Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
May 13, 2026DiseasesOpen Access

Predicting Diagnostic Success and Procedural Efficiency in Robotic Bronchoscopy Using Machine Learning

View Full Paper
Ask AI
Bookmark
Share

Authors

JGJuliana GuarizeCBClaudia BardoniCDCristina Diotti

Discussion

Loading...

Member takes

Overview

Retrospective cohort study analyzes lesion factors' impact on robotic bronchoscopy outcomes, suggesting improved prediction methods.

Key Points

  • This research aims to explore how specific lesion characteristics influence procedural duration and diagnostic yield in robotic bronchoscopy.
  • Single-center retrospective cohort study of 189 procedures (November 2024–June 2025)
  • Utilized multivariable regression and gradient boosting machine learning for predictive modeling
  • Analyzed the impact of lesion diameter, radiological appearance, and bronchial signs on outcomes.
  • Median lesion diameter was 12.3 mm with a diagnostic yield of 87.3%
  • Gradient boosting identified lesion diameter as the primary predictor of procedural time (89.2% importance, test MSE = 865.6)
  • Diagnostic classification achieved an ROC-AUC of 0.68, with lesion diameter and bronchial sign as key predictors.

Cite This Study

Guarize et al. (2026) studied this question.

synapsesocial.com/papers/6a0414f679e20c90b4444d0bhttps://doi.org/10.3390/diseases14050169
View Full Paper
Ask AI
Bookmark
Share