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: Sep 5, 2025

Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale
19:15

Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale

Published on: August 25, 2014

86.3K

A High-Fidelity Model to Predict Length-of-Stay in the Neonatal Intensive Care Unit (NICU).

Kanix Wang1, Walid Hussain2, John R Birge1

  • 1Booth School of Business, The University of Chicago, Chicago, Illinois 60637.

INFORMS Journal on Computing
|July 11, 2022
PubMed
Summary

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

From InSurE to MIST: A Quality Improvement Initiative in a Level IV NICU.

American journal of perinatology·2026
Same author

Implementation of the early-onset sepsis calculator in a tertiary care NICU.

Antimicrobial stewardship & healthcare epidemiology : ASHE·2026
Same author

Cystic Encephalomalacia in a Neonate With a Rash.

NeoReviews·2026
Same author

Signals within Complexity: Diabetes Genetic Heterogeneity and Clinical Outcomes in CKD.

Clinical journal of the American Society of Nephrology : CJASN·2026
Same author

The effect of postnatal steroids on lung ultrasound scores and extubation readiness in very low birth weight infants.

Journal of perinatology : official journal of the California Perinatal Association·2026
Same author

A Survey of Minimally Invasive Surfactant Use in the United States.

American journal of perinatology·2024

This study introduces an interpretable dynamic model for predicting patient length-of-stay (LOS) using electronic medical record (EMR) data. The model integrates clinical knowledge for improved healthcare decision-making and operational efficiency.

Area of Science:

  • Health Informatics
  • Clinical Decision Support
  • Predictive Modeling

Background:

  • Electronic Medical Record (EMR) systems generate vast amounts of health data.
  • Integrating EMR data into healthcare operations for improved decision-making remains a challenge.
  • Interpretable dynamic models are needed to predict patient length-of-stay (LOS).

Purpose of the Study:

  • To propose a framework for modeling patient LOS using established clinical knowledge.
  • To develop dynamic predictive models for remaining LOS (RLOS), discharges, and census probabilities.
  • To ensure medical interpretability alongside predictive accuracy.

Main Methods:

  • A framework integrating expert clinical knowledge to group raw EMR data into meaningful variables.
Keywords:
computational methodshealthcarehospitalsnonparametricstatistics

More Related Videos

A Neonatal Imaging Model of Gram-Negative Bacterial Sepsis
08:46

A Neonatal Imaging Model of Gram-Negative Bacterial Sepsis

Published on: August 12, 2020

6.5K
The Perinatal Asphyxiated Lamb Model: A Model for Newborn Resuscitation
09:03

The Perinatal Asphyxiated Lamb Model: A Model for Newborn Resuscitation

Published on: August 15, 2018

10.9K

Related Experiment Videos

Last Updated: Sep 5, 2025

Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale
19:15

Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale

Published on: August 25, 2014

86.3K
A Neonatal Imaging Model of Gram-Negative Bacterial Sepsis
08:46

A Neonatal Imaging Model of Gram-Negative Bacterial Sepsis

Published on: August 12, 2020

6.5K
The Perinatal Asphyxiated Lamb Model: A Model for Newborn Resuscitation
09:03

The Perinatal Asphyxiated Lamb Model: A Model for Newborn Resuscitation

Published on: August 15, 2018

10.9K
  • Development of dynamic predictive models to forecast patient trajectories.
  • Utilizing patient health trajectories to predict RLOS, future discharges, and census probabilities.

    • Main Results:

    • The dynamic model significantly improves predictive power compared to previous literature.
    • The model demonstrates enhanced performance when evaluated on large-scale EMR data.
    • The developed model maintains medical interpretability.

    Conclusions:

    • The proposed framework effectively models patient LOS by integrating clinical knowledge.
    • Dynamic predictive models using EMR data can significantly enhance healthcare operations.
    • This approach offers a medically interpretable solution for predicting patient LOS and improving care quality.