Predicting overall survivability in comorbidity of cancers: A data mining approach

Hamed Majidi Zolbanin, Dursun Delen, Amir Hassan Zadeh

Research output: Contribution to journalArticle

38 Citations (Scopus)

Abstract

Cancer and other chronic diseases have constituted (and will do so at an increasing pace) a significant portion of healthcare costs in the United States in recent years. Although prior research has shown that diagnostic and treatment recommendations might be altered based on the severity of comorbidities, chronic diseases are still being investigated in isolation from one another in most cases. To illustrate the significance of concurrent chronic diseases in the course of treatment, this study uses SEER's cancer data to create two comorbid data sets: one for breast and female genital cancers and another for prostate and urinal cancers. Several popular machine learning techniques are then applied to the resultant data sets to build predictive models. Comparison of the results shows that having more information about comorbid conditions of patients can improve models' predictive power, which in turn, can help practitioners make better diagnostic and treatment decisions. Therefore, proper identification, recording, and use of patients' comorbidity status can potentially lower treatment costs and ease the healthcare related economic challenges.

Original languageEnglish
Pages (from-to)150-161
Number of pages12
JournalDecision Support Systems
Volume74
DOIs
StatePublished - 19 Apr 2015
Externally publishedYes

Fingerprint

Data Mining
Data mining
Comorbidity
Chronic Disease
Health Care Costs
Prostatic Neoplasms
Neoplasms
Learning systems
Costs
Breast
Therapeutics
Economics
Delivery of Health Care
Research
Cancer
Survivability
Chronic disease
Datasets
Diagnostics
Healthcare

Keywords

  • Comorbidity
  • Concomitant diseases
  • Concurrent diseases
  • Medical decision making
  • Predictive modeling
  • Random forest

Cite this

Zolbanin, Hamed Majidi ; Delen, Dursun ; Hassan Zadeh, Amir. / Predicting overall survivability in comorbidity of cancers : A data mining approach. In: Decision Support Systems. 2015 ; Vol. 74. pp. 150-161.
@article{86232af4209e4f478c24d19758eccb20,
title = "Predicting overall survivability in comorbidity of cancers: A data mining approach",
abstract = "Cancer and other chronic diseases have constituted (and will do so at an increasing pace) a significant portion of healthcare costs in the United States in recent years. Although prior research has shown that diagnostic and treatment recommendations might be altered based on the severity of comorbidities, chronic diseases are still being investigated in isolation from one another in most cases. To illustrate the significance of concurrent chronic diseases in the course of treatment, this study uses SEER's cancer data to create two comorbid data sets: one for breast and female genital cancers and another for prostate and urinal cancers. Several popular machine learning techniques are then applied to the resultant data sets to build predictive models. Comparison of the results shows that having more information about comorbid conditions of patients can improve models' predictive power, which in turn, can help practitioners make better diagnostic and treatment decisions. Therefore, proper identification, recording, and use of patients' comorbidity status can potentially lower treatment costs and ease the healthcare related economic challenges.",
keywords = "Comorbidity, Concomitant diseases, Concurrent diseases, Medical decision making, Predictive modeling, Random forest",
author = "Zolbanin, {Hamed Majidi} and Dursun Delen and {Hassan Zadeh}, Amir",
year = "2015",
month = "4",
day = "19",
doi = "10.1016/j.dss.2015.04.003",
language = "English",
volume = "74",
pages = "150--161",
journal = "Decision Support Systems",
issn = "0167-9236",
publisher = "Elsevier",

}

Predicting overall survivability in comorbidity of cancers : A data mining approach. / Zolbanin, Hamed Majidi; Delen, Dursun; Hassan Zadeh, Amir.

In: Decision Support Systems, Vol. 74, 19.04.2015, p. 150-161.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Predicting overall survivability in comorbidity of cancers

T2 - A data mining approach

AU - Zolbanin, Hamed Majidi

AU - Delen, Dursun

AU - Hassan Zadeh, Amir

PY - 2015/4/19

Y1 - 2015/4/19

N2 - Cancer and other chronic diseases have constituted (and will do so at an increasing pace) a significant portion of healthcare costs in the United States in recent years. Although prior research has shown that diagnostic and treatment recommendations might be altered based on the severity of comorbidities, chronic diseases are still being investigated in isolation from one another in most cases. To illustrate the significance of concurrent chronic diseases in the course of treatment, this study uses SEER's cancer data to create two comorbid data sets: one for breast and female genital cancers and another for prostate and urinal cancers. Several popular machine learning techniques are then applied to the resultant data sets to build predictive models. Comparison of the results shows that having more information about comorbid conditions of patients can improve models' predictive power, which in turn, can help practitioners make better diagnostic and treatment decisions. Therefore, proper identification, recording, and use of patients' comorbidity status can potentially lower treatment costs and ease the healthcare related economic challenges.

AB - Cancer and other chronic diseases have constituted (and will do so at an increasing pace) a significant portion of healthcare costs in the United States in recent years. Although prior research has shown that diagnostic and treatment recommendations might be altered based on the severity of comorbidities, chronic diseases are still being investigated in isolation from one another in most cases. To illustrate the significance of concurrent chronic diseases in the course of treatment, this study uses SEER's cancer data to create two comorbid data sets: one for breast and female genital cancers and another for prostate and urinal cancers. Several popular machine learning techniques are then applied to the resultant data sets to build predictive models. Comparison of the results shows that having more information about comorbid conditions of patients can improve models' predictive power, which in turn, can help practitioners make better diagnostic and treatment decisions. Therefore, proper identification, recording, and use of patients' comorbidity status can potentially lower treatment costs and ease the healthcare related economic challenges.

KW - Comorbidity

KW - Concomitant diseases

KW - Concurrent diseases

KW - Medical decision making

KW - Predictive modeling

KW - Random forest

UR - http://www.scopus.com/inward/record.url?scp=84928949248&partnerID=8YFLogxK

U2 - 10.1016/j.dss.2015.04.003

DO - 10.1016/j.dss.2015.04.003

M3 - Article

AN - SCOPUS:84928949248

VL - 74

SP - 150

EP - 161

JO - Decision Support Systems

JF - Decision Support Systems

SN - 0167-9236

ER -