Historically, most health systems:

1. Have limited visibility into real-time OR supply, surgeon capacity, and demand for surgical services across the system.
2. Schedule OR blocks using under-informed or inaccurate estimates of procedure length.
3. React to scheduling changes and cancellations too late to preserve the scheduled OR time.

These inefficiencies lead to uneven OR utilization across a system or region, wait times that are longer than necessary, OR overruns (and clinician overtime), and unused OR time. 

Leading health systems are developing the capability to proactively assess demand and match OR and surgeon supply to meet it. They are investing in solutions that enable them to:
 

1. Gain visibility into “true” demand and real-time OR and surgeon capacity across the system to evenly distribute cases across all ORs.
2. Schedule cases based on long-term surgeon performance data and clinical variables that could introduce variance to the anticipated procedure length.
3. Predict and proactively prevent or intervene against surgery cancellations.

1. Centralized waitlist management programs. These programs enable health systems to determine “true” surgical demand and optimize their supply to meet it. First, clinicians determine a patients’ appropriateness and need for surgery based on standardized eligibility criteria co-developed by surgeon cohorts for specific case types. Surgery scheduling teams can then determine the optimal location for each case based on patient urgency, patient and staff preference, and the patient and staff’s proximity to each OR. Spreading out cases this way maximizes surgeon capacity and reduces idle OR time. The scheduling efficiency gains enable surgeons to generate more revenue by performing more procedures. Systems can emphasize this benefit or create new incentives to generate buy-in from surgeons.
2. Machine learning (ML)-enabled scheduling optimization tools. These artificial intelligence (AI) tools help OR scheduling and patient flow teams optimize individual OR blocks and daily OR schedules by accounting for the probability that a procedure will overrun. Here, OR blocks are calculated based on historical non-clinical and surgeon performance data from thousands of past cases, compared to the current practice of averaging a surgeon’s previous 10 to 15 cases. Some scheduling tools are also leveraging patient-related clinical variables that may alter procedure time to yield even more accurate predictions.
3. ML-enabled cancellation prediction tools. These AI tools can reduce OR throughput disruptions by identifying which appointments are most likely to be cancelled or rescheduled based on historic cancellation data. These tools learn from non-clinical variables, such as surgeons’ track record of cancelling procedures and time between scheduling and appointment date. These tools enable scheduling teams to proactively intervene before the appointment is cancelled. If cancellations cannot be prevented, scheduling teams can book a new patient into the cancelled slot, thus reducing unused OR time and sunk costs associated with cancellations. 

This capability enables systems to: reduce patient wait times to consultation and to treatment, reduce OR overruns, reduce clinician overtime, and reduce OR cancellations and idle time. Below are outcomes from organizations that are developing this capability.

Historically, most health systems:

1. Equip surgeons with traditional imaging tools like X-rays, ultrasounds, or MRIs to inform pre-op plans.
2. Have limited ability to quantify patient risk, limiting surgeons’ ability to proactively tailor patients’ treatment to avoid complications. 

Overall, health systems underleverage technology in the pre-operative stage of surgical patients’ journeys, resulting in reduced productivity and preventing surgeons from making the most appropriate treatment decisions for patients.

Leading health systems are investing in tools that enable surgeons to make more accurate treatment decisions earlier in the patient journey. They are investing in solutions that enable surgeons to:
 

1. Minimize manual hours spent on pre-op planning while simultaneously improving treatment accuracy.
2. Modify treatment plans before surgery to prevent complications and readmissions.

1. Extended reality (XR) and ML-enabled pre-operative planning software. Systems are partnering with technology vendors or developing tools in-house to automate the pre-op planning process and reduce surgeon time spent on non-patient-facing care. These XR and computer vision technologies enable surgical teams to better visualize the patients’ anatomy before procedures by turning traditional imaging into 3-D, interactive holograms. Surgeons can use the tools to optimize their treatment plan and determine ideal incision, implant, or device placement. This not only reduces planning time but also operation time and risk of complication or readmission. Some systems are even able to reduce the staff count per case. The tools are most common for orthopedic, oncology, and cardiovascular cases.
2. ML-enabled post-operative risk prediction tools. These clinical decision support tools help clinicians proactively optimize patients’ treatment plans by using hundreds of clinical data points from a patient’s record to quantify post-operative complication or readmission risk. These models may be prescriptive or descriptive. In addition to quantifying risk factors, they may also offer suggestions for how to maximize outcomes or pinpoint the clinical variables that are likely to lead to a complication.

This capability enables systems to reduce patient wait times, reduce OR turnover times, and reduce complication rates. Below are outcomes from several organizations developing this capability.

Historically, health systems fully equip most or all their ORs — including inpatient, outpatient, and ambulatory/day case — with resources that are not used in every procedure. They resource their ORs to treat a wide case mix, leading to increased turnover times and unnecessary costs.

Leading health systems are tiering their ORs by case complexity or case type, allowing them to drastically reduce the cost structure of each OR tier and increase throughput and margin. They are adopting operating practices that enable them to rightsize the staff, equipment, and tools within each OR, often starting with outpatient/day surgeries.

1. Minimally resourced, segmented ORs. In this model, health systems tier their ORs by case  complexity and resource intensity. Within each tier, they determine the appropriate complement of surgical tools and support staff needed to maintain care quality and gradually pare them down over time through contained pilots. The number of tools may be reduced by 75% or more. This work generally starts with low complexity, high-throughput cases. Once proof-of-concept has been developed, health systems can expand the number and kinds of services delivered through the model to other ORs, including inpatient ones. A slow, phased shift toward this model ensures that clinicians remain engaged in the process.

This competency enables health systems to reduce OR turnover time, reduce cost per case, and reduce recovery time. Below are outcomes from one organization that developed this capability.