Optimizing Medication Access in Public Healthcare Centers: A Machine Learning Stochastic Model for Inventory Management and Demand Forecasting in Primary Health Services

This article discusses the critical issue of inefficient inventory management and demand forecasting in public healthcare systems, highlighting the significant impact of this problem on patient care and healthcare costs. It introduces a novel approach that leverages machine learning and advanced forecasting techniques to address this challenge. The methodology involves mapping the supply chain, data collection, preprocessing, regression analysis, and the creation of three forecasting models: Projective, Causal, and Stochastic. The results of regression analysis identify key factors affecting stockouts, while the forecasting models predict drug demand and supply requirements. The integration of inventory cost optimization models further enhances the precision of stock requirement forecasts. These models offer a promising solution to improve medication access, reduce stockouts, and optimize resource allocation in primary healthcare services, ultimately leading to more efficient and equitable healthcare delivery in the public sector.