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 26, 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

Development of a Machine Learning Model for Distant Metastasis Risk Stratification in Acral Melanoma.

Ye Shanyuan1, Zhang Rundong1, Cao Meng1

  • 1Hospital for Skin Diseases, Institute of Dermatology, Chinese Academy of Medical Sciences & Peking Union Medical College, Nanjing, Jiangsu, China.

Cancer Reports (Hoboken, N.J.)
|May 24, 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

Painful Destructive Plaques of the Face and Scalp: A Quiz.

Acta dermato-venereologica·2026
Same author

Koenen tumours revealing tuberous sclerosis complex in late adulthood.

The British journal of dermatology·2026
Same author

Clinical Prioritization of Adverse Events Associated With Hedgehog Pathway Inhibitors in Basal Cell Carcinoma Patients: Insights From the FDA Adverse Event Reporting (FAERS) System.

Journal of cutaneous medicine and surgery·2026
Same author

A "Beret-Like" Giant Congenital Melanocytic Nevus of the Scalp with Nodal Nevus on a Girl: A Surgical Challenge.

Balkan medical journal·2026
Same author

Therapeutic options for perifolliculitis capitis abscedens et suffodens: A review.

Dermatologic therapy·2022
Same author

Identification of KRAS mutation in a patient with linear nevus sebaceous syndrome: a case report.

BMC medical genomics·2020

A new machine learning model can help predict distant metastasis risk in acral melanoma (AM) patients. Key factors include N stage, sentinel lymph node biopsy, and income, aiding personalized risk assessment.

Area of Science:

  • Oncology
  • Machine Learning in Medicine
  • Biostatistics

Background:

  • Acral melanoma (AM) is an aggressive subtype with poor prognosis after metastasis.
  • Current models for predicting distant metastasis in AM are limited.
  • Early diagnosis and risk stratification are crucial for acral melanoma patients.

Purpose of the Study:

  • To develop and internally validate a machine learning model for predicting distant metastasis risk in acral melanoma.
  • To enable individualized risk assessment for acral melanoma patients.
  • To identify key predictors of distant metastasis in acral melanoma.

Main Methods:

  • Utilized SEER database data from 1822 acral melanoma patients (2000-2021).
  • Developed and compared six machine learning algorithms, including LightGBM.
Keywords:
LightGBMacral melanomadistant metastasismachine learningprediction model

More Related Videos

A 3D Organotypic Melanoma Spheroid Skin Model
08:49

A 3D Organotypic Melanoma Spheroid Skin Model

Published on: May 18, 2018

Related Experiment Videos

Last Updated: May 26, 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

A 3D Organotypic Melanoma Spheroid Skin Model
08:49

A 3D Organotypic Melanoma Spheroid Skin Model

Published on: May 18, 2018

  • Employed logistic regression and SHAP analysis to identify risk factors and model predictors.

    • Main Results:

    • Identified sentinel lymph node biopsy as protective, while higher N stage and lower income were risk factors.
    • The LightGBM model demonstrated moderate predictive performance for distant metastasis.
    • N stage, sentinel lymph node biopsy, and median household income were key predictors identified by SHAP analysis.

    Conclusions:

    • The developed LightGBM model shows potential for research-oriented, individualized distant metastasis risk stratification in acral melanoma.
    • External validation is necessary before clinical implementation.
    • The model highlights the importance of clinical and socioeconomic factors in acral melanoma progression.