Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: Journal of Medical Internet Research

Date Submitted: Mar 6, 2025
Open Peer Review Period: Mar 6, 2025 - May 1, 2025
Date Accepted: May 15, 2025
(closed for review but you can still tweet)

The final, peer-reviewed published version of this preprint can be found here:

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

Chen K, Qu Y, Han Y, Li Y, Gao H, Zheng D

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

J Med Internet Res 2025;27:e73528

DOI: 10.2196/73528

PMID: 40680189

PMCID: 12294651

Performance of Machine Learning in Diagnosing KRAS Mutations in Colorectal Cancer: A Systematic Review and Meta-Analysis

  • Kaixin Chen; 
  • Yin Qu; 
  • Ye Han; 
  • Yan Li; 
  • Huiyan Gao; 
  • De Zheng

ABSTRACT

Background:

With the widespread application of machine learning (ML) in the diagnosis and treatment of colorectal cancer (CRC), some studies have investigated the utilization of ML techniques for the detection of KRAS mutation. Nevertheless, there is scarce evidence from evidence-based medicine to substantiate its efficacy.

Objective:

Our study was carried out to systematically review the performance of ML models developed using different modeling approaches, in detecting KRAS mutations in CRC. Our findings aim to offer evidence-based foundations for the development and enhancement of future intelligent diagnostic tools.

Methods:

PubMed, Cochrane Library, Embase, and Web of Science were systematically retrieved, with the search cutoff date set to December 22, 2024. The risk of bias in the encompassed models was evaluated via the Prediction Model Risk of Bias Assessment Tool (PROBAST). In our data analysis, subgroup analyses were undertaken based on the type of modeling variables incorporated into the models, including clinical characteristics, imaging features, and pathological features.

Results:

43 studies involving 10,888 patients, were included, of which 12 studies (comprising 3,013 patients) focused specifically on KRAS mutations in rectal cancer (RC). The modeling variables were derived from clinical characteristics (n=6), CT (n=15), MRI (n=15), PET/CT (n=4), and pathological histology (n=7). In the validation cohorts, meta-analysis results demonstrated that the ML models developed based on clinical characteristics, CT, MRI, PET/CT, and pathological histology exhibited c-index values of 0.65 (95% CI: 0.60–0.70), 0.87 (95% CI: 0.84–0.90), 0.77 (95% CI: 0.71–0.83), 0.84 (95% CI: 0.77–0.90), and 0.94 (95% CI: 0.92–0.96). Additionally, deep learning (DL) techniques were found to demonstrate superior predictive performance. Particularly, DL models based on pathological images and MRI achieved pooled c-index values of 0.96 (95% CI: 0.94–0.98) and 0.93 (95% CI: 0.90–0.96).

Conclusions:

ML is highly accurate in detecting KRAS mutations in CRC, and DL models based on MRI and pathological images exhibit particularly strong predictive performance. Future research should focus on increasing sample sizes, improving model architectures, and developing more advanced DL models to facilitate the creation of highly efficient intelligent diagnostic tools for KRAS mutation detection in CRC. Clinical Trial: N/A


 Citation

Please cite as:

Chen K, Qu Y, Han Y, Li Y, Gao H, Zheng D

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

J Med Internet Res 2025;27:e73528

DOI: 10.2196/73528

PMID: 40680189

PMCID: 12294651

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.