Deep learning now underpins many state-of-the-art systems for biomedical image and signal processing, enabling automated lesion detection, physiological monitoring, and therapy planning with accuracy that rivals expert performance. This survey reviews the principal model families as convolutional, recurrent, generative, reinforcement, autoencoder, and transfer-learning approaches as emphasising how their architectural choices map to tasks such as segmentation, classification, reconstruction, and anomaly detection. A dedicated treatment of multimodal fusion networks shows how imaging features can be integrated with genomic profiles and clinical records to yield more robust, context-aware predictions. To support clinical adoption, we outline post-hoc explainability techniques (Grad-CAM, SHAP, LIME) and describe emerging intrinsically interpretable designs that expose decision logic to end users. Regulatory guidance from the U.S. FDA, the European Medicines Agency, and the EU AI Act is summarised, linking transparency and lifecycle-monitoring requirements to concrete development practices. Remaining challenges as data imbalance, computational cost, privacy constraints, and cross-domain generalization are discussed alongside promising solutions such as federated learning, uncertainty quantification, and lightweight 3-D architectures. The article therefore offers researchers, clinicians, and policymakers a concise, practice-oriented roadmap for deploying trustworthy deep-learning systems in healthcare.

This research introduces an innovative ensemble approach, combining Deep Residual Networks (ResNets) and Bidirectional Gated Recurrent Units (BiGRU), augmented with an Attention Mechanism, for the classification of heart arrhythmias. The escalating prevalence of cardiovascular diseases necessitates advanced diagnostic tools to enhance accuracy and efficiency. The model leverages the deep hierarchical feature extraction capabilities of ResNets, which are adept at identifying intricate patterns within electrocardiogram (ECG) data, while BiGRU layers capture the temporal dynamics essential for understanding the sequential nature of ECG signals. The integration of an Attention Mechanism refines the model’s focus on critical segments of ECG data, ensuring a nuanced analysis that highlights the most informative features for arrhythmia classification. Evaluated on a comprehensive dataset of 12-lead ECG recordings, our ensemble model demonstrates superior performance in distinguishing between various types of arrhythmias, with an accuracy of 98.4%, a precision of 98.1%, a recall of 98%, and an F-score of 98%. This novel combination of convolutional and recurrent neural networks, supplemented by attention-driven mechanisms, advances automated ECG analysis, contributing significantly to healthcare’s machine learning applications and presenting a step forward in developing non-invasive, efficient, and reliable tools for early diagnosis and management of heart diseases.

Robotic manipulators increasingly operate in complex three-dimensional workspaces where accuracy and strict limits on position, velocity, and acceleration must be satisfied. Conventional geometric planners emphasize path smoothness but often ignore dynamic feasibility, motivating control-aware trajectory generation. This study presents a novel model predictive control (MPC) framework for three-dimensional trajectory planning of robotic manipulators that integrates second-order dynamic modeling and multi-objective parameter optimization. Unlike conventional interpolation techniques such as cubic splines, B-splines, and linear interpolation, which neglect physical constraints and system dynamics, the proposed method generates dynamically feasible trajectories by directly optimizing over acceleration inputs while minimizing both tracking error and control effort. A key innovation lies in the use of Pareto front analysis for tuning prediction horizon and sampling time, enabling a systematic balance between accuracy and motion smoothness. Comparative evaluation using simulated experiments demonstrates that the proposed MPC approach achieves a minimum mean absolute error (MAE) of 0.170 and reduces maximum acceleration to 0.0217, compared to 0.0385 in classical linear methods. The maximum deviation error was also reduced by approximately 27.4% relative to MPC configurations without tuned parameters. All experiments were conducted in a simulation environment, with computational times per control cycle consistently remaining below 20 milliseconds, indicating practical feasibility for real-time applications. This work advances the state-of-the-art in MPC-based trajectory planning by offering a scalable and interpretable control architecture that meets physical constraints while optimizing motion efficiency, thus making it suitable for deployment in safety-critical robotic applications.

Clinical applications of Artificial Intelligence (AI) for mental health care have experienced a meteoric rise in the past few years. AI-enabled chatbot software and applications have been administering significant medical treatments that were previously only available from experienced and competent healthcare professionals. Such initiatives, which range from “virtual psychiatrists” to “social robots” in mental health, strive to improve nursing performance and cost management, as well as meeting the mental health needs of vulnerable and underserved populations. Nevertheless, there is still a substantial gap between recent progress in AI mental health and the widespread use of these solutions by healthcare practitioners in clinical settings. Furthermore, treatments are frequently developed without clear ethical concerns. While AI-enabled solutions show promise in the realm of mental health, further research is needed to address the ethical and social aspects of these technologies, as well as to establish efficient research and medical practices in this innovative sector. Moreover, the current relevant literature still lacks a formal and objective review that specifically focuses on research questions from both developers and psychiatrists in AI-enabled chatbot-psychologists development. Taking into account all the problems outlined in this study, we conducted a systematic review of AI-enabled chatbots in mental healthcare that could cover some issues concerning psychotherapy and artificial intelligence. In this systematic review, we put five research questions related to technologies in chatbot development, psychological disorders that can be treated by using chatbots, types of therapies that are enabled in chatbots, machine learning models and techniques in chatbot psychologists, as well as ethical challenges.