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

Optimizing discharge after major surgery using an artificial intelligence-based decision support tool (DESIRE): An

Davy van de Sande1, Michel E van Genderen2, Cornelis Verhoef3

  • 1Department of Adult Intensive Care, Erasmus University Medical Center, Rotterdam, The Netherlands. Electronic address: https://twitter.com/davy_sande.

Surgery
|May 7, 2022
PubMed
Summary

Related Concept Videos

Appendicitis-II: Diagnostic Studies and Management01:29

Appendicitis-II: Diagnostic Studies and Management

153
Diagnosing and managing appendicitis requires a structured and comprehensive approach that spans from initial assessment to postoperative care. Here is an overview of the process:
Diagnosing Appendicitis
It requires a multifaceted approach, starting with a detailed physical examination to pinpoint the location and nature of the pain and identify any associated symptoms. Laboratory tests play a crucial role. A complete Blood Count (CBC) typically reveals leukocytosis (an increased number of...
153
Peripheral Artery Disease V: Postoperative Nursing Management01:23

Peripheral Artery Disease V: Postoperative Nursing Management

29
During the postoperative period, it is crucial to focus on maintaining circulation, identifying and managing potential complications, and planning for discharge.Nursing AssessmentVital signs monitoring: Regularly monitor vital signs, including blood pressure, heart rate, respiratory rate, and temperature, to detect early signs of complications such as bleeding and infection.Circulation assessment: Monitor pulses, perform Doppler assessments, and check capillary refill, color, temperature, and...
29

You might also read

Related Articles

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

Sort by
Same author

Predicting response to neoadjuvant therapy using artificial intelligence on digitized histopathology slides: a systematic review.

NPJ digital medicine·2026
Same author

Steatosis shapes prognosis-defining liver metastasis heterogeneity in CRC.

Nature·2026
Same author

Assessing Intraoperative Tumor-to-Background Ratios Across Different Subsites of the Oral Cavity Using an Integrin-Specific Fluorescent Tracer.

Cancers·2026
Same author

Patient-led, home-based follow-up for colorectal cancer: the DISTANCE multicentre stepped-wedge cluster-randomised trial.

The British journal of surgery·2026
Same author

The Clinical Relevance of Indeterminate Pulmonary Nodules in Patients Amenable to Local Treatment of Colorectal Liver Metastases.

Annals of surgery open : perspectives of surgical history, education, and clinical approaches·2026
Same author

Prehabilitation Prior to Colorectal Cancer Surgery: Impact and Implementation.

Journal of surgical oncology·2026
Same journal

Familiar but unprepared: Artificial intelligence training needs in graduate medical education.

Surgery·2026
Same journal

One-year health care expenditures and patient out-of-pocket spending after open versus minimally invasive hepatopancreatobiliary surgery.

Surgery·2026
Same journal

Shock index, hypotension, and blood product transfusion as predictors of post-traumatic stress disorder in firearm-related trauma.

Surgery·2026
Same journal

Outcomes following endovascular aortic aneurysm repair in nonagenarian patients.

Surgery·2026
Same journal

Fistulotomy with primary sphincteroplasty for complex anal fistulas: Should we be concerned about incontinence?

Surgery·2026
Same journal

No need for mesh in the repair of hiatal hernias: Autologous tissue hiatoplasty techniques for the repair of the complex diaphragmatic defect.

Surgery·2026
See all related articles
This summary is machine-generated.

A machine learning model can predict safe hospital discharge for gastrointestinal and oncology surgery patients across different hospitals. This artificial intelligence tool aids in reducing hospital stays and improving bed capacity management.

Area of Science:

  • Surgical outcomes research
  • Artificial intelligence in healthcare
  • Clinical decision support systems

Background:

  • The DESIRE study previously developed a machine learning (ML) model to predict safe hospital discharge after the second postoperative day in 1,677 gastrointestinal and oncology surgery patients.
  • The model demonstrated strong performance (AUC 0.88) in an academic setting, but its generalizability to other hospitals and populations was unknown.

Purpose of the Study:

  • To externally validate the generalizability of the previously developed ML concept for predicting safe hospital discharge.
  • To assess the ML model's performance in nonacademic hospital settings and diverse surgical populations.

Main Methods:

  • External validation of the ML concept in gastrointestinal and oncology surgery patients across 3 nonacademic hospitals in The Netherlands (January 2017 - June 2021).

Related Experiment Videos

  • Prediction of hospital interventions (unplanned reoperations, radiological interventions, IV antibiotics) after the second postoperative day.
  • Local training and evaluation of four random forest models using AUC, sensitivity, specificity, PPV, and NPV.

    • Main Results:

    • Models were trained on 1,693 episodes; 29.9% required hospital intervention.
    • The ML models demonstrated strong performance with minimal variation (AUC change of 4%) across settings.
    • The best model achieved an AUC of 0.83, sensitivity of 77.9%, specificity of 79.2%, PPV of 61.6%, and NPV of 89.3%.

    Conclusions:

    • The study confirms that the ML concept can predict safe discharge in varied surgical populations and hospital settings (academic vs. nonacademic) when models are trained on local data.
    • Integration into clinical workflows can expedite surgical discharge and help hospitals manage capacity by reducing unnecessary bed-days.