Comparing machine learning clustering with latent class analysis on cancer symptoms' data

Nikolaos Papachristou, Christine Miaskowski, Payam Barnaghi, Roma Maguire, Nazli Farajidavar, Bruce Cooper, Xiao Hu

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

2 Citations (Scopus)

Abstract

Symptom Cluster Research is a major topic in Cancer Symptom Science. In spite of the several statistical and clinical approaches in this domain, there is not a consensus on which method performs better. Identifying a generally accepted analytical method is important in order to be able to utilize and process all the available data. In this paper we report a secondary analysis on cancer symptom data, comparing the performance of five Machine Learning (ML) clustering algorithms in doing so. Based on how well they separate specific subsets of symptom measurements we select the best of them and proceed to compare its performance with the Latent Class Analysis (LCA) method. This analysis is a part of an ongoing study for identifying suitable Machine Learning algorithms to analyse and predict cancer symptoms in cancer treatment.
LanguageEnglish
Title of host publicationHealthcare Innovation Point-Of-Care Technologies Conference (HI-POCT), 2016 IEEE
Place of PublicationPiscataway, NJ.
PublisherIEEE
Pages162-166
Number of pages5
ISBN (Print)9781509011674
DOIs
Publication statusPublished - 9 Nov 2016

Fingerprint

Learning algorithms
Cluster Analysis
Learning systems
Oncology
Clustering algorithms
Neoplasms
Machine Learning
Research
Therapeutics

Keywords

  • Symptom Cluster Research
  • machine learning
  • cancer symptom science
  • learning algorithms
  • cancer treatment

Cite this

Papachristou, N., Miaskowski, C., Barnaghi, P., Maguire, R., Farajidavar, N., Cooper, B., & Hu, X. (2016). Comparing machine learning clustering with latent class analysis on cancer symptoms' data. In Healthcare Innovation Point-Of-Care Technologies Conference (HI-POCT), 2016 IEEE (pp. 162-166). [16560390] Piscataway, NJ.: IEEE. https://doi.org/10.1109/HIC.2016.7797722
Papachristou, Nikolaos ; Miaskowski, Christine ; Barnaghi, Payam ; Maguire, Roma ; Farajidavar, Nazli ; Cooper, Bruce ; Hu, Xiao. / Comparing machine learning clustering with latent class analysis on cancer symptoms' data. Healthcare Innovation Point-Of-Care Technologies Conference (HI-POCT), 2016 IEEE. Piscataway, NJ. : IEEE, 2016. pp. 162-166
@inproceedings{9a847d24b11b4019b7f96e4f41d5cd35,
title = "Comparing machine learning clustering with latent class analysis on cancer symptoms' data",
abstract = "Symptom Cluster Research is a major topic in Cancer Symptom Science. In spite of the several statistical and clinical approaches in this domain, there is not a consensus on which method performs better. Identifying a generally accepted analytical method is important in order to be able to utilize and process all the available data. In this paper we report a secondary analysis on cancer symptom data, comparing the performance of five Machine Learning (ML) clustering algorithms in doing so. Based on how well they separate specific subsets of symptom measurements we select the best of them and proceed to compare its performance with the Latent Class Analysis (LCA) method. This analysis is a part of an ongoing study for identifying suitable Machine Learning algorithms to analyse and predict cancer symptoms in cancer treatment.",
keywords = "Symptom Cluster Research, machine learning, cancer symptom science, learning algorithms, cancer treatment",
author = "Nikolaos Papachristou and Christine Miaskowski and Payam Barnaghi and Roma Maguire and Nazli Farajidavar and Bruce Cooper and Xiao Hu",
note = "{\circledC} 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.",
year = "2016",
month = "11",
day = "9",
doi = "10.1109/HIC.2016.7797722",
language = "English",
isbn = "9781509011674",
pages = "162--166",
booktitle = "Healthcare Innovation Point-Of-Care Technologies Conference (HI-POCT), 2016 IEEE",
publisher = "IEEE",

}

Papachristou, N, Miaskowski, C, Barnaghi, P, Maguire, R, Farajidavar, N, Cooper, B & Hu, X 2016, Comparing machine learning clustering with latent class analysis on cancer symptoms' data. in Healthcare Innovation Point-Of-Care Technologies Conference (HI-POCT), 2016 IEEE., 16560390, IEEE, Piscataway, NJ., pp. 162-166. https://doi.org/10.1109/HIC.2016.7797722

Comparing machine learning clustering with latent class analysis on cancer symptoms' data. / Papachristou, Nikolaos; Miaskowski, Christine; Barnaghi, Payam; Maguire, Roma; Farajidavar, Nazli; Cooper, Bruce; Hu, Xiao.

Healthcare Innovation Point-Of-Care Technologies Conference (HI-POCT), 2016 IEEE. Piscataway, NJ. : IEEE, 2016. p. 162-166 16560390.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Comparing machine learning clustering with latent class analysis on cancer symptoms' data

AU - Papachristou, Nikolaos

AU - Miaskowski, Christine

AU - Barnaghi, Payam

AU - Maguire, Roma

AU - Farajidavar, Nazli

AU - Cooper, Bruce

AU - Hu, Xiao

N1 - © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2016/11/9

Y1 - 2016/11/9

N2 - Symptom Cluster Research is a major topic in Cancer Symptom Science. In spite of the several statistical and clinical approaches in this domain, there is not a consensus on which method performs better. Identifying a generally accepted analytical method is important in order to be able to utilize and process all the available data. In this paper we report a secondary analysis on cancer symptom data, comparing the performance of five Machine Learning (ML) clustering algorithms in doing so. Based on how well they separate specific subsets of symptom measurements we select the best of them and proceed to compare its performance with the Latent Class Analysis (LCA) method. This analysis is a part of an ongoing study for identifying suitable Machine Learning algorithms to analyse and predict cancer symptoms in cancer treatment.

AB - Symptom Cluster Research is a major topic in Cancer Symptom Science. In spite of the several statistical and clinical approaches in this domain, there is not a consensus on which method performs better. Identifying a generally accepted analytical method is important in order to be able to utilize and process all the available data. In this paper we report a secondary analysis on cancer symptom data, comparing the performance of five Machine Learning (ML) clustering algorithms in doing so. Based on how well they separate specific subsets of symptom measurements we select the best of them and proceed to compare its performance with the Latent Class Analysis (LCA) method. This analysis is a part of an ongoing study for identifying suitable Machine Learning algorithms to analyse and predict cancer symptoms in cancer treatment.

KW - Symptom Cluster Research

KW - machine learning

KW - cancer symptom science

KW - learning algorithms

KW - cancer treatment

U2 - 10.1109/HIC.2016.7797722

DO - 10.1109/HIC.2016.7797722

M3 - Conference contribution book

SN - 9781509011674

SP - 162

EP - 166

BT - Healthcare Innovation Point-Of-Care Technologies Conference (HI-POCT), 2016 IEEE

PB - IEEE

CY - Piscataway, NJ.

ER -

Papachristou N, Miaskowski C, Barnaghi P, Maguire R, Farajidavar N, Cooper B et al. Comparing machine learning clustering with latent class analysis on cancer symptoms' data. In Healthcare Innovation Point-Of-Care Technologies Conference (HI-POCT), 2016 IEEE. Piscataway, NJ.: IEEE. 2016. p. 162-166. 16560390 https://doi.org/10.1109/HIC.2016.7797722