Coronary heart disease (CHD), the most common cause of mortality globally, poses a formidable challenge to modern healthcare systems. Artificial intelligence (AI) is playing an increasingly important role in multiple diagnostic applications of CHD, by facilitating early intervention and personalized treatment. This mini review describing the state of the art provides clinicians with updated insights into the transformative potential of AI to enhance CHD detection. AI can be used to increase diagnostic and prognostic accuracy. However, its reliance on homogeneous numerical data might potentially lead to misdiagnoses and unnecessary radiation exposure in diagnosing CHD. Multimodal data fusion brings new potential for accurate diagnosis and personalized medicine. Finally, unmet challenges and future research directions in ethical, regulatory, and technical aspects are discussed. This mini review is aimed at bridging the gap between AI advancements and practical applications in clinical settings, to achieve a future in which AI empowers CHD diagnosis in the context of a modern healthcare ecosystem.

Background: The diagnostic test for vasovagal syncope (VVS), the most common cause of syncope is head-up tilt test (HUTT) assessment. During the test, subjects experienced clinical symptoms such as nausea, sweating, pallor, the feeling of palpitations, being on the verge of passing out, and fainting. The study's goal is to develop an algorithm to classify VVS patients based on physiological signals blood pressure (BP) and electrocardiography (ECG) obtained from the HUTT. Methods: After 10 min of supine rest, the subject was tilted at a 70-degree angle on a tilt table for approximately a total of 35 min. 400 µg of glyceryl trinitrate (GTN) was administered sublingually after the first 20 min and monitoring continued for another 15 min. Mean imputation and K-nearest neighbors (KNN) imputation approaches to handle missing values. Next, feature selection techniques were implemented, including genetic algorithm, recursive feature elimination, and feature importance, to determine the crucial features. The Mann–Whitney U test was then performed to determine the statistical difference between two groups. Patients with VVS are categorized via machine learning models including Support Vector Machine (SVM), Gaussian Naïve Bayes (GNB), Multinomial Naïve Bayes (MNB), KNN, Logistic Regression (LR), and Random Forest (RF). The developed model is interpreted using an explainable artificial intelligence (XAI) model known as partial dependence plot. Results: A total of 137 subjects aged between 9 and 93 years were recruited for this study, 54 experienced clinical symptoms were considered positive tests, while the remaining 83 tested negative. Optimal results were obtained by combining the KNN imputation technique and three tilting features with SVM with 90.5% accuracy, 87.0% sensitivity, 92.7% specificity, 88.6% precision, 87.8% F1 score, and 95.4% ROC (receiver operating characteristics) AUC (area under curve). Conclusions: The proposed algorithm effectively classifies VVS patients with over 90% accuracy. However, the study was confined to a small sample size. More clinical datasets are required to ensure that our approach is generalizable.

• The first systematic review on syncope classification using machine learning (ML) algorithms includes an evaluation of ML algorithm performance in predicting syncope based on hemodynamic parameters. • The machine learning algorithms have demonstrated their capability to detect syncope with a sensitivity of 88.8%, specificity of 81.5%, and an overall accuracy of 85.8%. • Integration of ML in syncope diagnosis holds the potential to simplify diagnosis with a reduced set of parameters for more efficient assessments and, as a result, reduce unnecessary hospital investigations.

A parametric representation of Alzheimer’s disease (AD) indicates cognitive, behavioral, and intellectual difficulties. Aging is the biggest risk factor for most neurodegenerative diseases including AD. Age-related genetic, biochemical, structural, and functional changes commonly contribute to the liability to AD. Clinical electroencephalogram (EEG) technology enables the detection of the underlying neurophysiological abnormalities associated with AD, such as neuronal loss, synaptic dysfunction, and aberrant network connections, which can be reflected in the variations of EEG features and their temporal evolution. EEG data can be analyzed using a range of signal processing techniques, including discrete wavelet transform, the Burg method, and average periodogram, to investigate the cerebral activity linked to various cognitive and behavioral activities. Artificial intelligence (AI) can improve the efficiency of signal processing and achieve automatic classification of patients. Interest is growing in the use of AI algorithms and other cutting-edge computational techniques to analyze EEG data for the diagnosis of AD. By assisting in the detection of specific changes in EEG patterns, these techniques might enable earlier and more accurate diagnosis of AD. <!----> <!----> <!----> <!---->

The Internet of Things (IoT) plays an increasingly central role in healthcare by enabling continuous patient monitoring, remote diagnosis, and data-driven clinical decision-making through interconnected medical devices and sensing infrastructures. Despite these advances, IoT healthcare systems remain constrained by persistent challenges related to data privacy, computational efficiency, scalability, and regulatory compliance. Federated learning (FL) reduces reliance on centralised data aggregation but remains vulnerable to inference-based privacy risks, while edge-oriented approaches are limited by device heterogeneity and restricted computational and energy resources; the deployment of large language models (LLMs) further exacerbates concerns surrounding privacy exposure, communication overhead, and practical feasibility. This study introduces Trustworthy Intelligence (TI) as a guiding framework for privacy-preserving distributed intelligence in IoT healthcare, explicitly integrating predictive performance, privacy protection, and deployment-oriented system design. Within this framework, split learning (SL) is examined as a core architectural mechanism and extended to support split-aware LLM integration across heterogeneous devices, supported by a structured taxonomy spanning architectural configurations, system adaptation strategies, and evaluation considerations. The study establishes a systematic mapping between SL design choices and representative healthcare scenarios, including wearable monitoring, multi-modal data fusion, clinical text analytics, and cross-institutional collaboration, and analyses key technical challenges such as activation-level privacy leakage, early-round vulnerability, reconstruction risks, and communication–computation trade-offs. An energy- and resource-aware adaptive cut layer selection strategy is outlined to support efficient deployment across devices with varying capabilities. A proof-of-concept experimental evaluation compares the proposed SL–LLM framework with centralised learning (CL), federated learning (FL), and conventional SL in terms of training latency, communication overhead, model accuracy, and privacy exposure under realistic IoT constraints, providing system-level evidence for the applicability of the TI framework in distributed healthcare environments and outlining directions for clinically viable and regulation-aligned IoT healthcare intelligence.