Artificial intelligence in dentistry: Harnessing big data to predict oral cancer survival

Abstract

BACKGROUND Oral cancer is the sixth most prevalent cancer worldwide. Public knowledge in oral cancer risk factors and survival is limited. AIM To come up with machine learning (ML) algorithms to predict the length of survival for individuals diagnosed with oral cancer, and to explore the most important factors that were responsible for shortening or lengthening oral cancer survival. METHODS We used the Surveillance, Epidemiology, and End Results database from the years 1975 to 2016 that consisted of a total of 257880 cases and 94 variables. Four ML techniques in the area of artificial intelligence were applied for model training and validation. Model accuracy was evaluated using mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), R 2 and adjusted R 2 . RESULTS The most important factors predictive of oral cancer survival time were age at diagnosis, primary cancer site, tumor size and year of diagnosis. Year of diagnosis referred to the year when the tumor was first diagnosed, implying that individuals with tumors that were diagnosed in the modern era tend to have longer survival than those diagnosed in the past. The extreme gradient boosting ML algorithms showed the best performance, with the MAE equaled to 13.55, MSE 486.55 and RMSE 22.06. CONCLUSION Using artificial intelligence, we developed a tool that can be used for oral cancer survival prediction and for medical-decision making. The finding relating to the year of diagnosis represented an important new discovery in the literature. The results of this study have implications for cancer prevention and education for the public.

Machine Learning Incorporating Host Factors for Predicting Survival in Head and Neck Squamous Cell Carcinoma Patients

“…However, this is not applicable for primary cancer patients at baseline. In another study, Hung et al used demographic and clinical data to model oral cancer survival as a continuous variable with all censored observations excluded [ 29 ]. The study was conducted on a patient cohort spanning from 1975 to 2016 and the year of diagnosis was found as the most predictive feature.…”

“…The study was conducted on a patient cohort spanning from 1975 to 2016 and the year of diagnosis was found as the most predictive feature. Due to the high heterogeneity in diagnostic years and different metrics of performance, the model is not directly comparable with ours [ 29 ]. Moreover, the output of these models cannot be directly converted into survival functions or survival probabilities, so the application is quite limited.…”

Machine learning in dental, oral and craniofacial imaging: a review of recent progress

“…Furthermore, to improve the degree of accuracy, other indicators including tumor grading and staging should be taken into account. The year of diagnosis, the age at diagnosis and cancer size and site are of significance in the lifetime of patients ( Hung et al, 2020b ).…”

Aplicación de la inteligencia artificial en Odontología

“…Dentro del área de patología oral se han reportado diferentes tipos de IA con diferentes usos desde el diagnóstico de lesiones quísticas odontológicas por medio del análisis panorámico y tomográfico utilizando Deep CNN architecture y YOLOv2 según refieren Lee et al 29 y Yang et al 30 respectivamente. Predicciones en la positividad de márgenes tumorales como indicativo de la calidad de la atención a través del análisis de registros 31 Predicciones de supervivencia del cáncer oral con algoritmos de aprendizaje profundo Deepsurv 32 ; utilizando algoritmos como Linear regression, DT,RF y XGBoost 33 ; así como también basándose en el análisis de imágenes fotográficas con el uso de redes convolucionales 34 .…”