Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 20, 2025Journal of Medical Internet ResearchOpen Access

Performance of Machine Learning in Diagnosing KRAS (Kirsten Rat Sarcoma) Mutations in Colorectal Cancer: Systematic Review and Meta-Analysis

View Full Paper
Ask AI
Bookmark
Share

Authors

KCKaixin ChenYQYin QuShanghai University of Traditional Chinese MedicineYHYe Ri HanDuksung Women's University

Discussion

Loading...

Member takes

Overview

Systematic review finds machine learning models show high accuracy in diagnosing KRAS mutations in colorectal cancer, suggesting advances for intelligent diagnostic tools.

Key Points

  • ML models demonstrate high accuracy in diagnosing KRAS mutations in colorectal cancer with a c-index of 0.96 for deep learning models based on pathological images.
  • Examining 43 studies with 10,888 patients, models based on radiomic features from CT and MRI show sensitivities between 0.73-0.86.
  • The use of deep learning in MRI and pathological images yields strong diagnostic performances, with high specificity rates of 0.87 and 0.83, respectively.
  • Further research is needed to enhance model architectures and increase patient sample sizes for better KRAS mutation diagnostics in clinical settings.

Cite This Study

Chen et al. (2025) studied this question.

synapsesocial.com/papers/689a02c9e6551bb0af8ccf95https://doi.org/10.2196/73528
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Machine learning models using 18F-FDG PET/CT radiomics for RAS mutation prediction and prognostic stratification in colorectal cancer2026
  2. 2Machine learning and deep learning models for predicting colorectal cancer metastases: A comprehensive review2026 · 1 citations
  3. 3Research progress on predicting KRAS gene mutations in colorectal cancer by combining radiomics and multimodal medical imaging2025
  4. 4Prediction of KRAS gene mutations in colorectal cancer using a CT-based radiomic model2025 · 6 citations
  5. 5Abstract 5335: Integrated machine learning and large language models reveal molecular determinants of survival and treatment response in KRAS-mutant lung cancer.2026