EUVIMEDEUVIMED entdecken
Crossref

A novel colorectal cancer screening framework with feature interpretability to identify high‐risk populations for colonoscopy

Mingshan Li, Yangming Gong, Yi Pang, Mengyin Wu, Kai Gu, Yuanyuan Wang, Yi Guo iD

Journal of Gastroenterology and Hepatology · 2024

DOI: 10.1111/jgh.16600 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Gastroenterology and Hepatology, 2024. Verfasst von Mingshan Li und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronic Engineering, Fudan University, Shanghai, China. Hauptthemen laut MEDLINE: Colonoscopy, Colorectal Neoplasms, Early Detection of Cancer. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 27 Literaturangaben. Gefördert von: Science and Technology Commission of Shanghai Municipality, Yangfan Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background and Aim Risk assessment is of paramount importance for the detection and treatment of colorectal cancer. We developed and validated a feature interpretability screening framework to identify high‐risk populations and recommend colonoscopy for them.

Methods

We utilized a training cohort consisting of 1 252 605 participants who underwent colonoscopies in Shanghai from 2013 to 2015 to develop the screening framework. We incorporated Shapley additive explanation values into feature selection to provide interpretability for the framework. Two sampling methods were separately employed to mitigate potential model bias caused by class imbalance. Furthermore, we employed various machine learning algorithms to construct risk assessment models and compared their performance. We tested the screening models on an external validation cohort of 359 462 samples and conducted comprehensive evaluation and statistical analysis of the validation results.

Results

The external validation results demonstrated that the models in the proposed framework achieved sensitivity over 0.734, specificity over 0.790, and area under the receiver operating characteristic curve ranging from 0.808 to 0.859. In the predictions of the best‐performing model, the prevalence rates of colorectal cancer were 0.059% and 1.056% in the low‐ and high‐risk groups, respectively. If colonoscopies were performed only on the high‐risk group predicted by the model, only 14.36% of total colonoscopies would be needed to detect 74.86% of colorectal cancer cases.

Conclusions

We developed and validated a novel framework to identify populations at high risk for colorectal cancer. Those classified as high risk should undergo colonoscopy for further diagnosis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ColonoscopyColorectal NeoplasmsEarly Detection of CancerHumansRisk AssessmentMiddle AgedMaleFemaleAgedMachine LearningCohort StudiesMass ScreeningSensitivity and SpecificityChinaAlgorithmsROC Curve

Stichwörter der Autor:innen

Class imbalanceColorectal cancerFeature interpretabilityMachine learning

Autor:innen und Institutionen

  • Department of Electronic Engineering, Fudan University, Shanghai, China.
  • Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention (MICCAI) of Shanghai, Shanghai, China.
  • Divison of Chronic Non-Communicable Diseases and Injury, Shanghai Municipal Center for Disease Control and Prevention, Shanghai, China.

ORCID-Profile: Yi Guo

Förderung

  • Science and Technology Commission of Shanghai Municipality
  • Yangfan Project

Zitieren

APA

Li, M., Gong, Y., Pang, Y., Wu, M., Gu, K., Wang, Y., & Guo, Y. (2024). A novel colorectal cancer screening framework with feature interpretability to identify high‐risk populations for colonoscopy. Journal of Gastroenterology and Hepatology. https://doi.org/10.1111/jgh.16600

Vancouver

Li M, Gong Y, Pang Y, Wu M, Gu K, Wang Y, et al. A novel colorectal cancer screening framework with feature interpretability to identify high‐risk populations for colonoscopy. Journal of Gastroenterology and Hepatology. 2024. doi:10.1111/jgh.16600

BibTeX
@article{Li2024,
  author = {Li, Mingshan and Gong, Yangming and Pang, Yi and Wu, Mengyin and Gu, Kai and Wang, Yuanyuan and Guo, Yi},
  title = {A novel colorectal cancer screening framework with feature interpretability to identify high‐risk populations for colonoscopy},
  journal = {Journal of Gastroenterology and Hepatology},
  year = {2024},
  doi = {10.1111/jgh.16600}
}
Kostenlos starten →