Advanced

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

Haghighi, Mona; Johnson, Suzanne Bennett LU ; Qian, Xiaoning; Lynch, Kristian F. LU ; Vehik, Kendra LU ; Huang, Shuai; Rewers, Marian; Barriga, Katherine; Baxter, Judith and Eisenbarth, George, et al. (2016) In Scientific Reports 6.
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... (More)

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.

(Less)
Please use this url to cite or link to this publication:
author
, et al. (More)
(Less)
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Scientific Reports
volume
6
publisher
Nature Publishing Group
external identifiers
  • scopus:84984691670
ISSN
2045-2322
DOI
10.1038/srep30828
language
English
LU publication?
yes
id
a2de59dd-9346-47ed-955f-c875e0383197
date added to LUP
2016-12-02 08:57:52
date last changed
2017-07-23 05:21:10
@article{a2de59dd-9346-47ed-955f-c875e0383197,
  abstract     = {<p>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.</p>},
  articleno    = {30828},
  author       = {Haghighi, Mona and Johnson, Suzanne Bennett and Qian, Xiaoning and Lynch, Kristian F. and Vehik, Kendra and Huang, Shuai and Rewers, Marian and Barriga, Katherine and Baxter, Judith and Eisenbarth, George and Frank, Nicole and Gesualdo, Patricia and Hoffman, Michelle and Norris, Jill and Ide, Lisa and Robinson, Jessie and Waugh, Kathleen and She, Jin Xiong and Schatz, Desmond and Hopkins, Diane and Steed, Leigh and Choate, Angela and Silvis, Katherine and Shankar, Meena and Huang, Yi Hua and Yang, Ping and Wang, Hong Jie and Leggett, Jessica and English, Kim and McIndoe, Richard and Dequesada, Angela and Haller, Michael and Anderson, Stephen W. and Ziegler, Anette G. and Boerschmann, Heike and Bonifacio, Ezio and Bunk, Melanie and Försch, Johannes and Henneberger, Lydia and Hummel, Michael and Hummel, Sandra and Joslowski, Gesa and Kersting, Mathilde and Knopff, Annette and Kocher, Nadja and Koletzko, Sibylle and Krause, Stephanie and Lauber, Claudia and Mollenhauer, Ulrike and Peplow, Claudia and Pflüger, Maren and Pöhlmann, Daniela and Ramminger, Claudia and Rash-Sur, Sargol and Roth, Roswith and Schenkel, Julia and Thümer, Leonore and Voit, Katja and Winkler, Christiane and Zwilling, Marina and Simell, Olli G. and Nanto-Salonen, Kirsti and Ilonen, Jorma and Knip, Mikael and Veijola, Riitta and Simell, Tuula and Hyöty, Heikki and Virtanen, Suvi M. and Kronberg-Kippilä, Carina and Torma, Maija and Simell, Barbara and Ruohonen, Eeva and Romo, Minna and Mantymaki, Elina and Schroderus, Heidi and Nyblom, Mia and Stenius, Aino and Lernmark, Åke and Agardh, Daniel and Almgren, Peter and Andersson, Eva and Andrén-Aronsson, Carin and Ask, Maria and Karlsson, Ulla Marie and Cilio, Corrado and Bremer, Jenny and Ericson-Hallström, Emilie and Gard, Thomas and Gerardsson, Joanna and Gustavsson, Ulrika and Hansson, Gertie and Hansen, Monica and Hyberg, Susanne and Håkansson, Rasmus and Ivarsson, Sten and Johansen, Fredrik and Larsson, Helena and Lernmark, Barbro and Markan, Maria and Massadakis, Theodosia and Melin, Jessica and Månsson-Martinez, Maria and Nilsson, Anita and Nilsson, Emma and Rahmati, Kobra and Rang, Sara and Järvirova, Monica Sedig and Sibthorpe, Sara and Sjöberg, Birgitta and Törn, Carina and Wallin, Anne and Wimar, Åsa and Hagopian, William A. and Yan, Xiang and Killian, Michael and Crouch, Claire Cowen and Hay, Kristen M. and Ayres, Stephen and Adams, Carissa and Bratrude, Brandi and Fowler, Greer and Franco, Czarina and Hammar, Carla and Heaney, Diana and Marcus, Patrick and Meyer, Arlene and Mulenga, Denise and Scott, Elizabeth and Skidmore, Jennifer and Small, Erin and Stabbert, Joshua and Stepitova, Viktoria and Becker, Dorothy and Franciscus, Margaret and Dalmagro-Elias Smith, Maryellen and Daftary, Ashi and Krischer, Jeffrey P. and Abbondondolo, Michael and Ballard, Lori and Brown, Rasheedah and Cuthbertson, David and Eberhard, Christopher and Gowda, Veena and Lee, Hye Seung and Liu, Shu and Malloy, Jamie and McCarthy, Cristina and McLeod, Wendy and Smith, Laura and Smith, Stephen and Smith, Susan and Uusitalo, Ulla and Yang, Jimin and Akolkar, Beena and Briese, Thomas and Erlich, Henry and Oberste, Steve},
  issn         = {2045-2322},
  language     = {eng},
  month        = {08},
  publisher    = {Nature Publishing Group},
  series       = {Scientific Reports},
  title        = {A Comparison of Rule-based Analysis with Regression Methods in Understanding the Risk Factors for Study Withdrawal in a Pediatric Study},
  url          = {http://dx.doi.org/10.1038/srep30828},
  volume       = {6},
  year         = {2016},
}