Learning from data to predict future symptoms of oncology patients

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.

[1]  Douglas G. Altman,et al.  Measurement in Medicine: The Analysis of Method Comparison Studies , 1983 .

[2]  Kathryn A. Lee,et al.  Sleep disturbances, vitality, and fatigue among a select group of employed childbearing women. , 1992, Birth.

[3]  Paul McCrone,et al.  The eSMART study protocol: a randomised controlled trial to evaluate electronic symptom management using the advanced symptom management system (ASyMS) remote technology for patients with cancer , 2017, BMJ Open.

[4]  D. Karnofsky,et al.  The use of the nitrogen mustards in the palliative treatment of carcinoma. With particular reference to bronchogenic carcinoma , 1948 .

[5]  M. Liang,et al.  The Self-Administered Comorbidity Questionnaire: a new method to assess comorbidity for clinical and health services research. , 2003, Arthritis and rheumatism.

[6]  M. Mukaka,et al.  Statistics corner: A guide to appropriate use of correlation coefficient in medical research. , 2012, Malawi medical journal : the journal of Medical Association of Malawi.

[7]  S. S. Salankar,et al.  MRI brain cancer classification using Support Vector Machine , 2014, 2014 IEEE Students' Conference on Electrical, Electronics and Computer Science.

[8]  Feng Chu,et al.  Applications of support vector machines to cancer classification with microarray data , 2005, Int. J. Neural Syst..

[9]  Max Kuhn,et al.  Building Predictive Models in R Using the caret Package , 2008 .

[10]  N. Kearney,et al.  The symptom phenotype of oncology outpatients remains relatively stable from prior to through 1 week following chemotherapy , 2017, European journal of cancer care.

[11]  J. Levine,et al.  Inflammatory pathway genes associated with inter‐individual variability in the trajectories of morning and evening fatigue in patients receiving chemotherapy , 2017, Cytokine.

[12]  Ji-Hyun Kim,et al.  Estimating classification error rate: Repeated cross-validation, repeated hold-out and bootstrap , 2009, Comput. Stat. Data Anal..

[13]  Kathryn A. Lee,et al.  Pain, fatigue, and sleep disturbances in oncology outpatients receiving radiation therapy for bone metastasis: a pilot study. , 1999, Journal of pain and symptom management.

[14]  J. Levine,et al.  Subgroups of chemotherapy patients with distinct morning and evening fatigue trajectories , 2016, Supportive Care in Cancer.

[15]  M. Antony,et al.  The State-Trait Anxiety Inventory, Trait version: structure and content re-examined. , 1998, Behaviour research and therapy.

[16]  Gang Huang,et al.  Application of support vector machine in cancer diagnosis , 2011, Medical oncology.

[17]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[18]  J. Neuhaus,et al.  Differences in depression, anxiety, and quality of life between women with and without breast pain prior to breast cancer surgery. , 2013, European journal of oncology nursing : the official journal of European Oncology Nursing Society.

[19]  Kristin P. Bennett,et al.  Support vector machines: hype or hallelujah? , 2000, SKDD.

[20]  D. Basak,et al.  Support Vector Regression , 2008 .

[21]  John Salvatier,et al.  Theano: A Python framework for fast computation of mathematical expressions , 2016, ArXiv.

[22]  T. J. Sheehan,et al.  The measurement structure of the Center for Epidemiologic Studies Depression Scale. , 1995, Journal of personality assessment.

[23]  A Rogier T Donders,et al.  Imputation of missing values is superior to complete case analysis and the missing-indicator method in multivariable diagnostic research: a clinical example. , 2006, Journal of clinical epidemiology.

[24]  Lan Hu,et al.  A novel strategy for forensic age prediction by DNA methylation and support vector regression model , 2015, Scientific Reports.

[25]  L. Grassi,et al.  Depressive Spectrum Disorders in Cancer: Diagnostic Issues and Intervention. A Critical Review , 2017, Current Psychiatry Reports.

[26]  Craig K. Enders,et al.  A Primer on Maximum Likelihood Algorithms Available for Use With Missing Data , 2001 .

[27]  Christine Miaskowski,et al.  Co-occurrence of anxiety and depressive symptoms following breast cancer surgery and its impact on quality of life. , 2016, European journal of oncology nursing : the official journal of European Oncology Nursing Society.

[28]  M. Kenward,et al.  Multiple imputation for missing data in epidemiological and clinical research: potential and pitfalls , 2009, BMJ : British Medical Journal.

[29]  Kathryn A. Lee,et al.  Prevalence, severity, and impact of symptoms on female family caregivers of patients at the initiation of radiation therapy for prostate cancer. , 2008, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[30]  Helen Skerman,et al.  Latent Class Analysis Reveals Distinct Subgroups of Patients Based on Symptom Occurrence and Demographic and Clinical Characteristics. , 2015, Journal of pain and symptom management.

[31]  R. Roberts,et al.  A Systematic Review Assessing Bidirectionality between Sleep Disturbances, Anxiety, and Depression. , 2013, Sleep.

[32]  S. Hanneman,et al.  Design, Analysis, and Interpretation of Method‐Comparison Studies , 2008, AACN advanced critical care.

[33]  B Sachs,et al.  Psychometrics for two short forms of the Center for Epidemiologic Studies-Depression Scale. , 1998, Issues in mental health nursing.

[34]  C. Miaskowski,et al.  Changes in perceived attentional function in women following breast cancer surgery , 2011, Breast Cancer Research and Treatment.

[35]  K. Bjordal,et al.  Patient factors and quality of life outcomes differ among four subgroups of oncology patients based on symptom occurrence , 2017, Acta oncologica.

[36]  Kathryn A. Lee,et al.  Validity and reliability of a scale to assess fatigue , 1991, Psychiatry Research.

[37]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[38]  William W. Hsieh,et al.  Nonlinear canonical correlation analysis by neural networks , 2000, Neural Networks.

[39]  Mehrbakhsh Nilashi,et al.  Accuracy Improvement for Predicting Parkinson’s Disease Progression , 2016, Scientific Reports.

[40]  L. Radloff.  The CES-D Scale , 1977 .

[41]  Nicole A. Lazar,et al.  Statistical Analysis With Missing Data , 2003, Technometrics.

[42]  Kathryn A. Lee,et al.  Self-reported sleep disturbances in employed women. , 1992, Sleep.

[43]  Max Kuhn,et al.  The caret Package , 2007 .

[44]  B. Efron.  Estimating the Error Rate of a Prediction Rule: Improvement on Cross-Validation , 1983 .

[45]  R. Tibshirani,et al.  Improvements on Cross-Validation: The 632+ Bootstrap Method , 1997 .

[46]  Jae Warrander,et al.  Performance of Scale , 2013 .

[47]  B. Cimprich,et al.  Attentional fatigue following breast cancer surgery. , 1992, Research in nursing & health.

[48]  Richard L. Morris,et al.  Assessment of State and Trait Anxiety in Subjects with Anxiety and Depressive Disorders , 2004, Psychiatric Quarterly.

[49]  M. Ahluwalia,et al.  Sleep disturbances in cancer patients: Underrecognized and undertreated , 2013, Cleveland Clinic Journal of Medicine.

[50]  Lori A. Post,et al.  Strategies for Dealing with Missing Data in Clinical Trials: From Design to Analysis , 2013, The Yale journal of biology and medicine.