Explainable artificial intelligence: A survey of needs, techniques, applications, and future direction

Neurocomputing, Journal Year: 2024, Volume and Issue: 599, P. 128111 - 128111

Published: Sept. 1, 2024

Language: Английский

---

AI in diagnostics: Enhancing accuracy and efficiency

Elsevier eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 279 - 304

Published: Jan. 1, 2025

Language: Английский

---

Dynamic Surgical Prioritization: A Machine Learning and XAI-Based Strategy

Technologies, Journal Year: 2025, Volume and Issue: 13(2), P. 72 - 72

Published: Feb. 8, 2025

Surgical waiting lists present significant challenges to healthcare systems, particularly in resource-constrained settings where equitable prioritization and efficient resource allocation are critical. We aim address these issues by developing a novel, dynamic, interpretable framework for prioritizing surgical patients. Our methodology integrates machine learning (ML), stochastic simulations, explainable AI (XAI) capture the temporal evolution of dynamic scores, qp(t), while ensuring transparency decision making. Specifically, we employ Light Gradient Boosting Machine (LightGBM) predictive modeling, simulations account variables competitive interactions, SHapley Additive Explanations (SHAPs) interpret model outputs at both global patient-specific levels. hybrid approach demonstrates strong performance using dataset 205 patients from an otorhinolaryngology (ENT) unit high-complexity hospital Chile. The LightGBM achieved mean squared error (MSE) 0.00018 coefficient determination (R2) value 0.96282, underscoring its high accuracy estimating qp(t). Stochastic effectively captured changes, illustrating that Patient 1’s qp(t) increased 0.50 (at t=0) 1.026 t=10) due growth such as severity urgency. SHAP analyses identified (Sever) most influential variable, contributing substantially non-clinical factors, capacity participate family activities (Lfam), exerted moderating influence. Additionally, our achieves reduction times up 26%, demonstrating effectiveness optimizing prioritization. Finally, strategy combines adaptability interpretability, transparent aligns with evolving patient needs constraints.

Language: Английский

---

Artificial Intelligence in Personalized Medicine for Head and Neck Cancer: Optimizing Prescriptions and Treatment Planning

Deleted Journal, Journal Year: 2025, Volume and Issue: unknown

Published: March 27, 2025

Language: Английский

---

Optimized Disease Prediction in Healthcare Systems Using HDBN and CAEN Framework

MethodsX, Journal Year: 2025, Volume and Issue: 14, P. 103338 - 103338

Published: April 25, 2025

Classification and segmentation play a pivotal role in transforming decision-making processes healthcare, IoT, edge computing. However, existing methodologies often struggle with accuracy, precision, specificity when applied to large, heterogeneous datasets, particularly minimizing false positives negatives. To address these challenges, we propose robust hybrid framework comprising three key phases: feature extraction using Hybrid Deep Belief Network (HDBN), dynamic prediction aggregation via Custom Adaptive Ensemble (CAEN), an optimization mechanism ensuring adaptability robustness. Extensive evaluations on four diverse datasets demonstrate the framework's superior performance, achieving 93 % 87 95 specificity, 91 recall. Advanced metrics, including Matthews Correlation Coefficient of 0.8932, validate its reliability. The proposed establishes new benchmark for scalable, high-performance classification segmentation, offering solutions real-world applications paving way future integration explainable AI real-time systems.•Designed novel integrating HDBN CAEN adaptive prediction.•Proposed strategies enhancing robustness across data scenarios.

Language: Английский

---

Blockchain-Based Explainable AI for Secure and Privacy-Preserving Automated Machine Learning in IoT-Edge for Smart Medical Healthcare

IGI Global eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 59 - 80

Published: April 30, 2025

Coronary Heart Disease (CHD) continues to affect close 145 million males and 110 females across the globe, taking nine lives each year. A new evolving framework incorporating IoT-edge computing, Explainable AI, blockchain technology is in process of development order create a secure, privacy-preserving, interpretable automated machine learning environment predict chronic diseases. The IoT-based system utilizes medical sensors assistive devices for real-time monitoring patient. patient information transmitted securely using architecture so that various health practitioners have access it with guarantee data integrity, confidentiality, control. use AI (XAI) enables predictions clinicians fosters confidence transparency. Physicians are able make evidence-based decisions beyond traditional methods since XAI provides reasons predictions.

Language: Английский

---

Explainable Artificial Intelligence: A Survey of the Need, Techniques, Applications, and Future Direction

Published: Jan. 1, 2024

Artificial intelligence models encounter significant challenges due to their black-box nature, particularly in safety-critical domains such as healthcare, finance, autonomous vehicles, and justice. Explainable Intelligence (XAI) addresses these by providing explanations for how make decisions predictions, ensuring transparency, accountability, fairness. Existing studies have examined the fundamental concepts of XAI, its general principles, scope XAI techniques. However, there remains a gap literature are no comprehensive reviews that delve into detailed mathematical representations, design methodologies models, other associated aspects. This paper provides review encompassing common terminologies definitions, need beneficiaries taxonomy methods, application methods different areas. The survey is aimed at researchers, practitioners, AI model developers, who interested enhancing trustworthiness, fairness models.

Language: Английский

---

Unravelling AI and Machine Learning Essentials in Alzheimer's Research

Advances in medical technologies and clinical practice book series, Journal Year: 2024, Volume and Issue: unknown, P. 147 - 159

Published: June 28, 2024

Artificial intelligence (AI) and system mastering (ML) have received a good-sized interest in Alzheimer's studies due to their capability enhance prognosis treatment. But comprehensive know-how of these technologies software remains lacking. This review objectives resolve the essentials AI ML studies, highlighting capacity effect on sickness development control. The results outline modern-day nation use research challenges implementation, providing foundation for additional improvements this subject. field has been greatly impacted by way fast improvement artificial studying techniques. With growing quantity records being generated discipline need more accurate predictions remedies, come be crucial gear unraveling complexities disease.

Language: Английский

---

Early Breast Cancer Detection Based on Deep Learning: An Ensemble Approach Applied to Mammograms

BioMedInformatics, Journal Year: 2024, Volume and Issue: 4(4), P. 2338 - 2373

Published: Dec. 13, 2024

Background: Breast cancer is one of the leading causes death in women, making early detection through mammography crucial for improving survival rates. However, human interpretation mammograms often prone to diagnostic errors. This study addresses challenge accuracy breast by leveraging advanced machine learning techniques. Methods: We propose an extended ensemble deep model that integrates three state-of-the-art convolutional neural network (CNN) architectures: VGG16, DenseNet121, and InceptionV3. The utilizes multi-scale feature extraction enhance both benign malignant masses mammograms. approach evaluated on two benchmark datasets: INbreast CBIS-DDSM. Results: proposed achieved significant performance improvements. On dataset, attained 90.1%, recall 88.3%, F1-score 89.1%. For CBIS-DDSM reached 89.5% 90.2% specificity. method outperformed each individual CNN model, reducing false positives negatives, thereby providing more reliable results. Conclusions: demonstrated strong potential as a decision support tool radiologists, offering accurate earlier cancer. By complementary strengths multiple architectures, this can improve clinical accessibility high-quality screening.

Language: Английский

---

Demystifying Machine Learning by Unraveling Interpretability

Advances in systems analysis, software engineering, and high performance computing book series, Journal Year: 2024, Volume and Issue: unknown, P. 145 - 156

Published: April 29, 2024

In this chapter, the authors embark on a journey to unveil complexities of machine learning by focusing crucial aspect interpretability. As algorithms become increasingly sophisticated and pervasive across industries, understanding how these models make decisions is essential for trust, accountability, ethical considerations. They delve into various techniques methodologies aimed at unraveling black box learning, shedding light arrive their predictions classifications. From explainable AI approaches model-agnostic techniques, they explore practical strategies interpreting explaining models. Through real-world examples case studies, illustrate importance interpretability in ensuring transparency, fairness, compliance decision-making processes. Whether you're data scientist, researcher, or business leader, chapter serves as guide navigating complex landscape unlocking true potential technologies.

Language: Английский

---