Jonathan Shoemaker
The battle for the bed: How intelligent patient flow gives hospitals an edge
June 02, 2025
By Jonathan Shoemaker
Hospitals today are fighting a daily battle – not just for resources, staff, or space, but the staffed bed for the acute inpatient stay.
The ability to move patients seamlessly through the acute patient journey is increasingly constrained by post-pandemic realities: staffing shortages, rising costs, and increasingly complex patient needs. These challenges are not going away anytime soon. In fact, a recent study published in JAMA Network Open found that by 2032, the U.S. could face a full-scale hospital bed shortage.
With national hospital occupancy rates now at 75%, dangerously close to the threshold where hospitals begin running out of available beds, health system leaders must act now. The answer isn’t simply more beds – it’s smarter patient flow. Artificial intelligence (AI), predictive analytics, and automation offer new ways to anticipate patient needs, proactively manage capacity, and create a more efficient and coordinated care environment.
The real cost of poor patient flow
Many hospitals still operate under a reactive model when it comes to patient flow, relying on outdated manual processes to manage admissions, transfers, and discharges. This results in avoidable bottlenecks that delay care, decrease efficiency, and impact financial performance.
Consider this: when patients stay in an acute care setting longer than necessary due to delays in discharge or transfer, they not only could have compromised outcomes, but they also occupy beds that could be used for new patients. Hospitals then face situations where patients in the emergency department (ED), transfers, or those awaiting scheduled procedures have nowhere to go. This creates overcrowding in the ED, increases the burden on care teams, and ultimately leads to poorer patient outcomes.
The traditional approach to managing patient throughput is no longer sufficient. Hospitals must move away from manual, siloed decision-making and embrace real-time intelligence that enables proactive, strategic management of patient movement across the hospital and health system. AI and predictive analytics provide the necessary visibility and decision support to improve patient throughput in several ways:
• Real-time capacity awareness: AI-driven platforms continuously analyze real-time and historical data to predict demand surges, identify bottlenecks, and recommend actions to optimize bed utilization.
• Automated admission and discharge prioritization: AI can assess which patients are most in need of admission and which patients are ready for discharge, ensuring that the right patient is in the right bed at the right time.
• Streamlined care coordination: Predictive analytics can facilitate smoother transitions between hospital departments and between the hospital and post-acute care settings, reducing delays caused by miscommunication.
Reducing avoidable delays and ED overcrowding with AI-powered discharge planning
A major source of inefficiency in hospitals is delayed discharges. Whether due to incomplete documentation, outstanding orders, or difficulty in securing post-acute care, these unnecessary delays prevent hospitals from optimizing their limited capacity. AI can help by:
• Predicting discharge needs early: AI models can analyze patient data to anticipate discharge readiness days in advance, allowing hospitals to coordinate with post-acute facilities ahead of time.
• Automating administrative tasks: From securing insurance approvals to coordinating patient discharge orders and logistics, automation can eliminate the manual work that slows down discharges.
• Providing clear, data-driven insights: AI-powered dashboards can alert care teams to potential barriers before they cause discharge delays.
Emergency departments are frequently overwhelmed, not because of an influx of new patients, but because admitted patients have no available inpatient beds. AI-powered predictive models can forecast ED demand and optimize inpatient bed availability in advance. Hospitals leveraging real-time patient flow intelligence can anticipate trends and adjust staffing and resources accordingly, reducing ED boarding times and improving overall patient outcomes.
The future of AI-driven patient flow
AI and automation are already proving their value in optimizing patient flow and enhancing care coordination. But as these technologies evolve, their impact will grow even further:
• Enhanced forecasting models: AI will continue to improve in predicting not only bed demand but also the clinical acuity of incoming patients, enabling even better resource allocation.
• Expanded interoperability: Seamless integration across electronic health records (EHRs) and hospital management systems will improve collaboration between different care settings.
• Personalized patient pathways: AI-driven insights will allow for more individualized care planning, ensuring patients receive the right care in the right place at the right time.
Hospital executives must rethink their approach to patient flow. The future is not about managing beds – it’s about managing patient movement to optimize capacity and staffed beds. AI, predictive analytics, and automation provide a pathway to overcoming current capacity constraints while improving both financial and clinical outcomes. By investing in intelligence-driven patient flow solutions today, hospitals can ensure they are prepared to meet the increasing demands of tomorrow.
The battle for the bed isn’t about adding more; it’s about using them smarter. And with AI, predictive analytics, and automation, hospitals can finally gain the strategic edge they need to optimize patient flow and address capacity issues.
About the author: Jonathan Shoemaker joined ABOUT in 2023 as CEO, bringing more than 25 years of health system and information systems experience with a proven track record of transforming and delivering initiatives and solutions that improve healthcare delivery, operations, and growth.
Before joining ABOUT, Jonathan most recently was senior vice president of operations and chief integration officer as well as a member of the senior executive team leading Allina Health’s Performance Transformation Office. Before his most recent role at Allina, Shoemaker spent six years as Allina Health’s chief information officer and chief improvement officer. Prior to Jonathan’s tenure at Allina, he held leadership positions at prominent IT & healthcare firms, including NorthPoint Health and Wellness Center, BORN Consulting, and Hennepin County Medical Center.
Hospitals today are fighting a daily battle – not just for resources, staff, or space, but the staffed bed for the acute inpatient stay.
The ability to move patients seamlessly through the acute patient journey is increasingly constrained by post-pandemic realities: staffing shortages, rising costs, and increasingly complex patient needs. These challenges are not going away anytime soon. In fact, a recent study published in JAMA Network Open found that by 2032, the U.S. could face a full-scale hospital bed shortage.
With national hospital occupancy rates now at 75%, dangerously close to the threshold where hospitals begin running out of available beds, health system leaders must act now. The answer isn’t simply more beds – it’s smarter patient flow. Artificial intelligence (AI), predictive analytics, and automation offer new ways to anticipate patient needs, proactively manage capacity, and create a more efficient and coordinated care environment.
The real cost of poor patient flow
Many hospitals still operate under a reactive model when it comes to patient flow, relying on outdated manual processes to manage admissions, transfers, and discharges. This results in avoidable bottlenecks that delay care, decrease efficiency, and impact financial performance.
Consider this: when patients stay in an acute care setting longer than necessary due to delays in discharge or transfer, they not only could have compromised outcomes, but they also occupy beds that could be used for new patients. Hospitals then face situations where patients in the emergency department (ED), transfers, or those awaiting scheduled procedures have nowhere to go. This creates overcrowding in the ED, increases the burden on care teams, and ultimately leads to poorer patient outcomes.
The traditional approach to managing patient throughput is no longer sufficient. Hospitals must move away from manual, siloed decision-making and embrace real-time intelligence that enables proactive, strategic management of patient movement across the hospital and health system. AI and predictive analytics provide the necessary visibility and decision support to improve patient throughput in several ways:
• Real-time capacity awareness: AI-driven platforms continuously analyze real-time and historical data to predict demand surges, identify bottlenecks, and recommend actions to optimize bed utilization.
• Automated admission and discharge prioritization: AI can assess which patients are most in need of admission and which patients are ready for discharge, ensuring that the right patient is in the right bed at the right time.
• Streamlined care coordination: Predictive analytics can facilitate smoother transitions between hospital departments and between the hospital and post-acute care settings, reducing delays caused by miscommunication.
Reducing avoidable delays and ED overcrowding with AI-powered discharge planning
A major source of inefficiency in hospitals is delayed discharges. Whether due to incomplete documentation, outstanding orders, or difficulty in securing post-acute care, these unnecessary delays prevent hospitals from optimizing their limited capacity. AI can help by:
• Predicting discharge needs early: AI models can analyze patient data to anticipate discharge readiness days in advance, allowing hospitals to coordinate with post-acute facilities ahead of time.
• Automating administrative tasks: From securing insurance approvals to coordinating patient discharge orders and logistics, automation can eliminate the manual work that slows down discharges.
• Providing clear, data-driven insights: AI-powered dashboards can alert care teams to potential barriers before they cause discharge delays.
Emergency departments are frequently overwhelmed, not because of an influx of new patients, but because admitted patients have no available inpatient beds. AI-powered predictive models can forecast ED demand and optimize inpatient bed availability in advance. Hospitals leveraging real-time patient flow intelligence can anticipate trends and adjust staffing and resources accordingly, reducing ED boarding times and improving overall patient outcomes.
The future of AI-driven patient flow
AI and automation are already proving their value in optimizing patient flow and enhancing care coordination. But as these technologies evolve, their impact will grow even further:
• Enhanced forecasting models: AI will continue to improve in predicting not only bed demand but also the clinical acuity of incoming patients, enabling even better resource allocation.
• Expanded interoperability: Seamless integration across electronic health records (EHRs) and hospital management systems will improve collaboration between different care settings.
• Personalized patient pathways: AI-driven insights will allow for more individualized care planning, ensuring patients receive the right care in the right place at the right time.
Hospital executives must rethink their approach to patient flow. The future is not about managing beds – it’s about managing patient movement to optimize capacity and staffed beds. AI, predictive analytics, and automation provide a pathway to overcoming current capacity constraints while improving both financial and clinical outcomes. By investing in intelligence-driven patient flow solutions today, hospitals can ensure they are prepared to meet the increasing demands of tomorrow.
The battle for the bed isn’t about adding more; it’s about using them smarter. And with AI, predictive analytics, and automation, hospitals can finally gain the strategic edge they need to optimize patient flow and address capacity issues.
About the author: Jonathan Shoemaker joined ABOUT in 2023 as CEO, bringing more than 25 years of health system and information systems experience with a proven track record of transforming and delivering initiatives and solutions that improve healthcare delivery, operations, and growth.
Before joining ABOUT, Jonathan most recently was senior vice president of operations and chief integration officer as well as a member of the senior executive team leading Allina Health’s Performance Transformation Office. Before his most recent role at Allina, Shoemaker spent six years as Allina Health’s chief information officer and chief improvement officer. Prior to Jonathan’s tenure at Allina, he held leadership positions at prominent IT & healthcare firms, including NorthPoint Health and Wellness Center, BORN Consulting, and Hennepin County Medical Center.