Scholarlink

The study describes a method of using machine learning to forecast the volume of patients attending peripheral health centers and the cost of their treatment to enhance efficiency, funding plans. Forecast patient numbers and spending for 2025 and 2026 are based on the historical data from several hospitals and the XGBoost Regressor. The predictions increase the intuition for patient inflow throughout the years, which directly correlates with the actual data. Some hospitals, like Hospital 3, had perfect prediction accuracy as compared to Hospital 8, that has higher prediction errors. The study also forecasts even faster growth of healthcare expenditure for the period 2025–2026, with the selected hospitals, such as Hospital 8, having the highest absolute difference between the actual and forecasted values. Such forecasts are useful for decision-makers in the healthcare systems, since they help predict workload and costs in the subsequent periods. Based on the study, the author postulates that an AI solution can enhance the future readiness of healthcare organizations in meeting patient and financial needs. Thus, the interaction with the tool appears to be fully optimized, but additional improvements are needed to make the tool suitable for individual hospitals.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

AI-Driven Predictions for Patient Load and Medical Expenditure in Peripheral Health Centers: A Machine Learning Approach

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Evan Varun Dsouza,
  • Mladen Saldanha,
  • Ajit M. Hebbale,
  • Ankeeta Menona Jacob,
  • A. N. Parameswaran

摘要

The study describes a method of using machine learning to forecast the volume of patients attending peripheral health centers and the cost of their treatment to enhance efficiency, funding plans. Forecast patient numbers and spending for 2025 and 2026 are based on the historical data from several hospitals and the XGBoost Regressor. The predictions increase the intuition for patient inflow throughout the years, which directly correlates with the actual data. Some hospitals, like Hospital 3, had perfect prediction accuracy as compared to Hospital 8, that has higher prediction errors. The study also forecasts even faster growth of healthcare expenditure for the period 2025–2026, with the selected hospitals, such as Hospital 8, having the highest absolute difference between the actual and forecasted values. Such forecasts are useful for decision-makers in the healthcare systems, since they help predict workload and costs in the subsequent periods. Based on the study, the author postulates that an AI solution can enhance the future readiness of healthcare organizations in meeting patient and financial needs. Thus, the interaction with the tool appears to be fully optimized, but additional improvements are needed to make the tool suitable for individual hospitals.