Time series forecasting using ARIMA for modeling of glioma growth in response to radiotherapy

Silva, Larissa Miguez da; Alvarez, Gustavo Benitez; Christo, Eliane da Silva; Sierra, Gerardo Amado Pelén; Garcia, Vanessa da Silva

doi:10.5433/1679-0375.2021v42n1p3

Cited by 2 publications

(2 citation statements)

References 22 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An ARIMA model was used to capture the trend of pulse production in India by [ 19 ] to predict pulse production from 2020 to 2029 to bridge the gap between the supply and demand. Two time series models were employed to estimate the growth rate of glioblastoma in response to ionizing radiotherapy treatment in a comparative study presented by [ 20 ]. Their study showed that ARIMA performed better based on the mean square error (MSE) and MAPE values obtained than the Holt method.…”

Section: Introductionmentioning

confidence: 99%

A Predictive Analysis of Heart Rates Using Machine Learning Techniques

Oyeleye

Chen

Titarenko

et al. 2022

IJERPH

View full text Add to dashboard Cite

Heart disease, caused by low heart rate, is one of the most significant causes of mortality in the world today. Therefore, it is critical to monitor heart health by identifying the deviation in the heart rate very early, which makes it easier to detect and manage the heart’s function irregularities at a very early stage. The fast-growing use of advanced technology such as the Internet of Things (IoT), wearable monitoring systems and artificial intelligence (AI) in the healthcare systems has continued to play a vital role in the analysis of huge amounts of health-based data for early and accurate disease detection and diagnosis for personalized treatment and prognosis evaluation. It is then important to analyze the effectiveness of using data analytics and machine learning to monitor and predict heart rates using wearable device (accelerometer)-generated data. Hence, in this study, we explored a number of powerful data-driven models including the autoregressive integrated moving average (ARIMA) model, linear regression, support vector regression (SVR), k-nearest neighbor (KNN) regressor, decision tree regressor, random forest regressor and long short-term memory (LSTM) recurrent neural network algorithm for the analysis of accelerometer data to make future HR predictions from the accelerometer’s univariant HR time-series data from healthy people. The performances of the models were evaluated under different durations. Evaluated on a very recently created data set, our experimental results demonstrate the effectiveness of using an ARIMA model with a walk-forward validation and linear regression for predicting heart rate under all durations and other models for durations longer than 1 min. The results of this study show that employing these data analytics techniques can be used to predict future HR more accurately using accelerometers.

show abstract

Section: Introductionmentioning

confidence: 99%

A Predictive Analysis of Heart Rates Using Machine Learning Techniques

Oyeleye

Chen

Titarenko

et al. 2022

IJERPH

View full text Add to dashboard Cite

show abstract

“…Two mathematical models that describe the growth of gliomas were proposed in Leder et al (2014), Rockne et al (2009) and Swanson et al (2003). Both models were analyzed in Barbosa et al (2019), Silva et al (2016) and Souza et al (2015), and new approaches based on time series were suggested in Jesus et al (2014) and Silva et al (2021).…”

Section: Introductionmentioning

confidence: 99%

Reactive-Advective-Diffusive Models for the Growth of Gliomas Treated with Radiotherapy

Machado

Alvarez

Lobão

2023

Semin., Ciênc. Exatas Tecnol.

Self Cite

View full text Add to dashboard Cite

Gliomas are malignant brain tumors responsible for 50% of primary human brain cancer cases. They have a combination of rapid growth and invasiveness, and high fatality rates with a median survival time of one year. Mathematical models that describe its growth have helped to improve treatment. In this paper, a combined model formed by terms of two other models known in the literature is analyzed. The combined model is a Reactive-Advective-Diffusive partial differential equation, which is solved by combining the finite difference method, the Crank-Nicolson method and the upwind method. Logistic growth is used for cell proliferation ensuring a saturation threshold for glioma growth, which is crucial to properly estimate patient survival time. The well-known linear-quadratic radiobiological model is used to describe cell death due to radiotherapy treatment. Two initial conditions are compared in the simulations, indicating the need for further studies to have a model as close as possible to reality. Simulation results are shown for four scenarios: no radiotherapy, application of a single dose, and two dose fractionation schemes.

show abstract

Time series forecasting using ARIMA for modeling of glioma growth in response to radiotherapy

Cited by 2 publications

References 22 publications

A Predictive Analysis of Heart Rates Using Machine Learning Techniques

A Predictive Analysis of Heart Rates Using Machine Learning Techniques

Reactive-Advective-Diffusive Models for the Growth of Gliomas Treated with Radiotherapy

Contact Info

Product

Resources

About