy 94.10% sensitivity 94.30%. A 10-fold cross-validation was performed ensure the robustness mean standard deviation various performance indicators were calculated across multiple runs. This model also outperforms state-of-the-art models in all indicators, indicating its superior performance. demonstrates effectiveness diagnosis using makes tool diagnosis. may have significant implications reducing mortality rates.

Language: Английский

---

Multi-engineered Graphene Extended-Gate Field-Effect Transistor for Peroxynitrite Sensing in Alzheimer’s Disease

ACS Nano, Journal Year: 2023, Volume and Issue: 17(21), P. 21984 - 21992

Published: Oct. 24, 2023

The expression of β-amyloid peptides (Aβ), a pathological indicator Alzheimer's disease (AD), was reported to be inapparent in the early stage AD. While peroxynitrite (ONOO–) is produced excessively and emerges earlier than Aβ plaques progression AD, it thus significant sensitively detect ONOO– for diagnosis AD its research. Herein, we unveiled an integrated sensor monitoring ONOO–, which consisted commercially available field-effect transistor (FET) high-performance multi-engineered graphene extended-gate (EG) electrode. In configuration presented EG electrode, laser-induced (LIG) intercalated with MnO2 nanoparticles (MnO2/LIG) can improve electrical properties LIG sensitivity sensor, oxide (GO)-MnO2/Hemin nanozyme isomerase activity selectively trigger isomerization NO3–. With this synergistic effect, our EG-FET respond high selectivity. Moreover, taking advantage modularly assembled portable sensing platform wireless tracking levels brain tissue transgenic mice at stages before massive appeared, systematically explored complex role occurrence development

Language: Английский

---

An Interpretable PyCaret Approach for Alzheimer's Disease Prediction

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2024, Volume and Issue: 10(4)

Published: Nov. 29, 2024

Alzheimer's Disease (AD) is a major global health concern. The research focuses on early and accurate diagnosis of AD for its effective treatment management. This study presents novel Machine Learning (ML) approach utilizing PyCaret SHAP interpretable prediction. employs span classification algorithms the identifies best model. value determines contribution individual features final prediction thereby enhancing model’s interpretability. feature selection using improves overall performance proposed XAI framework clinical decision making patient care by providing reliable transparent method detection.

Language: Английский

---

BVFLEMR: an integrated federated learning and blockchain technology for cloud-based medical records recommendation system

Journal of Cloud Computing Advances Systems and Applications, Journal Year: 2022, Volume and Issue: 11(1)

Published: July 28, 2022

Abstract Blockchain is the latest boon in world which handles mainly banking and finance. The blockchain also used healthcare management system for effective maintenance of electronic health medical records. technology ensures security, privacy, immutability. Federated Learning a revolutionary learning technique deep learning, supports from distributed environment. This work proposes framework by integrating Deep order to provide tailored recommendation system. focuses on two modules blockchain-based storage records, where uses Hyperledger fabric capable continuously monitoring tracking updates Electronic Health Records cloud server. In second module, LightGBM N-Gram models are collaborative module recommend treatment patient’s cloud-based database after analyzing EHR. shows good accuracy. Several metrics like precision, recall, F1 scores measured showing its utilization security.

Language: Английский

---