Data imputation and body weight variability calculation using linear and nonlinear methods in data collected from digital smart scales: Simulation and validation study

Research output: Contribution to journal › Journal article › Research › peer-review

Standard

Data imputation and body weight variability calculation using linear and nonlinear methods in data collected from digital smart scales : Simulation and validation study. / Turicchi, Jake; O'Driscoll, Ruairi; Finlayson, Graham; Duarte, Cristiana; Palmeira, A. L.; Larsen, Sofus C.; Heitmann, Berit L.; James Stubbs, R.

In: JMIR mHealth and uHealth, Vol. 8, No. 9, e17977, 2020.

Research output: Contribution to journal › Journal article › Research › peer-review

Harvard

Turicchi, J, O'Driscoll, R, Finlayson, G, Duarte, C, Palmeira, AL, Larsen, SC, Heitmann, BL & James Stubbs, R 2020, 'Data imputation and body weight variability calculation using linear and nonlinear methods in data collected from digital smart scales: Simulation and validation study', JMIR mHealth and uHealth, vol. 8, no. 9, e17977. https://doi.org/10.2196/17977

APA

Turicchi, J., O'Driscoll, R., Finlayson, G., Duarte, C., Palmeira, A. L., Larsen, S. C., Heitmann, B. L., & James Stubbs, R. (2020). Data imputation and body weight variability calculation using linear and nonlinear methods in data collected from digital smart scales: Simulation and validation study. JMIR mHealth and uHealth, 8(9), [e17977]. https://doi.org/10.2196/17977

Vancouver

Turicchi J, O'Driscoll R, Finlayson G, Duarte C, Palmeira AL, Larsen SC et al. Data imputation and body weight variability calculation using linear and nonlinear methods in data collected from digital smart scales: Simulation and validation study. JMIR mHealth and uHealth. 2020;8(9). e17977. https://doi.org/10.2196/17977

Author

Turicchi, Jake ; O'Driscoll, Ruairi ; Finlayson, Graham ; Duarte, Cristiana ; Palmeira, A. L. ; Larsen, Sofus C. ; Heitmann, Berit L. ; James Stubbs, R. / Data imputation and body weight variability calculation using linear and nonlinear methods in data collected from digital smart scales : Simulation and validation study. In: JMIR mHealth and uHealth. 2020 ; Vol. 8, No. 9.

Bibtex

@article{104e6c7cd5bc4d23af1bfbbc0c27f50c,
title = "Data imputation and body weight variability calculation using linear and nonlinear methods in data collected from digital smart scales: Simulation and validation study",
abstract = "Background: Body weight variability (BWV) is common in the general population and may act as a risk factor for obesity or diseases. The correct identification of these patterns may have prognostic or predictive value in clinical and research settings. With advancements in technology allowing for the frequent collection of body weight data from electronic smart scales, new opportunities to analyze and identify patterns in body weight data are available. Objective: This study aims to compare multiple methods of data imputation and BWV calculation using linear and nonlinear approaches Methods: In total, 50 participants from an ongoing weight loss maintenance study (the NoHoW study) were selected to develop the procedure. We addressed the following aspects of data analysis: cleaning, imputation, detrending, and calculation of total and local BWV. To test imputation, missing data were simulated at random and using real patterns of missingness. A total of 10 imputation strategies were tested. Next, BWV was calculated using linear and nonlinear approaches, and the effects of missing data and data imputation on these estimates were investigated. Results: Body weight imputation using structural modeling with Kalman smoothing or an exponentially weighted moving average provided the best agreement with observed values (root mean square error range 0.62%-0.64%). Imputation performance decreased with missingness and was similar between random and nonrandom simulations. Errors in BWV estimations from missing simulated data sets were low (2%-7% with 80% missing data or a mean of 67, SD 40.1 available body weights) compared with that of imputation strategies where errors were significantly greater, varying by imputation method. Conclusions: The decision to impute body weight data depends on the purpose of the analysis. Directions for the best performing imputation methods are provided. For the purpose of estimating BWV, data imputation should not be conducted. Linear and nonlinear methods of estimating BWV provide reasonably accurate estimates under high proportions (80%) of missing data.",
keywords = "Body weight, Digital tracking, Energy balance, Imputation, Smart scales, Validation, Weight cycling, Weight fluctuation, Weight instability, Weight variability",
author = "Jake Turicchi and Ruairi O'Driscoll and Graham Finlayson and Cristiana Duarte and Palmeira, {A. L.} and Larsen, {Sofus C.} and Heitmann, {Berit L.} and {James Stubbs}, R.",
year = "2020",
doi = "10.2196/17977",
language = "English",
volume = "8",
journal = "J M I R mHealth and uHealth",
issn = "2291-5222",
publisher = "J M I R Publications, Inc.",
number = "9",

}

RIS

TY - JOUR

T1 - Data imputation and body weight variability calculation using linear and nonlinear methods in data collected from digital smart scales

T2 - Simulation and validation study

AU - Turicchi, Jake

AU - O'Driscoll, Ruairi

AU - Finlayson, Graham

AU - Duarte, Cristiana

AU - Palmeira, A. L.

AU - Larsen, Sofus C.

AU - Heitmann, Berit L.

AU - James Stubbs, R.

PY - 2020

Y1 - 2020

N2 - Background: Body weight variability (BWV) is common in the general population and may act as a risk factor for obesity or diseases. The correct identification of these patterns may have prognostic or predictive value in clinical and research settings. With advancements in technology allowing for the frequent collection of body weight data from electronic smart scales, new opportunities to analyze and identify patterns in body weight data are available. Objective: This study aims to compare multiple methods of data imputation and BWV calculation using linear and nonlinear approaches Methods: In total, 50 participants from an ongoing weight loss maintenance study (the NoHoW study) were selected to develop the procedure. We addressed the following aspects of data analysis: cleaning, imputation, detrending, and calculation of total and local BWV. To test imputation, missing data were simulated at random and using real patterns of missingness. A total of 10 imputation strategies were tested. Next, BWV was calculated using linear and nonlinear approaches, and the effects of missing data and data imputation on these estimates were investigated. Results: Body weight imputation using structural modeling with Kalman smoothing or an exponentially weighted moving average provided the best agreement with observed values (root mean square error range 0.62%-0.64%). Imputation performance decreased with missingness and was similar between random and nonrandom simulations. Errors in BWV estimations from missing simulated data sets were low (2%-7% with 80% missing data or a mean of 67, SD 40.1 available body weights) compared with that of imputation strategies where errors were significantly greater, varying by imputation method. Conclusions: The decision to impute body weight data depends on the purpose of the analysis. Directions for the best performing imputation methods are provided. For the purpose of estimating BWV, data imputation should not be conducted. Linear and nonlinear methods of estimating BWV provide reasonably accurate estimates under high proportions (80%) of missing data.

AB - Background: Body weight variability (BWV) is common in the general population and may act as a risk factor for obesity or diseases. The correct identification of these patterns may have prognostic or predictive value in clinical and research settings. With advancements in technology allowing for the frequent collection of body weight data from electronic smart scales, new opportunities to analyze and identify patterns in body weight data are available. Objective: This study aims to compare multiple methods of data imputation and BWV calculation using linear and nonlinear approaches Methods: In total, 50 participants from an ongoing weight loss maintenance study (the NoHoW study) were selected to develop the procedure. We addressed the following aspects of data analysis: cleaning, imputation, detrending, and calculation of total and local BWV. To test imputation, missing data were simulated at random and using real patterns of missingness. A total of 10 imputation strategies were tested. Next, BWV was calculated using linear and nonlinear approaches, and the effects of missing data and data imputation on these estimates were investigated. Results: Body weight imputation using structural modeling with Kalman smoothing or an exponentially weighted moving average provided the best agreement with observed values (root mean square error range 0.62%-0.64%). Imputation performance decreased with missingness and was similar between random and nonrandom simulations. Errors in BWV estimations from missing simulated data sets were low (2%-7% with 80% missing data or a mean of 67, SD 40.1 available body weights) compared with that of imputation strategies where errors were significantly greater, varying by imputation method. Conclusions: The decision to impute body weight data depends on the purpose of the analysis. Directions for the best performing imputation methods are provided. For the purpose of estimating BWV, data imputation should not be conducted. Linear and nonlinear methods of estimating BWV provide reasonably accurate estimates under high proportions (80%) of missing data.

KW - Body weight

KW - Digital tracking

KW - Energy balance

KW - Imputation

KW - Smart scales

KW - Validation

KW - Weight cycling

KW - Weight fluctuation

KW - Weight instability

KW - Weight variability

U2 - 10.2196/17977

DO - 10.2196/17977

M3 - Journal article

C2 - 32915155

AN - SCOPUS:85085263273

VL - 8

JO - J M I R mHealth and uHealth

JF - J M I R mHealth and uHealth

SN - 2291-5222

IS - 9

M1 - e17977

ER -

ID: 252764783