Abstract
Lipid profile usually includes levels of total cholesterol (TCH), low density lipoprotein (LDL), high density lipoprotein (HDL) and triglycerides (TG), all of which require a blood test. Using advances in machine learning and a relationship between lipid profile and obesity, a model that predicts lipid profile without using any laboratory results can be developed and used in clinical diagnosis. The causal relationship between lipid profile and obesity is well known—TCH, LDL and TG show an increase, while HDL is decreased in obese persons. In this paper we are using artificial neural networks (ANN) to estimate the lipid profile values using non-lab electronic health record data and some measures of obesity. The ANN inputs are gender, age, systolic and diastolic blood pressures, and a single or a combination of multiple obesity parameters, which include body mass index, saggital abdominal diameter to height ratio, waist to height ratio and body fat percentage. Study shows that the presented solution is suitable for prediction of TCH (with accuracy 81.89%), LDL (with accuracy 79.29%) and HDL (with accuracy 81.23%), while not suitable for TG prediction (with accuracy 44.48%).
Similar content being viewed by others
References
Abu-Mostafa YS, Magdon-Ismail M, Lin HT (2012) Learning from data. AMLBook, Pasadena
Appel SJ, Jones ED, Kennedy-Malone L (2004) Central obesity and the metabolic syndrome: implications for primary care providers. J Am Acad Nurse Pract 16(8):335–342
Arabasadi Z, Alizadehsani R, Roshanzamir M, Moosaei H, Yarifard AA (2017) Computer aided decision making for heart disease detection using hybrid neural network-genetic algorithm. Comput Methods Programs Biomed 141:19–26. https://doi.org/10.1016/j.cmpb.2017.01.004
Arroyo M, Rocandio AM, Ansotegui L, Herrera H, Salces I, Rebato E (2004) Comparison of predicted body fat percentage from anthropometric methods and from impedance in university students. Br J Nutr 92(5):827–832
Ashwell M, Lejeune S, McPherson K (1996) Ratio of waist circumference to height may be better indicator of need for weight management. Br Med J 312(7027):377
Ashwell M, Gunn P, Gibson S (2012) Waist-to-height ratio is a better screening tool than waist circumference and BMI for adult cardiometabolic risk factors: systematic review and meta-analysis. Obes Rev 13(3):275–286. https://doi.org/10.1111/j.1467-789X.2011.00952.x
Beeson W, Batech M, Schultz E, Salto L, Firek A, Deleon M, Balcazar H, Cordero-Macintyre Z (2010) Comparison of body composition by bioelectrical impedance analysis and dual-energy X-ray absorptiometry in hispanic diabetics. Int J Body Compos Res 8(2):45–50
Belletti DA, Zacker C, Wogen J (2010) Effect of cardiometabolic risk factors on hypertension management: a cross-sectional study among 28 physician practices in the United States. Cardiovasc Diabetol 9(1):7
Bhatti MS, Akbri MZA, Shakoor M (2001) Lipid profile in obesity. J Ayub Med Coll Abbottabad 13(1):31–3
Cartwright MJ, Tchkonia T, Kirkland JL (2007) Aging in adipocytes: potential impact of inherent, depot-specific mechanisms. Exp Gerontol 42(6):463–471
Chung K, Yoo H, Choe DE (2018) Ambient context-based modeling for health risk assessment using deep neural network. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-018-1033-7
Cybenko G (1989) Approximation by superpositions of a sigmoidal function. Math Control Signals Syst 2(4):303–314
D’Agostino RB, Vasan RS, Pencina MJ, Wolf PA, Cobain M, Massaro JM, Kannel WB (2008) General cardiovascular risk profile for use in primary care: the Framingham heart study. Circulation 117(6):743–753. https://doi.org/10.1161/CIRCULATIONAHA.107.699579
Das R, Turkoglu I, Sengur A (2009) Effective diagnosis of heart disease through neural networks ensembles. Expert Syst Appl 36(4):7675–7680
Despres JP, Moorjani S, Lupien PJ, Tremblay A, Nadeau A, Bouchard C (1990) Regional distribution of body fat, plasma lipoproteins, and cardiovascular disease. Arteriosclerosis 10(4):497–511
Faeh D, Braun J, Bopp M (2012) Body mass index vs cholesterol in cardiovascular disease risk prediction models. JAMA Intern Med 172(22):1766–1768
Gallagher D, Visser M, Sepulveda D, Pierson RN, Harris T, Heymsfield SB (1996) How useful is body mass index for comparison of body fatness across age, sex, and ethnic groups? Am J Epidemiol 143(3):228–239
Gaziano TA, Young CR, Fitzmaurice G, Atwood S, Gaziano JM (2008) Laboratory-based versus non-laboratory-based method for assessment of cardiovascular disease risk: the NHANES I follow-up study cohort. The Lancet 371(9616):923–931
Green BB, Anderson ML, Cook AJ, Catz S, Fishman PA, McClure JB, Reid R (2012) Using body mass index data in the electronic health record to calculate cardiovascular risk. Am J Prev Med 42(4):342–347
Hinkle DE, Wiersma W, Jurs SG et al (1988) Applied statistics for the behavioral sciences, 2nd edn. Houghton Mifflin, Boston
Hsieh SD, Yoshinaga H (1999) Do people with similar waist circumference share similar health risks irrespective of height? Tohoku J Exp Med 188(1):55–60
Jackson AS, Stanforth P, Gagnon J, Rankinen T, Leon AS, Rao D, Skinner J, Bouchard C, Wilmore J (2002) The effect of sex, age and race on estimating percentage body fat from body mass index: the heritage family study. Int J Obes 26(6):789–796
Kahn HS, Bullard KM (2016) Beyond body mass index: advantages of abdominal measurements for recognizing cardiometabolic disorders. Am J Med 129(1):74–81. https://doi.org/10.1016/j.amjmed.2015.08.010
Kahn HS, Bullard KM (2017) Indicators of abdominal size relative to height associated with sex, age, socioeconomic position and ancestry among us adults. PloS ONE 12(3):e0172245. https://doi.org/10.1371/journal.pone.0172245
Kim MG, Ko H, Pan SB (2019) A study on user recognition using 2D ECG based on ensemble of deep convolutional neural networks. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-019-01195-4
Kononenko I (2001) Machine learning for medical diagnosis: history, state of the art and perspective. Artif Intell Med 23(1):89–109. https://doi.org/10.1016/S0933-3657(01)00077-X
Kuk JL, Lee S, Heymsfield SB, Ross R (2005) Waist circumference and abdominal adipose tissue distribution: influence of age and sex. Am J Clin Nutr 81(6):1330–1334
Kupusinac A, Stokić E, Srdić B (2012) Determination of WHtR limit for predicting hyperglycemia in obese persons by using artificial neural networks. TEM J 1(4):270–272
Kupusinac A, Doroslovački R, Malbaški D, Srdić B, Stokić E (2013) A primary estimation of the cardiometabolic risk by using artificial neural networks. Comput Biol Med 43(6):751–757. https://doi.org/10.1016/j.compbiomed.2013.04.001
Kupusinac A, Stokić E, Doroslovački R (2014) Predicting body fat percentage based on gender, age and BMI by using artificial neural networks. Comput Methods Programs Biomed 113(2):610–619. https://doi.org/10.1016/j.cmpb.2013.10.013
Kupusinac A, Stokić E, Lečić D, Tomić-Naglić D, Srdić-Galić B (2015) Gender-, age-, and BMI-specific threshold values of sagittal abdominal diameter obtained by artificial neural networks. J Med Biol Eng 35(6):783–788. https://doi.org/10.1007/s40846-015-0090-z
Malasinghe LP, Ramzan N, Dahal K (2019) Remote patient monitoring: a comprehensive study. J Ambient Intell Human Comput 10(1):57–76. https://doi.org/10.1007/s12652-017-0598-x
Meeuwsen S, Horgan G, Elia M (2010) The relationship between BMI and percent body fat, measured by bioelectrical impedance, in a large adult sample is curvilinear and influenced by age and sex. Clin Nutr 29(5):560–566
Misra A, Vikram NK (2003) Clinical and pathophysiological consequences of abdominal adiposity and abdominal adipose tissue depots. Nutrition 19(5):457–466
Orozco-Beltran D, Gil-Guillen VF, Redon J, Martin-Moreno JM, Pallares-Carratala V, Navarro-Perez J, Valls-Roca F, Sanchis-Domenech C, Fernandez-Gimenez A, Perez-Navarro A et al (2017) Lipid profile, cardiovascular disease and mortality in a mediterranean high-risk population: the ESCARVAL-RISK study. PLoS ONE 12(10):e0186196. https://doi.org/10.1371/journal.pone.0186196
Picard RR, Cook RD (1984) Cross-validation of regression models. J Am Stat Assoc 79(387):575–583
Risérus U, De Faire U, Berglund L, Hellénius ML (2010) Sagittal abdominal diameter as a screening tool in clinical research: cutoffs for cardiometabolic risk. J Obes. https://doi.org/10.1155/2010/757939
Shao J (1993) Linear model selection by cross-validation. J Am Stat Assoc 88(422):486–494
Stevens J, Katz EG, Huxley RR (2010) Associations between gender, age and waist circumference. Eur J Clin Nutr 64(1):6–15
Stokić E, Galić BS, Kupusinac A, Doroslovački R (2013) Estimating SAD low-limits for the adverse metabolic profile by using artificial neural networks. TEM J 2(2):115–119
Szczygielska A, Widomska S, Jaraszkiewicz M, Knera P, Muc K (2003) Blood lipids profile in obese or overweight patients. Ann Univ Mariae Curie-Sklodowska Sect D Med 58(2):343–9
Tabachnick BG, Fidell LS, Ullman JB (2007) Using multivariate statistics, 5th edn. Pearson, London
Voss R, Cullen P, Schulte H, Assmann G (2002) Prediction of risk of coronary events in middle-aged men in the prospective cardiovascular Münster study (PROCAM) using neural networks. Int J Epidemiol 31(6):1253–1262. https://doi.org/10.1093/ije/31.6.1253
Weng SF, Reps J, Kai J, Garibaldi JM, Qureshi N (2017) Can machine-learning improve cardiovascular risk prediction using routine clinical data? PLoS ONE 12(4):e0174944
World Health Organization (2000) Obesity: preventing and managing the global epidemic: report of a WHO consultation. Technical report 894
Acknowledgements
This work was partially supported by the Ministry of Education, Science and Technological Development of the Republic of Serbia within the Projects: ON 174026 and III 044006, and by the Provincial Secretariat for Higher Education and Scientific Research of the Autonomous Province of Vojvodina within the Projects: 114-451-2856/2016-02 and 142-451-3557/2017-01.
Funding
This study was funded by the Ministry of Education, Science and Technological Development of the Republic of Serbia (ON 174026 and III 044006) and by the Provincial Secretariat for Higher Education and Scientific Research of the Autonomous Province of Vojvodina (114-451-2856/2016-02 and 142-451-3557/2017-01).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors hereby declare that they have no conflicts of interest.
Ethical approval
This research was approved by Ethical Committee of the Clinical Centre of Vojvodina, Republic of Serbia (No. 00–20/354). All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.
Informed consent
Informed consent was obtained from all individual participants included in the study.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Vrbaški, M., Doroslovački, R., Kupusinac, A. et al. Lipid profile prediction based on artificial neural networks. J Ambient Intell Human Comput 14, 15523–15533 (2023). https://doi.org/10.1007/s12652-019-01374-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-019-01374-3