Medical Insurance Cost Prediction MedCost: Machine Learning Ensemble Approaches

Year 2024, , 88 - 95, 30.06.2024

Murat Emeç

https://doi.org/10.36222/ejt.1375677

Abstract

Healthcare insurance costs are a significant concern for individuals and providers. Accurately predicting these costs can assist in financial planning and risk assessment. This study explores machine learning ensemble methods to predict healthcare insurance costs based on various factors, including age, sex, body mass index (BMI), number of children, smoking status, and region. Additionally, new features were introduced by incorporating the mean and standard deviation of BMI and smoking habits, which are known to affect insurance costs substantially.
The study began with a comprehensive statistical analysis of the dataset, followed by feature engineering to enhance its predictive power. Categorical variables such as sex, smoking status, and region were appropriately encoded. Two datasets were constructed: one containing all the original features, and the other containing the engineered features. Ensemble learning methods, including Bagging, Stacking, and the proposed MedCost-AdaBoost model, were employed to predict the insurance costs for both datasets. The results revealed that the MedCost-AdaBoost model outperformed the other methods in terms of lower Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) values, along with higher R-squared (R2) scores.
These findings underscore the effectiveness of ensemble learning techniques in predicting healthcare insurance costs, with feature engineering playing a crucial role in improving prediction accuracy. Despite certain limitations, such as the dataset size, this study provides valuable insights for researchers and professionals in the healthcare insurance industry. Future research could explore additional factors and larger datasets to enhance the predictive models in this domain further.

Keywords

Medical cost, machine learning, ensemble methods, feature engineering, prediction accuracy

References

• [1] Saraswat, B. K., Singhal, A., Agarwal, S., & Singh, A. (2023, May). Insurance Claim Analysis Using Traditional Machine Learning Algorithms. In 2023 International Conference on Disruptive Technologies (ICDT) (pp. 623-628). IEEE.
• [2] Vijayalakshmi, V., Selvakumar, A., & Panimalar, K. (2023, January). Implementation of Medical Insurance Price Prediction System using Regression Algorithms. In 2023, the 5th International Conference on Smart Systems and Inventive Technology (ICSSIT) (pp. 1529-1534). IEEE.
• [3] Bora, A., Sah, R., Singh, A., Sharma, D., & Ranjan, R. K. (2022, October). Interpretation of machine learning models using xai-a study on health insurance dataset. In 2022, the 10th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO) (pp. 1-6). IEEE.
• [4] Jyothsna, C., Srinivas, K., Bhargavi, B., Sravanth, A. E., Kumar, A. T., & Kumar, J. S. (2022, May). Health Insurance Premium Prediction using XGboost Regressor. In 2022 International Conference on Applied Artificial Intelligence and Computing (ICAAIC) (pp. 1645-1652). IEEE.
• [5] Kaushik, K., Bhardwaj, A., Dwivedi, A. D., & Singh, R. (2022). Machine learning-based regression framework to predict health insurance premiums. International Journal of Environmental Research and Public Health, 19(13), 7898.
• [6] Chittilappilly, R. M., Suresh, S., & Shanmugam, S. (2023, May). A Comparative Analysis of Optimizing Medical Insurance Prediction Using Genetic Algorithm and Other Machine Learning Algorithms. In 2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI) (pp. 1-6). IEEE.
• [7] Albalawi, S., Alshahrani, L., Albalawi, N., & Alharbi, R. (2023). Prediction of healthcare insurance costs. Computers and Informatics, 3(1), 9-18.
• [8] Praveen, M., Manikanta, G. S., Gayathri, G., & Mehrotra, S. (2023, February). Comparative Analysis of Machine Learning Algorithms for Medical Insurance Cost Prediction. In International Conference On Innovative Computing and Communication (pp. 885-892). Singapore: Springer Nature Singapore.
• [9] Sahare, A. N. (2023). Forecasting Medical Insurance Claim Cost with Data Mining Techniques (Doctoral dissertation, Dublin, National College of Ireland).
• [10] Hassan, C. A., Iqbal, J., Hussain, S., AlSalman, H., Mosleh, M. A., & Sajid Ullah, S. (2021). A computational intelligence approach for predicting medical insurance cost. Mathematical Problems in Engineering, 2021, 1-13.
• [11] Demirci, F., Emec, M., Gursoy Doruk, O., Ormen, M., Akan, P., & Hilal Ozcanhan, M. (2023). Prediction of LDL in hypertriglyceridemic subjects using an innovative ensemble machine learning technique. Turkish Journal of Biochemistry, (0).
• [12] Kaya, Y., Yiner, Z., Kaya, M., & Kuncan, F. (2022). A new approach to COVID-19 detection from X-ray images using angle transformation with GoogleNet and LSTM. Measurement Science and Technology, 33(12), 124011.
• [13] Hemdan, E. E. D., El-Shafai, W., & Sayed, A. (2023). CR19: A framework for preliminary detection of COVID-19 in cough audio signals using machine learning algorithms for automated medical diagnosis applications. Journal of Ambient Intelligence and Humanized Computing, 14(9), 11715-11727.
• [14] AKDAĞ, S., Kuncan, F., & Kaya, Y. (2022). A new approach for classification of congestive heart failure and arrhythmia by downsampling local binary patterns with LSTM. Turkish Journal of Electrical Engineering and Computer Sciences, 30(6), 2145-2164.
• [15] Kaya, Y., & Kuncan, F. (2022). A hybrid model for classification of medical data set based on factor analysis and extreme learning machine: FA+ ELM. Biomedical Signal Processing and Control, 78, 104023.
• [16] Wu, X., Tang, H., Zhu, Z., Liu, L., Chen, G., & Yang, M. S. (2023). Nonlinear strict distance and similarity measures for intuitionistic fuzzy sets with applications to pattern classification and medical diagnosis. Scientific reports, 13(1), 13918.
• [17] Ayvaz, E., Kaplan, K., Kuncan, F., Ayvaz, E., & Türkoğlu, H. (2022). Reducing Operation Costs of Thyroid Nodules Using Machine Learning Algorithms with Thyroid Nodules Scoring Systems. Applied Sciences, 12(22), 11559.
• [18] Yurtsever, M., & Emeç, M. (2023). Potable Water Quality Prediction Using Artificial Intelligence and Machine Learning Algorithms for Better Sustainability. Ege Academic Review, 23(2), 265-278.
• [19] Orenc, S., Acar, E., & Özerdem, M. S. (2022, October). The Electricity Price Prediction of Victoria City Based on Various Regression Algorithms. In 2022 Global Energy Conference (GEC) (pp. 164-167). IEEE.
• [20] Gönenç, A., Acar, E., Demir, İ., & Yılmaz, M. (2022, October). Artificial Intelligence Based Regression Models for Prediction of Smart Grid Stability. In 2022 Global Energy Conference (GEC) (pp. 374-378). IEEE.
• [21] Ruzgar, S., & Acar, E. (2022). The statistical neural network-based regression approach for prediction of the optical band gap of CuO. Indian Journal of Physics, 96(12), 3547-3557.
• [22] Emeç, M., & Özcanhan, M. H. (2023). Veri Ön İşleme ve Öznitelik Mühendisliğinin Yapay Zekâ Yöntemlerine Uygulanması. MÜHENDİSLİKTE ÖNCÜ VE ÇAĞDAŞ ÇALIŞMALAR, 33-54.
• [23] Emeç, M., & Özcanhan, M. H. (2023). Makine Öğrenmesi Algoritmalarında Hiper Parametre Belirleme. MÜHENDİSLİKTE ÖNCÜ VE ÇAĞDAŞ ÇALIŞMALAR, 71-98.
• [24] Alzoubi, H. M., Sahawneh, N., AlHamad, A. Q., Malik, U., Majid, A., & Atta, A. (2022, October). Analysis Of Cost Prediction In Medical Insurance Using Modern Regression Models. In 2022 International Conference on Cyber Resilience (ICCR) (pp. 1-10). IEEE.