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

SmartAlert - Implementing Machine Learning-Driven Clinical Decision Support for Inpatient Laboratory Utilization

April S Liang1, Fatemeh Amrollahi2, Yixing Jiang2

  • 1Division of Hospital Medicine, Department of Medicine, Stanford University School of Medicine, Palo Alto, CA, USA.

NEJM AI
|July 15, 2026
PubMed

Related Concept Videos

Automated Microbial Diagnostics01:24

Automated Microbial Diagnostics

Automated diagnostic analyzers have transformed clinical microbiology by providing rapid and reliable methods for pathogen identification and antibiotic susceptibility testing. Among these systems, the Vitek 2 is widely used because it automates the traditionally labor-intensive processes of microbial identification (ID) and antibiotic susceptibility testing (AST), delivering standardized and timely results that are essential for effective patient care.Microbial Identification with ID CardsThe...

You might also read

Related Articles

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

Sort by
Same author

Evaluation of Large Language Models for Structured Data Extraction From Interstitial Lung Disease Clinical Notes: Comparative Study.

Journal of medical Internet research·2026
Same author

Employee preferences in health plan design: results from a national survey.

Health affairs scholar·2026
Same author

Patient perspectives on clinicians' use of ambient AI scribes.

JAMIA open·2026
Same author

Variation in Commercial Insurer Prior Authorization Rules.

Annals of internal medicine·2026
Same author

Performance of a large language model on the reasoning tasks of a physician.

Science (New York, N.Y.)·2026
Same author

Closing the Gap: Optimizing Hospital Discharge Planning for Improved Outcomes.

Health services research·2026
Summary

SmartAlert, a machine learning clinical decision support system, significantly reduced repetitive complete blood count (CBC) testing by 15% in hospitalized patients. This innovation offers precision guidance for laboratory utilization, lowering healthcare costs without compromising patient safety.

Area of Science:

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

Background:

  • Repetitive laboratory testing often yields minimal clinical value, increasing healthcare costs and patient burden.
  • Existing interventions like education and general restrictions have shown limited success in optimizing test ordering.
  • Electronic alerts can sometimes hinder appropriate clinical care.

Purpose of the Study:

  • To introduce and evaluate SmartAlert, a machine learning-driven clinical decision support (CDS) system designed to predict stable laboratory results and reduce unnecessary repeat testing.
  • To assess the impact of SmartAlert on complete blood count (CBC) utilization in an inpatient setting.
  • To identify implementation challenges and lessons learned from deploying an AI-based CDS tool in a real-world clinical environment.

Related Experiment Videos

Main Methods:

  • A randomized controlled pilot study was conducted across eight acute care units in two hospitals, involving 9270 admissions.
  • SmartAlert, integrated into the electronic health record, was deployed to predict stable CBC results and guide testing frequency.
  • Data was collected between August 15, 2024, and March 15, 2025, focusing on CBC ordering patterns and safety outcomes.

Main Results:

  • A significant decrease in CBC results within 52 hours of SmartAlert display was observed (1.54 vs. 1.82; P<0.01).
  • This represents a 15% relative reduction in repetitive CBC testing.
  • No adverse effects on secondary safety outcomes were detected during the pilot.

Conclusions:

  • Machine learning-driven CDS systems, like SmartAlert, can effectively reduce unnecessary inpatient laboratory testing.
  • A robust implementation strategy, including stakeholder engagement and governance, is crucial for deploying complex AI models in clinical settings.
  • SmartAlert demonstrates the potential for precision guidance in laboratory testing to improve efficiency and reduce costs safely.