Authors: Victor Petrov, Kenji Nakamura, Thomas Bauer, Elena Garcia, Ananya Kulkarni
Abstract: Healthcare systems operate in highly dynamic environments where patient demand, workforce availability, and clinical resource utilization fluctuate continuously, creating significant challenges for effective talent coordination and resource planning. Traditional workforce management approaches within enterprise resource planning (ERP) systems often rely on historical reporting and static scheduling mechanisms that struggle to respond to real-time operational changes. The growing adoption of Internet of Things (IoT)–enabled medical devices and hospital telemetry infrastructure has created opportunities to capture continuous streams of operational data across healthcare environments. This study proposes a real-time healthcare talent orchestration framework that integrates IoT-driven telemetry, scalable big data pipelines, and artificial intelligence–based forecasting models within enterprise ERP architectures. Telemetry data generated from clinical monitoring systems, hospital infrastructure sensors, and workforce management platforms are processed through distributed big data pipelines capable of handling high-velocity operational information. Machine learning algorithms analyze these data streams to forecast patient inflow, anticipate staffing requirements, and identify potential operational bottlenecks before they impact service delivery. By embedding predictive insights directly into ERP-driven workforce coordination systems, healthcare organizations can dynamically adjust staffing allocations, optimize resource utilization, and support proactive decision-making. The proposed approach demonstrates how combining IoT telemetry, big data engineering, and AI-based forecasting can significantly improve workforce agility, operational efficiency, and service continuity in modern healthcare environments.
DOI: https://doi.org/10.5281/zenodo.18813979
