Kronik hastalıkların Sosyoekonomik Belirleyicileri Üzerine bir Makine Öğrenmesi Analizi

Year 2025, Volume: 40 Issue: 4, 942 - 967, 01.10.2025

Ramazan Ekinci

https://doi.org/10.24988/ije.1491030

Abstract

Bu çalışmanın amacı sosyal, kültürel ve ekonomik değişkenlerle seçilmiş kronik hastalıklar (astım, kalp rahatsızlığı, hipertansiyon, şeker hastalığı, karaciğer yetmezliği, böbrek rahatsızlığı) arasındaki ilişkiyi analiz etmektir. Araştırmada kullanılan veri kümesinin büyük veri özelliğine sahip olması nedeniyle büyük veri tekniklerinden yararlanılmaktadır. Bu kapsamda, yapay zekanın bir alt dalı olan makine öğrenmesi yöntemi olan Derin öğrenme tekniği kullanılmaktadır. Çalışmada 2019 yılı Türkiye Sağlık Araştırması mikro veri seti kullanılmıştır. Derin öğrenme modelinden elde edilen sonuçlar, eğitim ve gelir düzeyindeki artışlar ile kronik rahatsızlıklar arasında negatif bir ilişkinin olduğunu göstermektedir. Modelde yer alan diğer değişkenlerden spor yapılan gün sayısı ile kronik hastalıklar arasında negatif bir ilişki görülürken, meyve yeme sıklığı ile kronik hastalıklar arasında hastalık türlerine göre pozitif (şeker hastalığı, böbrek rahatsızlığı) ve negatif (astım, kalp, hipertansiyon, karaciğer yetmezliği) bir ilişki görülmektedir. Bulgulardan hareketle, gelir düzeyi artan bireylerin yıpranan sağlık stoğunu telafi etmek amacıyla besin değeri yüksek gıdalara ve egzersiz gibi sportif faaliyetlere yöneleceği sonucuna ulaşılabilir. Öte yandan, eğitim düzeyindeki artış, bireylerin sağlığa yönelik riskleri daha iyi değerlendirmelerini sağlayarak, bireyleri koruyucu sağlık hizmetlerinden daha fazla yararlanmaları yönünde teşvik edebilir. Maliyet açısından ise diğer sağlık hizmetlerine göre daha uygun olan koruyucu sağlık hizmetlerine yönelik talebin artması sağlık sistemi üzerinde ortaya çıkan finansal yükü azaltabilir. Bu nedenle, koruyucu sağlık hizmetlerinin kullanımının artırılmasına yönelik politikalara önem verilmelidir.

Keywords

Kronik hastalıklar , sosyoekonomik faktörler , yapay zeka , makine öğrenimi , derin öğrenme

Supporting Institution

Bu çalışma İzmir Bakırçay Üniversitesi Bilimsel Araştırma Projeleri Koordinatörlüğü tarafından KBP.2021.004 nolu proje kapsamında desteklenmiştir.

A Machine Learning Analysis on Socioeconomic Determinants of Chronic Diseases

Abstract

This study explores the relationship between various social, cultural, and economic variables and selected chronic diseases such as asthma, heart disease, hypertension, diabetes, liver failure, and nephropathy. Given that the dataset exhibits characteristics typical of big data, big data techniques have been applied. Specifically, deep learning - a sub-branch of artificial intelligence within machine learning - was utilized. The analysis used the Türkiye Health Survey (2019) microdata set. Findings from the deep learning model reveal a negative correlation between levels of education and income and the incidence of chronic diseases. While the model reveals a negative correlation between the number of days engaging in sports activities and chronic diseases, it also shows that the relationship between another variable - the frequency of eating fruit -and chronic diseases can be either positive (diabetes, nephropathy) or harmful (asthma, heart disease, hypertension, liver failure), depending on the type of disease. The findings suggest that individuals with increasing income levels are likely to choose foods with high nutritional value and engage in sports activities such as exercise to compensate for their deteriorating health. On the other hand, increasing education levels may encourage individuals to use preventive health services more by enabling them to assess health risks better. As preventive health services are generally more cost-effective than other health services, increasing their demand can alleviate the financial strain on the healthcare system. Consequently, policies that promote the use of preventive healthcare services should be prioritized.

Keywords

Chronic diseases , socioeconomic factors , artificial intelligence , machine learning , deep learning

References

• Acton, J. P. (1975). Nonmonetary factors in the demand for medical services: Some empirical evidence. Journal of Political Economy, 83(3), 595-614.
• Adler, N., ve Stewart, J. (2010). The biology of disadvantage: Socioeconomic status and health. Annals of The New York Academy of Sciences, 1186(1), 1–275.
• Avlund, K., Holstein, B.E., Osler, M., Damsgaard, M.T., Holm-Pedersen, P., ve Rasmussen, N.K. (2003). Social position and health in old age: The relevance of different indicators of social position. Scandinavian journal of public health, 31(2):126-136.
• Behrendt, C. (2002). Do income surveys overestimate poverty in Western Europe? Evidence from a comparison with institutional frameworks. Social Indicators Research, 57(1-3), 429-440.
• Benzeval, M., ve Judge, K. (2001). Income and health: The time dimension. Social Science & Medicine, 52(9), 1371-1390.
• Bracke, P. (2000). The three-year persistence of depressive symptoms in men and women. Social Science & Medicine, 51(1), 51-64.
• Braveman, P., Egerter, S., ve Williams, D.R. (2011). The social determinants of health: Coming of age. Annual Review of Public Health, 32, 381-398.
• Carlson, P. (2004). The European health divide: A matter of financial or social capital? Social Science & Medicine, 59(1), 1985-1992.
• Cheng, Y.H., Chi, I., Boey, K.W., Ko, L.S., ve Chou, K.L. (2002). Self-rated economic condition and the health of elderly persons in Hong Kong. Social Science & Medicine, 55(8), 1415-1424.
• Chen, J. T., Beckfield, J., Waterman, P. D., ve Krieger, N. (2013). Can changes in the distributions of and associations between education and income bias temporal comparisons of health disparities? An exploration with causal graphs and simulations. American Journal of Epidemiology, 177(9), 870–881
• Doğan, F., ve Türkoğlu, İ. (2018). Derin öğrenme algoritmalarının yaprak sınıflandırma başarımlarının karşılaştırılması. Sakarya University Journal of Computer and Information Sciences, 1(1), 10-21.
• ECOSOC. (1998). Statement of commitment for action to eradicate poverty adopted by administrative committee on coordination. United Nations Economic and Social Council, ECOSOC/5759 , https://press.un.org/en/1998/19980520.eco5759.html
• Elliott, M. (2001). Gender differences in causes of depression. Women Health, 33(3-4), 163-177.
• Everson, S.A., Maty, S.C., Lynch, J.W., ve Kaplan, G.A. (2002). Epidemiologic Evidence for the relation between socioeconomic status and depression, obesity, and diabetes. Journal of Psychosomatic Research, 53(4), 891-895.
• Feinstein, J.S. (1993). The relationship between socioeconomic status and health: A review of the literature. The Milbank Quarterly, 71(2), 279-322.
• Fielding, J.E., ve Briss, P.A. (2006) Promoting evidence-based public health policy: Can we have better evidence and more action? Health Affairs, 25(4), 969-978.
• Fiscella, K., ve Franks, P. (1997). Poverty or income inequality as predictor of mortality: Longitudinal cohort study. BMJ, 314(7096), 1724-1727.
• Fritzell, J., Nermo, M., ve Lundberg, O. (2004). The impact of income: Assessing the relationship between income and health in Sweden. Scandinavian Journal of Public Health, 32(1), 6-16.
• Galea, S., Tracy, M., Hoggatt, K.J., Dimaggio, C., ve Karpati, A. (2011). Estimated deaths attributable to social factors in the United States. American Journal of Public Health, 101(8): 1456–1465.
• Galobardes, B., Smith, G. D., ve Lynch, J.W. (2006). Systematic review of the influence of childhood socioeconomic circumstances on risk for cardiovascular disease in adulthood. Annals of Epidemiology, 16(2), 91–104.
• Giordano, G. N., ve Lindstrom, M. (2010). The impact of changes in different aspects of social capital and material conditions on self-rated health over time: A longitudinal cohort study. Social Science & Medicine, 70(5), 700-710.
• Glasgow, R.E., ve Emmons, K.M. (2007). How can we increase translation of research into practice? Types of evidence needed. Annual Review of Public Health, 28, 413-33.
• Grosse, R.N., ve Harkavy, O. (1980). The role of health in development. Social Science & Medicine. Part C: Medical Economics, 14(2), 165-169.
• Grossman, M. (1999). The human capital model of the demand for health. National Bureau of Economic Research, Working Paper, No. 7078.
• Halleröd, B (1995). The truly poor: Indirect and direct measurement of consensual poverty in Sweden. Journal of European Social Policy, 5(2):111-129.
• Halleröd, B., ve Bask, M. (2008). Accumulation of welfare problems in a longitudinal perspective. Social Indicators Research, 88(2), 311-327.
• Harper, S., Lynch, J., Hsu, W.L., Everson, S.A., Hillemeier, M.M., Raghunathan, T.E., Salonen J.T., ve Kaplan, G.A. (2002). Life course socioeconomic conditions and adult psychosocial functioning. International Journal of Epidemiology, 31(2), 395-403.
• Hart, C.L., Smith, G.D., ve Blane, D. (1998). Inequalities in mortality by social class measured at 3 stages of the lifecourse. American Journal of Public Health, 88(3), 471-474.
• Ichoku, E. H., ve Leibbrandt, M. (2003). Demand for healthcare services in Nigeria: a multivariate nested logit model. African Development Review, 15(2‐3).
• Jemal, A., Siegel, R., Ward, E., Hao, Y., Xu, J., Murray, T., ve Thun, M.J. (2008). Cancer statistics, 2008. CA: A Cancer Journal for Clinicians, 58(2), 71-96.
• Kaplan, G.A., Shema, S.J., ve Leite, C.M. (2008). Socioeconomic determinants of psychological well-being: The role of income, income change, and income sources during the course of 29 years. Annals of Epidemiology, 18(7), 531-537.
• Kawachi, I., Subramanian, S.V., ve Almeida-Filho, N. (2002). A glossary for health inequalities. Journal of Epidemiology and Community Health, 56(9), 647 - 652.
• Kawachi, I., Kennedy, B.P., Lochner, K., ve Prowther-Stith, D. (1997). Social capital, income equality and mortality. American Journal of Public Health, 87(9), 1491–98.
• Koch, C.G., Li, L., Kaplan, G.A., Wachterman, J., Shishehbor, M.H., Sabik, J., ve Blackstone, E. H. (2010). Socioeconomic position, not race, is linked to death after cardiac surgery. Circulation: Cardiovascular Quality and Outcomes, 3(3), 267-76
• Laaksonen, M., Silventoinen, K., Martikainen, P., Rahkonen, O., Pitkäniemi, J., ve Lahelma, E. (2007). The effects of childhood circumstances, adult socioeconomic status, and material circumstances on physical and mental functioning: A structural equation modelling approach. Annals of Epidemiology, 17(6), 431-439.
• Laaksonen, E., Martikainen, P., Lahelma, E., Lallukka, T., Rahkonen, O., Head, J., ve Marmot, M. (2007). Socioeconomic circumstances and common mental disorders among Finnish and British public sector employees: Evidence from the Helsinki health study and the whitehall II study. International Journal of Epidemiology, 36(4), 776-786.
• Laaksonen, E., Lallukka, T., Lahelma, E., Ferrie, J.E., Rahkonen, O., Head, J., Marmot, M.G., ve Martikainen, P. (2010). Economic difficulties and physical functioning in Finnish and British employees: Contribution of social and behavioural factors. European Journal of Public Healty, 21(4), 456–462.
• Lahelma, E., Laaksonen, M., Martikainen, P., Rahkonen, O., ve Sarlio-Lähteenkorva, S. (2006). Multiple measures of socioeconomic circumstances and common mental disorders. Social Science & Medicine, 63(5), 1383-1399.
• Lee, D.W., Lee, J., Kim, H.R., ve Kang. M.Y. (2021). Health-related productivity loss according to health conditions among workers in South Korea. International Journal of Environmental Research and Public Health, 18(14), 1-22.
• Lépine, A., ve Le Nestour, A. (2011). Health care utilisation in rural Senegal: The facts before the extension of health insurance to farmers. International Labour Office, Geneva.
• Lewis, G., Bebbington, P., Brugha, T., Farrell, M., Gill, B., Jenkins, R., ve Meltzer, H. (1998). Socioeconomic status, standard of living, and neurotic disorder. The Lancet, 352(9128), 605-609.
• Lindelow, M. (2005). The utilisation of curative healthcare in Mozambique: Does income matter?. Journal of African Economies, 14(3), 435-482.
• Lynch, J.W., Kaplan, G.A., ve Shema, S.J. (1997). Cumulative impact of sustained economic hardship on physical, cognitive, psychological, and social functioning. New England Journal of Medicine, 337(26), 1889-1895.
• Lynch, J., Due, P., Muntaner, C., ve Smith, G.D. (2000). Social capital - is it a good investment strategy for public health? Journal of Epidemiology and Community Health, 54(6), 404-408.
• Lynch, J., Smith, G.D., Harper, S., Hillemeier, M., Ross, N., Kaplan, G.A., ve Wolfson, M. (2004). Is income inequality A determinant of population health? part 1. A systematic review. The Millbank Quarterly, 82(1), 5–99.
• Lorant, V., Deliege, D., Eaton, W., Robert, A., Philippot, P., ve Ansseau, M. (2003). Socioeconomic inequalities in depression: a meta-analysis. American Journal of Epidemiology, 157(2), 98-112.
• Lorant, V., Croux, C., Weich, S., Deliege, D., Mackenbach, J., ve Ansseau, M. (2007). Depression and socio-economic risk factors: 7-year longitudinal population study. British Journal of Psychiatry, 190(1), 293-298.
• Mackenbach, J.P. (2006). Health Inequalities: Europe in Profile. London: UK Dep. Healty
• Mackenbach, J.P., ve Howden-Chapman, P. (2003). New perspectives on socioeconomic inequalities in health. Perspectives in Biology and Medicine, 46 (1), 428–44.
• Marmot, M. (1999). Epidemiology of socioeconomic status and health: Are determinants within countries the same as between countries? Annals of The New York Academy of Sciences, 896 (1), 16–29.
• Martikainen, P., Adda, J., Ferrie, J.E., Davey Smith, G., ve Marmot, M. (2003). Effects of income and wealth on GHQ depression and poor self rated health in white collar women and men in the whitehall II study. Journal of Epidemiology and Community Health, 57(9),718-723.
• McGinnis, J.M, Williams-Russo, P., ve Knickman, J.R. (2002). The case for more active policy attention to health promotion. Health Affairs, 21(2), 78-93.
• McGinnis, J.M., ve Foege, W.H. (1993). Actual causes of death in the United States. The Journal of the American Medical Association (JAMA), 270(18), 2207–2212.
• McDonough, P., ve Berglund., P. (2003). Histories of poverty and self-rated health trajectories. Journal of Health and Social Behavior, 44(2), 198-214.
• Melzer, D., Fryers, T., Jenkins, R., Brugha, T., ve McWilliams, B. (2003). Social position and the common mental disorders with disability: Estimates from the national psychiatric survey of great britain. Social Psychiatry and Psychiatric Epidemiology, 38(5), 238-243.
• Mirowsky, J., ve Ross, C.E. (2001). Age and the effect of economic hardships on depression. Journal of Health and Social Behavior, 42(2), 132-150.
• Mocan, H. N., Tekin, E., ve Zax, J. S. (2004). The demand for medical care in urban China. World Development, 32(2),289-304.
• Mowafi, M., ve Khawaja, M. (2005). Poverty. Journal of Epidemiology and Community Health, 59(4):260-264.
• Muntaner, C., Borrell, C., Benach, J., Pasarin, M.I., ve Fernandez, E. (2003). The associations of social class and social stratification with patterns of general and mental health in a Spanish population. International Journal of Epidemiology, 32(6), 950-958.
• Nandakumar, A. K., Chawla, M., ve Khan, M. (2000). Utilization of outpatient care in Egypt and its implications for the role of government in health care provision. World Development, 28(1), 187-196.
• Pudrovska, T., Schieman, S., Pearlin, L.I., ve Nguyen, K. (2005). The sense of mastery as a mediator and moderator in the association between economic hardships and health in late life. Journal of Aging Research, 17(5), 634-660.
• Ssewanyana, S., Nabyonga, J. O., Kasirye, I., ve Lawson, D. (2004). Demand for health care services in Uganda: Implications for poverty reduction. Economic Policy Research Centre (EPRC). Research Series 150529, (No. 677-2016-46634).
• Ringbäck-Weitoft, G. (2001). Social differences, vulnerability and Ill-health. Scandinavian Journal of Public Health. Supplement, 29(58), 199-218
• Ringbäck-Weitoft, G., ve Rosén, M. (2005). Is perceived nervousness and anxiety a predictor of premature mortality and severe morbidity? A longitudinal follow up of the Swedish survey of living conditions. Journal of Epidemiology and Community Health, 59(9), 794-798.
• Ringen S. (1988). Direct and indirect measures of poverty. Journal of Social Policy. 17(3), 351-365.
• Skapinakis, P. (2007). Commentary: Socioeconomic position and common mental disorders: What do we need to know? International Journal of Epidemiology, 36(4), 786-788.
• Skapinakis, P., Weich, S., Lewis, G., Singleton, N., ve Araya, R. (2006). Socio-economic position and common mental disorders. Longitudinal study in the general population in The UK. The British Journal of Psychiatry, 189, 109-117.
• Smith, K.R., ve Zick, C.D. (1994). Linked lives, dependent demise? Survival analysis of husbands and wives. Demography, 31(1), 81-93.
• Stafford, M., De Silva, M., Stansfeld, S., ve Marmot, M. (2008). Neighbourhood social capital and common mental disorder: Testing the link in a general population sample. Health & Place, 14(1), 394-405.
• Stringhini, S., Sabia, S., Shipley, M., Brunner, E., Nabi, H., Kivimaki, M., ve Singh-Manoux, A. (2010). Association of socioeconomic position with health behaviors and mortality. The Journal of the American Medical Association (JAMA), 303, 1159-1166.
• Sun, X., Rehnberg, C., ve Meng, Q. (2009). How are individual-level social capital and poverty associated with health equity? A study from two Chinese Cities. International Journal for Equity in Health, 8(1), 1-13.
• Şeker, A., Diri, B., ve Balık, H. H. (2017). Derin öğrenme yöntemleri ve uygulamaları hakkında bir inceleme. Gazi Mühendislik Bilimleri Dergisi, 3(3), 47-64.
• Şişmanoğlu, G., Koçer, F., Önde, M. A., ve Şahingöz, O. K. (2020). Derin öğrenme yöntemleri ile borsada fiyat tahmini. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, 9 (1), 434-445.
• Townsend, P. (1979). Poverty in the United Kingdom: A Survey of Household Resources and Standards of Living. Penguin Books Ltd, Harmondsworth, Middlesex, England
• Wamala, S.P., Lynch, J., ve Kaplan, G.A. (2001). Women's exposure to early and later life socioeconomic disadvantage and coronary heart disease risk: The Stockholm female coronary risk study. International Journal of Epidemiology, 30(2), 275-284.
• Wang, J.L., Schmitz, N., ve Dewa, C.S. (2010). Socioeconomic status and the risk of major depression: the Canadian National Population Health Survey. Journal of Epidemiology and Community Health, 64(5), 447-452.
• Weich, S., ve Lewis, G. (1998). Material standard of living, social class, and the prevalence of the common mental disorders in Great Britain. Journal of Epidemiology and Community Health, 52(1), 8-14.
• Whelan, C., Layte, R., Nolan, B., ve Mailtre, B. (2001). Income, deprivation and economic strain: An analysis of the european community household panel. European Sociological Review, 17(4), 357-372.
• Wilkinson, R.G. (2000). Inequality and the social environment: A Reply to Lynchet al. Journal of Epidemiol Community Health, 54(6), 411-413.
• Wilkinson, R., ve Marmot, M. (2003). Social Determinants of Health: The Solid Facts. Copenhagen: World Health Organization.
• World Health Organization (WHO). (1986). The Ottawa Charter for Health Promotion. Copenhagen: WHO, Health Canada, CPHA.
• World Health Organization (WHO). (2008). Closing the Gap in a Generation: Health Equity Through Action on the Social Determinants of Health - Final Report of the Commission on Social Determinants of Health. Commission on Social Determinants of Health (CSDH) final report. Geneva.
• Yaylalı, M., Kaynak, S., ve Karaca, Z. (2012). Sağlık hizmetleri talebi: Erzurum ilinde bir araştırma. Ege Akademik Bakış, 12(4).
• Yılmaz, A., ve Kaya, U. (2022). Derin Öğrenme. 4. Baskı, Kodlab Yayın, İstanbul.
• Zimmerman, F.J., Katon, W. (2005). Socioeconomic status, depression disparities, and financial strain: What lies behind the income-depression relationship? Health Economics, 14(12), 1197-1215.