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 Videos

Human-AI co-design for clinical prediction models.

Jean Feng1, Avni Kothari2, Patrick Vossler2

  • 1University of California, San Francisco, CA, USA. jean.feng@ucsf.edu.

NPJ Digital Medicine
|June 6, 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

Predicting pain location from resting-state brain fMRI.

bioRxiv : the preprint server for biology·2026
Same author

Integrative simulation and spectroscopy illuminates L-asparaginase stability on nanocomposite surface for biosensing.

International journal of biological macromolecules·2026
Same author

Circulating metabolome as key biomarkers for ventilator-associated pneumonia: Case-Control study in a tertiary care hospital of North India.

International journal of critical illness and injury science·2026
Same author

Reducing Waste: Instrument Recycling in the Emergency Department.

The western journal of emergency medicine·2026
Same author

AI-Guided Surgical Blood Readiness: Overcoming Real-World Challenges in Prospective Validation for Safer, More Efficient Blood Preparation.

NEJM AI·2026
Same author

Emerging applications of traditional and generative artificial intelligence in liver transplantation.

Liver transplantation : official publication of the American Association for the Study of Liver Diseases and the International Liver Transplantation Society·2026
Same journal

Translation of frozen sections into FFPE images for skin cancer resection margins using generative AI.

NPJ digital medicine·2026
Same journal

FedFound: a federated foundation model for lifespan brain morphological connectome analysis.

NPJ digital medicine·2026
Same journal

A multimodal instruction dataset and benchmark for ultrasound understanding.

NPJ digital medicine·2026
Same journal

Evaluating the shift in psychiatric care: Associations between remote consultation use and clinical outcomes in a large longitudinal cohort.

NPJ digital medicine·2026
Same journal

Identifying suicide-related language in smartphone keyboard entries among high-risk adolescents.

NPJ digital medicine·2026
Same journal

Impact of a virtual nurse-led Early paLlIative Care IntervenTion (ELICIT) randomized controlled trial.

NPJ digital medicine·2026
See all related articles

We developed HACHI, an AI framework that speeds up the creation of interpretable clinical prediction models (CPMs) from patient notes. This human-in-the-loop system enhances collaboration and improves model performance in real-world healthcare settings.

Area of Science:

  • Artificial Intelligence in Medicine
  • Clinical Informatics
  • Health Data Science

Background:

  • Developing clinical prediction models (CPMs) demands extensive collaboration.
  • Unstructured clinical notes present a vast, complex data source for modeling.
  • Existing methods struggle with the scale and interpretability of CPMs derived from notes.

Purpose of the Study:

  • Introduce HACHI, a human-in-the-loop framework for developing interpretable CPMs from clinical notes.
  • Accelerate the creation of transparent and steerable CPMs through AI-expert collaboration.
  • Improve the generalizability and clinical relevance of predictive models.

Main Methods:

  • HACHI framework: iterative process alternating AI agent exploration and expert feedback.

Related Experiment Videos

  • AI agent utilizes statistical tools and embedded knowledge to identify predictive concepts.
  • Domain experts guide the AI, refining concepts and ensuring model transparency.
  • CPMs are defined as linear models based on yes-no questions derived from clinical notes.

    • Main Results:

    • HACHI outperforms existing approaches in real-world prediction tasks (acute kidney injury, traumatic brain injury).
    • The framework discovers clinically relevant concepts and enhances model generalizability across sites and time.
    • Demonstrates improved interpretability and transparency in the developed CPMs.

    Conclusions:

    • HACHI effectively accelerates the development of interpretable clinical prediction models from unstructured data.
    • Human-in-the-loop AI frameworks are crucial for optimizing collaboration and model performance.
    • Emphasizes the importance of human oversight in guiding AI for clinical applications, addressing bias and leakage.