Optimization Automates Emergency Department Nurse Scheduling at Hartford Hospital

Liangyuan Na (), Jean Pauphilet (), Ali Haddad-Sisakht (), Louis Raison (), Audrey Silver (), Patricia Veronneau (), Nicole Vogt () and Dimitris Bertsimas ()
Additional contact information
Liangyuan Na: Operations Research Center, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139
Jean Pauphilet: Management Science and Operations, London Business School, London NW1 4SA, United Kingdom
Ali Haddad-Sisakht: Dynamic Ideas LLC, Waltham, Massachusetts 02452
Louis Raison: Dynamic Ideas LLC, Waltham, Massachusetts 02452
Audrey Silver: Hartford HealthCare, Hartford, Connecticut 06103
Patricia Veronneau: Hartford HealthCare, Hartford, Connecticut 06103
Nicole Vogt: Hartford HealthCare, Hartford, Connecticut 06103
Dimitris Bertsimas: Sloan School of Management, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139

Interfaces, 2024, vol. 54, issue 6, 553-574

Abstract: To optimize nurse staffing in the emergency department (ED), Hartford Hospital has been collaborating with academics and consultants to schedule nurse shifts over each six-week staffing cycle. We develop and implement two-phase optimization models: a robust optimization model to find optimal staffing levels given the uncertainty in patient demands, followed by a pair of mixed-integer problems to generate individual schedules including work, trainee, and preceptor shifts for each nurse. Our approach leads to less costly (5%–8%) staffing with better coverage of patient care (8%–25%) and higher nurse satisfaction (5%). Moreover, nurses can work fewer shifts on weekends (17%), holidays (14%), and overtime (85%), as well as be assigned to more diverse positions (3.6) and more daily training opportunities (0.95). We implement our framework into an automated end-to-end scheduling optimization software, deployed for use at Hartford Hospital since March 2023. The software collects preferences from more than 200 ED nurses and enables managers to optimize schedules with guided dynamic adjustments. This transformative implementation streamlines a previously labor-expensive staffing process (currently taking more than 88 manual hours per cycle) and delivers schedules that are more suitable for patients and nurses together, with an annual projected cost saving of around $720,000.

Keywords: robust optimization; mixed integer optimization; software automation; nurse scheduling; emergency department (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://dx.doi.org/10.1287/inte.2023.0071 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:inm:orinte:v:54:y:2024:i:6:p:553-574

Access Statistics for this article

More articles in Interfaces from INFORMS Contact information at EDIRC.
Bibliographic data for series maintained by Chris Asher ().