98%
921
2 minutes
20
The emergence of foundational models represents a paradigm shift in medical imaging, offering extraordinary capabilities in disease detection, diagnosis, and treatment planning. These large-scale artificial intelligence systems, trained on extensive multimodal and multi-center datasets, demonstrate remarkable versatility across diverse medical applications. However, their integration into clinical practice presents complex ethical challenges that extend beyond technical performance metrics. This study examines the critical ethical considerations at the intersection of healthcare and artificial intelligence. Patient data privacy remains a fundamental concern, particularly given these models' requirement for extensive training data and their potential to inadvertently memorize sensitive information. Algorithmic bias poses a significant challenge in healthcare, as historical disparities in medical data collection may perpetuate or exacerbate existing healthcare inequities across demographic groups. The complexity of foundational models presents significant challenges regarding transparency and explainability in medical decision-making. We propose a comprehensive ethical framework that addresses these challenges while promoting responsible innovation. This framework emphasizes robust privacy safeguards, systematic bias detection and mitigation strategies, and mechanisms for maintaining meaningful human oversight. By establishing clear guidelines for development and deployment, we aim to harness the transformative potential of foundational models while preserving the fundamental principles of medical ethics and patient-centered care.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC12128638 | PMC |
http://dx.doi.org/10.3389/fmed.2025.1544501 | DOI Listing |
Macromol Rapid Commun
September 2025
Karlsruhe Institute of Technology, Karlsruhe, Germany.
Within this special issue we would like to celebrate 200 years of the Karlsruhe Institute of Technology (KIT) and the former Technical University Karlsruhe/Germany. The Technical University Karlsruhe served, according to the first president of MIT, William Barton Rogers, as the role model for the planned MIT in Boston/USA after he visited Karlsruhe. All authors of this special issue of Macromolecular Rapid Communications have been or are still active in Karlsruhe.
View Article and Find Full Text PDFJAMA Intern Med
September 2025
Bayer CC AG, Basel, Switzerland.
Importance: There is an unmet need for long-term, safe, effective, and hormone-free treatments for menopausal symptoms, including vasomotor symptoms (VMS) and sleep disturbances.
Objective: To evaluate the 52-week efficacy and safety of elinzanetant, a dual neurokinin-targeted therapy, for treating moderate to severe VMS associated with menopause.
Design, Setting, And Participants: OASIS-3 was a double-blind, placebo-controlled, randomized phase 3 clinical trial that was conducted at 83 sites in North America and Europe from August 27, 2021, to February 12, 2024, and included postmenopausal women aged 40 to 65 years who were seeking treatment for moderate to severe VMS (no requirement for a minimum number of VMS events per week).
Macromol Rapid Commun
September 2025
Key Laboratory of Textile Science & Technology, College of Textiles, Ministry of Education, Donghua University, Shanghai, China.
Persistent bacterial infections remain a major challenge in wound management. Although drug-loaded wound dressings have gained increasing attention, their therapeutic efficacy is often hindered by uncontrolled drug release and a lack of electrical signal responsiveness. Herein, an antibacterial dressing (CCS-PC) with electroactivity and stimulus-responsive drug release properties was fabricated via electro-assembly, wherein chitosan and ciprofloxacin hydrochloride (CIP) were co-deposited onto polypyrrole (PPy)-coated gauze.
View Article and Find Full Text PDFMultimed Man Cardiothorac Surg
September 2025
Department of Thoracic Surgery, New Cross Hospital, Royal Wolverhampton NHS Trust, Wolverhampton, UK
Three-dimensional (3D) guided robotic-assisted thoracic surgery is increasingly recognized as the pioneering approach for the most complex of pulmonary resections, offering high-definition 3D visualization, enhanced instrument augmentation and tremor-free tissue articulation. Compared with open thoracotomy, the robotic platform is associated with reduced peri-operative morbidity, shorter hospital admissions and faster patient recovery. However, sublobar resections such as segmentectomies remain anatomically and technically demanding, particularly in the context of resecting multiple segments, as showcased in this right S1 and S2 segmentectomy.
View Article and Find Full Text PDFMultimed Man Cardiothorac Surg
September 2025
Department of Cardiothoracic Surgery, St George’s Hospital, St George's University Hospitals NHS Foundation Trust, London, UK
Three-dimensional (3D) guided robotic-assisted thoracic surgery is increasingly recognized as a leading technique for undertaking the most complex pulmonary resections, providing high-definition 3D visualization, advanced instrument control and tremor-free tissue handling. Compared with open thoracotomy, the robotic platform offers reduced peri-operative complications, shorter hospital stays and faster patient recovery. Nevertheless, sublobar resections, such as segmentectomies, remain both anatomically intricate and technically challenging, particularly when resecting multiple segments, as in this left S1 and S2 segmentectomy.
View Article and Find Full Text PDF