As the world of medicine becomes increasingly digitized, the Web has become a de facto resource for physicians to quickly glean pertinent clinical information to carry out diagnostic and therapeutic decisions. At present, physicians face the dual challenge of judging the relevance of the information and trusting its Web source. This paper proposes a trust-relevance framework for conceptualizing computer-accessed medical information resources, a set of criteria for evaluating these information resources, and descriptions of a sample of available online resources. It also presents a usable framework for evaluating information retrieval innovations and explains the different capabilities of representative information retrieval tools and applications. By demystifying the concepts associated with information resources, search engines, and retrieval tools, and presenting a reasonable view of current opportunities as well as future possibilities, the authors hope to provide guidance so physicians can more rapidly adopt innovative computer-assisted search tools for acquiring information that facilitate patient care decision-making.
Download full-text PDF |
Source |
|---|
Publication Analysis
Top Keywords
Similar Publications
Evaluating simulated teaching audio for teacher trainees using RAG and local LLMs.
Sci Rep
January 2025
Office for the Advancement of Educational Information, Chengdu Normal University, Chengdu, 610000, China.
In the training of teacher students, simulated teaching is a key method for enhancing teaching skills. However, traditional evaluations of simulated teaching typically rely on direct teacher involvement and guidance, increasing teachers' workload and limiting the opportunities for teacher students to practice independently. This paper introduces a Retrieval-Augmented Generation (RAG) framework constructed using various open-source tools (such as FastChat for model inference and Whisper for speech-to-text) combined with a local large language model (LLM) for audio analysis of simulated teaching.
View Article and Find Full Text PDFBest evidence summary for the management of exercise in patients with central venous access devices.
J Vasc Access
January 2025
Department of Nasopharyngeal Carcinoma, Sun Yat-sen University Cancer Center, Guangzhou, P.R. China.
Background: Central venous access devices (CVAD) are widely used in patient care, providing an essential, reliable pathway for patients to receive chemotherapy, long-term infusions, and nutritional support. However, a system of exercise management has not been developed in patients with CVAD.
Purpose: To evaluate and summarize the evidence for management exercise in patients with CVAD and provide guidance for clinical practice.
Clinical entity-aware domain adaptation in low resource setting for inflammatory bowel disease.
Front Artif Intell
January 2025
Language Intelligence and Information Retrieval (LIIR) Lab, Department of Computer Science, KU Leuven, Leuven, Belgium.
The digitization of healthcare records has revolutionized medical research and patient care, with electronic health records (EHRs) containing a wealth of structured and unstructured data. Extracting valuable information from unstructured clinical text presents a significant challenge, necessitating automated tools for efficient data mining. Natural language processing (NLP) methods have been pivotal in this endeavor, aiming to extract crucial clinical concepts embedded within free-form text.
View Article and Find Full Text PDFInnovative epitopes in Protein-A an immuno-informatics approach to combat MDR-MRSA infections.
Front Cell Infect Microbiol
January 2025
Department of Haematology and Oncology, Shenzhen Children's Hospital, Shenzhen, China.
Background: Methicillin-resistant (MRSA) poses a significant challenge in clinical environments due to its resistance to standard antibiotics. Protein A (SpA), a crucial virulence factor of MRSA, undermines host immune responses, making it an attractive target for vaccine development. This study aimed to identify potential epitopes within SpA that could elicit robust immune responses, ultimately contributing to the combat against multidrug-resistant (MDR) MRSA.
View Article and Find Full Text PDFOpen-Source Large Language Models in Radiology: A Review and Tutorial for Practical Research and Clinical Deployment.
Radiology
January 2025
From the University of Maryland Medical Intelligent Imaging (UM2ii) Center, Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, 22 S Greene St, Baltimore, MD 21201 (C.H.S., A.K., V.P., F.X.D.); Departments of Radiology, Medicine, and Biomedical Data Science, Stanford University, Palo Alto, Calif (C.P.L.); Department of Computer Science and Electrical Engineering, College of Engineering and Information Technology, University of Maryland, Baltimore County, Baltimore, Md (A.J.); Department of Computer Science, University of Maryland, College Park, College Park, Md (H.H.); and University of Maryland Institute for Health Computing, University of Maryland, North Bethesda, Md (H.H., F.X.D.).
Integrating large language models (LLMs) into health care holds substantial potential to enhance clinical workflows and care delivery. However, LLMs also pose serious risks if integration is not thoughtfully executed, with complex challenges spanning accuracy, accessibility, privacy, and regulation. Proprietary commercial LLMs (eg, GPT-4 [OpenAI], Claude 3 Sonnet and Claude 3 Opus [Anthropic], Gemini [Google]) have received much attention from researchers in the medical domain, including radiology.
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!