FDNY and Columbia Strive to Improve EMS Response Operations and Balance Hospital Capacity Loads

By Leila Merrill

NEW YORK – Engineers at Columbia University are working with the New York Fire Department to improve EMS response operations and to help balance the capacity loads of local hospitals.

FDNY’s services have been strained during the pandemic, and the department has developed a number of innovations in its EMS system to reduce response time to life-threatening medical emergencies.

These efforts can have a significant effect on EMS care in the city due to the size of the department. FDNY oversees New York City’s 911 EMS system and directly operates two-thirds of the approximately 450 ambulances in New York City’s 911 system. In addition, 198 fire truck companies are providing medical answers.

One of its most critical innovations is improving its approach to deploying its EMS resources to minimize response time.

In January, FDNY launched an ambulance system optimization process designed by engineers at Columbia in collaboration with analysts and subject matter experts from FDNY, which was integrated with the existing computer-aided dispatch functionality of FDNY. The new system is the result of Columbia Engineering’s earlier collaboration with the New York Department of Transportation to analyze traffic data and a new optimization process designed to alleviate overcrowding of ambulances in a single hospital or groups of ‘hospitals while neighboring hospitals have the capacity.

Optimizing transportation when hospitals are likely to be overloaded is considered a “plan ahead” approach to hospital overloading, and is designed to minimize the need for hospital reorientation requests or referrals. hospital diversion, which remain in place as options of last resort to provide relief to overworked individuals. emergency services.

FDNY has worked with the Columbia engineering team, which is led by Andrew Smyth, Robert RW and Christine S. Carleton, professor of civil and mechanical engineering; and Henry Lam, associate professor of industrial engineering and operations research, for nearly two years.

“Our DOT project was a perfect fit for the needs of FDNY,” says Smyth, who is also president of the Smart Cities Center at Columbia’s Data Science Institute. “We had already developed a program for DOT that gave us very high resolution of the traffic speed distributions of every street in New York City by hour of the day and day of the week. Understanding the behavior of ambulance traffic throughout the city and spotting new patterns has given us a head start in optimizing the EMS. Our new model for FDNY EMS cuts ambulance trips from incident sites to hospitals by about one minute for thousands of emergencies. “

FDNY has also created a new approach to analysis management in order to consolidate efforts to analyze EMS innovations. This includes three collaborative teams specializing in data quality, operations research and geographic information systems.

Lam’s group was already working with the Smyth team to overlay a load balancing optimization program on Smyth’s traffic model. Lam’s program suggests hospital destinations for 911 patients that alleviate the workload of overwhelmed hospitals while ensuring short trips, thus optimally balancing patient demand and supply across the city. Underneath this program, which runs on the FDNY’s CAD on a daily basis, is a data-driven optimization algorithm that integrates predictive models of incidents, hospital capacity and travel time. Lam’s group worked closely with the FDNY to test the algorithm via simulation modeling and pandemic outbreak data, before the FDNY launched it on January 13.

“The integration of operations research and AI into this project created a powerful approach to improve the EMS system,” Lam said. “It provides a solution to protect hospital loads throughout the city against future incident surges. “

Kat Thomson, FDNY Deputy Commissioner, Management Analysis and Planning, added: “This new approach also integrates the concept of optimization directly into the EMS system, and it is very intuitive for stakeholders. Where the FDNY historically took corrective action in already overwhelmed emergency departments, this new approach gives the FDNY analysis team the ability to plan ahead, analyze the predicted overload against the data. real time on an ongoing basis and validate the results in near real time using data visualization. The data outputs of the optimization also facilitate the communication on the initiative between the hospitals and the agency.

The initiative uses FDNY 911 transport data and hospital bed availability data from the New York State Department of Health’s Health Electronic Response Data System daily survey. Lam’s optimization algorithm assesses the gaps between supply and demand for staffed hospital beds based on planned transports near receiving hospitals for the next day, assuming that 40% of ambulance transports will result in a admission.

FDNY runs the optimization every evening after receiving the HERDS data for the day. The optimization output is implemented each evening and is effective for the next 24 hours.