1
|
Agogo GO, Verani JR, Otieno NA, Nyawanda BO, Widdowson MA, Chaves SS. Correcting for measurement error in assessing gestational age in a low-resource setting: a regression calibration approach. Front Med (Lausanne) 2023; 10:1222772. [PMID: 37901408 PMCID: PMC10613090 DOI: 10.3389/fmed.2023.1222772] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/17/2023] [Accepted: 09/25/2023] [Indexed: 10/31/2023] Open
Abstract
Introduction Measurement error in gestational age (GA) may bias the association of GA with a health outcome. Ultrasound-based GA is considered the gold standard and is not readily available in low-resource settings. We corrected for measurement error in GA based on fundal height (FH) and date of last menstrual period (LMP) using ultrasound from the sub-cohort and adjusted for the bias in associating GA with neonatal mortality and low birth weight (< 2,500 grams, LBW). Methods We used data collected from 01/2015 to 09/2019 from pregnant women enrolled at two public hospitals in Siaya county, Kenya (N = 2,750). We used regression calibration to correct for measurement error in FH- and LMP-based GA accounting for maternal and child characteristics. We applied logistic regression to associate GA with neonatal mortality and low birth weight, with and without calibrating FH- and LMP-based GA. Results Calibration improved the precision of LMP (correlation coefficient, ρ from 0.48 to 0.57) and FH-based GA (ρ from 0.82 to 0.83). Calibrating FH/LMP-based GA eliminated the bias in the mean GA estimates. The log odds ratio that quantifies the association of GA with neonatal mortality increased by 29% (from -0.159 to -0.205) by calibrating FH-based GA and by more than twofold (from -0.158 to -0.471) by calibrating LMP-based GA. Conclusion Calibrating FH/LMP-based GA improved the accuracy and precision of GA estimates and strengthened the association of GA with neonatal mortality/LBW. When assessing GA, neonatal public health and clinical interventions may benefit from calibration modeling in settings where ultrasound may not be fully available.
Collapse
Affiliation(s)
- George O. Agogo
- Division of Global Health Protection, US Centers for Disease Control and Prevention, Nairobi, Kenya
| | - Jennifer R. Verani
- Division of Global Health Protection, US Centers for Disease Control and Prevention, Nairobi, Kenya
| | - Nancy A. Otieno
- Centre for Global Health Research, Kenya Medical Research Institute, Nairobi, Kenya
| | - Bryan O. Nyawanda
- Centre for Global Health Research, Kenya Medical Research Institute, Nairobi, Kenya
| | - Marc-Alain Widdowson
- Division of Global Health Protection, US Centers for Disease Control and Prevention, Nairobi, Kenya
- Institute of Tropical Medicine, Antwerp, Belgium
| | - Sandra S. Chaves
- Influenza Program, US Centers for Disease Control and Prevention, Nairobi, Kenya
| |
Collapse
|
2
|
Popoola AA, Frediani JK, Hartman TJ, Paynabar K. Mitigating underreported error in food frequency questionnaire data using a supervised machine learning method and error adjustment algorithm. BMC Med Inform Decis Mak 2023; 23:178. [PMID: 37689645 PMCID: PMC10492312 DOI: 10.1186/s12911-023-02262-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/30/2022] [Accepted: 08/08/2023] [Indexed: 09/11/2023] Open
Abstract
BACKGROUND Food frequency questionnaires (FFQs) are one of the most useful tools for studying and understanding diet-disease relationships. However, because FFQs are self-reported data, they are susceptible to response bias, social desirability bias, and misclassification. Currently, several methods have been created to combat these issues by modelling the measurement error in diet-disease relationships. METHOD In this paper, a novel machine learning method is proposed to adjust for measurement error found in misreported data by using a random forest (RF) classifier to label the responses in the FFQ based on the input dataset and creating an algorithm that adjusts the measurement error. We demonstrate this method by addressing underreporting in selected FFQ responses. RESULT According to the results, we have high model accuracies ranging from 78% to 92% in participant collected data and 88% in simulated data. CONCLUSION This shows that our proposed method of using a RF classifier and an error adjustment algorithm is efficient to correct most of the underreported entries in the FFQ dataset and could be used independent of diet-disease models. This could help nutrition researchers and other experts to use dietary data estimated by FFQs with less measurement error and create models from the data with minimal noise.
Collapse
|
3
|
Agogo GO, Muchene L, Orindi B, Murphy TE, Mwambi H, Allore HG. A multivariate joint model to adjust for random measurement error while handling skewness and correlation in dietary data in an epidemiologic study of mortality. Ann Epidemiol 2023; 82:8-15. [PMID: 36972757 PMCID: PMC10239394 DOI: 10.1016/j.annepidem.2023.03.007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/03/2022] [Revised: 03/20/2023] [Accepted: 03/23/2023] [Indexed: 03/29/2023]
Abstract
PURPOSE A substantial proportion of global deaths is attributed to unhealthy diets, which can be assessed at baseline or longitudinally. We demonstrated how to simultaneously correct for random measurement error, correlations, and skewness in the estimation of associations between dietary intake and all-cause mortality. METHODS We applied a multivariate joint model (MJM) that simultaneously corrected for random measurement error, skewness, and correlation among longitudinally measured intake levels of cholesterol, total fat, dietary fiber, and energy with all-cause mortality using US National Health and Nutrition Examination Survey linked to the National Death Index mortality data. We compared MJM with the mean method that assessed intake levels as the mean of a person's intake. RESULTS The estimates from MJM were larger than those from the mean method. For instance, the logarithm of hazard ratio for dietary fiber intake increased by 14 times (from -0.04 to -0.60) with the MJM method. This translated into a relative hazard of death of 0.55 (95% credible interval: 0.45, 0.65) with the MJM and 0.96 (95% credible interval: 0.95, 0.97) with the mean method. CONCLUSIONS MJM adjusts for random measurement error and flexibly addresses correlations and skewness among longitudinal measures of dietary intake when estimating their associations with death.
Collapse
Affiliation(s)
- George O Agogo
- StatsDecide Analytics and Consulting Ltd, Nakuru, Kenya.
| | | | - Benedict Orindi
- Department of Statistics, Center for Geographic Medicine Research, KEMRI-Wellcome Trust, Kilifi, Kenya
| | - Terrence E Murphy
- Public Health Sciences, Pennsylvania State University College of Medicine, Hershey
| | - Henry Mwambi
- School of Mathematics, Statistics and Computer Science, University of KwaZulu-Natal, Pietermaritzburg Campus, Pietermaritzburg, South Africa
| | - Heather G Allore
- Department of Internal Medicine, Section of Geriatrics, Yale School of Medicine, New Haven, CT; Department of Biostatistics, Yale School of Public Health, New Haven, CT
| |
Collapse
|
4
|
Agogo GO, Muoka AK. A three-part regression calibration to handle excess zeroes, skewness and heteroscedasticity in adjusting for measurement error in dietary intake data. J Appl Stat 2020; 49:884-901. [DOI: 10.1080/02664763.2020.1845622] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/23/2022]
Affiliation(s)
- George O. Agogo
- Division of Global Health Protection, US Centers for Disease Control and Prevention, Nairobi, Kenya
- Department of Internal Medicine, Yale University, New Haven, CT, USA
| | - Alexander K. Muoka
- School of Mathematics, Statistics & Computer Science, University of KwaZulu-Natal, Pietermaritzburg, South Africa
- School of Science and Informatics, Taita Taveta University, Voi, Kenya
| |
Collapse
|
5
|
Dietary and Lifestyle Patterns are Associated with Heart Rate Variability. J Clin Med 2020; 9:jcm9041121. [PMID: 32295262 PMCID: PMC7230664 DOI: 10.3390/jcm9041121] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/26/2020] [Revised: 03/31/2020] [Accepted: 04/10/2020] [Indexed: 12/28/2022] Open
Abstract
Assessment of heart rate variability (HRV) and cardiac ectopic beats is a clinically relevant topic. The present exploratory observational study aimed to inspect the relationships of lifestyle, dietary patterns, and anthropometrics with HRV, premature ventricular complexes (PVCs), and supraventricular premature complexes (SVPCs). A cross-sectional study enrolling subjects undergoing Holter monitoring was performed. Sociodemographic and clinical characteristics, body composition (full-body bio-impedentiometry), dietary patterns (validated food frequency questionnaire and 24 h dietary recall), and quality of life were assessed. Generalized additive models were estimated to evaluate the relationships between outcomes of interest and variables collected. The study enrolled 121 consecutive patients undergoing 24 h Holter monitoring. Upon univariable analysis, HRV was found to have an inverse association with mass of body fat (MBF) (p-value 0.015), while doing physical activity was associated with a significantly higher HRV (p-value 0.036). Upon multivariable analysis, fruit consumption in the 24 h dietary recall was found to be directly associated with HRV (p-value 0.044). The present findings might be useful for improving the management of patients attending cardiac rhythm labs, and to tailor ad hoc prevention strategies (modification of lifestyle and eating habits) based on Holter parameters.
Collapse
|
6
|
Intemann T, Mehlig K, De Henauw S, Siani A, Constantinou T, Moreno LA, Molnár D, Veidebaum T, Pigeot I. SIMEX for correction of dietary exposure effects with Box-Cox transformed data. Biom J 2019; 62:221-237. [PMID: 31702826 DOI: 10.1002/bimj.201900066] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/12/2019] [Revised: 09/09/2019] [Accepted: 09/14/2019] [Indexed: 11/11/2022]
Abstract
Modelling dietary data, and especially 24-hr dietary recall (24HDR) data, is a challenge. Ignoring the inherent measurement error (ME) leads to biased effect estimates when the association between an exposure and an outcome is investigated. We propose an adapted simulation extrapolation (SIMEX) algorithm for modelling dietary exposures. For this purpose, we exploit the ME model of the NCI method where we assume the assumption of normally distributed errors of the reported intake on the Box-Cox transformed scale and of unbiased recalls on the original scale. According to the SIMEX algorithm, remeasurements of the observed data with additional ME are generated in order to estimate the association between the level of ME and the resulting effect estimate. Subsequently, this association is extrapolated to the case of zero ME to obtain the corrected estimate. We show that the proposed method fulfils the key property of the SIMEX approach, that is, that the MSE of the generated data will converge to zero if the ME variance converges to zero. Furthermore, the method is applied to real 24HDR data of the I.Family study to correct the effects of salt and alcohol intake on blood pressure. In a simulation study, the method is compared with the NCI method resulting in effect estimates with either smaller MSE or smaller bias in certain situations. In addition, we found our method to be more informative and easier to implement. Therefore, we conclude that the proposed method is useful to promote the dissemination of ME correction methods in nutritional epidemiology.
Collapse
Affiliation(s)
- Timm Intemann
- Biometry and Data Management, Leibniz Institute for Prevention Research and Epidemiology-BIPS, Bremen, Germany.,Institute of Statistics, Faculty of Mathematics and Computer Science, University of Bremen, Bremen, Germany
| | - Kirsten Mehlig
- Department of Public Health and Community Medicine, Institute of Medicine, Sahlgrenska Academy at University of Gothenburg, Gothenburg, Sweden
| | | | - Alfonso Siani
- Institute of Food Sciences, National Research Council, Avellino, Italy
| | | | - Luis A Moreno
- GENUD (Growth, Exercise, Nutrition and Development) Research Group, Instituto Agroalimentario de Aragón (IA2), Instituto de Investigación Sanitaria Aragón (IIS Aragón), Centro de Investigación Biomédica en Red Fisiopatologa de la Obesidad y Nutrición (CIBERObn), University of Zaragoza, Zaragoza, Spain
| | - Dénes Molnár
- Department of Pediatrics, Medical School, University of Pécs, Pécs, Hungary
| | - Toomas Veidebaum
- Department of Chronic Diseases, National Institute for Health Development, Tallinn, Estonia
| | - Iris Pigeot
- Biometry and Data Management, Leibniz Institute for Prevention Research and Epidemiology-BIPS, Bremen, Germany.,Institute of Statistics, Faculty of Mathematics and Computer Science, University of Bremen, Bremen, Germany
| | | |
Collapse
|
7
|
Quah PL, Syuhada G, Fries LR, Chan MJ, Lim HX, Toh JY, Sugianto R, Aris IM, Lee YS, Yap F, Godfrey KM, Gluckman PD, Chong YS, Shek LP, Tan KH, Forde CG, Chong MFF. Maternal feeding practices in relation to dietary intakes and BMI in 5 year-olds in a multi-ethnic Asian population. PLoS One 2018; 13:e0203045. [PMID: 30226881 PMCID: PMC6143183 DOI: 10.1371/journal.pone.0203045] [Citation(s) in RCA: 17] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/13/2017] [Accepted: 08/14/2018] [Indexed: 12/19/2022] Open
Abstract
BACKGROUND In Asia, little is known about how maternal feeding practices are associated with dietary intakes and body mass index (BMI) in preschoolers. OBJECTIVE To assess the relationships between maternal feeding practices with dietary intakes and BMI in preschoolers in Asia using cross-sectional analysis in the GUSTO (Growing Up in Singapore Towards healthy Outcomes) cohort. PARTICIPANT SETTINGS Mothers (n = 511) who completed the Comprehensive Feeding Practices Questionnaire (CFPQ) and a semi-quantitative Food Frequency Questionnaire (FFQ) when children were 5 years old. STATISTICAL ANALYSIS Associations between 12 maternal feeding practices (mean scores divided into tertiles) and children's dietary intakes of seven food groups and BMI z-scores were examined using the general linear regression model. Weight and height of the child were measured, and dietary intakes derived from the FFQ. RESULTS Compared to those in the low tertile, mothers in the high tertile of modelling healthy food intakes had children with higher intakes of vegetables[+20.0g/day (95%CI:11.6,29.5)] and wholegrains[+ 20.9g/day (9.67,31.1)] but lower intakes of sweet snacks[-10.1g/day (-16.3,-4.94)] and fast-foods[-5.84g/day (-10.2,-1.48)]. Conversely, children of mothers in the high tertile for allowing child control (lack of parental control) had lower intake of vegetables[-15.2g/day (-26.6,-5.21)] and wholegrains[-13.6g/day (-22.9,-5.27)], but higher intakes of sweet snacks[+13.7g/day (7.7, 19.8)] and fast-foods[+6.63g/day (3.55,9.72)]. In relation to BMI at 5 years, food restrictions for weight was associated with higher BMI z-scores [0.86SD (0.61,1.21)], while use of pressure was associated with lower BMI z-scores[-0.49SD(-0.78,-0.21)]. CONCLUSIONS AND IMPLICATIONS Modelling healthy food intakes by mothers was the key feeding practice associated with higher intakes of healthy foods and lower intakes of discretionary foods. The converse was true for allowing child control. Only food restrictions for weight and use of pressure were associated with BMI z-scores.
Collapse
Affiliation(s)
- Phaik Ling Quah
- Singapore Institute for Clinical Sciences, Agency for Science, Technology, and Research, Singapore, Singapore
| | - Ginanjar Syuhada
- Singapore Institute for Clinical Sciences, Agency for Science, Technology, and Research, Singapore, Singapore
| | | | - Mei Jun Chan
- Singapore Institute for Clinical Sciences, Agency for Science, Technology, and Research, Singapore, Singapore
| | - Hui Xian Lim
- Singapore Institute for Clinical Sciences, Agency for Science, Technology, and Research, Singapore, Singapore
| | - Jia Ying Toh
- Singapore Institute for Clinical Sciences, Agency for Science, Technology, and Research, Singapore, Singapore
| | - Ray Sugianto
- Saw Swee Hock School of Public Health, National University of Singapore, Singapore, Singapore
| | - Izzuddin M. Aris
- Singapore Institute for Clinical Sciences, Agency for Science, Technology, and Research, Singapore, Singapore
- Department of Pediatrics, Yong Loo Lin School of Medicine, National University of Singapore and National University Health System, Singapore, Singapore
| | - Yung Seng Lee
- Singapore Institute for Clinical Sciences, Agency for Science, Technology, and Research, Singapore, Singapore
- Department of Pediatrics, Yong Loo Lin School of Medicine, National University of Singapore and National University Health System, Singapore, Singapore
- Khoo Teck Puat-National University Children’s Medical Institute, National University Health System, Singapore, Singapore
| | - Fabian Yap
- Pediatric Endocrinology, KK Women’s and Children’s Hospital, Singapore, Singapore
- Duke-NUS Graduate Medical School, Lee Kong Chian School of Medicine, Singapore, Singapore
- Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore, Singapore
| | - Keith M. Godfrey
- Medical Research Council Lifecourse Epidemiology Unit and National Institute for Health Research Southampton Biomedical Research Centre, University of Southampton and University Hospital, Southampton National Health Service Foundation Trust, Southampton, United Kingdom
| | - Peter D. Gluckman
- Singapore Institute for Clinical Sciences, Agency for Science, Technology, and Research, Singapore, Singapore
- Liggins Institute, University of Auckland, Auckland, New Zealand
| | - Yap- Seng Chong
- Singapore Institute for Clinical Sciences, Agency for Science, Technology, and Research, Singapore, Singapore
- Department of Obstetrics & Gynaecology, Yong Loo Lin School of Medicine, National University of Singapore and National University Health System, Singapore, Singapore
| | - Lynette P. Shek
- Singapore Institute for Clinical Sciences, Agency for Science, Technology, and Research, Singapore, Singapore
- Department of Pediatrics, Yong Loo Lin School of Medicine, National University of Singapore and National University Health System, Singapore, Singapore
| | - Kok Hian Tan
- Department of Obstetrics and Gynaecology, KK Women’s and Children’s Hospital, Singapore, Singapore
| | - Ciaran G. Forde
- Clinical Nutrition Research Center, Singapore Institute for Clinical Sciences (SICS), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore
- Department of Physiology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore
| | - Mary F. F. Chong
- Singapore Institute for Clinical Sciences, Agency for Science, Technology, and Research, Singapore, Singapore
- Saw Swee Hock School of Public Health, National University of Singapore, Singapore, Singapore
- Clinical Nutrition Research Center, Singapore Institute for Clinical Sciences (SICS), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore
| |
Collapse
|