This algorithm matches medical staff of nine different specialties to medical facilities efficiently along multiple dimensions such as geography, timing, skill sets required and offered, to expedite informed hiring decisions by medical facilities in the context of the COVID-19 pandemic. 
This algorithm also informs public health policymaking by identifying particular gaps in the healthcare system through the analysis of completed matches. 
Technology Overview
Northeastern researchers developed a matching model and an algorithm that calls a commercial solver to optimize the medical staff matching problem along with multiple objectives and a set of constraints.
This system also dynamically maintain a master database of staff supply availability and unmet facility demand that feed into the model in a daily basis to provide the maximum number of matches giving priority to urgent needs, staff geographical proximity to facilities, and assures that the staff for a given job type also have the necessary clinical qualifications identified by the facilities. Furthermore, given that in most emergencies there is a severe shortage of staff supply, this process has specific logic built in to rematch a given staff member if a previously matched facility does not indicate hiring intent after a given period. All of the parameters, objective function weights, number of job types, and the constraints for identifying feasible matches can be adjusted dynamically to incorporate changing needs of the situation on the ground.
- Automates the matching process while maximizing the coverage of urgent facility needs.
- Healthcare in crisis settings 
- Healthcare in steady-state operations 
- Emergency management settings (in addition to healthcare)
- License
- Partnering
- Research collaboration
Patent Information:
For Information, Contact:
Mark Saulich
Associate Director of Commercialization
Northeastern University
Ozlem Ergun