Machine Learning-Based Prediction of Lymph Node Metastasis Among Osteosarcoma Patients

Area of Science:

• Oncology
• Biostatistics
• Machine Learning in Medicine

Background:

• Regional lymph node metastasis significantly impacts osteosarcoma prognosis.
• Limited research exists on predicting lymph node metastasis in osteosarcoma.
• This study focuses on developing and validating machine learning models for this prediction.

Purpose of the Study:

• To develop and validate a machine learning model for predicting regional lymph node metastasis in osteosarcoma.
• To identify independent risk factors associated with lymph node metastasis.
• To create a practical tool for clinical risk assessment.

Main Methods:

• Utilized a dataset of 1201 osteosarcoma patients (SEER and Chinese medical centers).
• Employed six machine learning algorithms (LR, GBM, XGBoost, RF, DT, MLP) to assess metastasis risk.
• Validated model performance using AUC, accuracy, sensitivity, and specificity.

Main Results:

• 9.41% of patients developed regional lymph node metastasis.
• Key predictors identified include tumor (T) stage, metastasis (M) stage, surgery, and chemotherapy.
• The XGBoost algorithm demonstrated the highest predictive performance (AUC 0.882).

Conclusions:

• Tumor stage, surgery, and chemotherapy are independent risk factors for lymph node metastasis in osteosarcoma.
• The XGBoost model offers superior predictive accuracy.
• An online risk calculator is available to assist clinicians in assessing metastasis probability.