Chaotic gradient based optimization with fuzzy temporal optimized CNN for heart failure prediction

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 31, 2025

Language: Английский

---

Gene-related multi-network collaborative deep feature learning for predicting miRNA-disease associations

Computers & Electrical Engineering, Journal Year: 2025, Volume and Issue: 123, P. 110242 - 110242

Published: March 14, 2025

Language: Английский

---

Optimizing heart disease diagnosis with advanced machine learning models: a comparison of predictive performance

BMC Cardiovascular Disorders, Journal Year: 2025, Volume and Issue: 25(1)

Published: March 22, 2025

Abstract Cardiovascular disease is the leading cause of mortality globally, necessitating precise and prompt predictive instruments to enhance patient outcomes. In recent years, machine learning methodologies have demonstrated significant potential in enhancing precision efficacy health-related predictions, especially identification heart disease. The dataset used this study came from UC Irvine Machine Learning Repository included data Cleveland, Switzerland, Hungary, Long Beach, Statlog. We selected seven 1,190 cases, each with 12 attributes, for analysis. different models, like Random Forest, K-Nearest Neighbors, Logistic Regression, Naïve Bayes, Gradient Boosting, AdaBoost, XGBoost, Bagged Trees, check performance using accuracy, precision, recall, F1-score, ROC-AUC. K-fold cross-validation (K = 10, K 5) was conducted guarantee robustness generalizability these models. Forest exhibited remarkable stability, attaining 94% accuracy 10 92% 5, whereas XGBoost had a minor decrease during (90% 89% 5). KNN possible overfitting, evidenced by notable decline (71% 72% Trees achieved highest 93%, followed at 91%. Furthermore, ROC-AUC values 95%, 94%. results demonstrate effectiveness ensemble methods predicting cardiac diseases, along future advancement through incorporation hybrid models advanced survival analysis techniques.

Language: Английский

---

Enhancing Coronary Artery Disease Prognosis: A Novel Dual-Class Boosted Decision Trees Strategy for Robust Optimization

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 107119 - 107143

Published: Jan. 1, 2024

The rise in stable coronary artery disease (CAD) due to improved survival rates and population growth has increased patient numbers, straining healthcare systems. Machine learning (ML) models are being developed predict identify individual risk factors for early treatment, reducing harm individuals families. These can hospitalizations, enable close monitoring of high-risk patients, optimize medical care. Researchers developing robust based on ML algorithms real-world clinical data aid detection, contributing AI research healthcare. Advanced analyze imaging, genetic markers, lifestyle, environmental accurately heart (CHD) start progression. Our introduces four novel two-class Logistic Regression (two-class LR), Neural Network NN), Decision Jungle DJ), Boosted DT BDT). comparative analysis reveals that the model is most effective, achieving an AUC score 0.991. This excels real-time by predicting minor changes patient's health allowing timely adjustments treatment plans. It optimizes medication selection, dosing, intervention timing characteristics, improving therapeutic efficacy side effects. study transformative potential these advanced CAD prediction management. By focusing feature algorithm improvement, integration, our onset progression CHD. proposes valuable insights into capabilities revolutionize detection management, ensuring reliable interventions across various datasets.

Language: Английский

---

An adaptive dual-strategy constrained optimization-based coevolutionary optimizer for high-dimensional feature selection

Computers & Electrical Engineering, Journal Year: 2024, Volume and Issue: 118, P. 109362 - 109362

Published: June 14, 2024

Language: Английский

---

Alzheimer's Disease Prediction using Advanced Predictive Intelligence Model

Published: Aug. 23, 2024

Language: Английский

---

Soft-Computing Analysis and Prediction of the Mechanical Properties of High-Volume Fly-Ash Concrete Containing Plastic Waste and Graphene Nanoplatelets

Infrastructures, Journal Year: 2024, Volume and Issue: 9(12), P. 214 - 214

Published: Nov. 22, 2024

The rising population and demand for plastic materials lead to increasing waste (PW) annually, much of which is sent landfills without adequate recycling, posing serious environmental risks globally. PWs are grinded smaller sizes used as aggregates in concrete, where they improve sustainability. On the other hand, PW causes a significant reduction mechanical properties durability concrete. To mitigate negative effects PW, highly reactive pozzolanic normally added additives In this study, was partial substitute coarse aggregate, graphene nanoplatelets (GNPs) were high-volume fly-ash concrete (HVFAC). Utilizing GNPs has been found enhance HVFAC. Hence, study employed two machine-learning (ML) models, namely Gaussian Process Regression (GPR) Elman Neural Network (ELNN), forecast input variables FA, GNP, W/C, CP, density, slump, target compressive strength (CS), modulus elasticity (ME), splitting tensile (STS), flexural (FS). A total 240 datasets divided into calibration (70%) validation (30%) sets. During prediction CS, it that GPR-M3 outperforms all models with an R-value equal 0.9930 PCC value 0.9929 phase, = 0.9505 0.9339 verification phase. Additionally, during modeling FS, also noticed surpasses combinations R 0.9973 0.9684 0.9428 Moreover, ME modeling, best combination shows high accuracy 0.9945 0.9665 0.9584 STS 0.9856 0.9855 calibration, 0.9482 0.9353 Further quantitative analysis that, GPR improves ELNN by 0.49%, while strength, improved 1.54%. FS prediction, 7.66%, ME, 4.9%. conclusion, AI-based model proves how accurate effective employ ML-based forecasting

Language: Английский

---

Harmonizing Ensemble Learning Strategies for Enhanced Coronary Artery Disease Prediction

Published: Oct. 24, 2024

Language: Английский

---