Predicting and explaining inflammation in Crohn’s disease patients using predictive analytics methods and electronic medical record data

Bhargava K. Reddy, Dursun Delen, Rupesh K. Agrawal

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Crohn’s disease is among the chronic inflammatory bowel diseases that impact the gastrointestinal tract. Understanding and predicting the severity of inflammation in real-time settings is critical to disease management. Extant literature has primarily focused on studies that are conducted in clinical trial settings to investigate the impact of a drug treatment on the remission status of the disease. This research proposes an analytics methodology where three different types of prediction models are developed to predict and to explain the severity of inflammation in patients diagnosed with Crohn’s disease. The results show that machine-learning-based analytic methods such as gradient boosting machines can predict the inflammation severity with a very high accuracy (area under the curve = 92.82%), followed by regularized regression and logistic regression. According to the findings, a combination of baseline laboratory parameters, patient demographic characteristics, and disease location are among the strongest predictors of inflammation severity in Crohn’s disease patients.

Original languageEnglish
Pages (from-to)1201-1218
Number of pages18
JournalHealth Informatics Journal
Volume25
Issue number4
DOIs
StatePublished - 1 Dec 2019
Externally publishedYes

Fingerprint

Electronic Health Records
Crohn Disease
Inflammation
Disease Management
Inflammatory Bowel Diseases
Area Under Curve
Gastrointestinal Tract
Logistic Models
Demography
Clinical Trials
Research
Pharmaceutical Preparations
Therapeutics

Keywords

  • C-reactive protein
  • Crohn’s disease
  • data mining
  • electronic medical records
  • gradient boosting machine
  • logistic regression
  • machine learning
  • predictive analytics
  • regularized regression

Cite this

@article{2d7d6dd3f8254b8b8b2740409e58f97f,
title = "Predicting and explaining inflammation in Crohn’s disease patients using predictive analytics methods and electronic medical record data",
abstract = "Crohn’s disease is among the chronic inflammatory bowel diseases that impact the gastrointestinal tract. Understanding and predicting the severity of inflammation in real-time settings is critical to disease management. Extant literature has primarily focused on studies that are conducted in clinical trial settings to investigate the impact of a drug treatment on the remission status of the disease. This research proposes an analytics methodology where three different types of prediction models are developed to predict and to explain the severity of inflammation in patients diagnosed with Crohn’s disease. The results show that machine-learning-based analytic methods such as gradient boosting machines can predict the inflammation severity with a very high accuracy (area under the curve = 92.82{\%}), followed by regularized regression and logistic regression. According to the findings, a combination of baseline laboratory parameters, patient demographic characteristics, and disease location are among the strongest predictors of inflammation severity in Crohn’s disease patients.",
keywords = "C-reactive protein, Crohn’s disease, data mining, electronic medical records, gradient boosting machine, logistic regression, machine learning, predictive analytics, regularized regression",
author = "Reddy, {Bhargava K.} and Dursun Delen and Agrawal, {Rupesh K.}",
year = "2019",
month = "12",
day = "1",
doi = "10.1177/1460458217751015",
language = "English",
volume = "25",
pages = "1201--1218",
journal = "Health Informatics Journal",
issn = "1460-4582",
publisher = "SAGE Publications Ltd",
number = "4",

}

Predicting and explaining inflammation in Crohn’s disease patients using predictive analytics methods and electronic medical record data. / Reddy, Bhargava K.; Delen, Dursun; Agrawal, Rupesh K.

In: Health Informatics Journal, Vol. 25, No. 4, 01.12.2019, p. 1201-1218.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Predicting and explaining inflammation in Crohn’s disease patients using predictive analytics methods and electronic medical record data

AU - Reddy, Bhargava K.

AU - Delen, Dursun

AU - Agrawal, Rupesh K.

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Crohn’s disease is among the chronic inflammatory bowel diseases that impact the gastrointestinal tract. Understanding and predicting the severity of inflammation in real-time settings is critical to disease management. Extant literature has primarily focused on studies that are conducted in clinical trial settings to investigate the impact of a drug treatment on the remission status of the disease. This research proposes an analytics methodology where three different types of prediction models are developed to predict and to explain the severity of inflammation in patients diagnosed with Crohn’s disease. The results show that machine-learning-based analytic methods such as gradient boosting machines can predict the inflammation severity with a very high accuracy (area under the curve = 92.82%), followed by regularized regression and logistic regression. According to the findings, a combination of baseline laboratory parameters, patient demographic characteristics, and disease location are among the strongest predictors of inflammation severity in Crohn’s disease patients.

AB - Crohn’s disease is among the chronic inflammatory bowel diseases that impact the gastrointestinal tract. Understanding and predicting the severity of inflammation in real-time settings is critical to disease management. Extant literature has primarily focused on studies that are conducted in clinical trial settings to investigate the impact of a drug treatment on the remission status of the disease. This research proposes an analytics methodology where three different types of prediction models are developed to predict and to explain the severity of inflammation in patients diagnosed with Crohn’s disease. The results show that machine-learning-based analytic methods such as gradient boosting machines can predict the inflammation severity with a very high accuracy (area under the curve = 92.82%), followed by regularized regression and logistic regression. According to the findings, a combination of baseline laboratory parameters, patient demographic characteristics, and disease location are among the strongest predictors of inflammation severity in Crohn’s disease patients.

KW - C-reactive protein

KW - Crohn’s disease

KW - data mining

KW - electronic medical records

KW - gradient boosting machine

KW - logistic regression

KW - machine learning

KW - predictive analytics

KW - regularized regression

UR - http://www.scopus.com/inward/record.url?scp=85072514148&partnerID=8YFLogxK

U2 - 10.1177/1460458217751015

DO - 10.1177/1460458217751015

M3 - Article

C2 - 29320910

AN - SCOPUS:85072514148

VL - 25

SP - 1201

EP - 1218

JO - Health Informatics Journal

JF - Health Informatics Journal

SN - 1460-4582

IS - 4

ER -