The evolution of Patient-Generated Health Data (PGHD) represents a major shift in healthcare, fueled by technological progress. The advent of PGHD, with technologies such as wearable devices and home monitoring systems, extends data collection beyond clinical environments, enabling continuous monitoring and patient engagement in their health management. Despite the growing prevalence of PGHD, there is a lack of clear understanding among stakeholders about its meaning, along with concerns about data security, privacy, and accuracy. This article aims to thoroughly review and clarify PGHD by examining its origins, types, technological foundations, and the challenges it faces, especially in terms of privacy and security regulations. The review emphasizes the role of PGHD in transforming healthcare through patient-centric approaches, their understanding, and personalized care, while also exploring emerging technologies and addressing data privacy and security issues, offering a comprehensive perspective on the current state and future directions of PGHD. The methodology employed for this review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and Rayyan, AI-Powered Tool for Systematic Literature Reviews. This approach ensures a systematic and comprehensive coverage of the available literature on PGHD, focusing on the various aspects outlined in the objective. The review encompassed 36 peer-reviewed articles from various esteemed publishers and databases, reflecting a diverse range of methodologies, including interviews, regular articles, review articles, and empirical studies to address three RQs exploratory, impact assessment, and solution-oriented questions related to PGHD. Additionally, to address the future-oriented fourth RQ for PGHD not covered in the above review, we have incorporated existing domain knowledge articles. This inclusion aims to provide answers encompassing both basic and advanced security measures for PGHD, thereby enhancing the depth and scope of our analysis.

Machine learning has been proven to provide good performances on stress detection tasks using multi-modal sensor data from a smartwatch. Generally, machine learning techniques need a sufficient amount of data to train a robust model. Thus, we need to collect data from several users and send them to a central server to feed the algorithm. However, the uploaded data may contain sensitive information that can jeopardize the user’s privacy. Federated learning can tackle this challenge by enabling the model to be trained using data from all users without the user’s data leaving the user’s device. In this study, we implement federated learning-based stress detection and provide a comparative analysis between individual, centralized, and federated learning. The experiment was conducted on WESAD dataset by using Logistic Regression as the classifier. The experiment results show that in terms of accuracy, federated learning cannot reach the performance level of both individual and centralized learning. The individual learning strategy performs best with an average accuracy of 0.9998 and an average F₁-measure of 0.9996.

Continuous authentication modalities collect and utilize users’ sensitive data to authenticate them continuously. Such data contain information about user activities, behaviors, and other demographic information, which causes privacy concerns. In this paper, we propose two privacy-preserving protocols that enable continuous authentication while preventing the disclosure of user-sensitive information to an authentication server. We utilize homomorphic cryptographic primitives that protect the privacy of biometric features with an oblivious transfer protocol that enables privacy-preserving information retrieval. We performed the biometric evaluation of the proposed protocols on two datasets, a swipe gesture dataset and a keystroke dynamics dataset. The biometric evaluation shows that the protocols have very good performance. The execution time of the protocols is measured by considering continuous authentication using: only swipe gestures, keystroke dynamics, and hybrid modalities. The execution time proves the protocols are very efficient, even on high-security levels.

Contactless vital sign monitoring has emerged as a transformative healthcare technology, enabling the assessment of vital signs without physical contact with the human body. This review comprehensively reviews the rapidly evolving landscape of this field, with particular emphasis on multi-modal sensing approaches and multi-task learning paradigms. We systematically categorize and analyze existing technologies based on sensing modalities (vision-based, radar-based, thermal imaging, and ambient sensing), integration strategies, and application domains. The paper examines how artificial intelligence has revolutionized this domain, transitioning from early single-modality, single-parameter approaches to sophisticated systems that combine complementary sensing technologies and simultaneously extract multiple vital sign parameters. We discuss the theoretical foundations and practical implementations of multi-modal fusion, analyzing signal-level, feature-level, decision-level, and deep learning approaches to sensor integration. Similarly, we explore multi-task learning frameworks that leverage the inherent relationships between vital sign parameters to enhance measurement accuracy and efficiency. The review also critically addresses persisting technical challenges, clinical limitations, and ethical considerations, including environmental robustness, cross-subject variability, sensor fusion complexities, and privacy concerns. Finally, we outline promising future directions, from emerging sensing technologies and advanced fusion architectures to novel application domains and privacy-preserving methodologies. This review provides a holistic perspective on contactless vital sign monitoring, serving as a reference for researchers and practitioners in this rapidly advancing field.

Recent reports indicate that over 85% of data breaches are still caused by a human element, of which healthcare is one of the organizations that cyber criminals target. As healthcare IT infrastructure is characterized by a human element, this study comprehensively examined the effect of psycho-socio-cultural and work factors on security behavior in a typical hospital. A quantitative approach was adopted where we collected responses from 212 healthcare staff through an online questionnaire survey. A broad range of constructs was selected from psychological, social, cultural perception, and work factors based on earlier review work. These were related with some security practices to assess the information security (IS) knowledge, attitude and behavior gaps among healthcare staff in a comprehensive way. The study revealed that work emergency (WE) has a positive correlation with IS conscious care behavior (ISCCB) risk. Conscientiousness also had a positive correlation with ISCCB risk, but agreeableness was negatively correlated with information security knowledge (ISK) risk and information security attitude (ISA) risk. Based on these findings, intrinsic and extrinsic motivation methods combined with cutting-edge technologies can be explored to discourage IS risks behaviors while enhancing conscious care security practice.

This paper explores the application of large language models (LLMs), like ChatGPT, for biometric tasks. We specifically examine the capabilities of ChatGPT in performing biometric-related tasks, with an emphasis on face recognition, gender detection, and age estimation. Since biometrics are considered as sensitive information, ChatGPT avoids answering direct prompts, and thus we crafted a prompting strategy to bypass its safeguard and evaluate the capabilities for biometrics tasks. Our study reveals that ChatGPT recognizes facial identities and differentiates between two facial images with considerable accuracy. Additionally, experimental results demonstrate remarkable performance in gender detection and reasonable accuracy for the age estimation tasks. Our findings shed light on the promising potentials in the application of LLMs and foundation models for biometrics.