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 Experiment Video

Updated: Jul 3, 2026

Bringing the Clinic Home: An At-Home Multi-Modal Data Collection Ecosystem to Support Adaptive Deep Brain Stimulation
06:32

Bringing the Clinic Home: An At-Home Multi-Modal Data Collection Ecosystem to Support Adaptive Deep Brain Stimulation

Published on: July 14, 2023

Text Knows What, Tables Know When: Clinical Timeline Reconstruction via Retrieval-Augmented Multimodal Alignment.

Sayantan Kumar, Shahriar Noroozizadeh, Juyong Kim

    Arxiv
    |July 2, 2026
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    You might also read

    Related Articles

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

    Sort by
    Same author

    Temporally Phenotyping GLP-1RA Case Reports with Large Language Models: A Textual Time Series Corpus and Risk Modeling.

    ArXiv·2026
    Same author

    Hierarchical Barycentric Multimodal Representation Learning for Medical Image Analysis.

    medRxiv : the preprint server for health sciences·2026
    Same author

    Temporally Phenotyping GLP-1RA Case Reports with Large Language Models: A Textual Time Series Corpus and Risk Modeling.

    medRxiv : the preprint server for health sciences·2026
    Same author

    MIMIC-IV-Ext-22MCTS: A 22 Million-Event Temporal Clinical Time-Series Dataset for Risk Prediction.

    Research square·2025
    Same author

    Forecasting Clinical Risk from Textual Time Series: Structuring Narratives for Temporal AI in Healthcare.

    medRxiv : the preprint server for health sciences·2025
    Same author

    The Impact of Medication Non-adherence on Adverse Outcomes: Evidence from Schizophrenia Patients via Survival Analysis.

    Proceedings of machine learning research·2025
    Same journal

    MetaboNet-Bench: A Multi-modal Benchmark for Glucose Forecasting in Type 1 Diabetes.

    ArXiv·2026
    Same journal

    A Positron Range Correction with Texture Preservation Framework in PET Imaging.

    ArXiv·2026
    Same journal

    Automated optimization of force field parameters against ensemble-averaged measurements with Bayesian Inference of Conformational Populations.

    ArXiv·2026
    Same journal

    Droplet Fusion as a Relaxation Process: Comparison with Shape Recovery of Newtonian and Viscoelastic Droplets.

    ArXiv·2026
    Same journal

    Ridge-filter crosstalk in conformal proton FLASH planning: dependence on beamlet pitch and iterative mitigation.

    ArXiv·2026
    Same journal

    Electrochemical DNA Hairpin Sensors for Differentiating Small Molecule Intercalation from Minor Groove Binding.

    ArXiv·2026
    See all related articles

    This study introduces a multimodal framework to precisely reconstruct patient timelines from clinical notes and electronic health records. The method enhances temporal accuracy for better patient trajectory modeling and risk forecasting.

    Area of Science:

    • Biomedical Informatics
    • Clinical Data Science
    • Artificial Intelligence in Healthcare

    Background:

    • Precise clinical timelines are crucial for patient trajectory modeling and risk forecasting, especially in complex conditions like sepsis.
    • Unstructured clinical narratives offer rich context but lack temporal precision, while structured electronic health record (EHR) data has precise timestamps but incomplete event capture.

    Purpose of the Study:

    • To develop and evaluate a retrieval-augmented multimodal alignment framework to improve the temporal precision of clinical timelines extracted from text.
    • To bridge the gap between the semantic richness of narratives and the temporal accuracy of structured EHR data.

    Main Methods:

    • A graph-based, multistep process involving extraction of anchor events from narratives to form a temporal scaffold.

    More Related Videos

    A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery
    09:41

    A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

    Published on: May 20, 2016

    Midface Hypoplasia and Cranial Base Morphology in Syndromic Craniosynostosis: A Comparative Analysis Study Using a Predictive Regression Model
    08:03

    Midface Hypoplasia and Cranial Base Morphology in Syndromic Craniosynostosis: A Comparative Analysis Study Using a Predictive Regression Model

    Published on: November 4, 2025

    Related Experiment Videos

    Last Updated: Jul 3, 2026

    Bringing the Clinic Home: An At-Home Multi-Modal Data Collection Ecosystem to Support Adaptive Deep Brain Stimulation
    06:32

    Bringing the Clinic Home: An At-Home Multi-Modal Data Collection Ecosystem to Support Adaptive Deep Brain Stimulation

    Published on: July 14, 2023

    A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery
    09:41

    A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

    Published on: May 20, 2016

    Midface Hypoplasia and Cranial Base Morphology in Syndromic Craniosynostosis: A Comparative Analysis Study Using a Predictive Regression Model
    08:03

    Midface Hypoplasia and Cranial Base Morphology in Syndromic Craniosynostosis: A Comparative Analysis Study Using a Predictive Regression Model

    Published on: November 4, 2025

  • Placement of non-central events relative to the scaffold and calibration using retrieved structured EHR data as external temporal evidence.
  • Evaluation using instruction-tuned large language models on the i2m4 benchmark (MIMIC-III and MIMIC-IV).

    • Main Results:

    • The multimodal pipeline consistently improved absolute timestamp accuracy (AULTC) and temporal concordance compared to text-only reconstruction across multiple models.
    • Event match rates were not compromised by the multimodal approach.
    • Analysis revealed 34.8% of text-derived events were absent from tabular records, highlighting the value of multimodal alignment.

    Conclusions:

    • Aligning unstructured narratives with structured EHR data produces more temporally faithful and clinically informative patient trajectory reconstructions than using either source alone.
    • The developed framework enhances the temporal precision of clinical timelines, benefiting patient modeling and risk prediction.
    • Multimodal data integration is essential for comprehensive clinical timeline reconstruction.