AI Summary & Key Takeaways
AI InsightThis research will provide decision-makers with evidence-based information for future drug reimbursement decisions.
📌 3 Key Takeaways
Abstract
This study uses time series models to examine the trend and seasonality components of the Social Security Institution's prescription count, prescription cost, and total prescription cost data from 2015 to 2024 in Türkiye. Based on the findings, the study also aims to produce a projection for the period from 2025 to 2030. The Prophet forecasting model was used to project the time series data used in the study. Model performance was evaluated using R², mean absolute error, and root mean square error metrics. Time series modeling and preliminary analyses were conducted in the Python 3.8 environment. A steady increase in prescription numbers was observed during the 2015–2024 period, alongside seasonal fluctuations, and the forecast showed consistent results. However, the forecast model did not fully predict the decline in prescription numbers during 2020, when the pandemic’s effects were at their most severe. Projections indicate that the per-prescription amount and the total number of prescriptions will increase, with the former exceeding 2,000 TRY and the latter exceeding 110 billion TRY by 2030. These findings suggest that the Social Security Institution's drug expenditure burden will increase. This research will provide decision-makers with evidence-based information for future drug reimbursement decisions.