Using artificial intelligence and machine learning in predictive analytics to forecast household demand
Bed capacity management is critical to health systems, impacting patient care and safety, operational efficiency, system sustainability, and financial performance. Efforts to improve and streamline administration are often isolated to areas within the center and may result in suboptimal resource use, inconsistent patient care, and inefficiencies between care units for transfers and other care coordination.
Evaluating end-to-end bed demand management globally from admission to hospital discharge eliminates many unintended consequences of local improvement efforts. The Froedtert Health Network and the Medical College of Wisconsin have identified improving capacity management as an important, targetable goal that can be achieved through artificial intelligence, machine learning, and data analysis methods.
Understanding and dissecting patient flow and its sources allowed the team to create a set of predictive tools specifically designed for the Care Coordination Center. The Froedtert & MCW Health Network has been able to improve patient care, drive key performance indicators and streamline operations by deploying and utilizing staff more effectively and by proactively responding to anticipated changes in patient bed demand.
This resulted in optimal allocation of resources, improved patient flow, improved coordination between departments and cost savings.
Ravi Teja Carey is a machine learning engineer at Froedtert Health. He and two colleagues will talk about these achievements at HIMSS25 in a session titled “Improving capacity planning and bed demand forecasting using machine learning.” We interviewed Curry to get a sneak peek at what he plans to discuss this March at HIMSS25 during his panel.
S. What is the main topic of your session, and why is it particularly relevant to healthcare and health IT today?
A. The main topic of our session focuses on improving hospital capacity management and bed demand forecasting by applying artificial intelligence and machine learning techniques. This topic is gaining increasing importance in healthcare as hospitals face unexpected changes in patient volume.
Seasonal increases, unplanned admissions, and fluctuating patient needs make it difficult to maintain optimal resource allocation. Leveraging AI and machine learning to forecast bed demand and patient flow enables hospitals to optimize staffing, bed allocation and streamline operations, resulting in enhanced patient care and overall efficiency.
Our session will also explore how healthcare organizations can leverage AI and machine learning to transform operations into a proactive workflow rather than a reactive one. This proactive approach allows for more accurate forecasting of patient volumes and better coordination between departments, ultimately enhancing the patient experience through more efficient resource allocation and timely delivery of care.
Incorporating these predictive models into daily operations enables healthcare organizations to better anticipate demand fluctuations, reduce the risk of overcrowding, and enhance coordination between departments.
Q: You focus on artificial intelligence and machine learning, which are important technologies in healthcare today. How are they used in healthcare in the context of the focus and content of your session?
A. Our session focuses on artificial intelligence and machine learning techniques, specifically their application in predictive analytics to forecast bed demand and manage capacity in hospitals. Machine learning models are designed to analyze large sets of data, including historical patient admissions, discharge trends, seasonal disease patterns and other factors, to predict future hospital capacity needs.
We will explore how these models can predict patient flow and bed demand, enabling healthcare organizations to make more informed decisions about resource allocation, staffing, and patient care management.
These predictive models use algorithms to identify patterns and trends in inpatient admissions, length of stay and discharge rates, enabling hospitals to forecast fluctuations in demand with a high degree of accuracy. Machine learning integrates data from multiple sources, including emergency departments, surgical units, and outpatient care, to provide a comprehensive view of organizational capacity.
This analysis helps hospital leaders and care coordinators anticipate increases in bed demand — such as those that occur during flu seasons or following natural disasters — and plan effectively to ensure resources are available when they are needed most. By applying these technologies, healthcare organizations can move from a reactive approach to a more proactive and forward-looking model of patient flow management.
In our session we will examine how machine learning can be effectively applied in healthcare to forecast bed demand and enhance capacity management. By analyzing historical data such as patient admission rates, discharge patterns, and seasonal trends, machine learning models can predict hospital capacity needs.
These forecasts allow healthcare organizations to optimize resource allocation, plan staffing requirements and deliver improved patient care, enabling a proactive rather than reactive approach to operations.
We will also discuss how these machine learning models can be integrated into healthcare workflows, turning predictions into actions for hospital staff. Rather than remaining in isolated sandboxes or tools, predictions are processed, stored, and made available for decision making through business intelligence platforms.
These BI tools enable healthcare staff to access insights for effective planning, such as bed allocation, staffing management, and patient discharge coordination, ultimately improving operational efficiency and patient outcomes.
S. What’s one piece of advice you hope attendees leave your session with and can apply when they return to their organizations?
A. One of the key takeaways we hope attendees gain from our session is the knowledge needed to implement machine learning-based predictive analytics tools to enhance their hospital capacity management.
Attendees will discover how predictive models can accurately forecast bed demand and identify potential bottlenecks in patient flow before they occur. These insights will enable leaders to make data-driven decisions, allocate resources more efficiently, and avoid overloading units or employees during peak periods.
With this toolkit, healthcare providers can reduce last-minute staffing adjustments, optimize bed utilization, and ensure uninterrupted patient care during periods of high demand. Predicting patient flow across the entire hospital, rather than isolated units, allows resources to be optimally allocated across departments and reduces delays caused by mismatches between patient demand and available resources.
This will foster better communication between clinical teams and operational leaders, leading to smoother transitions between phases of patient care and improving the overall patient experience.
Ravi Teja Kari’s session, “Improving Capacity Planning and Bed Demand Forecasting Using Machine Learning,” is scheduled for Tuesday, March 4, at 10:15 a.m. in HIMSS25 in Las Vegas.
Follow Bill’s HIT coverage on LinkedIn: Bill Siwicki
Email him: bsiwicki@himss.org
Healthcare IT News is a HIMSS media publication