Prediction of lymph node metastasis of lung squamous cell carcinoma by machine learning algorithm classifiers

Area of Science:

• Oncology
• Medical Informatics
• Machine Learning

Background:

• Lymph node metastasis (LNM) significantly impacts prognosis and treatment strategy in lung squamous cell carcinoma (LUSC).
• Accurate prediction of LNM is crucial for effective clinical decision-making in LUSC management.

Purpose of the Study:

• To develop and validate machine learning classifiers for predicting LNM in LUSC.
• To identify key clinical parameters for LNM prediction in LUSC patients.

Main Methods:

• Utilized the Surveillance, Epidemiology, and End Results (SEER) database to train machine learning algorithms.
• Developed and compared multiple classifiers, including boosted trees (BTs), using primary clinical parameters.
• Validated classifier performance on independent test and in-house cohorts.

Main Results:

• The boosted trees (BT) classifier demonstrated the highest performance, with an accuracy of 0.654 and an AUC of 0.714.
• Tumor stage was identified as a critical factor influencing LNM in LUSC.
• Classifiers effectively distinguished between patients with and without LNM.

Conclusions:

• Machine learning classifiers, especially BT, offer a valuable tool for enhancing clinical precision in LUSC.
• These tools can support individualized treatment strategies for patients with LUSC.
• The study highlights the potential of AI in improving oncological patient care.