A Comparison of Rule-based Analysis with Regression Methods in Understanding the Risk Factors for Study Withdrawal in a Pediatric Study

TEDDY study group

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Regression models are extensively used in many epidemiological studies to understand the linkage between specific outcomes of interest and their risk factors. However, regression models in general examine the average effects of the risk factors and ignore subgroups with different risk profiles. As a result, interventions are often geared towards the average member of the population, without consideration of the special health needs of different subgroups within the population. This paper demonstrates the value of using rule-based analysis methods that can identify subgroups with heterogeneous risk profiles in a population without imposing assumptions on the subgroups or method. The rules define the risk pattern of subsets of individuals by not only considering the interactions between the risk factors but also their ranges. We compared the rule-based analysis results with the results from a logistic regression model in The Environmental Determinants of Diabetes in the Young (TEDDY) study. Both methods detected a similar suite of risk factors, but the rule-based analysis was superior at detecting multiple interactions between the risk factors that characterize the subgroups. A further investigation of the particular characteristics of each subgroup may detect the special health needs of the subgroup and lead to tailored interventions.

Original languageEnglish (US)
Article number30828
JournalScientific Reports
Volume6
DOIs
StatePublished - Aug 26 2016

Fingerprint

Regression Analysis
Pediatrics
Logistic Models
Population
Health
Epidemiologic Studies

ASJC Scopus subject areas

  • General

Cite this

A Comparison of Rule-based Analysis with Regression Methods in Understanding the Risk Factors for Study Withdrawal in a Pediatric Study. / TEDDY study group.

In: Scientific Reports, Vol. 6, 30828, 26.08.2016.

Research output: Contribution to journalArticle

@article{157b32a470f74bf3afa506d083997f97,
title = "A Comparison of Rule-based Analysis with Regression Methods in Understanding the Risk Factors for Study Withdrawal in a Pediatric Study",
abstract = "Regression models are extensively used in many epidemiological studies to understand the linkage between specific outcomes of interest and their risk factors. However, regression models in general examine the average effects of the risk factors and ignore subgroups with different risk profiles. As a result, interventions are often geared towards the average member of the population, without consideration of the special health needs of different subgroups within the population. This paper demonstrates the value of using rule-based analysis methods that can identify subgroups with heterogeneous risk profiles in a population without imposing assumptions on the subgroups or method. The rules define the risk pattern of subsets of individuals by not only considering the interactions between the risk factors but also their ranges. We compared the rule-based analysis results with the results from a logistic regression model in The Environmental Determinants of Diabetes in the Young (TEDDY) study. Both methods detected a similar suite of risk factors, but the rule-based analysis was superior at detecting multiple interactions between the risk factors that characterize the subgroups. A further investigation of the particular characteristics of each subgroup may detect the special health needs of the subgroup and lead to tailored interventions.",
author = "{TEDDY study group} and Mona Haghighi and Johnson, {Suzanne Bennett} and Xiaoning Qian and Lynch, {Kristian F.} and Kendra Vehik and Shuai Huang and Marian Rewers and Katherine Barriga and Judith Baxter and George Eisenbarth and Nicole Frank and Patricia Gesualdo and Michelle Hoffman and Jill Norris and Lisa Ide and Jessie Robinson and Kathleen Waugh and She, {Jin Xiong} and Desmond Schatz and Jin-Xiong She and Leigh Steed and Angela Choate and Katherine Silvis and Meena Shankar and Huang, {Yi Hua} and Ping Yang and Wang, {Hong Jie} and Jessica Leggett and Kim English and Richard McIndoe and Angela Dequesada and McIndoe, {Richard A} and Anderson, {Stephen W.} and Ziegler, {Anette G.} and Heike Boerschmann and Ezio Bonifacio and Melanie Bunk and Johannes F{\"o}rsch and Lydia Henneberger and Michael Hummel and Sandra Hummel and Gesa Joslowski and Mathilde Kersting and Annette Knopff and Nadja Kocher and Sibylle Koletzko and Stephanie Krause and Claudia Lauber and Ulrike Mollenhauer and Claudia Peplow",
year = "2016",
month = "8",
day = "26",
doi = "10.1038/srep30828",
language = "English (US)",
volume = "6",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",

}

TY - JOUR

T1 - A Comparison of Rule-based Analysis with Regression Methods in Understanding the Risk Factors for Study Withdrawal in a Pediatric Study

AU - TEDDY study group

AU - Haghighi, Mona

AU - Johnson, Suzanne Bennett

AU - Qian, Xiaoning

AU - Lynch, Kristian F.

AU - Vehik, Kendra

AU - Huang, Shuai

AU - Rewers, Marian

AU - Barriga, Katherine

AU - Baxter, Judith

AU - Eisenbarth, George

AU - Frank, Nicole

AU - Gesualdo, Patricia

AU - Hoffman, Michelle

AU - Norris, Jill

AU - Ide, Lisa

AU - Robinson, Jessie

AU - Waugh, Kathleen

AU - She, Jin Xiong

AU - Schatz, Desmond

AU - She, Jin-Xiong

AU - Steed, Leigh

AU - Choate, Angela

AU - Silvis, Katherine

AU - Shankar, Meena

AU - Huang, Yi Hua

AU - Yang, Ping

AU - Wang, Hong Jie

AU - Leggett, Jessica

AU - English, Kim

AU - McIndoe, Richard

AU - Dequesada, Angela

AU - McIndoe, Richard A

AU - Anderson, Stephen W.

AU - Ziegler, Anette G.

AU - Boerschmann, Heike

AU - Bonifacio, Ezio

AU - Bunk, Melanie

AU - Försch, Johannes

AU - Henneberger, Lydia

AU - Hummel, Michael

AU - Hummel, Sandra

AU - Joslowski, Gesa

AU - Kersting, Mathilde

AU - Knopff, Annette

AU - Kocher, Nadja

AU - Koletzko, Sibylle

AU - Krause, Stephanie

AU - Lauber, Claudia

AU - Mollenhauer, Ulrike

AU - Peplow, Claudia

PY - 2016/8/26

Y1 - 2016/8/26

N2 - Regression models are extensively used in many epidemiological studies to understand the linkage between specific outcomes of interest and their risk factors. However, regression models in general examine the average effects of the risk factors and ignore subgroups with different risk profiles. As a result, interventions are often geared towards the average member of the population, without consideration of the special health needs of different subgroups within the population. This paper demonstrates the value of using rule-based analysis methods that can identify subgroups with heterogeneous risk profiles in a population without imposing assumptions on the subgroups or method. The rules define the risk pattern of subsets of individuals by not only considering the interactions between the risk factors but also their ranges. We compared the rule-based analysis results with the results from a logistic regression model in The Environmental Determinants of Diabetes in the Young (TEDDY) study. Both methods detected a similar suite of risk factors, but the rule-based analysis was superior at detecting multiple interactions between the risk factors that characterize the subgroups. A further investigation of the particular characteristics of each subgroup may detect the special health needs of the subgroup and lead to tailored interventions.

AB - Regression models are extensively used in many epidemiological studies to understand the linkage between specific outcomes of interest and their risk factors. However, regression models in general examine the average effects of the risk factors and ignore subgroups with different risk profiles. As a result, interventions are often geared towards the average member of the population, without consideration of the special health needs of different subgroups within the population. This paper demonstrates the value of using rule-based analysis methods that can identify subgroups with heterogeneous risk profiles in a population without imposing assumptions on the subgroups or method. The rules define the risk pattern of subsets of individuals by not only considering the interactions between the risk factors but also their ranges. We compared the rule-based analysis results with the results from a logistic regression model in The Environmental Determinants of Diabetes in the Young (TEDDY) study. Both methods detected a similar suite of risk factors, but the rule-based analysis was superior at detecting multiple interactions between the risk factors that characterize the subgroups. A further investigation of the particular characteristics of each subgroup may detect the special health needs of the subgroup and lead to tailored interventions.

UR - http://www.scopus.com/inward/record.url?scp=84984691670&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84984691670&partnerID=8YFLogxK

U2 - 10.1038/srep30828

DO - 10.1038/srep30828

M3 - Article

C2 - 27561809

AN - SCOPUS:84984691670

VL - 6

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

M1 - 30828

ER -