Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 16, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

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

Published on: August 16, 2020

An interpretable machine learning-based approach: development, validation, and clinical utility for distant

Ruijie Sun1, Yuhui Ma2, Yushan Jiang3

  • 1Department of Otolaryngology, Qilu Hospital of Shandong University (Qingdao)​, Qingdao, Shandong, China.

Frontiers in Endocrinology
|May 15, 2026
PubMed
Summary

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

Uterine cystic adenomyoma arising from cesarean scar diverticulum: a case report and literature review.

BMC pregnancy and childbirth·2026
Same author

Feasibility study of transvaginal biplanar convex ultrasound for evaluating levator ani muscle.

Journal of ultrasound·2026
Same author

Identifying serum amino acid as biomarkers of gestational diabetes mellitus in second-trimester among Chinese pregnant women: a machine learning-based cross-sectional study.

Reproductive health·2026
Same author

Optimization of the single-side drift method for shallow-buried tunnels under large eccentric pressure based on the BiDoseResp settlement model.

Scientific reports·2025
Same author

Training Indoor and Scene-Specific Semantic Segmentation Models to Assist Blind and Low Vision Users in Activities of Daily Living.

IEEE open journal of engineering in medicine and biology·2025
Same author

High-quality randomised controlled trials of acupuncture interventions for autism spectrum disorder in the last 10 years (2015-2024): A literature review.

Current opinion in pharmacology·2025

This study developed an interpretable machine learning model to predict metastasis in papillary thyroid carcinoma (PTC) patients. The model accurately identifies high-risk individuals, improving upon traditional methods for better patient stratification.

Area of Science:

  • Oncology
  • Medical Informatics
  • Biostatistics

Background:

  • Papillary thyroid carcinoma (PTC) accounts for 80-90% of thyroid cancers.
  • A significant subset of PTC patients (20-30%) faces intermediate/high-risk features, elevating the risk of distant metastasis.
  • Conventional predictors like TNM staging and tumor size show limitations in accurately forecasting metastasis, necessitating advanced prediction tools.

Purpose of the Study:

  • To develop and validate a precise, interpretable machine learning (ML) model for predicting distant metastasis in papillary thyroid carcinoma (PTC) patients.
  • To enhance the accuracy of risk stratification beyond traditional clinicopathological factors.
  • To support personalized treatment decisions for PTC management.

Main Methods:

  • Utilized data from 2,452 PTC patients (2015-2023), incorporating clinical, pathological, laboratory, and ultrasound indices.
Keywords:
LightGBM algorithmSHAP (shapley additive explanation)machine learningmetastasisthyroid cancer

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

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

Published on: October 10, 2018

Related Experiment Videos

Last Updated: May 16, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

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

Published on: August 16, 2020

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

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

Published on: October 10, 2018

  • Applied feature selection techniques (LASSO, RFE, ReliefF) to identify 7 core predictive features.
  • Compared nine ML algorithms, employing SHAP analysis for model interpretability and external validation with 432 patients.

    • Main Results:

    • The LightGBM model achieved an AUC of 0.886 on the test set and 0.758 in external validation, with 88.7% accuracy.
    • SHAP analysis highlighted extrathyroidal invasion and thyroglobulin antibody (TgAb) as key predictors.
    • The model demonstrated a 93.6% negative predictive value (NPV), effectively excluding low-risk patients.

    Conclusions:

    • The developed interpretable ML model surpasses traditional predictors in forecasting metastasis for PTC patients.
    • This tool offers significant potential for improved clinical risk stratification and personalized treatment strategies.
    • The model's high accuracy and interpretability suggest broad applicability in clinical settings for thyroid cancer management.