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: May 21, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Quantum machine learning for predicting anastomotic leak: a clinical study.

Vojtěch Novák1,2, Ivan Zelinka3,4, Lenka Přibylová5

  • 1Department of Computer Science, VSB-Technical University of Ostrava, Ostrava, Czech Republic. vojtech.novak.st1@vsb.cz.

Scientific Reports
|May 19, 2026
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

A Dataset of Abdominal CT with Artery and Vein Segmentations for Colorectal Cancer Surgical Planning.

Scientific data·2026
Same author

Astrocyte-induced dynamics of a pyramidal cell with a dendrite-connected astrocyte.

Journal of computational neuroscience·2026
Same author

Radicality of mediastinal lymphadenectomy in anatomic lung resection for lung cancer: a comparative analysis of uniportal video-assisted thoracoscopic and robotic-assisted thoracoscopic approaches.

Surgical endoscopy·2026
Same author

Therapeutic role of venous sinus stenting in pediatric IIH: evidence review for clinical practice.

Acta neurochirurgica·2025
Same author

Pain and recovery after robotic vs. uniportal lobectomy for lung cancer: a comparative analysis.

Surgical endoscopy·2025
Same author

Rethinking lumbar puncture safety: pathophysiology, diagnostic uncertainty, and research gaps in herniation risk.

Acta neurologica Belgica·2025
This summary is machine-generated.

Quantum Neural Networks (QNNs) show promise in predicting anastomotic leaks after colorectal surgery, offering higher specificity than classical models. Further validation is needed for clinical screening applications.

Area of Science:

  • Computational Science
  • Medical Informatics
  • Quantum Computing

Background:

  • Anastomotic leak is a critical complication after colorectal surgery.
  • Accurate prediction of anastomotic leaks is essential for patient outcomes.

Purpose of the Study:

  • To benchmark Quantum Neural Networks (QNNs) against classical machine learning models for anastomotic leak prediction.
  • To evaluate the performance of QNNs under realistic noise conditions.

Main Methods:

  • A 200-patient clinical dataset was used.
  • Simulated QNNs with ZZFeatureMap encoding and EfficientSU2/RealAmplitudes ansatze were employed.
  • Performance was compared against logistic regression, multi-layer perceptrons, and boosting algorithms.

More Related Videos

Creation of Colonic Anastomosis in Mice
07:22

Creation of Colonic Anastomosis in Mice

Published on: January 17, 2019

Related Experiment Videos

Last Updated: May 21, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Creation of Colonic Anastomosis in Mice
07:22

Creation of Colonic Anastomosis in Mice

Published on: January 17, 2019

Main Results:

  • Specific QNN configurations demonstrated superior specificity and Negative Predictive Value compared to classical models at a clinically relevant sensitivity.
  • EfficientSU2-BFGS achieved the highest Area Under the Curve (AUC).
  • RealAmplitudes with CMA-ES maximized Average Precision, though classical models offered better probability calibration.

Conclusions:

  • QNNs exhibit robust discriminative performance for clinical screening of anastomotic leaks.
  • QNNs effectively minimize false positives, a crucial factor in clinical decision-making.
  • Larger, independent cohorts are required for further QNN validation in this domain.