Deep learning neural network prediction of postoperative complications in patients undergoing laparoscopic right hemicolectomy with or without CME and CVL for colon cancer: insights from SICE (Società Italiana di Chirurgia Endoscopica) CoDIG data - Summary - MDSpire

Deep learning neural network prediction of postoperative complications in patients undergoing laparoscopic right hemicolectomy with or without CME and CVL for colon cancer: insights from SICE (Società Italiana di Chirurgia Endoscopica) CoDIG data

  • By

  • G. Anania

  • P. Mascagni

  • M. Chiozza

  • G. Resta

  • A. Campagnaro

  • S. Pedon

  • G. Silecchia

  • D. Cuccurullo

  • C. Bergamini

  • G. Sica

  • V. Nicola

  • M. Alberti

  • M. Ortenzi

  • R. Reddavid

  • D. Azzolina

  • June 11, 2025

  • 0 min

Share

Objective:

To develop a machine learning-based tool for predicting postoperative complications specifically in patients undergoing laparoscopic right hemicolectomy with CME and CVL.

Key Findings:
  • Machine learning models can improve predictive accuracy for postoperative complications.
  • CME and CVL surgeries are complex and may increase the risk of complications.
  • Existing predictive tools have limitations in performance, such as low accuracy and poor integration with clinical workflows.
Interpretation:

The application of machine learning in predicting postoperative complications could enhance patient care, optimize resource allocation, and improve clinical decision-making in surgical settings.

Limitations:
  • Current predictive tools are hindered by performance issues, such as low accuracy and time-consuming manual data entry requirements.
  • The exploration of machine learning for postoperative prediction in laparoscopic surgery is still limited, with few studies validating its effectiveness.
Conclusion:

The study highlights the potential of machine learning to provide personalized risk assessments for patients undergoing complex surgical procedures, ultimately aiming to improve outcomes and resource management in surgical care.

Original Source(s)

Deep learning neural network prediction of postoperative complications in patients undergoing laparoscopic right hemicolectomy with or without CME and CVL for colon cancer: insights from SICE (Società Italiana di Chirurgia Endoscopica) CoDIG data

  • by G. Anania, P. Mascagni, M. Chiozza, G. Resta, A. Campagnaro, S. Pedon, G. Silecchia, D. Cuccurullo, C. Bergamini, G. Sica, V. Nicola, M. Alberti, M. Ortenzi, R. Reddavid, D. Azzolina

  • June 11, 2025

Related Content

Enhanced exposure and visualization in splenic flexure mobilization with comparable perioperative outcomes: experience with Artisential® during laparoscopic low anterior resection

Double-tube end ileostomy: an alternative to classical defunctioning stoma in rectal surgery

Color Vision Tied to Bladder Survival

Patients with impaired color perception may be less likely to recognize blood in urine, potentially delaying diagnosis of cancers that rely on visible bleeding as an early warning sign.