Download full-text PDF |
Source |
|---|
Publication Analysis
Top Keywords
Similar Publications
FL-W3S: Cross-domain federated learning for weakly supervised semantic segmentation of white blood cells.
Int J Med Inform
January 2025
Department of Computer Science and Artificial Intelligence, University of Udine, 33100, Italy.
Background: Segmentation models for clinical data experience severe performance degradation when trained on a single client from one domain and distributed to other clients from different domain. Federated Learning (FL) provides a solution by enabling multi-party collaborative learning without compromising the confidentiality of clients' private data.
Methods: In this paper, we propose a cross-domain FL method for Weakly Supervised Semantic Segmentation (FL-W3S) of white blood cells in microscopic images.
Questionnaire and analysis of the standardized use of home self-monitoring portable blood glucose meters.
Medicine (Baltimore)
January 2025
Department of Clinical Laboratory, Zhejiang Hospital, Hangzhou, Zhejiang, China.
To evaluate the accuracy of home self-monitoring portable blood glucose meters, we analyzed the current problems of patients using portable blood glucose meters and put forward reasonable suggestions. A self-designed questionnaire was used to survey 142 patients and 132 healthcare professionals. The questionnaire consisted of 16 items with an overall score ranging from 1 to 13 (with a higher score indicating better experience).
View Article and Find Full Text PDFParental Mental Health and Child Maltreatment in the COVID-19 Pandemic: Importance of Sampling in a Quantitative Statistical Study.
J Med Internet Res
January 2025
Clinical Psychology and Psychotherapy, Department of Education and Psychology, Freie Universität Berlin, Berlin, Germany.
Background: Results on parental burden during the COVID-19 pandemic are predominantly available from nonrepresentative samples. Although sample selection can significantly influence results, the effects of sampling strategies have been largely underexplored.
Objective: This study aimed to investigate how sampling strategy may impact study results.
Virtual patients using large language models: Scalable, contextualized simulation of clinician-patient dialog with feedback.
J Med Internet Res
January 2025
Division of General Internal Medicine, Mayo Clinic College of Medicine and Science, 200 First St SW, Rochester, US.
Background: Virtual patients (VPs) are computer screen-based simulations of patient-clinician encounters. VP use is limited by cost and low scalability.
Objective: Show proof-of-concept that VPs powered by large language models (LLMs) generate authentic dialogs, accurate representations of patient preferences, and personalized feedback on clinical performance; and explore LLMs for rating dialog and feedback quality.
Magnetic resonance angiography in diagnostic long-term follow-up of primary patency of the MOTIV drug-eluting bioresorbable vascular scaffold in the region below the knee: 5 years of experience.
PLoS One
January 2025
Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria.
Purpose: Treatment of peripheral artery disease (PAD) in the region below the knee (BTK) is dissatisfying as failure of treated target lesions (TLF) is frequent and diagnostic imaging is often challenging. In the BTK-region metallic drug-eluting stents (mDES) yielded best results concerning primary patency (PP), but also annihilate signal in magnetic resonance angiography (MR-A). A recently introduced non-metallic drug eluting bioresorbable Tyrocore® vascular scaffold (deBVS), that offers an option for re-treatment of lesions due to its full degradation within 3-4 years after placement, was investigated with respect to its compatibility with MR-A to unimpededly depict previously treated target lesions.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!