Comparison of supervised machine learning classification techniques in prediction of locoregional recurrences in early oral tongue cancer

Although patients with early-stage oral tongue squamous cell carcinoma (OTSCC) show better survival than those with advanced disease, there is still a number of early-stage cases who will suffer from recurrence, cancer-related mortality and worse overall survival. Incorporation of an immune descriptive factor in the staging system can aid in improving risk assessment of early OTSCC. A total of 290 cases of early-stage OTSCC re-classified according to the American Joint Committee on Cancer (AJCC 8) staging were included in this study. Scores of tumor-infiltrating lymphocytes (TILs) were divided as low or high and incorporated in TNM AJCC 8 to form our proposed TNM-Immune system. Using AJCC 8, there were no significant differences in survival between T1 and T2 tumors (p > 0.05). Our proposed TNM-Immune staging system allowed for significant discrimination in risk between tumors of T1N0M0-Immune vs. T2N0M0-Immune. The latter associated with a worse overall survival with hazard ratio (HR) of 2.87 (95% CI 1.92–4.28; p < 0.001); HR of 2.41 (95% CI 1.26–4.60; p = 0.008) for disease-specific survival; and HR of 1.97 (95% CI 1.13–3.43; p = 0.017) for disease-free survival. The TNM-Immune staging system showed a powerful ability to identify cases with worse survival. The immune response is an important player which can be assessed by evaluating TILs, and it can be implemented in the staging criteria of early OTSCC. TNM-Immune staging forms a step towards a more personalized classification of early OTSCC.

Download Full-text

Machine Learning Classification and Regression Approaches for Optical Network Traffic Prediction

Electronics ◽

10.3390/electronics10131578 ◽

2021 ◽

Vol 10 (13) ◽

pp. 1578

Author(s):

Daniel Szostak ◽

Adam Włodarczyk ◽

Krzysztof Walkowiak

Keyword(s):

Machine Learning ◽

Optical Networks ◽

Network Traffic ◽

Optical Network ◽

Optimization Methods ◽

Supervised Machine Learning ◽

Traffic Prediction ◽

Machine Learning Classification ◽

Classification And Regression ◽

Network Technologies

Rapid growth of network traffic causes the need for the development of new network technologies. Artificial intelligence provides suitable tools to improve currently used network optimization methods. In this paper, we propose a procedure for network traffic prediction. Based on optical networks’ (and other network technologies) characteristics, we focus on the prediction of fixed bitrate levels called traffic levels. We develop and evaluate two approaches based on different supervised machine learning (ML) methods—classification and regression. We examine four different ML models with various selected features. The tested datasets are based on real traffic patterns provided by the Seattle Internet Exchange Point (SIX). Obtained results are analyzed using a new quality metric, which allows researchers to find the best forecasting algorithm in terms of network resources usage and operational costs. Our research shows that regression provides better results than classification in case of all analyzed datasets. Additionally, the final choice of the most appropriate ML algorithm and model should depend on the network operator expectations.

Download Full-text