AUTHOR=Luo Wenjin , Gong Lilin , Chen Xiangjun , Gao Rufei , Peng Bin , Wang Yue , Luo Ting , Yang Yi , Kang Bing , Peng Chuan , Ma Linqiang , Mei Mei , Liu Zhiping , Li Qifu , Yang Shumin , Wang Zhihong , Hu Jinbo 

TITLE=Lifestyle and chronic kidney disease: A machine learning modeling study

JOURNAL=Frontiers in Nutrition

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/nutrition/articles/10.3389/fnut.2022.918576

DOI=10.3389/fnut.2022.918576

ISSN=2296-861X

ABSTRACT=Background: Individual lifestyle varies in the real world, and the comparative efficacy of lifestyles to preserve renal function remains indeterminate. We aimed to systematically compare effects of lifestyles on chronic kidney disease (CKD) incidence, and establish a lifestyle scoring system for CKD risk identification. 

Methods: Using the data of UK Biobank cohort, we included 470,778 participants who were free of CKD at baseline. We harnessed the light gradient boosting machine algorithm to rank importance of 37 lifestyle factors (including dietary patterns, physical activity, sleep, psychological health, smoking and alcohol) on the risk of CKD. Lifestyle score was calculated by a combination of machine learning and Cox proportional-hazards model. CKD event was defined as estimated glomerular filtration rate <60 ml/min per 1.73 m2, mortality and hospitalization due to chronic renal failure and self-reported chronic renal failure, initiated renal replacement therapy.

Results: During a median of 11-year follow-up, 13,555 participants developed CKD event. Bread, walking time, moderate activity, vigorous activity and bread ranked as the top five risk factors of CKD. Healthy lifestyle mainly consisted of whole grain bread, walking, moderate physical activity, oat cereal and muesli, which were scored 12, 12, 10, 7 and 7, respectively. Unhealthy lifestyle mainly included white bread, tea >4 cups/day, biscuit cereal, low drink temperature and processed meat, which were scored -12, -9, -7, -4 and -3, respectively. In restricted cubic spline regression analysis, a higher lifestyle score was associated with a lower risk of CKD event (P for linear relation <0.001). Compared to participants with lifestyle score < 0, participants scoring 0-20, 20-40, 40-60, >60 exhibited 25%, 42%, 55% and 70% lower risk of CKD event, respectively. The C-statistic of age-adjusted lifestyle score for predicting CKD event was 0.710 (0.703-0.718).

Conclusions: A lifestyle scoring system for CKD prevention was established. Based on the system, individuals could flexibly choose healthy lifestyles and avoid unhealthy lifestyles to prevent CKD.