Bayesian nonparametric clustering of patients with advanced cancer on anxiety and depression Conference Paper


Authors: Li, Y.; Rosenfeld, B.; Pessin, H.; Breitbart, W.
Editors: Chen, X.; Luo, B.; Luo, F.; Palade, V.; Wani, M. A.
Title: Bayesian nonparametric clustering of patients with advanced cancer on anxiety and depression
Conference Title: 16th IEEE International Conference on Machine Learning and Applications (ICMLA 2017)
Abstract: Bayesian nonparametric (BNP) statistical techniques are thriving in Machine Learning, yet they are not widely used in psychiatric research, in part because of a lack of accessible tutorials and statistical computing solutions for researchers who are often non-technicians. We wrote a program to carry out BNP cluster analysis. We applied it to psychological data collected in a randomized controlled trial comparing Individual Meaning Centered Psychotherapy (IMCP, n=109), Supportive Psychotherapy (SP, n=108) and Enhanced Usual Care (EUC, n=104) in reducing psychological distress and improving meaning making in patients with advanced and terminal cancer. A BNP cluster analysis identified 5 subgroups of patients with unique profiles of anxiety and depression scores before psychotherapy. Our findings show that cancer patients who report mild symptoms in both anxiety and depression are most likely to respond to IMCP as compared to EUC. Somewhat unexpectedly, patients with anxiety and depression both at an elevated level do not show the highest response. We aim to introduce BNP statistical techniques to behavioral researchers in psychiatry, using BNP cluster analysis in IMPC psychotherapy as an illustrative example, and discuss with other researchers how they may use it in their own work. © 2017 IEEE.
Keywords: cluster analysis; randomized controlled trial; artificial intelligence; computer simulation; diseases; behavioral research; psychological distress; cancer patients; monte carlo methods; numerical methods; learning systems; barium compounds; statistical techniques; numerical simulation; bayes methods; bayes method; bayesian nonparametric clustering; psychiatric research; statistical computing
Journal Title Proceedings of the 16th IEEE International Conference on Machine Learning and Applications
Conference Dates: 2017 Dec 18-21
Conference Location: Cancun, Mexico
ISBN: 978-1-5386-1417-4
Publisher: IEEE  
Date Published: 2017-01-01
Start Page: 674
End Page: 678
Language: English
DOI: 10.1109/ICMLA.2017.00-83
PROVIDER: scopus
DOI/URL:
Notes: Conference Paper -- Export Date: 2 July 2018 -- Source: Scopus
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
  1. Yuelin Li
    220 Li
  2. William S Breitbart
    505 Breitbart
  3. Hayley Ann Pessin
    88 Pessin