Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Improving Translational Accuracy02:07

Improving Translational Accuracy

11.9K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
11.9K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Language-Serving Hospitals and Seven-Day Readmission Among Patients With a Non-English Primary Language.

American journal of public health·2026
Same author

Real-world implementation of clinical decision support systems in emergency departments: a scoping review protocol.

JBI evidence synthesis·2026
Same author

AI-induced never-skilling in medical education.

Nature medicine·2026
Same author

Author Correction: Real-time surveillance system for patient deterioration: a pragmatic cluster-randomized controlled trial.

Nature medicine·2026
Same author

Obstetric History Versus Biomarkers: Hypertension Risk Up to 15 Years Postpartum.

Hypertension (Dallas, Tex. : 1979)·2026
Same author

Autoregressive With Exogenous Input (ARX) Decision Support for Blood Pressure Maintenance During Cesarean Delivery Under Spinal Anesthesia: A Prospective Pilot Study With Matched Nonconcurrent Controls.

medRxiv : the preprint server for health sciences·2026

Related Experiment Video

Updated: Sep 12, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

681

SPELL-LLMs: A Scalable and Privacy-Compliant NLP Pipeline Using Locally Hosted Large Language Models for Clinical

Ricardo Kleinlein, Kathryn J Gray, David Bates

    Medrxiv : the Preprint Server for Health Sciences
    |August 8, 2025
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a privacy-preserving natural language processing (NLP) workflow that efficiently extracts structured data from electronic health records (EHRs). The hybrid approach significantly speeds up analysis and improves data usability for clinical research.

    More Related Videos

    Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
    05:47

    Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

    Published on: June 13, 2025

    578
    Asthma Detection Research Based on Voice Signal Processing and Machine Learning
    04:04

    Asthma Detection Research Based on Voice Signal Processing and Machine Learning

    Published on: July 22, 2025

    407

    Related Experiment Videos

    Last Updated: Sep 12, 2025

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
    03:14

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

    Published on: December 6, 2024

    681
    Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
    05:47

    Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

    Published on: June 13, 2025

    578
    Asthma Detection Research Based on Voice Signal Processing and Machine Learning
    04:04

    Asthma Detection Research Based on Voice Signal Processing and Machine Learning

    Published on: July 22, 2025

    407

    Area of Science:

    • Biomedical Informatics
    • Natural Language Processing
    • Health Data Science

    Background:

    • Electronic health records (EHRs) offer rich data for research but are challenging to use due to unstructured notes, heterogeneity, and missing information.
    • Extracting structured insights from clinical narratives is crucial for advancing clinical research and decision-making.
    • Existing methods often struggle with the scale and complexity of unstructured EHR data.

    Purpose of the Study:

    • To develop a scalable and privacy-preserving natural language processing (NLP) workflow for extracting structured clinical insights from large volumes of unstructured EHR data.
    • To improve the efficiency and accuracy of clinical data extraction compared to traditional methods.
    • To create an adaptable and computationally efficient platform for diverse institutional settings.

    Main Methods:

    • A hybrid NLP approach combining regular expressions (regex) for snippet identification and locally hosted large language models (LLMs) for interpretation.
    • Secure, in-house data processing to ensure strict adherence to privacy regulations.
    • A modular, Python-based workflow designed for computational efficiency and adaptability across institutions.

    Main Results:

    • The NLP pipeline processed millions of clinical reports, significantly reducing processing time by 80% compared to full document LLM inference and 97% compared to manual annotation.
    • High accuracy was achieved in extracting numerical values, dates, and diagnoses (e.g., HELLP syndrome), with 95% agreement with expert annotations.
    • The workflow demonstrated generalizability by accurately identifying ventricular tachycardia in a public dataset.

    Conclusions:

    • The developed hybrid NLP framework substantially enhances the utility of unstructured EHR data.
    • This approach supports large-scale retrospective analyses, clinical research, and decision support systems.
    • The privacy-preserving, efficient, and adaptable workflow facilitates broader use of clinical narratives in healthcare.