A Race Against Time To Save Lives
Boeing’s market leading Jeppesen digital aviation software solved a crucial nurse scheduling problem for the intensive care unit (ICU) for Karolinska University Hospital in Stockholm, Sweden’s second largest hospital, at the start of the COVID-19 pandemic.
Using Jeppesen Crew Rostering, which employs FICO® Xpress Optimization, Boeing created rosters for over 300 nurses and healthcare workers during the peak period, resulting in more workable shifts for staff and better coverage for the hospital.
You can read more about this story in the full media release.
A Challenge with a Human Cost
The arrival of the COVID-19 pandemic turned everything on its head, creating an immediate need to rapidly expand intensive care units, and challenged the existing employment practices and regulation. The virus was spreading throughout Sweden and Karolinska University Hospital needed to scale up their operation significantly to cope with the rapidly increasing volume of patients.
“The biggest challenge, by far, was time,” said Daniel Roth, Senior Business Advisor with Boeing. “We only had a week to produce the initial schedule, which had to incorporate who could work when, individual nurse competences, special requirements with respect to their schedules, and other factors. This data was not available in a structured way, but rather in the heads of current schedulers and management. Fortunately, our extensively used aviation solution with FICO Xpress Optimization as an integral part, enables an end-user to quickly build schedules.”
Optimization Solves Complex Problems Fast
When factoring in the labor rules of the Crisis Agreement, it became apparent that the Crisis Agreement work limits exceeded those at which a human being can work for an extended period of time. Therefore, it was essential to establish reasonable workloads and shift patterns. In the end, the structure ended up being two types of 12.5 hour overlapping shifts, meaning 56 per week. 7 different competence profiles were established, with minimum requirements per shift and an objective to maximize coverage.
“The resulting optimization problems fall into the class of NP-Hard in complexity theory, meaning one cannot expect to solve larger instances exactly in reasonable time,” said Tomas Gustafsson, Portfolio Manager with Boeing. “The Jeppesen solution approach combines heuristics and exact methods to reach those practical run times, where the sub-problem linear and integer programs are solved using FICO Xpress.”
The situation at Karolinska ICUs this spring was overwhelming and unprecedented. The staff were working at extreme levels, exposing and risking their health and life, but diligently coping with the influx of patients. “Expanding the ICU and quickly implementing Boeing’s Jeppesen-optimized scheduling system enabled for more efficient, safer work and eased some of the burden the hospital faced through the height of the pandemic,” said Roth. “It is hard to put a number on the benefits and performance of an effort like this, but we believe we have, in our own small way, contributed to battling the pandemic and supporting those on the frontlines.”
For its achievements, Boeing’s crew solution team has won the 2021 FICO® Decisions Award for AI, machine learning & optimization.
This is a fantastic use of optimization to solve one of the most pressing problems worldwide last year. Anyone looking for examples of the positive benefits of using optimization should look at what Boeing and Karolinska did in a matter of days to help healthcare professionals manage the coronavirus crisis.
“Boeing adapted its Jeppesen airline and railway scheduling optimization system to solve ICU nurse scheduling problems during the pandemic," said Lisa Morgan, contributing writer at InformationWeek and one of the FICO Decisions Awards judges. “The judges were impressed how quickly Boeing’s team understood the problem, addressed it, and implemented a solution. These data scientists did an excellent job of rising to the occasion.”