Using AI and ML in predictive analytics for predicting bed demand
Managing bed capacity is critical to healthcare systems, impacting patient care and safety, operational efficiency, system sustainability, and financial performance. Efforts to improve and streamline management are often limited to regions within the center and can lead to suboptimal use of resources, inconsistent patient care, and inefficiencies between care units in transfers and other care coordination.
Assessing the end-to-end management of bed demand globally, from admission to discharge, eliminates many of the unintended consequences of local optimization efforts. Froedtert Health identified improving capacity management as a key and targeted goal that could be achieved through AI, machine learning and data analytics approaches.
By understanding and parsing patient flow and its sources, the team was able to create a suite of predictive tools designed specifically for the care coordination center. Froedtert Health was able to improve patient care, operationalize key performance indicators and streamline operations through more effective deployment and utilization of staff and by responding preemptively to expected changes in patient bed demand.
This led to optimized resource allocation, improved patient flow, better coordination between departments and cost savings.
Ravi Teja Karri is a machine learning engineer at Froedtert ThedaCare Health. He and two colleagues will speak about these achievements during HIMSS25 in a session titled “Improving capacity planning and predicting bed demand using machine learning.” We interviewed Karri to get a taste of what he plans to discuss in March at HIMSS25 during his session.
Q. What is the overarching theme of your session, and why is it especially relevant to healthcare and healthcare IT today?
A. The overarching theme of our session focuses on improving hospital capacity management and predicting bed demand through the application of artificial intelligence and machine learning techniques. This topic is becoming increasingly relevant in healthcare as hospitals experience unpredictable changes in patient volume.
Seasonal peaks, unplanned admissions and fluctuating patient needs make it challenging to maintain optimal resource allocation. By using AI and ML to predict bed demand and patient flow, hospitals can optimize staffing, allocate beds, and streamline operations, resulting in improved patient care and overall efficiency.
Our session will also explore how healthcare organizations can leverage AI and ML to transform processes into anticipatory workflows rather than reactive workflows. This proactive approach enables more accurate patient volume forecasting and better coordination between departments, ultimately improving the patient experience through more efficient resource allocation and timely care delivery.
By integrating these predictive models into daily operations, healthcare organizations can better anticipate demand fluctuations, minimize the risk of overcrowding and improve coordination between departments.
Q. You focus on AI and ML, key technologies in today’s healthcare. 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 technologies, especially their application in predictive analytics for predicting bed demand and capacity management in hospitals. ML models are designed to analyze large data sets, including historical patient admissions, discharge trends, seasonal disease patterns, and other factors, to predict hospitals’ future capacity needs.
We will explore how these models can predict patient flow and bed demand, helping healthcare organizations make more informed decisions about resource allocation, staffing, and patient care management.
These predictive models use algorithms to identify patterns and trends in patient admissions, length of stay and discharge rates, allowing hospitals to predict fluctuations in demand with a high degree of accuracy. ML 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 spikes in bed demand – such as during flu seasons or after natural disasters – and plan effectively to ensure resources are available when needed most. By implementing these technologies, healthcare organizations can move from a reactive approach to a more proactive and anticipatory model of patient flow management.
In our session we explore how machine learning can be effectively applied in healthcare to predict bed demand and improve capacity management. By analyzing historical data such as patient admissions, discharge patterns, and seasonal trends, ML models can predict hospital capacity needs.
These predictions enable healthcare organizations to optimize resource allocation, plan staffing needs and deliver improved patient care, enabling a proactive rather than reactive approach to business operations.
We will also discuss how these ML models can be integrated into healthcare workflows, turning predictions into action for hospital staff. Rather than remaining in experimental environments or siled tools, the predictions are processed, stored and made available for decision making through business intelligence platforms.
These BI tools give healthcare professionals access to insights for effective planning, such as assigning beds, managing staffing, and coordinating patient discharges, ultimately improving operational efficiency and patient outcomes.
Q. What is one of the several insights you hope participants will leave your session with and be able to connect to when they get home to their organization?
A. An important lesson we hope participants from our session will gain is the knowledge to implement machine learning-based predictive analytics tools to improve their own hospital capacity management.
Participants will discover how predictive models can accurately predict 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 staff during peak periods.
By using this toolkit, healthcare providers can minimize last-minute staffing adjustments, optimize bed utilization and ensure patient care remains uninterrupted during periods of high demand. Predicting patient flow across the entire hospital, rather than in isolated units, enables optimized allocation of resources across departments and minimizes delays caused by mismatches between patient demand and available resources.
This will promote better communication between clinical teams and operational leaders, resulting in smoother transitions between phases of patient care and an improved overall patient experience.
Ravi Teja Karri’s session, “Improving Capacity Planning and Bed Demand Forecasting Using Machine Learning,” is scheduled for Tuesday, March 4 at 10:15 a.m. at 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