Implications for Social Health Insurance Fund (SHIF) Implementation from Determinants of Health Insurance Uptake in Kenya Before and During the COVID-19 Pandemic
DOI:
https://doi.org/10.53819/81018102t4399Abstract
Kenya is transitioning from the National Hospital Insurance Fund (NHIF) to the Social Health Insurance Fund (SHIF) to advance Universal Health Coverage (UHC). Effective SHIF implementation requires understanding the factors influencing health insurance uptake and how these changed during the COVID-19 pandemic. This study analyzed nationally representative data from two sources: the Kenya Integrated Household Budget Survey (KIHBS 2015/16), comprising 21,536 households, and the Kenya Demographic and Health Survey (KDHS 2022), with 19,582 households. Both datasets included complete insurance-status information. The analysis used descriptive statistics, logistic regression, Random Forest, Artificial Neural Networks, SHAP-based feature interpretation, and spatial analysis to identify and compare determinants of health insurance uptake. These determinants were examined both before and during the COVID-19 pandemic, clearly establishing the timeframes for comparison. Health insurance coverage was linked with educational attainment, household wealth, digital inclusion, and geographic location in both survey periods. Higher educational attainment and greater household wealth were consistently associated with higher probabilities of insurance coverage. Digital-access indicators, like mobile phone ownership, mobile money registration, mobile banking use, and television ownership, were also strong predictors. During the pandemic, wealth-related disparities grew. Healthcare utilization variables, such as hospitalizations and healthcare spending, became more predictive. County-level effects were among the strongest determinants in both statistical and machine-learning models, indicating persistent geographic inequalities in insurance uptake. Spatial analysis found lower predicted coverage in the Northeastern and some coastal counties compared to Central, Western, and parts of the Rift Valley regions. Health insurance uptake in Kenya is influenced by interconnected socioeconomic, digital, healthcare-utilization, and geographic factors. The findings suggest that for SHIF to succeed, strategies must target socioeconomic vulnerability, digital exclusion, and ongoing regional disparities. This will help achieve more equitable progress toward Universal Health Coverage.
Keywords: Health Insurance Uptake, SHIF, Universal Health Coverage, Kenya, Machine Learning, Digital Inclusion, Health Financing, COVID-19
References
Barasa, E., Rogo, K., Mwaura, N., & Chuma, J. (2018). Kenya National Hospital Insurance Fund Reforms: Implications and Lessons for Universal Health Coverage. Health Systems & Reform, 4(4), 346–361. https://doi.org/10.1080/23288604.2018.1513267
Demirgüç-Kunt, A., Klapper, L., Singer, D., & Ansar, S. (2022). The Global Findex Database 2021: Financial Inclusion, Digital Payments, and Resilience in the Age of COVID-19. The World Bank. https://doi.org/10.1596/978-1-4648-1897-4
Géron, A. (2019). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems (Second edition). O’Reilly.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. The MIT Press.
Kazungu, J. S., & Barasa, E. W. (2017). Examining levels, distribution and correlates of health insurance coverage in Kenya. Tropical Medicine & International Health, 22(9), 1175–1185. https://doi.org/10.1111/tmi.12912
Lundberg, S., & Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions (Version 2). arXiv. https://doi.org/10.48550/ARXIV.1705.07874
Ministry of Health. (2021). Kenya Universal Health Coverage Policy 2020-2030. http://guidelines.health.go.ke:8000/media/Kenya_Universal_Health_Coverage_Policy_2020__2030.pdf
Parliament of Kenya. (2023). Social Health Insurance Act. Parliament of Kenya. https://new.kenyalaw.org/akn/ke/act/2023/16/eng@2023-11-24
Russell, S. J., & Norvig, P. (with Chang, M., Devlin, J., Dragan, A., Forsyth, D., Goodfellow, I., Malik, J., Mansinghka, V., Pearl, J., & Wooldridge, M. J.). (2021). Artificial intelligence: A modern approach (Fourth Edition). Pearson.
World Bank. (2020). Kenya Economic Update: Navigating the Pandemic. World Bank. https://ourworldindata.org/covid-vaccinations?utm_source=chatgpt.com
World Health Organization. (2023). Tracking Universal Health Coverage: 2023 Global Monitoring Report (1st ed). World Health Organization.
