Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Comparative Efficacy of Poly-ADP-Ribose Polymerase Inhibitors (Parpis) in the Treatment of Advanced Ovarian Cancer in Younger and Elderly Patients: A Systematic Review and Meta-Analysis.

Anti-cancer agents in medicinal chemistry·2026

Same author

Simultaneous molecular detection of <i>Mycobacterium tuberculosis</i> and multidrug resistance using CRISPR-AaCas12b-based nucleic acid assay.

Frontiers in cellular and infection microbiology·2026

Same author

ABCA1-mediated lipid efflux restrains oxidative stress and neuroinflammation after spinal cord injury.

Journal of neuroinflammation·2026

Same author

[Analysis of a Chinese pedigree affected with Hereditary factor Ⅴ deficiency due to compound heterozygous variants of F5 gene].

Zhonghua yi xue yi chuan xue za zhi = Zhonghua yixue yichuanxue zazhi = Chinese journal of medical genetics·2026

Same author

Machine learning models based on laboratory data: new insight into the differential diagnosis of tuberculous and viral meningitis.

Frontiers in cellular and infection microbiology·2026

Same author

A comparative study of the quality control efficacy of multiple error-introduction methods for patient-based real-time quality control.

Practical laboratory medicine·2026

Search research articles

Related Experiment Video

Updated: May 12, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Explainable Machine Learning Models for Colorectal Cancer Prediction Using Clinical Laboratory Data.

Rui Li¹, Xiaoyan Hao¹, Yanjun Diao¹

¹Department of Clinical Laboratory Medicine, Xijing Hospital, Air Force Medical University, Xi'an, China.

Cancer Control : Journal of the Moffitt Cancer Center

|May 7, 2025

Summary

Machine learning models using routine lab data show high accuracy for colorectal cancer (CRC) risk prediction, outperforming traditional tests like fecal occult blood testing (FOBT) and carcinoembryonic antigen (CEA). Incorporating stool miR-92a further enhances diagnostic performance.

Keywords:

clinical laboratory data colorectal cancer machine learning miR-92a risk prediction

More Related Videos

Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery

Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery

Published on: September 27, 2024

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Related Experiment Videos

Last Updated: May 12, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery

Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery

Published on: September 27, 2024

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Area of Science:

Oncology
Biomedical Informatics
Clinical Diagnostics

Background:

Early diagnosis of colorectal cancer (CRC) remains a significant clinical challenge.
Current diagnostic biomarkers like carcinoembryonic antigen (CEA) and fecal occult blood testing (FOBT) have limitations.
Machine learning (ML) offers potential for improved risk prediction using complex datasets.

Purpose of the Study:

To develop and evaluate ML models for predicting CRC risk.
To compare the diagnostic performance of ML models against established biomarkers.
To identify key laboratory features contributing to CRC diagnosis.

Main Methods:

Retrospective analysis of laboratory data from 31,539 subjects (healthy controls, polyp patients, CRC patients) between 2013-2023.
Development and comparison of five ML algorithms (AdaBoost, XGBoost, DT, LR, RF) for classification tasks.
Feature importance analysis using Shapley additive explanations (SHAP) and assessment of stool miR-92a incorporation.

Main Results:

The XGBoost model achieved high AUCs (0.966 for HC vs CRC, 0.881 for Polyp vs CRC), outperforming CEA and FOBT.
The model successfully identified CRC patients negative for CEA or FOBT.
Key features identified include FOBT, CEA, lymphocyte percentage (LYMPH%), and hematocrit (HCT).

Conclusions:

ML models utilizing routine laboratory data demonstrate superior diagnostic accuracy for CRC compared to traditional biomarkers.
The developed models can aid in early CRC detection, including in cases missed by standard tests.
Further enhancement of diagnostic capabilities is achievable by integrating stool miR-92a levels.