A comprehensive multi-task deep learning approach for predicting metabolic syndrome with genetic, nutritional, and clinical data

Eckel, R. H., Grundy, S. M. & Zimmet, P. Z. The metabolic syndrome. Lancet 365(9468), 1415–1428 (2005).Article 
CAS 
PubMed 

Google Scholar 
Grundy, S. M. et al. Definition of metabolic syndrome: Report of the National Heart, Lung, and Blood Institute/American Heart Association conference on scientific issues related to definition. Circulation 109(3), 433–438 (2004).Article 
PubMed 

Google Scholar 
Shang, X. et al. Dietary protein from different food sources, incident metabolic syndrome and changes in its components: An 11-year longitudinal study in healthy community-dwelling adults. Clin. Nutr. 36(6), 1540–1548 (2017).Article 
MathSciNet 
CAS 
PubMed 

Google Scholar 
Kim, H. et al. Development of a metabolic syndrome classification and prediction model for Koreans using deep learning technology: The Korea National Health and Nutrition Examination Survey (KNHANES)(2013–2018). Clin. Nutr. Res. 12(2), 138 (2023).Article 
PubMed 
PubMed Central 

Google Scholar 
Kong, S. & Cho, Y. S. Identification of female-specific genetic variants for metabolic syndrome and its component traits to improve the prediction of metabolic syndrome in females. BMC Med. Genet. 20(1), 1–13 (2019).Article 

Google Scholar 
Cortes, C. & Vapnik, V. Support-vector networks. Mach. Learn. 20, 273–297 (1995).Article 

Google Scholar 
Song, Y.-Y. & Ying, L. Decision tree methods: Applications for classification and prediction. Shanghai Arch. Psychiatry 27(2), 130 (2015).PubMed 
PubMed Central 

Google Scholar 
Rokach, L. Ensemble-based classifiers. Artif. Intell. Rev. 33, 1–39 (2010).Article 

Google Scholar 
Breiman, L. Bagging predictors. Mach. Learn. 24, 123–140 (1996).Article 

Google Scholar 
Ho, T. K. Random decision forests. In Proceedings of 3rd International Conference on Document Analysis and Recognition (ed. Ho, T. K.) (IEEE, 1995).
Google Scholar 
Mayr, A. et al. The evolution of boosting algorithms. Methods Inf. Med. 53(06), 419–427 (2014).Article 
CAS 
PubMed 

Google Scholar 
Friedman, J. H. Greedy function approximation: A gradient boosting machine. Ann. Stat. 29, 1189–1232 (2001).Article 
MathSciNet 

Google Scholar 
Chen, T. and C. Guestrin. Xgboost: A scalable tree boosting system. In: Proc. 22nd acm sigkdd international conference on knowledge discovery and data mining. (2016).Ke, G., et al. Lightgbm: A highly efficient gradient boosting decision tree. Adv. Neural Inf. Process. Syst. 30, (2017).Dorogush, A.V., V. Ershov, & A. Gulin, CatBoost: gradient boosting with categorical features support. Preprint at http://arxiv.org/quant-ph/1810.11363 (2018).Gutiérrez-Esparza, G. O. et al. Prediction of metabolic syndrome in a Mexican population applying machine learning algorithms. Symmetry 12(4), 581 (2020).Article 
ADS 

Google Scholar 
Choe, E. K. et al. Metabolic syndrome prediction using machine learning models with genetic and clinical information from a nonobese healthy population. Genom. Inform. 16(4), e31 (2018).Article 
MathSciNet 

Google Scholar 
Saffarian, M. et al. Developing a novel continuous metabolic syndrome score: A data mining based model. J. AI Data Min. 9(2), 193–202 (2021).
Google Scholar 
Kim, J. et al. Prediction of metabolic and pre-metabolic syndromes using machine learning models with anthropometric, lifestyle, and biochemical factors from a middle-aged population in Korea. BMC Public Health 22(1), 664 (2022).Article 
PubMed 
PubMed Central 

Google Scholar 
Shin, H., Shim, S. & Oh, S. Machine learning-based predictive model for prevention of metabolic syndrome. Plos One 18(6), e0286635 (2023).Article 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Sghaireen, M. G. et al. Machine learning approach for metabolic syndrome diagnosis using explainable data-augmentation-based classification. Diagnostics 12(12), 3117 (2022).Article 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Gutierrez-Esparza, G. O. et al. Machine and deep learning applied to predict metabolic syndrome without a blood screening. Appl. Sci. 11(10), 4334 (2021).Article 
CAS 

Google Scholar 
Tavares, L. D. et al. Prediction of metabolic syndrome: A machine learning approach to help primary prevention. Diabetes Res. Clin. Pract. 191, 110047 (2022).Article 

Google Scholar 
Yang, H. et al. Machine learning-aided risk prediction for metabolic syndrome based on 3 years study. Sci. Rep. 12(1), 2248 (2022).Article 
ADS 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Vandenhende, S., et al., Revisiting multi-task learning in the deep learning era. Preprint at https://arXiv.org/quant-ph/2004.13379, (2020).Standley, T. et al. Which tasks should be learned together in multi-task learning? In International Conference on Machine Learning (eds Standley, T. et al.) (PMLR, 2020).
Google Scholar 
Badré, A. & Pan, C. Explainable multi-task learning improves the parallel estimation of polygenic risk scores for many diseases through shared genetic basis. PLOS Computat. Biol. 19(7), e1011211 (2023).Article 
ADS 

Google Scholar 
Zhang, Y. & Yang, Q. An overview of multi-task learning. Natl. Sci. Rev. 5(1), 30–43 (2018).Article 
ADS 

Google Scholar 
Ruder, S., An overview of multi-task learning in deep neural networks. Preprint at https://arXiv.org/quant-ph/1706.05098 (2017).Zhou, J. et al. Modeling disease progression via multi-task learning. NeuroImage 78, 233–248 (2013).Article 
PubMed 

Google Scholar 
He, T. et al. Multi-task learning for the segmentation of organs at risk with label dependence. Med. Image Anal. 61, 101666 (2020).Article 
PubMed 

Google Scholar 
Gao, F. et al. A feature transfer enabled multi-task deep learning model on medical imaging. Expert Syst. Appl. 143, 112957 (2020).Article 

Google Scholar 
Kim, G. et al. Intra-person multi-task learning method for chronic-disease prediction. Sci. Rep. 13(1), 1069 (2023).Article 
ADS 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Kim, Y. J. et al. Large-scale genome-wide association studies in East Asians identify new genetic loci influencing metabolic traits. Nat. Genet. 43(10), 990–995 (2011).Article 
CAS 
PubMed 

Google Scholar 
Paik, J. K. et al. Dietary protein to carbohydrate ratio and incidence of metabolic syndrome in Korean adults based on a long-term prospective community-based cohort. Nutrients 12(11), 3274 (2020).Article 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Heid, I. M. et al. Genome-wide association analysis of high-density lipoprotein cholesterol in the population-based KORA study sheds new light on intergenic regions. Circ. Cardiovasc. Genet. 1(1), 10–20 (2008).Article 
CAS 
PubMed 

Google Scholar 
Kulminski, A. M. et al. Strong impact of natural-selection–free heterogeneity in genetics of age-related phenotypes. Aging (Albany NY) 10(3), 492 (2018).Article 
PubMed 

Google Scholar 
Hoffmann, T. J. et al. A large electronic-health-record-based genome-wide study of serum lipids. Nat. Genet. 50(3), 401–413 (2018).Article 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Saxena, R. et al. Genome-wide association analysis identifies loci for type 2 diabetes and triglyceride levels. Science 316(5829), 1331–1336 (2007).Article 
CAS 
PubMed 

Google Scholar 
Keller, M. et al. THOC5: A novel gene involved in HDL-cholesterol metabolism. J. Lipid Res. 54(11), 3170–3176 (2013).Article 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Li, D. et al. Progressive effects of single-nucleotide polymorphisms on 16 phenotypic traits based on longitudinal data. Genes Genom. 42(4), 393–403 (2020).Article 
CAS 

Google Scholar 
Wojcik, G. L. et al. Genetic analyses of diverse populations improves discovery for complex traits. Nature 570(7762), 514–518 (2019).Article 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Willer, C. J. et al. Newly identified loci that influence lipid concentrations and risk of coronary artery disease. Nat. Genet. 40(2), 161–169 (2008).Article 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Moon, S. et al. The Korea Biobank Array: design and identification of coding variants associated with blood biochemical traits. Sci. Rep. 9(1), 1382 (2019).Article 
ADS 
PubMed 
PubMed Central 

Google Scholar 
Spracklen, C. N. et al. Association analyses of East Asian individuals and trans-ancestry analyses with European individuals reveal new loci associated with cholesterol and triglyceride levels. Hum. Mol. Genet. 26(9), 1770–1784 (2017).Article 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Harshfield, E. L. et al. Genome-wide analysis of blood lipid metabolites in over 5000 South Asians reveals biological insights at cardiometabolic disease loci. BMC Med. 19, 1–17 (2021).Article 

Google Scholar 
Moon, S. et al. Multiple genotype–phenotype association study reveals intronic variant pair on SIDT2 associated with metabolic syndrome in a Korean population. Hum. Genom. 12(1), 1–10 (2018).Article 
ADS 

Google Scholar 
Coram, M. A. et al. Genome-wide characterization of shared and distinct genetic components that influence blood lipid levels in ethnically diverse human populations. Am. J. Hum. Genet. 92(6), 904–916 (2013).Article 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Sinnott-Armstrong, N. et al. Genetics of 35 blood and urine biomarkers in the UK Biobank. Nat. Genet. 53(2), 185–194 (2021).Article 
CAS 
PubMed 

Google Scholar 
Oh, S.-W. et al. Genome-wide association study of metabolic syndrome in Korean populations. PloS One 15(1), e0227357 (2020).Article 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Baik, I. et al. Genome-wide association studies identify genetic loci related to alcohol consumption in Korean men. Am. J. Clin. Nutr. 93(4), 809–816 (2011).Article 
CAS 
PubMed 

Google Scholar 
Jorgenson, E. et al. Genetic contributors to variation in alcohol consumption vary by race/ethnicity in a large multi-ethnic genome-wide association study. Mol. Psychiatry 22(9), 1359–1367 (2017).Article 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Shim, U. et al. Pathway analysis of metabolic syndrome using a genome-wide association study of Korea Associated Resource (KARE) cohorts. Genom. Inform. 12(4), 195 (2014).Article 

Google Scholar 
Wen, W. et al. Meta-analysis of genome-wide association studies in East Asian-ancestry populations identifies four new loci for body mass index. Hum. Mol. Genet. 23(20), 5492–5504 (2014).Article 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Jeon, S. et al. Structural equation modeling for hypertension and type 2 diabetes based on multiple SNPs and multiple phenotypes. PLoS One 14(9), e0217189 (2019).Article 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Kato, N. et al. Meta-analysis of genome-wide association studies identifies common variants associated with blood pressure variation in east Asians. Nat. Genet. 43(6), 531–538 (2011).Article 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Jeong, H. et al. Identifying interactions between dietary sodium, potassium, sodium–potassium ratios, and FGF5 rs16998073 variants and their associated risk for hypertension in Korean adults. Nutrients 12(7), 2121 (2020).Article 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Lu, X. et al. Genome-wide association study in Chinese identifies novel loci for blood pressure and hypertension. Hum. Mol. Genet. 24(3), 865–874 (2015).Article 
CAS 
PubMed 

Google Scholar 
Lu, X. et al. Genetic susceptibility to lipid levels and lipid change over time and risk of incident hyperlipidemia in Chinese populations. Circ. Cardiovasc. Genet. 9, 37–44 (2016).Article 
CAS 
PubMed 

Google Scholar 
Lu, X. et al. Genome-wide association study in Han Chinese identifies four new susceptibility loci for coronary artery disease. Nat. Genet. 44(8), 890–894 (2012).Article 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Graham, S. E. et al. The power of genetic diversity in genome-wide association studies of lipids. Nature 600(7890), 675–679 (2021).Article 
ADS 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Lee, S.-B. et al. Dyslipidaemia—Genotype interactions with nutrient intake and cerebro-cardiovascular disease. Biomedicines 10(7), 1615 (2022).Article 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Carlson, J. C. et al. Genome-wide association studies in Samoans give insight into the genetic architecture of fasting serum lipid levels. J. Hum. Genet. 66(2), 111–121 (2021).Article 
CAS 
PubMed 

Google Scholar 
Li-Gao, R. et al. Genetic studies of metabolomics change after a liquid meal illuminate novel pathways for glucose and lipid metabolism. Diabetes 70(12), 2932–2946 (2021).Article 
CAS 
PubMed 

Google Scholar 
Dupuis, J. et al. New genetic loci implicated in fasting glucose homeostasis and their impact on type 2 diabetes risk. Nat. Genet. 42(2), 105–116 (2010).Article 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Wu, B. & Pankow, J. S. Fast and accurate genome-wide association test of multiple quantitative traits. Computat. Math. Methods Med. 2018, 1–9 (2018).MathSciNet 
CAS 

Google Scholar 
Lagou, V. et al. Sex-dimorphic genetic effects and novel loci for fasting glucose and insulin variability. Nat. Commun. 12(1), 24 (2021).Article 
ADS 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Hwang, J.-Y. et al. Genome-wide association meta-analysis identifies novel variants associated with fasting plasma glucose in East Asians. Diabetes 64(1), 291–298 (2015).Article 
CAS 
PubMed 

Google Scholar 
Schumann, G. et al. KLB is associated with alcohol drinking, and its gene product β-Klotho is necessary for FGF21 regulation of alcohol preference. Proc. Natl. Acad. Sci. 113(50), 14372–14377 (2016).Article 
ADS 
CAS 
PubMed 
PubMed Central 

Google Scholar 
Kristiansson, K. et al. Genome-wide screen for metabolic syndrome susceptibility Loci reveals strong lipid gene contribution but no evidence for common genetic basis for clustering of metabolic syndrome traits. Circ. Cardiovasc. Genet. 5(2), 242–249 (2012).Article 
PubMed 
PubMed Central 

Google Scholar 
Lundberg, S.M. and S.-I. Lee, A unified approach to interpreting model predictions. Adv. Neural Inf. Process. Syst. 30, (2017).Zabaneh, D. & Balding, D. J. A genome-wide association study of the metabolic syndrome in Indian Asian men. PloS One 5(8), e11961 (2010).Article 
ADS 
PubMed 
PubMed Central 

Google Scholar 
McCarthy, J. J. et al. Evidence for substantial effect modification by gender in a large-scale genetic association study of the metabolic syndrome among coronary heart disease patients. Hum. Genet. 114, 87–98 (2003).Article 
CAS 
PubMed 

Google Scholar 
McCarthy, J. J. Gene by sex interaction in the etiology of coronary heart disease and the preceding metabolic syndrome. Nutr. Metab. Cardiovasc. Dis. 17(2), 153–161 (2007).Article 
PubMed 

Google Scholar 
Cho, Y. S. et al. A large-scale genome-wide association study of Asian populations uncovers genetic factors influencing eight quantitative traits. Nat. Genet. 41(5), 527–534 (2009).Article 
ADS 
CAS 
PubMed 

Google Scholar 
Grundy, S. M. et al. Diagnosis and management of the metabolic syndrome: An American Heart Association/National Heart, Lung, and Blood Institute scientific statement. Circulation 112(17), 2735–2752 (2005).Article 
PubMed 

Google Scholar 
Alberti, K. G. et al. Harmonizing the metabolic syndrome: a joint interim statement of the international diabetes federation task force on epidemiology and prevention; national heart, lung, and blood institute; American heart association; world heart federation; international atherosclerosis society; and international association for the study of obesity. Circulation 120(16), 1640–1645 (2009).Article 
CAS 
PubMed 

Google Scholar 
Blanquet, M. et al. Socio-economics status and metabolic syndrome: A meta-analysis. Diabetes Metab. Syndr. 13(3), 1805–1812 (2019).Article 
CAS 
PubMed 

Google Scholar 
Mauvais-Jarvis, F. Sex differences in metabolic homeostasis, diabetes, and obesity. Biol. Sex Differ. 6, 14 (2015).Article 
PubMed 
PubMed Central 

Google Scholar 
Lumish, H. S., O’Reilly, M. & Reilly, M. P. Sex differences in genomic drivers of adipose distribution and related cardiometabolic disorders: Opportunities for precision medicine. Arterioscl. Thromb. Vasc. Biol. 40(1), 45–60 (2020).Article 
CAS 
PubMed 

Google Scholar 
D’Amour, A. et al. Underspecification presents challenges for credibility in modern machine learning. J. Mach. Learn. Res. 23(1), 10237–10297 (2022).MathSciNet 

Google Scholar 
Ribeiro, M.T., Singh, S., & Guestrin, C. “Why should i trust you?” Explaining the predictions of any classifier. In: Proc. 22nd ACM SIGKDD international conference on knowledge discovery and data mining. (2016).Ross, A.S., Hughes, M.C., & Doshi-Velez, F. Right for the right reasons: Training differentiable models by constraining their explanations. Preprint at https://arXiv.org/quant-ph/1703.03717 (2017).Shrikumar, A., Greenside, P. & Kundaje, A. Learning important features through propagating activation differences. In International conference on machine learning (eds Shrikumar, A. et al.) (PMLR, 2017).
Google Scholar