Accelerating the translation of new scientific discoveries to improve human health and disease management is the overall goal of a series of initiatives integrated in the National Institutes of Health (NIH) "Roadmap for Medical Research." The Clinical and Translational Science Award (CTSA) program is, arguably, the most visible component of the NIH Roadmap providing resources to institutions to transform their clinical and translational research enterprises along the goals of the Roadmap. The CTSA program emphasizes biomedical informatics as a critical component for the accomplishment of the NIH's translational objectives. To be optimally effective, emerging biomedical informatics programs must link with the information technology platforms of the enterprise clinical operations within academic health centers.This report details one academic health center's transdisciplinary initiative to create an integrated academic discipline of biomedical informatics through the development of its infrastructure for clinical and translational science infrastructure and response to the CTSA mechanism. This approach required a detailed informatics strategy to accomplish these goals. This transdisciplinary initiative was the impetus for creation of a specialized biomedical informatics core, the Center for Biomedical Informatics (CBI). Development of the CBI codified the need to incorporate medical informatics including quality and safety informatics and enterprise clinical information systems within the CBI. This article describes the steps taken to develop the biomedical informatics infrastructure, its integration with clinical systems at one academic health center, successes achieved, and barriers encountered during these efforts.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3137749 | PMC |
| http://dx.doi.org/10.2310/JIM.0b013e31821452bf | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
The Venus score for the assessment of the quality and trustworthiness of biomedical datasets.
BioData Min
January 2025
Fondazione Bruno Kessler, Trento, Italy.
Biomedical datasets are the mainstays of computational biology and health informatics projects, and can be found on multiple data platforms online or obtained from wet-lab biologists and physicians. The quality and the trustworthiness of these datasets, however, can sometimes be poor, producing bad results in turn, which can harm patients and data subjects. To address this problem, policy-makers, researchers, and consortia have proposed diverse regulations, guidelines, and scores to assess the quality and increase the reliability of datasets.
View Article and Find Full Text PDFThe TRIPOD-LLM reporting guideline for studies using large language models.
Nat Med
January 2025
Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA, USA.
Large language models (LLMs) are rapidly being adopted in healthcare, necessitating standardized reporting guidelines. We present transparent reporting of a multivariable model for individual prognosis or diagnosis (TRIPOD)-LLM, an extension of the TRIPOD + artificial intelligence statement, addressing the unique challenges of LLMs in biomedical applications. TRIPOD-LLM provides a comprehensive checklist of 19 main items and 50 subitems, covering key aspects from title to discussion.
View Article and Find Full Text PDFMedical large language models are vulnerable to data-poisoning attacks.
Nat Med
January 2025
Department of Neurosurgery, NYU Langone Health, New York, NY, USA.
The adoption of large language models (LLMs) in healthcare demands a careful analysis of their potential to spread false medical knowledge. Because LLMs ingest massive volumes of data from the open Internet during training, they are potentially exposed to unverified medical knowledge that may include deliberately planted misinformation. Here, we perform a threat assessment that simulates a data-poisoning attack against The Pile, a popular dataset used for LLM development.
View Article and Find Full Text PDFToward expert-level medical question answering with large language models.
Nat Med
January 2025
Google Research, Mountain View, CA, USA.
Large language models (LLMs) have shown promise in medical question answering, with Med-PaLM being the first to exceed a 'passing' score in United States Medical Licensing Examination style questions. However, challenges remain in long-form medical question answering and handling real-world workflows. Here, we present Med-PaLM 2, which bridges these gaps with a combination of base LLM improvements, medical domain fine-tuning and new strategies for improving reasoning and grounding through ensemble refinement and chain of retrieval.
View Article and Find Full Text PDFA foundation model of transcription across human cell types.
Nature
January 2025
Program of Mathematical Genomics, Department of Systems Biology, Columbia University, New York, NY, USA.
Transcriptional regulation, which involves a complex interplay between regulatory sequences and proteins, directs all biological processes. Computational models of transcription lack generalizability to accurately extrapolate to unseen cell types and conditions. Here we introduce GET (general expression transformer), an interpretable foundation model designed to uncover regulatory grammars across 213 human fetal and adult cell types.
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!