Learning from data to predict future symptoms of oncology patients

Papachristou, Nikolaos and Puschmann, Daniel and Barnaghi, Payam and Cooper, Bruce and Hu, Xiao and Maguire, Roma and Apostolidis, Kathi and Conley, Yvette P. and Hammer, Marilyn and Katsaragakis, Stylianos and Kober, Kord M. and Levine, Jon D. and McCann, Lisa and Patiraki, Elisabeth and Furlong, Eileen P. and Fox, Patricia A. and Paul, Steven M. and Ream, Emma and Wright, Fay and Miaskowski, Christine (2018) Learning from data to predict future symptoms of oncology patients. PLoS ONE, 13 (12). e0208808. ISSN 1932-6203 (https://doi.org/10.1371/journal.pone.0208808)

[thumbnail of Papachristou-etal-POS2018-Learning-from-data-to-predict-future-symptoms-of-oncology]
Preview
Text. Filename: Papachristou_etal_POS2018_Learning_from_data_to_predict_future_symptoms_of_oncology.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo

Download (1MB)| Preview

Abstract

Effective symptom management is a critical component of cancer treatment. Computational tools that predict the course and severity of these symptoms have the potential to assist oncology clinicians to personalize the patient's treatment regimen more efficiently and provide more aggressive and timely interventions. Three common and inter-related symptoms in cancer patients are depression, anxiety, and sleep disturbance. In this paper, we elaborate on the efficiency of Support Vector Regression (SVR) and Non-linear Canonical Correlation Analysis by Neural Networks (n-CCA) to predict the severity of the aforementioned symptoms between two different time points during a cycle of chemotherapy (CTX). Our results demonstrate that these two methods produced equivalent results for all three symptoms. These types of predictive models can be used to identify high risk patients, educate patients about their symptom experience, and improve the timing of pre-emptive and personalized symptom management interventions.