Weihong Zhou1, Spencer Eckler2, Andrew Barszczyk3, Alex Waese-Perlman2, Yingjie Wang1, Xiaoping Gu4, Zhong-Ping Feng3, Yuzhu Peng5, Kang Lee6. 1. Department of Health Management Centre, Drum Tower Hospital Affiliated to Nanjing University Medical School, No. 321 Zhongshan Road, Nanjing, 210008, China. 2. Dr. Eric Jackman Institute of Child Study, University of Toronto, 45 Walmer Rd, Toronto, ON, M5R 2X2, Canada. 3. Department of Physiology, University of Toronto, Medical Sciences Building, Rm. 3306. 1 King's College, Toronto, ON, M5S 1A8, Canada. 4. Department of Anaesthesiology, Drum Tower Hospital Affiliated to Nanjing University Medical School, No. 321 Zhongshan Road, Nanjing, 210008, China. 5. Department of Health Management Centre, Drum Tower Hospital Affiliated to Nanjing University Medical School, No. 321 Zhongshan Road, Nanjing, 210008, China. yuzhupeng4@gmail.com. 6. Dr. Eric Jackman Institute of Child Study, University of Toronto, 45 Walmer Rd, Toronto, ON, M5R 2X2, Canada. kang.lee@utoronto.ca.
Abstract
BACKGROUND: Waist circumference is becoming recognized as a useful predictor of health risks in clinical research. However, clinical datasets tend to lack this measurement and self-reported values tend to be inaccurate. Predicting waist circumference from standard physical features could be a viable method for generating this information when it is missing or mitigating the impact of inaccurate self-reports. This study determined the degree to which the XGBoost advanced machine learning algorithm could build models that predict waist circumference from height, weight, calculated Body Mass Index, age, race/ethnicity and sex, whether they perform better than current models based on linear regression, and the relative importance of each feature in this prediction. METHODS: We trained tree-based models (via XGBoost gradient boosting) and linear models (via regression) to predict waist circumference from height, weight, Body Mass Index, age, race/ethnicity and sex (n = 60,740 participants). We created 10 iterations of each model, each using 90% of the dataset for training and the remaining 10% for testing performance (this group was different for each iteration). We calculated model performance and feature importance as an average across 10 iterations. We then externally validated the ensembled version of the top model. RESULTS: The XGBoost model predicted waist circumference with a mean bias ± standard deviation of 0.0 ± 0.04 cm and a root mean squared error of 4.7 ± 0.05 cm, with performance varying slightly by sex and race/ethnicity. The XGBoost model showed varying degrees of improvement over linear regression models. The top 3 predictors were Body Mass Index, weight and race (Asian). External validation found that on average this model overestimated waist circumference by 4.65 cm in the United Kingdom population (mainly due to overprediction in females) and underestimated waist circumference by 1.7 cm in the Chinese population. The respective root mean squared errors were 7.7 cm and 7.1 cm. CONCLUSIONS: XGBoost-based models accurately predict waist circumference from standard physical features. Waist circumference prediction using this approach would be valuable for epidemiological research and beyond.
BACKGROUND: Waist circumference is becoming recognized as a useful predictor of health risks in clinical research. However, clinical datasets tend to lack this measurement and self-reported values tend to be inaccurate. Predicting waist circumference from standard physical features could be a viable method for generating this information when it is missing or mitigating the impact of inaccurate self-reports. This study determined the degree to which the XGBoost advanced machine learning algorithm could build models that predict waist circumference from height, weight, calculated Body Mass Index, age, race/ethnicity and sex, whether they perform better than current models based on linear regression, and the relative importance of each feature in this prediction. METHODS: We trained tree-based models (via XGBoost gradient boosting) and linear models (via regression) to predict waist circumference from height, weight, Body Mass Index, age, race/ethnicity and sex (n = 60,740 participants). We created 10 iterations of each model, each using 90% of the dataset for training and the remaining 10% for testing performance (this group was different for each iteration). We calculated model performance and feature importance as an average across 10 iterations. We then externally validated the ensembled version of the top model. RESULTS: The XGBoost model predicted waist circumference with a mean bias ± standard deviation of 0.0 ± 0.04 cm and a root mean squared error of 4.7 ± 0.05 cm, with performance varying slightly by sex and race/ethnicity. The XGBoost model showed varying degrees of improvement over linear regression models. The top 3 predictors were Body Mass Index, weight and race (Asian). External validation found that on average this model overestimated waist circumference by 4.65 cm in the United Kingdom population (mainly due to overprediction in females) and underestimated waist circumference by 1.7 cm in the Chinese population. The respective root mean squared errors were 7.7 cm and 7.1 cm. CONCLUSIONS: XGBoost-based models accurately predict waist circumference from standard physical features. Waist circumference prediction using this approach would be valuable for epidemiological research and beyond.
Authors: Eric J Jacobs; Christina C Newton; Yiting Wang; Alpa V Patel; Marjorie L McCullough; Peter T Campbell; Michael J Thun; Susan M Gapstur Journal: Arch Intern Med Date: 2010-08-09
Authors: N Okamoto; A Hosono; K Shibata; S Tsujimura; K Oka; H Fujita; M Kamiya; F Kondo; R Wakabayashi; T Yamada; S Suzuki Journal: Obes Sci Pract Date: 2017-11-03
Authors: Robert Ross; Ian J Neeland; Shizuya Yamashita; Iris Shai; Jaap Seidell; Paolo Magni; Raul D Santos; Benoit Arsenault; Ada Cuevas; Frank B Hu; Bruce A Griffin; Alberto Zambon; Philip Barter; Jean-Charles Fruchart; Robert H Eckel; Yuji Matsuzawa; Jean-Pierre Després Journal: Nat Rev Endocrinol Date: 2020-02-04 Impact factor: 43.330
Authors: Samuel R Bozeman; David C Hoaglin; Tanya M Burton; Chris L Pashos; Rami H Ben-Joseph; Christopher S Hollenbeak Journal: BMC Med Res Methodol Date: 2012-08-03 Impact factor: 4.615