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

Retrieval01:12

Retrieval

Retrieval is the process of getting information out of memory storage and back into conscious awareness. This ability is essential for daily tasks like brushing hair and teeth, driving to work, and performing job duties. Retrieval occurs in three ways: recall, recognition, and relearning.
Recall involves accessing information without cues, such as during an essay test, where individuals must retrieve facts and concepts from memory unaided. Another example is remembering the name of a colleague...
Multiple Comparison Tests01:13

Multiple Comparison Tests

Multiple comparison test, abbreviated as MCT, is a post hoc analysis generally performed after comparing multiple samples with one or more tests. An MCT will help identify a significantly different sample among multiple samples or a factor among multiple factors.
It would be easy to compare two samples using a significance alpha level of 0.05. In other words, there is only one sample pair to be compared. However, it would be difficult to identify a significantly different sample if the number...
Pharmacokinetic Models: Comparison and Selection Criterion01:26

Pharmacokinetic Models: Comparison and Selection Criterion

Physiological and compartmental models are valuable tools used in studying biological systems. These models rely on differential equations to maintain mass balance within the system, ensuring an accurate representation of the dynamic processes at play.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
Typical Model Studies01:30

Typical Model Studies

Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.
Multiple Regression01:25

Multiple Regression

Multiple regression assesses a linear relationship between one response or dependent variable and two or more independent variables. It has many practical applications.
Farmers can use multiple regression to determine the crop yield based on more than one factor, such as water availability, fertilizer, soil properties, etc. Here, the crop yield is the response or dependent variable as it depends on the other independent variables. The analysis requires the construction of a scatter plot...
Causes of Similarity-Dissimilarity Effect01:26

Causes of Similarity-Dissimilarity Effect

The similarity-dissimilarity effect, a fundamental concept in social psychology, explains how interpersonal similarities and differences influence attraction and social interactions. This effect is supported by three key psychological perspectives: balance theory, social comparison theory, and consensual validation.Balance Theory and Cognitive ConsistencyBalance theory, developed by Fritz Heider, posits that individuals seek cognitive consistency in their relationships. When two people share...

You might also read

Related Articles

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

Sort by
Same journal

AI-Assisted Detection of Supraspinatus Tendon Pathologies Using a Hierarchical Deep Learning Model to Improve Clinical Applicability: Development and Evaluation Study.

JMIR medical informatics·2026
Same journal

"Do It by Myself" or Autonomy, Participation, and Assistive Devices and Technology Needs of Children and Youth With Disabilities: Text Mining Analysis of a National Survey in France.

JMIR medical informatics·2026
Same journal

The Orphanet Nomenclature and Classification of Rare Diseases for Improved Patient Recognition and Data Interoperability: Qualitative and Quantitative Analysis.

JMIR medical informatics·2026
Same journal

Feasibility of Tailoring Artificial Intelligence-Assisted Ambient Scribes for Intensive Care Unit Rounds: Algorithm Development and Validation.

JMIR medical informatics·2026
Same journal

Determinants of Acute Kidney Injury After Endoscopic Retrograde Cholangiopancreatography in Patients With Liver Cirrhosis: Retrospective Observational Study.

JMIR medical informatics·2026
Same journal

Multimodule Human-Artificial Intelligence Collaboration Pipeline for Large Language Model-Assisted Thematic Analysis Across Digital Health Interview Studies: Comparative Evaluation Study.

JMIR medical informatics·2026

Related Experiment Video

Updated: May 9, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Clinical Context Variables Collectively Rival Model Choice in Embedding-Based Retrieval: Multi-Corpus Benchmark

Yngve Mikkelsen1

  • 1Saïd Business School, University of Oxford, Oxford, England, United Kingdom.

JMIR Medical Informatics
|May 7, 2026
PubMed
Summary
This summary is machine-generated.

Clinical context variables significantly impact retrieval performance in retrieval-augmented generation (RAG) systems, comparable to embedding model choice. Local validation is crucial for clinical RAG deployment due to performance variations across corpora.

Keywords:
BM25benchmarkclinical documentationclinical informaticsdense retrievalembedding modelsretrieval-augmented generation

More Related Videos

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments
08:12

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

Published on: March 1, 2022

Related Experiment Videos

Last Updated: May 9, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments
08:12

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

Published on: March 1, 2022

Area of Science:

  • Medical Informatics
  • Natural Language Processing
  • Artificial Intelligence in Healthcare

Background:

  • Retrieval-augmented generation (RAG) systems enhance clinical decision-making by integrating evidence from large language models.
  • Effective retrieval is critical for RAG, as downstream generation cannot compensate for missed documents.
  • Current embedding model selection for clinical RAG often relies on general-domain benchmarks, which may not generalize to diverse clinical data.

Purpose of the Study:

  • To evaluate the impact of clinical context variables (corpus type, query format) on retrieval performance in RAG.
  • To compare the influence of context variables against embedding model choice for clinical retrieval tasks.
  • To determine the generalizability of general-domain embedding model rankings to clinical retrieval.

Main Methods:

  • Benchmarked 13 retrieval configurations, including 10 embedding models and a BM25 baseline, across three clinical corpora (MTSamples, PMC-Patients, synthetic notes).
  • Evaluated 12 embedding configurations across 3 corpora, 2 query formats (keyword vs. natural language), and 4 chunking strategies (294 conditions total).
  • Utilized factorial ANOVA with η² effect sizes to quantify relative contributions of factors and interactions on retrieval metrics like MRR@10.

Main Results:

  • Embedding model choice accounted for 40.8% of variance in MRR@10, while corpus type (24.6%) and query format (19.2%) also significantly contributed.
  • Combined context variables (corpus, query format, interactions) explained 49.0% of variance, nearly matching model-related effects (47.6%).
  • Model rankings shifted across corpora, indicating poor portability; domain-specific models underperformed general-purpose embeddings.

Conclusions:

  • Clinical context variables significantly influence retrieval performance, rivaling embedding model choice.
  • Embedding model rankings are not universally portable across different clinical documentation types.
  • Mandatory local validation of RAG systems is essential, rather than relying on general-domain benchmarks.