Appl Clin Inform 2016; 07(03): 693-706
DOI: 10.4338/ACI-2016-01-RA-0015
Research Article
Schattauer GmbH

Developing an Algorithm to Detect Early Childhood Obesity in Two Tertiary Pediatric Medical Centers

Todd Lingren*
1  Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA
,
Vidhu Thaker*
2  Boston Children’s Hospital, Boston, MA, USA
,
Cassandra Brady
1  Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA
3  Vanderbilt University Medical Center, Nashville, TN, USA
,
Bahram Namjou
1  Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA
,
Stephanie Kennebeck
1  Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA
,
Jonathan Bickel
2  Boston Children’s Hospital, Boston, MA, USA
,
Nandan Patibandla
2  Boston Children’s Hospital, Boston, MA, USA
,
Yizhao Ni
1  Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA
,
Sara L. Van Driest
3  Vanderbilt University Medical Center, Nashville, TN, USA
,
Lixin Chen
3  Vanderbilt University Medical Center, Nashville, TN, USA
,
Ashton Roach
1  Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA
,
Beth Cobb
1  Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA
,
Jacqueline Kirby
3  Vanderbilt University Medical Center, Nashville, TN, USA
,
Josh Denny
3  Vanderbilt University Medical Center, Nashville, TN, USA
,
Lisa Bailey-Davis
4  Obesity Institute, Geisinger Health System, Danville, PA, USA
,
Marc S. Williams
5  Genomic Medicine Institute, Geisinger Health System, Danville, PA, USA
,
Keith Marsolo
1  Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA
,
Imre Solti
1  Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA
,
Ingrid A. Holm
2  Boston Children’s Hospital, Boston, MA, USA
,
John Harley
1  Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA
,
Isaac S. Kohane
2  Boston Children’s Hospital, Boston, MA, USA
,
Guergana Savova
2  Boston Children’s Hospital, Boston, MA, USA
,
Nancy Crimmins
1  Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA
› Author Affiliations
Funding All phases of this study were supported by United States National Institutes of Health (U1 1U01HG006828–01) as part of the Electronic Medical Record and Genomics project (eMERGE), NIH-NIDDK grant T32DK007699, K12DK094721 and Nutrition and Obesity Research Center at Harvard (P30-DK040561), as well as institutional funding from CCHMC, BCH, Vanderbilt University, Children’s Hospital of Philadelphia and Geisinger Health System.
Further Information

Publication History

received: 03 March 2016

accepted: 15 June 2016

Publication Date:
19 December 2017 (online)

Summary

Objective

The objective of this study is to develop an algorithm to accurately identify children with severe early onset childhood obesity (ages 1–5.99 years) using structured and unstructured data from the electronic health record (EHR).

Introduction

Childhood obesity increases risk factors for cardiovascular morbidity and vascular disease. Accurate definition of a high precision phenotype through a standardize tool is critical to the success of large-scale genomic studies and validating rare monogenic variants causing severe early onset obesity.

Data and Methods

Rule based and machine learning based algorithms were developed using structured and unstructured data from two EHR databases from Boston Children’s Hospital (BCH) and Cincinnati Children’s Hospital and Medical Center (CCHMC). Exclusion criteria including medications or comorbid diagnoses were defined. Machine learning algorithms were developed using cross-site training and testing in addition to experimenting with natural language processing features.

Results

Precision was emphasized for a high fidelity cohort. The rule-based algorithm performed the best overall, 0.895 (CCHMC) and 0.770 (BCH). The best feature set for machine learning employed Unified Medical Language System (UMLS) concept unique identifiers (CUIs), ICD-9 codes, and RxNorm codes.

Conclusions

Detecting severe early childhood obesity is essential for the intervention potential in children at the highest long-term risk of developing comorbidities related to obesity and excluding patients with underlying pathological and non-syndromic causes of obesity assists in developing a high-precision cohort for genetic study. Further such phenotyping efforts inform future practical application in health care environments utilizing clinical decision support.

Citation: Lingren T, Thaker V, Brady C, Namjou B, Kennebeck S, Bickel J, Patibandla N, Ni Y, Van Driest SL, Chen L, Roach A, Cobb B, Kirby J, Denny J, Bailey-Davis L, Williams MS, Marsolo K, Solti I, Holm IA, Harley J, Kohane IS, Savova G, Crimmins N. Developing an algorithm to detect early childhood obesity in two tertiary pediatric medical centers.

* Equal contribution