PD_EBM: An Integrated Boosting Approach Based on Selective Features for Unveiling Parkinson's Disease Diagnosis With Global and Local Explanations

Engineering Reports, Journal Year: 2025, Volume and Issue: 7(1)

Published: Jan. 1, 2025

ABSTRACT Early detection and characterization are crucial for treating managing Parkinson's disease (PD). The increasing prevalence of PD its significant impact on the motor neurons brain impose a substantial burden healthcare system. Early‐stage is vital improving patient outcomes reducing costs. This study introduces an ensemble boosting machine, termed PD_EBM, PD. PD_EBM leverages machine learning (ML) algorithms hybrid feature selection approach to enhance diagnostic accuracy. While ML has shown promise in medical applications detection, interpretability these models remains challenge. Explainable (XML) addresses this by providing transparency clarity model predictions. Techniques such as Local Interpretable Model‐agnostic Explanations (LIME) SHapley Additive exPlanations (SHAP) have become popular interpreting models. Our experiment used dataset 195 clinical records patients from University California Irvine (UCI) Machine Learning repository. Comprehensive data preparation included encoding categorical features, imputing missing values, removing outliers, addressing imbalance, scaling data, selecting relevant so on. We propose framework that focuses most important features prediction. employs Decision Tree (DT) classifier with AdaBoost, followed linear discriminant analysis (LDA) optimizer, achieving impressive accuracy 99.44%, outperforming other

Language: Английский

---

An Optimized Predictive Machine Learning Model for Lung Cancer Diagnosis

Biomedical & Pharmacology Journal, Journal Year: 2025, Volume and Issue: 18(December Spl Edition), P. 85 - 98

Published: Jan. 20, 2025

Lung cancer is one of the leading causes death worldwide. Increasing patient survival rates requires early detection. Traditional methods diagnosis often result in late-stage detection, necessitating development more advanced and accurate predictive models. This paper has proposed a methodology for lung prediction using machine learning Synthetic minority over-sampling technique (SMOTE) used before classification to resolve problem class imbalance. Bayesian optimization enhance model’s performance. Performance three classifiers adaptive boosting (AdaBoost), random forest (RF), extreme gradient (XGBoost) evaluated both with without hyperparmater optimization. Optimized models RF, AdaBoost XGBoost achieved accuracies 96.11%, 95.74% 95.92% respectively. Results demonstrate effectiveness combining classifiers, SMOTE, hyperparameter tuning improving accuracy.

Language: Английский

---

A comprehensive evaluation of ensemble machine learning in geotechnical stability analysis and explainability

International Journal of Mechanics and Materials in Design, Journal Year: 2023, Volume and Issue: 20(2), P. 331 - 352

Published: Oct. 2, 2023

Language: Английский

---

Enhancing the accuracy in the prediction of gold rate using innovative random forest algorithm in comparing support vector machine algorithm

AIP conference proceedings, Journal Year: 2025, Volume and Issue: 3270, P. 020128 - 020128

Published: Jan. 1, 2025

Language: Английский

---

Explainable deep learning model with the internet of medical devices for early lung abnormality detection

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 153, P. 110961 - 110961

Published: April 29, 2025

Language: Английский

---

Enhancing Lung Cancer Classification Effectiveness Through Hyperparameter-Tuned Support Vector Machine

Journal of Computing Theories and Applications, Journal Year: 2024, Volume and Issue: 1(4), P. 396 - 406

Published: March 25, 2024

This research aims to improve the effectiveness of lung cancer classification performance using Support Vector Machines (SVM) with hyperparameter tuning. Using Radial Basis Function (RBF) kernels in SVM helps deal non-linear problems. At same time, tuning is done through Random Grid Search find best combination parameters. Where parameter settings are C = 10, Gamma Probability True. Test results show that tuned improves accuracy, precision, specificity, and F1 score significantly. However, there was a slight decrease recall, namely 0.02. Even though recall one most important measuring tools disease classification, especially imbalanced datasets, specificity also plays vital role avoiding misidentifying negative cases. Without tuning, so poor considering both becomes very important. Overall, obtained by proposed method 0.99 for 1.00 0.98 f1-score, specificity. confirms potential SVMs addressing complex data challenges offers insights medical diagnostic applications.

Language: Английский

---

XEMLPD: an explainable ensemble machine learning approach for Parkinson disease diagnosis with optimized features

International Journal of Speech Technology, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 16, 2024

Language: Английский

---

Comparative analysis of explainable AI models for predicting lung cancer using diverse datasets

IAES International Journal of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 13(2), P. 1980 - 1980

Published: April 5, 2024

Lung cancer prediction is crucial for early detec-tion and treatment, explainable AI models have gained attention their interpretability. This study aims to compare various using diverse datasets lung prediction. Clinical, genomic, imaging data from multiple sources were collected, prepro-cessed, used train such as Logistic Regression, SVC-Linear, SVC-rbf, Decision Tree, Random Forest, AdaBoost Classifier, XGBoost Classifier. Preliminary results indicate that Forest achieved the highest accuracy of 98.9% across datasets. Evaluation metrics accuracy, precision, recall, F1 score utilized, along with interpretability techniques like feature importance rankings rule extraction methods. The study's findings will aid in identifying effective interpretable models, facilitating detection treatment decisions cancer.

Language: Английский

---

Hybrid Deep Learning Based GRU Model for Classifying the Lung Cancer from CT Scan Images

Published: April 26, 2024

Lung cancer is a potentially fatal condition, posing significant challenges for early detection and treatment within the healthcare domain. Despite extensive efforts, etiology cure of remain elusive. However, offers hope effective treatment. This study explores application image processing techniques, including noise reduction, feature extraction, identification cancerous regions lung, augmented by patient medical history data. Leveraging machine learning processing, this research presents methodology precise lung categorization prognosis. While computed tomography (CT) scans are cornerstone imaging, diagnosing solely through CT remains challenging even seasoned professionals. The emergence computer-assisted diagnostics has revolutionized diagnosis. utilizes images from Image Database Consortium (LIDC-IDRI) evaluates various preprocessing filters such as median, Gaussian, Wiener, Otsu, rough body area filters. Subsequently, extraction employs Karhunen-Loeve (KL) methodology, followed tumor classification using hybrid model comprising One-Dimensional Convolutional Neural Network (1D-CNN) Gated Recurrent Unit (GRU). Experimental findings demonstrate that proposed achieves sensitivity 99.14%, specificity 90.00%, F -measure 95.24%, accuracy 95%.

Language: Английский

---

Development and Validation of Data-Level Innovation Data-Balancing Machine Learning Models for Predicting Optimal Implantable Collamer Lens Size and Postoperative Vault

Ophthalmology and Therapy, Journal Year: 2023, Volume and Issue: 13(1), P. 267 - 286

Published: Nov. 9, 2023

There are only four sizes of implantable collamer lens (ICL) available for selection, which cannot completely fit all patients as a result the discontinuity ICL sizes. Sizing an optimal and predicting postoperative vault still unresolved problems. This study aimed to develop validate innovative data-level data-balancing machine learning-based models size vault.

Language: Английский

---