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.
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.
Entities:
Keywords:
Electronic health record; algorithm; machine learning; obesity; phenotype
Authors: Lorenzo Moja; Koren H Kwag; Theodore Lytras; Lorenzo Bertizzolo; Linn Brandt; Valentina Pecoraro; Giulio Rigon; Alberto Vaona; Francesca Ruggiero; Massimo Mangia; Alfonso Iorio; Ilkka Kunnamo; Stefanos Bonovas Journal: Am J Public Health Date: 2014-10-16 Impact factor: 9.308
Authors: Katherine M Newton; Peggy L Peissig; Abel Ngo Kho; Suzette J Bielinski; Richard L Berg; Vidhu Choudhary; Melissa Basford; Christopher G Chute; Iftikhar J Kullo; Rongling Li; Jennifer A Pacheco; Luke V Rasmussen; Leslie Spangler; Joshua C Denny Journal: J Am Med Inform Assoc Date: 2013-03-26 Impact factor: 4.497
Authors: Elsie M Taveras; Richard Marshall; Ken P Kleinman; Matthew W Gillman; Karen Hacker; Christine M Horan; Renata L Smith; Sarah Price; Mona Sharifi; Sheryl L Rifas-Shiman; Steven R Simon Journal: JAMA Pediatr Date: 2015-06 Impact factor: 16.193
Authors: J C Lo; B Maring; M Chandra; S R Daniels; A Sinaiko; M F Daley; N E Sherwood; E O Kharbanda; E D Parker; K F Adams; R J Prineas; D J Magid; P J O'Connor; L C Greenspan Journal: Pediatr Obes Date: 2013-05-15 Impact factor: 4.000
Authors: Joan C Lo; Malini Chandra; Alan Sinaiko; Stephen R Daniels; Ronald J Prineas; Benjamin Maring; Emily D Parker; Nancy E Sherwood; Matthew F Daley; Elyse O Kharbanda; Kenneth F Adams; David J Magid; Patrick J O'Connor; Louise C Greenspan Journal: Int J Pediatr Endocrinol Date: 2014-03-03
Authors: Maria Caterina De Rosa; Alessandra Chesi; Shana McCormack; Justin Zhou; Benjamin Weaver; Molly McDonald; Sinead Christensen; Kalle Liimatta; Michael Rosenbaum; Hakon Hakonarson; Claudia A Doege; Struan F A Grant; Joel N Hirschhorn; Vidhu V Thaker Journal: J Clin Endocrinol Metab Date: 2019-07-01 Impact factor: 5.958
Authors: Tellen D Bennett; Tiffany J Callahan; James A Feinstein; Debashis Ghosh; Saquib A Lakhani; Michael C Spaeder; Stanley J Szefler; Michael G Kahn Journal: J Pediatr Date: 2019-01-25 Impact factor: 4.406
Authors: Amy Joseph; Charles Mullett; Christa Lilly; Matthew Armistead; Harold J Cox; Michael Denney; Misha Varma; David Rich; Donald A Adjeroh; Gianfranco Doretto; William Neal; Lee A Pyles Journal: Appl Clin Inform Date: 2021-01-06 Impact factor: 2.342
Authors: Cassandra C Brady; Vidhu V Thaker; Todd Lingren; Jessica G Woo; Stephanie S Kennebeck; Bahram Namjou-Khales; Ashton Roach; Jonathan P Bickel; Nandan Patibandla; Guergana K Savova; Imre Solti; Ingrid A Holm; John B Harley; Isaac S Kohane; Nancy A Crimmins Journal: Int J Pediatr Date: 2016-09-06