Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Clinical Trial
. 2018 Dec 31;13(12):e0208808.
doi: 10.1371/journal.pone.0208808. eCollection 2018.

Learning from data to predict future symptoms of oncology patients

Nikolaos Papachristou  1 , Daniel Puschmann  1 , Payam Barnaghi  1 , Bruce Cooper  2 , Xiao Hu  2 , Roma Maguire  3 , Kathi Apostolidis  4 , Yvette P Conley  5 , Marilyn Hammer  6 , Stylianos Katsaragakis  7 , Kord M Kober  2 , Jon D Levine  2 , Lisa McCann  3 , Elisabeth Patiraki  8 , Eileen P Furlong  9 , Patricia A Fox  9 , Steven M Paul  2 , Emma Ream  1 , Fay Wright  10 , Christine Miaskowski  2
Affiliations
Clinical Trial

Learning from data to predict future symptoms of oncology patients

Nikolaos Papachristou et al. PLoS One. .

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.

PubMed Disclaimer

Conflict of interest statement

The authors have declared that no competing interests exist.

Figures

Fig 1
Fig 1. Overview of our analytic approach to learn from data to predict future symptoms of oncology patients.
Fig 2
Fig 2. Multiple imputation.
Fig 3
Fig 3. Support Vector Regression.
Fig 4
Fig 4. n-CCA training and validation: (i) training of the n-CCA model, (ii) validation of the n-CCA model.
Fig 5
Fig 5. Bland—Atman plot of the SVR model with the polynomial function and the n-CCA model on the dataset with Maximum Likelihood imputation.
Fig 6
Fig 6. Missing values pattern (Little’s MCAR test, p>0.05).
Fig 7
Fig 7. Correlation analysis of predictor variables.
Fig 8
Fig 8. Density plots of the sleep disturbance (GSDS), anxiety (STAI-S) and depression (CES-D) real values compared to the density plots of predicted values with the SVR (polynomial kernel) and n-CCA on the dataset with the Maximum Likelihood Estimation imputation.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Astrup GL, Hofsø K, Bjordal K, Guren MG, Vistad I, Cooper B, et al. Patient factors and quality of life outcomes differ among four subgroups of oncology patients based on symptom occurrence. Acta Oncologica. 2017;56(3):462–470. 10.1080/0284186X.2016.1273546 - DOI - PubMed
    1. Miaskowski C, Cooper B, Aouizerat B, Melisko M, Chen LM, Dunn L, et al. The symptom phenotype of oncology outpatients remains relatively stable from prior to through 1 week following chemotherapy. European journal of cancer care. 2017;26(3). 10.1111/ecc.12437 - DOI - PMC - PubMed
    1. Miaskowski C, Dunn L, Ritchie C, Paul SM, Cooper B, Aouizerat BE, et al. Latent class analysis reveals distinct subgroups of patients based on symptom occurrence and demographic and clinical characteristics. Journal of pain and symptom management. 2015;50(1):28–37. 10.1016/j.jpainsymman.2014.12.011 - DOI - PMC - PubMed
    1. Caruso R, GiuliaNanni M, Riba MB, Sabato S, Grassi L. Depressive Spectrum Disorders in Cancer: Diagnostic Issues and Intervention. A Critical Review. Current Psychiatry Reports. 2017;19(6):33 10.1007/s11920-017-0785-7 - DOI - PMC - PubMed
    1. Kyranou M, Paul SM, Dunn LB, Puntillo K, Aouizerat BE, Abrams G, et al. Differences in depression, anxiety, and quality of life between women with and without breast pain prior to breast cancer surgery. European Journal of Oncology Nursing. 2013;17(2):190–195. 10.1016/j.ejon.2012.06.001 - DOI - PMC - PubMed

Publication types