Classification of Chronic Disease Status of Individuals Using Machine Learning Methods: An Application on The 2023 Income and Living Conditions Survey of the Turkish Statistical Institute

Abstract

The increasing prevalence of chronic diseases and their negative impact on the quality of life of individuals is one of the priority issues in the field of public health. Early diagnosis and management of these diseases is a process complicated by inequalities in access to healthcare services and socio-economic factors. In this context, machine learning methods offer significant potential for making predictions by extracting information from large and complex data sets. In particular, the TabNet method stands out for its strong predictive capabilities and ability to model complex relationships. This study aims to classify the chronic disease status of individuals using methods such as Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), Support Vector Machines (SVM), Random Forest, Gradient Boosting and TabNet using data from the 2023 Income and Living Conditions Survey of the Turkish Statistical Institute. The results showed that overall access to health services is good, but some segments still have difficulty accessing it; chronic diseases have a strong relationship with factors such as general health status and employment; and the TabNet method can perform effective classification with performance metrics such as high accuracy, precision and sensitivity. As a result, the model successfully classified chronic disease status with an overall accuracy rate of 97%. This study provides valuable information that can be used to make strategic decisions for health policy development and sectoral analysis, and highlights the importance of using machine learning methods, particularly the TabNet technique, effectively in health data analysis.

Keywords

• Machine Learning
• Data Classification
• Chronic Disease Management
• Health Policy Development
• TabNet

Makine Öğrenimi Yöntemleri ile Bireylerin Kronik Hastalık Durumlarının Sınıflandırılması: Türkiye İstatistik Kurumu’nun 2023 Gelir ve Yaşam Koşulları Araştırması Üzerine Bir Uygulama

Abstract

Kronik hastalıkların artan prevalansı (görülme sıklığı) ve bunların bireylerin yaşam kalitesi üzerindeki olumsuz etkileri, kamu sağlığı alanında öncelikli meseleler arasında yer almaktadır. Bu hastalıkların erken teşhis ve yönetimi, sağlık hizmetlerine erişimdeki eşitsizlikler ve sosyoekonomik faktörlerle karmaşıklaşan bir süreçtir. Bu bağlamda, makine öğrenimi yöntemleri, büyük ve karmaşık veri kümelerinden bilgi çıkararak tahminlerde bulunma konusunda önemli bir potansiyel sunmaktadır. Özellikle TabNet yöntemi, güçlü tahmin yetenekleri ve karmaşık ilişkileri modelleme kapasitesi ile dikkat çekmektedir. Bu çalışma, Türkiye İstatistik Kurumu’nun 2023 Gelir ve Yaşam Koşulları Araştırması verilerini kullanarak, Yapay Sinir Ağları (YSA), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Destek Vektör Makinesi (DVM), Rastgele Orman, Gradient Boosting ve TabNet gibi yöntemler ile bireylerin kronik hastalık durumlarının sınıflandırılmasını amaçlamaktadır. Bulgular, sağlık hizmetlerine genel erişimin iyi olduğunu, ancak bazı kesimlerin hala erişimde zorluklar yaşadığını; kronik hastalıkların genel sağlık durumu ve istihdam gibi faktörlerle güçlü bir ilişkisi olduğunu ve TabNet yönteminin yüksek doğruluk, kesinlik ve duyarlılık gibi performans metrikleri ile etkili bir sınıflandırma yapabildiğini ortaya koymuştur. Sonuç olarak model, %97 genel doğruluk oranı ile kronik hastalık durumunu başarıyla sınıflandırmıştır. Bu çalışma, sağlık politikalarının geliştirilmesi ve sektörel analizler için stratejik kararlar alınmasında kullanılabilecek değerli bilgiler sunmakta ve makine öğrenimi yöntemlerinin, özellikle TabNet tekniğinin, sağlık verileri analizinde etkin bir şekilde kullanılmasının önemini vurgulamaktadır.

Keywords

• Makine Öğrenimi
• Veri Sınıflandırma
• Kronik Hastalık Yönetimi
• TabNet
• Sağlık Politikaları Geliştirme

References

1. Ahmed, N. A., Yiğit, A., Işık, Z., Alpkoçak, A., 2019. Identification of leukemia subtypes from microscopic images using convolutional neural network. Diagnostics, 9(3), 104. https://doi.org/10.3390/diagnostics9030104
2. Ahsan, M., Khan, A., Khan, K. R., Sinha, B. B., Sharma, A. 2023. Advancements in medical diagnosis and treatment through machine learning: a review. Expert Systems, 41(3). https://doi.org/10.1111/exsy.13499
3. Akcan, F., Sertbaş, A., 2021. Topluluk Öğrenmesi Yöntemleri ile Göğüs Kanseri Teşhisi. Electronic Turkish Studies, 16(2).
4. Albin Ahmed, A., Shaahid, A., Alnasser, F., Alfaddagh, S., Binagag, S., Alqahtani, D., 2023. Android ransomware detection using supervised machine learning techniques based on traffic analysis. Sensors, 24(1), 189. https://doi.org/10.3390/s24010189
5. Almutairi, M., Chiroma, H., Abubakar, S., 2022. Detecting elderly behaviors based on deep learning for healthcare: recent advances, methods, real-world applications and challenges. IEEE Access, 10, 69802-69821. https://doi.org/10.1109/access.2022.3186701
6. Al-Shamisi, M. H., Assi, A., Hejase, H., 2013. Artificial neural networks for predicting global solar radiation in al ain city - uae. International Journal of Green Energy, 10(5), 443-456. https://doi.org/10.1080/15435075.2011.641187
7. Altuntaş, O., Esra, A. K. I., Huri, M., 2015. Kronik hastalıklarda ilaç kullanımının yaşam kalitesi ve sosyal katılıma etkisi üzerine nitel bir çalışma. Ergoterapi ve Rehabilitasyon Dergisi, 3(2), 79-86.
8. An, W., Liang, M., 2012. A new intrusion detection method based on svm with minimum within‐class scatter. Security and Communication Networks, 6(9), 1064-1074. https://doi.org/10.1002/sec.666

9. Anjum, M. J., Tariq, F., Anjum, K. M., Shaheen, M., Ahmad, F., 2023. Identification of diseases caused by non-synonymous single nucleotide polymorphism using random forest and linear regression algorithms. https://doi.org/10.21203/rs.3.rs-3001745/v1
10. Arik, S. Ö., Pfister, T., 2021. Tabnet: Attentive interpretable tabular learning. In Proceedings of the AAAI conference on artificial intelligence, 35(8), 6679-6687. https://doi.org/10.48550/arXiv.1908.07442
11. Arkin, F. S., Aras, G., Doğu, E., 2020. Comparison of artificial neural networks and logistic regression for 30-days survival prediction of cancer patients. Acta Informatica Medica, 28(2), 108. https://doi.org/10.5455/aim.2020.28.108-113
12. Bissacco, A., Yang, M.-H., Soatto, S., 2007. Fast human pose estimation using appearance and motion via multi-dimensional boosting regression, in IEEE Conference on Computer Vision and Pattern Recognition, CVPR’07. (Minneapolis, MN). https://doi.org/10.1109/CVPR.2007.383129
13. Breiman, L., 2001. Random forests. Mach. Learn. 45, 5–32. https://doi.org/10.1023/A:1010933404324
14. Chen, C., Fan, L., 2022. Cnn-lstm-attention deep learning model for mapping landslide susceptibility in kerala, india. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, X-3/W1-2022, 25-30. https://doi.org/10.5194/isprs-annals-x-3-w1-2022-25-2022
15. Choubey, S. B., Chitra, T., Hephzipah, J. J., 2024. Big Data Mining for Chronic Disease Prediction using Principal Component Analysis and eXtreme Gradient Boosting. GK International Journal of Advanced Research in Engineering and Technology, 1(1), 1-11.
16. Coşkun, C., Yüksek, E., 2023. Hepatit hastalığının tespitinde bulanık mantık ve makine öğrenmesi yöntemlerinin karşılaştırılması. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 14(4), 539-546.
17. Dai, X., Yin, H., Jha, N. K., 2020. Grow and prune compact, fast, and accurate lstms. IEEE Transactions on Computers, 69(3), 441-452. https://doi.org/10.1109/tc.2019.2954495
18. Dubey, G., Khera, R., Grover, A., Kaur, A., Goyal, A., Rajkumar, R., Srivastava, S., 2023. A hybrid convolutional network and long short-term memory (hbcnls) model for sentiment analysis on movie reviews. International Journal on Recent and Innovation Trends in Computing and Communication, 11(4), 341-348. https://doi.org/10.17762/ijritcc.v11i4.6458
19. Duyar, C., Senica, S. O., Kalkan, H., 2023. Detection of cardiovascular disease using gut microbiota data. https://doi.org/10.21203/rs.3.rs-2794999/v1
20. Elkholy, S., Rezk, A., Saleh, A. A., 2023. Enhanced optimized classification model of chronic kidney disease. International Journal of Advanced Computer Science and Applications, 14(2). https://doi.org/10.14569/ijacsa.2023.0140239
21. El-Shafeiy, E., El-Desouky, A. I., Elghamrawy, S. M., 2024. An optimized artificial neural network approach based on sperm whale optimization algorithm for predicting fertility quality. Studies in Informatics and Control, 27(3), 349-358. https://doi.org/10.24846/v27i3y201810
22. Ersöz, A. G., 2003. Dünya konferansları belgelerinde aile ve yoksulluk: Saptamalar ve öneriler. Sosyal Politika Çalışmaları Dergisi, 6(6).
23. Fanelli, G., Dantone, M., Gall, J., Fossati, A., Gool, L., 2012. Random forests for real time 3D face analysis. Int. J. Comput. Vis. 1, 1–22. https://doi.org/10.1007/s11263- 012-0549-0
24. Freund, Y., Schapire, R., 1997. A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55, 119–139.
25. Friedman, J., 2001. Greedy boosting approximation: a gradient boosting machine. Ann. Stat. 29, 1189–1232. https://doi.org/10.1214/aos/1013203451
26. Friedman, J., Hastie, T., Tibshirani, R., 2000. Additive logistic regression: a statistical view of boosting. Ann. Stat. 28, 337–407. https://doi.org/10.1214/aos/1016218222
27. Gaddam, C. M. Pattnaik, S. S., 2020. An ann ensemble based ecg signal classification approach for accurate arrhythmia detection. International Journal of Emerging Technology and Advanced Engineering, 10(8), 57-61. https://doi.org/10.46338/ijetae0820_08
28. Gao, X., Chen, D., Pan, Q., 2022. An interpretable classification model of breast tumors with tabular mammography data. 2nd International Conference on Signal Image Processing and Communication (ICSIPC 2022). https://doi.org/10.1117/12.2643654
29. Guhan, T., Bhavishya, S. Kalaiarasan, S., Lalith, K., Dhitchith, O. P., 2024. Chronic Illness Detection using Gradient Boosting Algorithm. Grenze International Journal of Engineering & Technology (GIJET), 10.
30. Guido, R., Ferrisi, S., Lofaro, D., Conforti, D., 2024. An overview on the advancements of support vector machine models in healthcare applications: a review. Information, 15(4), 235. https://doi.org/10.3390/info15040235
31. Gündoğdu, S., 2021. Kalp hastalık risk tahmini için Python aracılığıyla sınıflandırıcı algoritmalarının performans değerlendirmesi. Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi, 23(69), 1005-1013.
32. Hansen, L., Salamon, P., 1990. Neural network ensembles. IEEE Trans. Pattern Anal. Mach. Intell. 12, 993–1001. https://doi.org/10.1109/34.58871
33. Hegde, S. Mundada, M. R., 2020. Early prediction of chronic disease using an efficient machine learning algorithm through adaptive probabilistic divergence based feature selection approach. International Journal of Pervasive Computing and Communications, 17(1), 20-36. https://doi.org/10.1108/ijpcc-04-2020-0018
34. Huang, Y., Gao, Z., Zhang, H., 2020. Comparison of common machine learning algorithms trained with multi-zone models for identifying the location and strength of indoor pollutant sources. Indoor and Built Environment, 30(8), 1142-1158. https://doi.org/10.1177/1420326x20931576
35. Hutchinson, R. A., Liu, L.P., Dietterich, T. G., 2011. “Incorporating boosted regression trees into ecological latent variable models,” in AAAI’11, (San Francisco, CA), 1343–1348. Available online at: http://www.aaai.org/ocs/ index.php/AAAI/AAAI11/paper/view/3711
36. Johnson, R., Zhang, T., 2012. Learning Nonlinear Functions Using Regularized Greedy Forest. Technical Report. arXiv:1109.0887. doi: 10.2172/1052139
37. Jongjaraunsuk, R., Taparhudee, W., Suwannasing, P., 2024. Comparison of water quality prediction for red tilapia aquaculture in an outdoor recirculation system using deep learning and a hybrid model. Water, 16(6), 907. https://doi.org/10.3390/w16060907
38. Kim, G., Lim, H., Kim, Y., Kwon, O., Choi, J., 2023. Intra-person multi-task learning method for chronic-disease prediction. Scientific Reports, 13(1). https://doi.org/10.1038/s41598-023-28383-9
39. Kim, J. O., Jeong, Y. S., Kim, J. H., Lee, J. W., Park, D., Kim, H. S., 2021. Machine learningbased cardiovascular disease prediction model: A cohort study on the Korean national health ınsurance service health screening database. Diagnostics, 11(6), 943.
40. Kumsar, A. K., Yılmaz, F. T., 2014. Kronik Hastaliklarda Yaşam Kalitesine Genel Bakiş. ERÜ Sağlık Bilimleri Fakültesi Dergisi, 2(2), 62-70.
41. Küçükberber, N., Özdilli, K., Yorulmaz, H., 2011. Kalp hastalarında sağlıklı yaşam biçimi davranışları ve yaşam kalitesine etki eden faktörlerin değerlendirilmesi. Anadolu Kardiyol Derg, 11, 619-626.
42. Lee, E. Y., Fulan, B. M., Wong, G. C. L., Ferguson, A. L., 2016. Mapping membrane activity in undiscovered peptide sequence space using machine learning. Proceedings of the National Academy of Sciences, 113(48), 13588-13593. https://doi.org/10.1073/pnas.1609893113
43. Liu, Q., Li, S., Li, Y., Yu, L., Zhao, Y., Wu, Z., Zhang, Y., 2023. Identification of urinary volatile organic compounds as a potential non-invasive biomarker for esophageal cancer. Scientific Reports, 13(1). https://doi.org/10.1038/s41598-023-45989-1
44. Liu, Y., Wang, Y., Li, Y., Zhang, B., Wu, G., 2004. Earthquake prediction by RBF neural network ensemble, in Advances in Neural Networks - ISNN 2004, eds F.-L. Yin, J. Wang, and C. Guo (Berlin; Heidelberg: Springer), 962–969. https://doi.org/10.1007/978-3-540-28648-6_153
45. Loey, M., Naman, M. R., Zayed, H. H., 2020. Deep transfer learning in diagnosing leukemia in blood cells. Computers, 9(2), 29. https://doi.org/10.3390/computers9020029
46. Luo, L., Zhang, F., Yao, Y., Gong, R., Fu, M., Xiao, J., 2018. Machine learning for identification of surgeries with high risks of cancellation. Health Informatics Journal, 26(1), 141-155. https://doi.org/10.1177/1460458218813602
47. Maggiori, E., Tarabalka, Y., Charpiat, G., Alliez, P., 2017. Convolutional neural networks for large-scale remote-sensing image classification. IEEE Transactions on Geoscience and Remote Sensing, 55(2), 645-657. https://doi.org/10.1109/tgrs.2016.2612821
48. McLaughlin, R. T., Asthana, M., Meo, M. D., Ceccarelli, M., Jacob, H. J., Masica, D. L., 2023. Fast, accurate, and racially unbiased pan-cancer tumor-only variant calling with tabular machine learning. NPJ Precision Oncology, 7(1). https://doi.org/10.1038/s41698-022-00340-1
49. Özdemir, A., 2023. Makine Öğrenmesi Algoritmaları ile Aritmilerin Sınıflandırılması. Erciyes Üniversitesi Fen Bilimleri Enstitüsü Fen Bilimleri Dergisi, 39(3), 394-402.
50. Özkan, Y., 2019. Hastalık tanısı verilerinde veri ön işlemenin topluluk öğrenme sınıflandırma algoritmaları üzerindeki etkisinin incelenmesi, Ege Üniversitesi, Sağlık Bilimleri Enstitüsü, Yayınlanmamış Yüksek Lisans Tezi, İzmir.
51. Pacci, Z., Şengül, Y. A., Attar, R., Alagöz, O., 2021. Yapay Zeka Tabanlı Klinik Karar Destek Sistemi ile Tüp Bebek Tedavisi Gebelik Sonucu Tahmini. EMO Bilimsel Dergi, 11(22), 27-35.
52. Pittman, S. J., Brown, K. A., 2011. Multi-scale approach for predicting fish species distributions across coral reef seascapes. PLoS ONE 6:e20583. https://doi.org/10.1371/journal.pone.0020583
53. Qi, Y., 2012. Random forest for bioinformatics, in Ensemble Machine Learning, eds C. Zhang and Y. Ma (New York, NY: Springer), 307. https://doi.org/10.1007/978-1- 4419-9326-7_11
54. Schapire, R., 2002. The boosting approach to machine learning: an overview. Nonlin. Estimat. Classif. Lect. Notes Stat. 171, 149–171. https://doi.org/10.1007/978-0-387- 21579-2_9
55. Sevli, O., 2023. Diagnosis of diabetes mellitus using various classifiers. Journal of the Faculty of Engineering and Architecture of Gazi University, 38(2), 989-1001.
56. Sewell, M., 2011. Ensemble Learning. Technical Report, Department of Computer Science, University College London. Available online at: http://www.cs. ucl.ac.uk/fileadmin/UCL-CS/research/Research_Notes/RN_11_02.pdf Erişim tarihi: 20.02.2024
57. Shu, C., Burn, D. H., 2004. Artificial neural network ensembles and their application in pooled flood frequency analysis. Water Resour. Res. 40, 1–10. https://doi.org/10.1029/2003WR002816
58. Sönmez, O., Zengin, K., 2023. Süt Sığırlarının Buzağılama Zamanının Tahmininde Makine Öğrenme Yöntemlerinin Kullanımı Çalışmaları Üzerine Bir Değerlendirme. Journal of New Results in Engineering and Natural Sciences, 2023(18), 27-39.
59. Tang, X. Liu, J., 2021. Comparing different algorithms for the course of alzheimer’s disease using machine learning. Annals of Palliative Medicine, 10(9), 9715-9724. https://doi.org/10.21037/apm-21-2013
60. Toğaçar, M., Cömert, Z., Ergen, B., 2021. Intelligent skin cancer detection applying autoencoder, MobileNetV2 and spiking neural networks. Chaos, Solitons & Fractals, 144, 110714.
61. Vidya, G., Hari, V. S., 2023. Lstm network integrated with particle filter for predicting the bus passenger traffic. Journal of Signal Processing Systems, 95(2-3), 161-176. https://doi.org/10.1007/s11265-022-01831-x
62. Wade, C., Glynn, K., 2020. Hands-On Gradient Boosting with XGBoost and scikit-learn: Perform accessible machine learning and extreme gradient boosting with Python. Packt Publishing Ltd.
63. Xi, J., Liang, R., Fei, X., 2017. An algorithm of improving speech emotional perception for hearing aid. Modern Physics Letters B, 31(19-21), 1740094. https://doi.org/10.1142/s0217984917400942
64. Yangın, G., 2019. XGboost ve Karar Ağacı tabanlı algoritmaların diyabet veri setleri üzerine uygulaması, Mimar Sinan Güzel Sanatlar Üniversitesi, Fen Bilimleri Enstitüsü, Yayınlanmamış Yüksek Lisans Tezi, İstanbul.
65. Yar, F., 2015. Türkiye’de gelir dağılımı & yoksulluk. Global Analiz, 2, 1-30.
66. Zhang, P., Swaminathan, A., Uddin, A. A., 2023. Pulmonary disease detection and classification in patient respiratory audio files using long short-term memory neural networks. Frontiers in Medicine, 10. https://doi.org/10.3389/fmed.2023.1269784