Nutritional Signatures of Diabetes Mellitus, Cognitive Impairment, and Their Co-Occurrence: A Machine-Learning Analysis of NHANES 2011–2014

Guangsha Xia

doi:10.54097/n2c5zj03

Authors

Guangsha Xia

DOI:

https://doi.org/10.54097/n2c5zj03

Keywords:

type-2 diabetes; cognitive impairment; dietary patterns; NHANES; precision nutrition.

Abstract

Type-2 diabetes mellitus (DM) and cognitive impairment (CI) share pathophysiological pathways modifiable by diet. Whether their co-occurrence (DM+CI) confers a unique nutritional phenotype has not been examined at population scale. We harmonised NHANES 2011–2012 and 2013–2014 cycles (n = 19,151 adults aged ≥18 y). DM was defined by self-reported physician diagnosis; CI by age-stratified 20th-centile DSST score. Eleven 24-h recall nutrients were z-standardised and reduced by PCA. A multi-class XGBoost model was tuned with Optuna and validated with 5-fold stratified cross-validation. SHAP explained feature contributions. Among 19,151 participants, 1,261 had DM alone, 349 CI alone, 141 DM+CI. Three PCA patterns explained 86.6 % variance: PC1 “energy-dense” (69.0 %), PC2 “carbohydrate–fat balance” (9.4 %), PC3 “fiber-rich” (8.3 %). DM+CI displayed a low-calorie, low-carbohydrate signature (calories −23 %, carbohydrates −30 % vs. healthy controls; p < 0.001). The optimised model achieved macro-F1 0.72; AUROC was 0.960 for DM+CI, 0.926 for CI, 0.836 for DM. SHAP attributed greatest importance to age and PC1; carbohydrate reduction specifically drove DM+CI classification. DM+CI exhibits a distinct low-energy-density nutritional phenotype. Interpretable ML provides actionable dietary targets for precision nutrition.

Downloads

Download data is not yet available.

References

[1] International Diabetes Federation. IDF Diabetes Atlas, 10th ed. Brussels, Belgium: International Diabetes Federation; 2021

[2] World Health Organization. Dementia Fact Sheet. Geneva, Switzerland: WHO; 2022. Available at: https://www.who.int/news-room/fact-sheets/detail/dementia

[3] Biessels GJ, Strachan MWJ, Visseren FLJ, et al. Dementia and cognitive decline in type 2 diabetes and prediabetic stages: a systematic review and meta-analysis. Lancet Neurol. 2018;17(2):169–182. doi:10.1016/S1474-4422(17)30377-6

[4] Rawlings AM, Sharrett AR, Schneider ALC, et al. Diabetes in midlife and cognitive change over 20 years: a cohort study. Ann Intern Med. 2014;161(11):785–793. doi:10.7326/M14-0737

[5] Xue M, Xu W, Ou YN, et al. Diabetes mellitus and risks of cognitive impairment and dementia: a systematic review and meta-analysis of 144 prospective studies. Ageing Res Rev. 2019; 55:100944. doi: 10.1016/j.arr.2019.100944

[6] Ohara T, Doi Y, Ninomiya T, et al. Glucose tolerance status and risk of dementia in the community: the Hisayama study. Neurology. 2011;77(12):1126–1134. doi:10.1212/WNL.0b013e31822f0435

[7] Singh VP, Bali A, Singh N, Jaggi AS. Advanced glycation end products and diabetic complications. Korean J Physiol Pharmacol. 2014;18(1):1–14. doi:10.4196/kjpp.2014.18.1.1

[8] Kellar D, Craft S. Brain insulin resistance in Alzheimer’s disease and related disorders: mechanisms and therapeutic approaches. Lancet Neurol. 2022;21(8):722–734. doi:10.1016/S1474-4422(22)00153-3

[9] Last D, Alsop DC, Abduljalil AM, et al. Global and regional effects of type 2 diabetes on brain tissue volumes and cerebral vasoreactivity. Diabetes Care. 2017;40(5):703–710. doi:10.2337/dc16-2258

[10] Srikanthan K, Feyh A, Visweshwar H, et al. Systemic inflammation and metabolic syndrome. Cardiol Rev. 2015;23(1):15–22. doi:10.1097/CRD.0000000000000093

[11] Liu S, Manson JE. Dietary carbohydrates, physical inactivity, obesity, and the 'metabolic syndrome' as predictors of coronary heart disease. Curr Opin Lipidol. 2001;12(4):395–404. doi:10.1097/00041433-200108000-00004

[12] Power MC, Mormino E, Soldan A, et al. Added sugar intake and cognitive score in a longitudinal cohort. J Prev Alzheimers Dis. 2021;8(2):164–170. doi:10.14283/jpad.2020.48

[13] Salas-Salvadó J, Guasch-Ferré M, Lee CH, et al. Protective effects of the Mediterranean diet on type 2 diabetes and metabolic syndrome. J Nutr. 2018;148(11):1801–1812. doi:10.1093/jn/nxy201

[14] Scarmeas N, Anastasiou CA, Yannakoulia M. Nutrition and prevention of cognitive impairment. Lancet Neurol. 2018;17(11):1006–1015. doi:10.1016/S1474-4422(18)30338-7

[15] Hu FB. Dietary pattern analysis: a new direction in nutritional epidemiology. Curr Opin Lipidol. 2002;13(1):3–9. doi:10.1097/00041433-200202000-00002

[16] Khera R, Krumholz HM. Machine learning for clinical prediction models: a review. Circulation. 2018;137(23):2435–2441. doi:10.1161/CIRCULATIONAHA.118.034512

[17] Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst. 2017; 30:4765–4774.

[18] Centers for Disease Control and Prevention (CDC). National Health and Nutrition Examination Survey (NHANES), 2011–2014. Hyattsville, MD: National Center for Health Statistics.

[19] Willett WC. Nutritional Epidemiology. 3rd ed. Oxford University Press; 2019.

[20] Spanakis EK, Golden SH. Race/ethnicity and diabetes diagnosis in NHANES: validation of self-reported diagnosis. Diabetes Care. 2022;45(2): e30–e31. doi:10.2337/dc21-1952

[21] Dodge HH, Zhu J, Lee CW, et al. Use of screening tests for cognitive impairment in older adults. J Am Geriatr Soc. 2007;55(12):1925–1932. doi:10.1111/j.1532-5415.2007. 01446.x

[22] Kuo HK, Sorond FA, Chen JH, et al. The role of DSST in cognitive impairment screening. J Alzheimers Dis. 2022;87(3):1103–1111. doi:10.3233/JAD-215567

[23] Moshfegh AJ, Rhodes DG, Baer DJ, et al. The US Department of Agriculture Automated Multiple-Pass Method reduces bias in the collection of energy intakes. Am J Clin Nutr. 2008;88(2):324–332. doi:10.1093/ajcn/88.2.324

[24] Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. J Artif Intell Res. 2002; 16:321–357. doi:10.1613/jair.953

[25] Kivipelto M, Mangialasche F, Ngandu T. Lifestyle interventions to prevent cognitive impairment, dementia and Alzheimer disease. Nat Rev Neurol. 2018;14(11):653–666. doi:10.1038/s41582-018-0070-3

[26] O’Donnell MJ, Yusuf S, Mente A, et al. Sodium and cardiovascular disease: a population-level analysis. N Engl J Med. 2020;382(13):1237–1249. doi:10.1056/NEJMoa1917169

[27] American Heart Association (AHA). Dietary Guidance to Improve Cardiovascular Health. AHA Scientific Statement; 2021.

[28] Lourida I, Soni M, Thompson-Coon J, et al. Mediterranean diet, cognitive function, and dementia: a systematic review. Epidemiology. 2013;24(4):479–489. doi:10.1097/EDE.0b013e3182944410

[29] de la Monte SM. Brain insulin resistance and deficiency as therapeutic targets in Alzheimer’s disease. Curr Alzheimer Res. 2012;9(1):35–66. doi:10.2174/156720512799015955

[30] Munshi MN. Management of diabetes in the elderly. Med Clin North Am. 2017;101(3):515–530. doi: 10.1016/j.mcna.2016.12.009

[31] Schwartz MW, Seeley RJ, Zeltser LM, et al. Obesity and diabetes: pathogenesis and treatment. J Clin Invest. 2020;130(9):4517–4529. doi:10.1172/JCI139934

[32] Madeo F, Carmona-Gutierrez D, Hofer SJ, Kroemer G. Caloric restriction mimetics against age-associated disease: targets, mechanisms, and therapeutic potential. Cell Metab. 2018;28(3):323–340. doi: 10.1016/j.cmet.2018.07.008

[33] Franzago M, Stuppia L, Vitacolonna E. Energy restriction and sarcopenia: mechanisms and nutritional interventions. Nutrients. 2022;14(3):599. doi:10.3390/nu14030599

[34] Bauer J, Biolo G, Cederholm T, et al. Evidence-based recommendations for optimal dietary protein intake in older people: a position paper from the PROT-AGE Study Group. J Am Med Dir Assoc. 2013;14(8):542–559. doi: 10.1016/j.jamda.2013.05.021

[35] World Health Organization (WHO). Guideline: Sodium Intake for Adults and Children. Geneva: WHO Press; 2021.

[36] Ding J, Strachan MWJ, Reynolds RM, Frier BM. Diabetic retinopathy and cerebral small vessel disease. Diabetologia. 2021;64(8):1858–1869. doi:10.1007/s00125-021-05488-2

[37] Dietary Guidelines Advisory Committee (DGAC). Scientific Report of the 2020 Dietary Guidelines Advisory Committee. Washington, DC: U.S. Department of Agriculture; 2020.

[38] Zhang X, Zhang G, Zhang H, et al. Fructose-induced neuroinflammation and insulin resistance in the brain. J Nutr Biochem. 2022; 102:108955. doi: 10.1016/j.jnutbio.2021.108955

[39] Ma Q, Xing C, Long W, et al. Impact of microbiota on central nervous system and neurological diseases: the gut–brain axis. J Neuroinflammation. 2022;19(1):45. doi:10.1186/s12974-022-02410-8

[40] European Society for Clinical Nutrition and Metabolism (ESPEN). ESPEN Guidelines on Clinical Nutrition and Metabolism in Older Adults. Clin Nutr. 2021;40(3):650–667. doi: 10.1016/j.clnu.2021.01.008

[41] American Diabetes Association (ADA). Standards of Medical Care in Diabetes—2023. Diabetes Care. 2023;46(Suppl 1): S1–S298. doi:10.2337/dc23-Sint

[42] Petersson SD, Philippou E. Mediterranean diet, cognitive function, and dementia: a systematic review. Epidemiol Health. 2022;44: e2022011. doi:10.4178/epih. e2022011

[43] Trieu K, Neal B, Hawkes C, et al. Salt reduction initiatives around the world: a systematic review. BMJ Glob Health. 2021;6(8): e005982. doi:10.1136/bmjgh-2021-005982

[44] Powell LM, Maciejewski ML. Sugar-sweetened beverage taxes and public health: a systematic review and meta-analysis. Obesity. 2020;28(1):1–14. doi:10.1002/oby.22639