Aug 2026· Discover Artificial Intelligence· 92 references
ECG Monitoring and Analysis
Abstract
Cardiovascular disease (CVD) are a leading cause of global morbidity and mortality, making early and accurate detection essential for improving patient outcomes. The electrocardiogram (ECG) is one of the most important diagnostic tools for identifying various cardiac abnormalities. Recent advances in machine learning (ML) and deep learning (DL) have shown strong potential for improving ECG-based CVD detection. This review critically analyzes recent ECG-based ML/DL models for CVD prediction, with particular attention to model performance, dataset characteristics, preprocessing strategies, and the integration of explainable artificial intelligence (XAI). The review covers a broad range of ECG-related applications, including arrhythmia, myocardial infarction, atrial fibrillation, heart failure, pediatric and fetal ECG analysis, wearable ECG monitoring, ECG image analysis, and ECG-centered multimodal approaches. Across the 75 included studies, reported diagnostic performance was generally high, with accuracy commonly ranging from approximately 90 to 99%, sensitivity from approximately 81 to 99%, specificity from approximately 84 to 99%, AUROC values reaching up to approximately 0.98–0.99, and F1-scores exceeding 0.90 in several benchmark datasets. However, these results varied substantially according to dataset characteristics, disease category, preprocessing strategy, model architecture, validation protocol, and evaluation metrics. Although many studies reported excellent internal validation performance, relatively few performed external or prospective clinical validation, highlighting an important gap in the translation of AI-assisted ECG models into routine clinical practice. The most frequently used datasets included MIT-BIH, PTB-XL, PhysioNet, CPSC, and UK Biobank, while dominant model families included CNN, LSTM, Transformer, SVM, RF, and hybrid CNN-LSTM architectures. Although ML/DL models have reported promising diagnostic performance, several challenges remain, including class imbalance, data quality variation, limited generalizability, model interpretability, and the limited availability of external and prospective clinical validation, which remain major barriers to the widespread clinical adoption of AI-assisted ECG diagnostic systems. In addition, ethical, legal, and social issues, such as data bias, privacy, transparency, and clinical trust, must be addressed before these models can be reliably and responsibly deployed in clinical practice. This review provides an integrated overview of ECG-based AI models for CVD prediction and highlights future research directions for developing more interpretable, generalizable, and clinically trustworthy AI-assisted ECG diagnostic systems.
Digital twins (DTs) are rapidly emerging as foundational enablers of 6G smart cities, offering real time monitoring, predictive analytics, and autonomous control across transportation, energy, healthcare, and industrial domains. Large scale DT adoption faces critical barriers including cybersecurity vulnerabilities, privacy risks, and the absence of standardized orchestration frameworks. This article presents Fed-DTOrch, a comprehensive end to end architecture that integrates federated intelligence, blockchain based audit trails, and AI governance to achieve secure and privacy preserving DT management. The proposed three tier architecture spans IoT and edge devices, domain specific twins, and a city level orchestrator, employing secure federated learning for model updates, lightweight cryptographic authentication, and tamper proof logging. We quantify the DT threat landscape, perform a standards gap analysis across ISO/IEC 27001, 3GPP TS 33.501, ITU-T IoT risk frameworks, and NIST AI RMF, and introduce a 6G ready security framework incorporating federated AI trust metrics, secure synchronization, and explainable AI audits. Cross domain evaluation across five smart city sectors demonstrates 35-60% privacy gain, 40-55% attack mitigation, 28-40% reliability uplift, 26-30% latency reduction, and >85% compliance readiness with <10% overhead. These results provide the first integrated blueprint that combines federated intelligence, blockchain-based auditability, and standards gap analysis to enable secure, standardized, and interoperable DT orchestration for trustworthy 6G ecosystems.
Li Wang, Xiuming Cheng· IEEE Communications Standard...· 1 citation
It is argued that both AI and bullshitters are untrustworthy informants, and for similar reasons, it is natural to describe AI’s informational outputs as bullshit, as it signals their distinctive kind of epistemic deficiencies, which they share with bullshit.
Algorithmic fairness and explainability are foundational pillars of responsible AI. Although often studied independently, their interplay is increasingly recognized as crucial for diagnosing and mitigating bias in machine learning systems. We first introduce two systematic taxonomies: one for algorithmic fairness and one for explainable AI, to organize the landscape of existing work across diverse tasks (classification, ranking, and recommendation) and data modalities (tabular, graph). Next, we categorize the use of explanations in fairness efforts into three main functions: (a) detecting and understanding the causes of unfairness, (b) defining enhanced fairness metrics, and (c) designing mitigation strategies. In addition, we examine how explanation methods themselves can be biased, underscoring the need to evaluate fairness for explanations. Finally, we identify open research challenges and outline promising directions for future research at the intersection of fairness and explainability.
Christos Fragkathoulas, Vasiliki Papanikou, Danae Pla Karidi et al.· IEEE Transactions on Knowled...· 0 citations
The Adaptive Repayment Optimisation Engine is introduced, a novel framework that applies constrained stochastic optimisation to the design of loan repayment schedules for small and medium-sized enterprises (SMEs) and contributes to the operations research literature by bridging stochastic programming, explainable AI, and financial regulation in a novel application domain.
John Christiansen· Open Access Journal of Artif...· 0 citations
What is consciousness? Despite millennia of inquiry, humanity still lacks a consensus definition. This paper proposes a unified, strictly materialist theory: consciousness is not an entity but a process-specifically, the dynamic process that occurs when a specific structure, formed within complex, chaotic circuits, formats and processes input data and produces output. The structure is the carrier; the processing itself is consciousness. Building on this definition, the paper introduces a two-layer architecture that distinguishes basal consciousness (the autonomous survival functions shared by nearly all living organisms) from advanced consciousness (spanning the awareness of basic sensations, self-awareness, metacognition, and abstract reasoning). We argue that the two layers are related not as a hierarchy of subordination, but as a partnership of trust shaped by natural selection. The paper further proposes the mechanism of the self-reinforcing circuit: advanced consciousness is not complete at birth; it must be "awakened" through sustained external stimulation. Once awakened, it consolidates its own existence by continuously reinforcing the neural pathways dedicated to it, sculpting the unique "I" of each individual. This mechanism offers a parsimonious explanation of dissociative identity disorder, personality change after brain injury, and the diversity of human personality. The Awakener model traces the complete evolutionary path: from primitive sensory-interpretation tools, through the emergence of intelligence, the first awakening event, and chained cultural transmission, to the birth of language and writing. We apply this framework to explain why intelligent animals never developed civilization, to predict which species might awaken next, and to redefine the current state of artificial intelligence as a frozen brain-structurally capable of consciousness, but temporally static: a single frame. Within a single, self-consistent framework, the theory unifies the core problems of consciousness research: the definition and essence of consciousness, the hard problem, the two-layer distinction, the physical basis of the "I", personality diversity, the evolutionary origin of consciousness, the boundaries of animal consciousness, the origin of language, the conscious status of AI, free will and the Libet experiments, split-brain interpretation, dreams and sleepwalking, and the relation between the subconscious and System 1/System 2. No immaterial components are required: every step rests on existing experimental evidence or established neuroscientific findings.
Yijun Mo· Zenodo (CERN European Organi...· 0 citations
A new method for surgically removing training examples from a model reveals that as datasets grow, the link between what a model learns and what it produces dissolves.
