Patient-specific digital simulation is emerging as a tool to support personalized planning of transcatheter aortic valve replacement (TAVR), particularly as the procedure expands to younger, lower-risk patients, and more complex anatomies. Despite procedural advances, complications such as paravalvular leak, conduction disturbances, coronary obstruction, and aortic injury remain important determinants of outcome. Current pre-procedural planning relies […]
Feasibility of weekly patient-reported symptom monitoring using patients’ own smartphones in outpatient cancer chemotherapy: the SMART-PRO study
Electronic patient-reported outcome (ePRO) systems using the Patient-Reported Outcomes version of the Common Terminology Criteria for Adverse Events (PRO-CTCAE) can improve symptom monitoring, but the feasibility of implementing such systems with a bring-your-own-device (BYOD) approach in routine oncology practice, particularly among older adults, is not well established. We conducted a single-arm prospective observational study in […]
Voice disorders classification using machine learning: a scoping review
ObjectivesThis review aims to identify the key barriers to clinical application of Machine Learning (ML) in multi-class voice disorder classification.DesignScoping Review.MethodsA comprehensive scoping review of research published between 2013 and May 2025 in seven clinical and engineering databases was conducted. Articles that applied ML techniques to classify voice disorders were examined, excluding publications limited to […]
Evaluating artificial intelligence large language models in dental education: a cross-sectional survey on usage, perceptions, and integration at a U.S. dental school
IntroductionThe adoption of artificial intelligence (AI) in higher education presents opportunities and challenges for dental education. This study explores the use of Large Language Model (LLM) based AI tools, including ChatGPT and Grammarly AI, among faculty and students at the UTHealth School of Dentistry in Houston (UTSDH). This research assessed usage patterns, perceived benefits and […]
Digital platforms for ethics review: a mini review
This mini review examines the emerging use of digital platforms for ethics review (DPER) and the extent to which research ethics committees (RECs) are prepared for digital transformation and operational autonomy. Drawing on a structured analysis of peer-reviewed studies published between 2013 and 2024, the review synthesises the existing research on DPER and examines reported […]
Personalized vs. population-based speech models for multi-dimensional mental health prediction
IntroductionMental disorders such as depression, anxiety, and stress are increasingly prevalent, particularly among young adults. Traditional assessment methods rely on self-reports and resource-intensive clinician interviews, limiting scalability and accessibility. Speech-based machine learning models offer a scalable and non-invasive alternative; however, population-level models often struggle to distinguish disorder-related signals from speaker-specific traits, reducing individual prediction accuracy.MethodsWe […]
SENTINEL-Chain: a blockchain-integrated privacy-preserving framework for secure healthcare data publishing
IntroductionElectronic health records (EHRs) are central to healthcare analytics, but their granularity increases re-identification risk when shared. Conventional privacy-preserving methods including k-anonymity, l-diversity, and differential privacy often protect confidentiality at the expense of analytical utility by weakening clinically meaningful correlations.MethodsWe propose SENTINEL-Chain, a blockchain-integrated privacy-preserving framework for secure EHR publishing. The privacy layer combines six […]
Performance of large language models in delivering accurate and comprehensible patient information on heart failure and cardiomyopathy
BackgroundLarge language models (LLMs) are increasingly used by patients seeking cardiovascular health information through digital platforms. However, their accuracy and suitability for providing guidance on heterogeneous diseases such as cardiomyopathies and heart failure remain inadequately evaluated. This study systematically benchmarked state-of-the-art LLMs on patient-oriented heart failure and cardiomyopathy queries regarding clinical appropriateness and comprehensibility.MethodsSix prominent […]
Secure healthcare data management using federated learning, blockchain, and explainable artificial intelligence: a systematic review
Due to the rapid digitization of healthcare systems, there has been a huge collection of sensitive personal data of patients. Thus, secure, privacy-preserving, and efficient data management systems are required. Current distributed healthcare systems increasingly use centralized data processing frameworks that are prone to privacy violations, data fragmentation, and malicious attacks. Despite advances in federated […]
The role of perceived competence in remote cochlear implant aftercare: a mixed-methods study
IntroductionRemote care and digital health tools are increasingly incorporated into cochlear implant aftercare to enhance accessibility and patient engagement. Their uptake, however, depends strongly on perceived competence, digital health literacy, and motivational factors among patients with cochlear implants (CI).MethodsThis exploratory sequential mixed-methods study investigated motivational mechanisms and digital readiness among patients with cochlear implants (PwCI). […]
A prototype smartwatch for monitoring dynamic, compound and plyometric exercises in cancer prehabilitation: a development and validation study
BackgroundCancer prehabilitation programmes increasingly rely on home-based exercise interventions, yet objective monitoring of exercise compliance remains challenging. Current commercial wearables focus primarily on aerobic activities and lack capability for monitoring dynamic, compound, and plyometric exercises essential for cancer prehabilitation.ObjectiveTo develop and validate a prototype smartwatch capable of monitoring specific prehabilitation exercises with objective compliance tracking.MethodsWe […]
ScaleSweep: Accurate NVFP4 Post-Training Quantization of LLMs via Block Scale Initialization
arXiv:2606.07618v1 Announce Type: cross Abstract: NVFP4 is a recently introduced hardware-supported FP4 format that improves the fidelity of 4-bit quantization through fine-grained block scales. However, existing NVFP4 scale initialization methods still primarily rely on AbsMax initialization, which leaves a noticeable gap to the optimal solution. To address this, we propose ScaleSweep, a simple and efficient […]