Global population aging is transforming healthcare systems, demanding efficient, equitable, and patient-centered care models. Operations research and industrial engineering have provided optimization tools, but they often focus on isolated processes such as staff routing, failing to translate operational efficiencies into measurable clinical outcomes. This article reviews how the approach is evolving from static models toward dynamic, stochastic frameworks integrated with artificial intelligence, and how digital technologies can bridge the gap between operational metrics and real health outcomes for the elderly.
Home healthcare, polypharmacy management, and clinical chronotherapy are areas where operations research has shown significant progress. However, most studies remain at the process level, such as nurse routing optimization or appointment scheduling, ignoring integration with patient health outcomes. To advance toward smart and resilient care, a paradigm shift is needed: from optimizing isolated tasks to multi-level decision support that spans daily operations to strategic planning.
Artificial intelligence and intelligent agents (AI agents) enable modeling uncertainty and adapting decisions in real time. For example, reinforcement learning systems can dynamically adjust caregiver assignments based on patients’ evolving health status. Companies like Q2BSTUDIO develop custom applications that integrate these algorithms with clinical workflows, facilitating the adoption of advanced technologies without disrupting daily practice.
Cloud infrastructure (AWS/Azure) is key to processing large volumes of patient data, sensors, and IoT devices, enabling the creation of digital twins that simulate clinical and operational scenarios. Cybersecurity becomes critical in this environment, as health data is highly sensitive; Q2BSTUDIO’s cybersecurity solutions protect information across all system layers. Furthermore, business intelligence (BI/Power BI) transforms operational data into visual dashboards that allow healthcare managers to monitor key indicators such as waiting times, medication adherence, or readmission rates, directly linking operational efficiency with clinical outcomes.
A fundamental aspect is the integration between hospital and community care levels. Current models rarely address the transition from hospital discharge to home care, a critical moment where medication errors and lack of follow-up occur. Custom software platforms can connect electronic health records, telemedicine applications, and wearable devices, offering a unified view of the patient. Q2BSTUDIO, with its expertise in BI and Power BI solutions, helps design dashboards that cross-reference data from different sources to predict risks and optimize resources.
The smartification of elderly care involves designing human-centered systems where automated decisions are transparent and controllable by professionals. AI agents, combined with large language models, can assist in polypharmacy management by recommending dose adjustments or alerting about dangerous interactions. Hybrid cloud (AWS/Azure) provides the elasticity needed to scale these services on demand, while cybersecurity protects data confidentiality.
In conclusion, this thematic review shows that the field of operations research in elderly care is transitioning from a purely operational focus to an outcome-oriented one. To achieve real impact on patient health, it is essential to integrate optimization tools with artificial intelligence, cloud, cybersecurity, and business intelligence. Companies like Q2BSTUDIO, specialized in custom application development, AI, and BI, offer the necessary bridge between academic theory and clinical practice, enabling the construction of intelligent, equitable, and person-centered healthcare systems for older adults.
