Jiaxi Yang1, Dongqing Wang2, Anne Marie Darling2, Enju Liu3, Nandita Perumal2, Wafaie W Fawzi1,2,4, Molin Wang5,6,7. 1. Department of Epidemiology, Harvard T.H. Chan School of Public Health, 677 Huntington Ave, Boston, MA, 02215, USA. 2. Department of Global Health and Population, Harvard T.H. Chan School of Public Health, Boston, MA, USA. 3. Institutional Centers for Clinical and Translational Research, Boston Children's Hospital, Boston, MA, USA. 4. Department of Nutrition, Harvard T. H. Chan School of Public Health, Boston, MA, USA. 5. Department of Epidemiology, Harvard T.H. Chan School of Public Health, 677 Huntington Ave, Boston, MA, 02215, USA. stmow@channing.harvard.edu. 6. Department of Biostatistics, Harvard T.H. Chan School of Public Health, 677 Huntington Ave, Boston, MA, 02215, USA. stmow@channing.harvard.edu. 7. Channing Division of Network Medicine, Harvard Medical School and Brigham and Women's Hosptial, Boston, MA, USA. stmow@channing.harvard.edu.
Abstract
BACKGROUND: Early pregnancy weights are needed to quantify gestational weight gain accurately. Different methods have been used in previous studies to impute early-pregnancy weights. However, no studies have systematically compared imputed weight accuracy across different imputation techniques. This study aimed to compare four methodological approaches to imputing early-pregnancy weight, using repeated measures of pregnancy weights collected from two pregnancy cohorts in Tanzania. METHODS: The mean gestational ages at enrollment were 17.8 weeks for Study I and 10.0 weeks for Study II. Given the gestational age distributions at enrollment, early-pregnancy weights were extrapolated for Study I and interpolated for Study II. The four imputation approaches included: (i) simple imputation based on the nearest measure, (ii) simple arithmetic imputation based on the nearest two measures, (iii) mixed-effects models, and (iv) marginal models with generalized estimating equations. For the mixed-effects model and the marginal model with generalized estimating equation methods, imputation accuracy was further compared across varying degrees of model flexibility by fitting splines and polynomial terms. Additional analyses included dropping third-trimester weights, adding covariate to the models, and log-transforming weight before imputation. Mean absolute error was used to quantify imputation accuracy. RESULTS: Study I included 1472 women with 6272 weight measures; Study II included 2131 individuals with 11,775 weight measures. Among the four imputation approaches, mixed-effects models had the highest accuracy (smallest mean absolute error: 1.99 kg and 1.60 kg for Studies I and II, respectively), while the other three approaches showed similar degrees of accuracy. Depending on the underlying data structure, allowing appropriate degree of model flexibility and dropping remote pregnancy weight measures may further improve the imputation performance. CONCLUSIONS: Mixed-effects models had superior performance in imputing early-pregnancy weight compared to other commonly used strategies.
BACKGROUND: Early pregnancy weights are needed to quantify gestational weight gain accurately. Different methods have been used in previous studies to impute early-pregnancy weights. However, no studies have systematically compared imputed weight accuracy across different imputation techniques. This study aimed to compare four methodological approaches to imputing early-pregnancy weight, using repeated measures of pregnancy weights collected from two pregnancy cohorts in Tanzania. METHODS: The mean gestational ages at enrollment were 17.8 weeks for Study I and 10.0 weeks for Study II. Given the gestational age distributions at enrollment, early-pregnancy weights were extrapolated for Study I and interpolated for Study II. The four imputation approaches included: (i) simple imputation based on the nearest measure, (ii) simple arithmetic imputation based on the nearest two measures, (iii) mixed-effects models, and (iv) marginal models with generalized estimating equations. For the mixed-effects model and the marginal model with generalized estimating equation methods, imputation accuracy was further compared across varying degrees of model flexibility by fitting splines and polynomial terms. Additional analyses included dropping third-trimester weights, adding covariate to the models, and log-transforming weight before imputation. Mean absolute error was used to quantify imputation accuracy. RESULTS: Study I included 1472 women with 6272 weight measures; Study II included 2131 individuals with 11,775 weight measures. Among the four imputation approaches, mixed-effects models had the highest accuracy (smallest mean absolute error: 1.99 kg and 1.60 kg for Studies I and II, respectively), while the other three approaches showed similar degrees of accuracy. Depending on the underlying data structure, allowing appropriate degree of model flexibility and dropping remote pregnancy weight measures may further improve the imputation performance. CONCLUSIONS: Mixed-effects models had superior performance in imputing early-pregnancy weight compared to other commonly used strategies.
Entities:
Keywords:
Africa; Epidemiologic methods; Gestational weight; Pregnancy; Statistical model; Tanzania
Authors: Jessica R Walter; Wei Perng; Ken P Kleinman; Sheryl L Rifas-Shiman; Janet W Rich-Edwards; Emily Oken Journal: Am J Obstet Gynecol Date: 2014-11-13 Impact factor: 8.661
Authors: Anne Marie Darling; Ferdinand M Mugusi; Analee J Etheredge; Nilupa S Gunaratna; Ajibola Ibraheem Abioye; Said Aboud; Christopher Duggan; Robert Mongi; Donna Spiegelman; Drucilla Roberts; Davidson H Hamer; Kevin C Kain; Wafaie W Fawzi Journal: Am J Trop Med Hyg Date: 2017-01-23 Impact factor: 2.345
Authors: Lisa Chasan-Taber; Michael D Schmidt; Penelope Pekow; Barbara Sternfeld; Caren G Solomon; Glenn Markenson Journal: Obesity (Silver Spring) Date: 2008-05-01 Impact factor: 5.002
Authors: Analee J Etheredge; Zul Premji; Nilupa S Gunaratna; Ajibola Ibraheem Abioye; Said Aboud; Christopher Duggan; Robert Mongi; Laura Meloney; Donna Spiegelman; Drucilla Roberts; Davidson H Hamer; Wafaie W Fawzi Journal: JAMA Pediatr Date: 2015-10 Impact factor: 16.193
Authors: Jonathan A C Sterne; Ian R White; John B Carlin; Michael Spratt; Patrick Royston; Michael G Kenward; Angela M Wood; James R Carpenter Journal: BMJ Date: 2009-06-29
Authors: Leila Cheikh Ismail; Deborah C Bishop; Ruyan Pang; Eric O Ohuma; Gilberto Kac; Barbara Abrams; Kathleen Rasmussen; Fernando C Barros; Jane E Hirst; Ann Lambert; Aris T Papageorghiou; William Stones; Yasmin A Jaffer; Douglas G Altman; J Alison Noble; Maria Rosa Giolito; Michael G Gravett; Manorama Purwar; Stephen H Kennedy; Zulfiqar A Bhutta; José Villar Journal: BMJ Date: 2016-02-29
Authors: Nicola L Hawley; William Johnson; Chantelle N Hart; Elizabeth W Triche; John Ah Ching; Bethel Muasau-Howard; Stephen T McGarvey Journal: BMC Pregnancy Childbirth Date: 2015-02-03 Impact factor: 3.007
Authors: Jiaxi Yang; Molin Wang; Deirdre K Tobias; Janet W Rich-Edwards; Anne Marie Darling; Ajibola I Abioye; Andrea B Pembe; Isabel Madzorera; Wafaie W Fawzi Journal: Reprod Health Date: 2022-06-16 Impact factor: 3.355
Authors: Dongqing Wang; Anne Marie Darling; Chloe R McDonald; Nandita Perumal; Enju Liu; Molin Wang; Said Aboud; Willy Urassa; Andrea L Conroy; Kyla T Hayford; W Conrad Liles; Kevin C Kain; Wafaie W Fawzi Journal: BMC Pregnancy Childbirth Date: 2021-10-06 Impact factor: 3.007