December 9, 2022
The COVID-19 pandemic has created new opportunities to develop and deploy high-impact analytics to combat severe resource shortages and a rapidly evolving healthcare ecosystem. Nursing organizations suffered both during and in the aftermath of the pandemic from excess demand for and diminishing supply of nurses. The nurse shortage was caused in part by nurses leaving the profession as well as nurses leaving their permanent jobs to take lucrative travel nursing contracts. With limited ability to replace nurses, hospitals struggle to maintain adequate staffing amidst the massive spike in workforce variability.
In January 2021, we embarked on a journey in partnership with Indiana University (IU) Health System, the largest health system in Indiana with 16 hospitals, to jointly develop a suite of advanced data and decision analytics to support a new internal travel nursing program at IU Health. In January 2021, we launched an academia-industry venture to develop and deploy a data-driven solution to support this systemwide program, which was branded the Delta Coverage program. Delta Coverage expands the floating capacity to their entire network. Effective implementation of this program requires an analytics tool integrating forecasting and optimization to improve quality of care while respecting the working conditions of the nursing staff. To provide 1-2 weeks advanced notice of travel, we developed a novel machine-learning-based occupancy forecasting model that accounts for different levels of patient acuity. Using distributional information from the forecast, we generate workload scenarios for the network along with a probability measure over the scenarios. These scenarios are fed into a two-stage stochastic program where the decision variables mimic the timing and type of decisions being made in practice.
The decision support tool was implemented in October 2020 as a Microsoft Power BI application that recommends how many nurses to put on-call 1-2 weeks in advance and how many on-call nurses to deploy to a remote hospital, with the option to cancel some of the planned travel if it is found not to be needed closer to the time of deployment. We logged the performance of the recommendations from October 2021 to March of 2022 as a proof of value, with the tool running each day in real time. Analysis indicates system-wide improvements in all metrics: with reductions of 5% understaffing, 3% misallocation of resource nurses, and 1% overstaffing. Further benefits include a narrowing of the staff to demand fluctuation, with a reduction in the third quartile of understaffing of 32% and in overall understaffing variance of 4%. The annualized savings estimated at over $400K.
Bio: Jonathan Helm (Ph.D. University of Michigan, Industrial and Operations Engineering), is the Grainger Fellow Associate Professor of Operations and Decision Technologies at Indiana University’s Kelley School of Business and is the Co-Director for Indiana University’s Kelley School of Business Center for the Business of Life Science. He has held operations management and supply chain roles at GE Healthcare and Mayo Clinic and was a three-year National Science Foundation Fellow.
Professor Helm’s vision is to drive a grassroots entrepreneurial research agenda to influence public policy and revolutionize the delivery of community services through a two-way pipeline where practice drives research and research changes practice. His specific domain foci lie in hospital operations and studies of the opioid crisis. The primary theory and analytical tools deployed include predictive modeling, stochastic modeling and control, and deterministic optimization. In his research, Professor Helm takes a problem driven approach, working closely with industry collaborators to solve high impact business and societal problems. Recent research interests include predictive and prescriptive analytics to support COVID-19 response, developing personalized treatment programs under capacity constraints for patients at risk for opioid addiction, and supply chain responsibility in the opioid crisis.
Several of Professor Helm’s research products have been implemented into healthcare practice. These include a census forecasting and surgical schedule control system that was implemented in a hospital in Singapore, readmission reduction analytics implemented as a web-based application at a hospital in Indiana, and, most recently, two implementations of predictive and prescriptive analytics applications at Indiana University Health, largest health system in Indiana serving over 1 million patients.