Related Experiment Video
Updated: May 21, 2025
07:15
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
6.6K
Construction and validation of machine learning models for predicting lymph node metastasis in cutaneous malignant
Ling-Feng Lan1, Yi-Long Kai1, Xiao-Ling Xu1
1Department of Otolaryngology, The First Affiliated Hospital, Zhejiang University School of Medicine, Liangzhu Branch (The First People's Hospital of Yuhang District), Hangzhou, China.
Translational Cancer Research
|March 19, 2025
Summary
A machine learning model accurately predicts lymph node metastases (LNM) in cutaneous malignant melanoma (CMM). The XGBoost model, identifying age and Breslow thickness as key factors, can guide surgical decisions and improve patient outcomes.
Area of Science:
- Oncology
- Medical Informatics
- Computational Biology
Background:
- Lymph node status is critical for predicting the prognosis of cutaneous malignant melanoma (CMM).
- Accurate prediction of lymph node metastases (LNM) is essential for effective treatment planning in CMM.
- Machine learning (ML) offers a promising approach to enhance the accuracy of LNM prediction.
Purpose of the Study:
- To develop and evaluate a machine learning (ML) model for predicting lymph node metastases (LNM) in cutaneous malignant melanoma (CMM).
- To identify key clinicopathologic variables associated with LNM in CMM.
- To provide a tool that assists clinicians in surgical decision-making and adjuvant therapy selection.
Main Methods:
- Utilized data from 6,196 CMM patients from the SEER database.
- Applied six ML algorithms (LR, SVM, CNB, XGBoost, RF, kNN) to predict LNM, addressing data imbalance with ADASYN.
- Assessed model performance using AP, sensitivity, specificity, accuracy, F1 score, and SHAP analysis for interpretability.
Main Results:
- The XGBoost model demonstrated superior predictive performance with an average precision (AP) of 0.805.
- Age and Breslow thickness were identified as the most significant predictors of LNM in CMM.
- The model achieved high precision in predicting LNM, outperforming other evaluated algorithms.
Conclusions:
- The developed XGBoost model accurately predicts LNM in CMM.
- This ML tool can aid surgeons in determining optimal surgical strategies and extent of resection.
- The model's predictions can inform adjuvant therapy decisions, potentially improving patient prognosis.
