Open AccessTime series forecasting using ARIMA for modeling of glioma growth in response to radiotherapy
Author(s) -
Larissa Miguez da Silva,
Gustavo Benitez Alvarez,
Eliane da Silva Christo,
Gerardo Amado Pelén Sierra,
Vanessa da Silva Garcia
Publication year - 2021
Publication title -
semina. ciências exatas e tecnológicas
Language(s) - English
Resource type - Journals
eISSN - 1679-0375
pISSN - 1676-5451
DOI - 10.5433/1679-0375.2021v42n1p3
Subject(s) - autoregressive integrated moving average , mean absolute percentage error , series (stratigraphy) , glioblastoma , time series , mean squared error , radiation therapy , autoregressive model , statistics , moving average , computer science , mathematics , medicine , surgery , biology , paleontology , cancer research
In present days, the growing number of people suffering from cancer has been a major cause for concern worldwide. Glioblastoma in particular, are primary tumors in glial cells located in the central nervous system. Because of this sensitive location, mathematical models have been studied and developed as alternative tools for analyzing tumor growth rates, assisting on the decision-making process for treatment dosage, without exposing the patient’s life. This paper presents two time series models to estimate the growth rate of glioblastoma in response to ionizing radiotherapy treatment. The results obtained indicate that the proposed time series methods attain predictions with a Mean Absolute Percentual Error (MAPE) of approximately 1% to 4%, and simulations show that the Autoregressive Integrated Moving Average (ARIMA) method surpasses the Holt method based on the Mean Square Error (MSE) and MAPE values obtained. Furthermore, the results show that the time series method is applicable to data from two different mathematical models for glioblastoma growth.