This text is part of the Research special section
How many patients are in the emergency department today? How long did they wait? Why are they consulted? All this information – and much more – is collected daily in Quebec hospitals. What if they were used to optimize emergency operations? This is the goal set by a management researcher and family doctor in Rouyn-Noranda.
“Since I became an emergency manager, I only spend about ten hours each month on the schedule,” says Dr. Justin Langevin, sighing from his side of the screen. He also has to juggle the work of managing his service with his responsibilities as a full-time doctor. “These are redundant tasks that I have to do in the evening or on the weekend. And it’s not my expertise: I didn’t have management training! »
The idea was born in a chance meeting with a professor of management sciences at the University of Quebec in Abitibi-Témiscamingue Chahid Ahabchane. Why not entrust the creation of schedules to artificial intelligence? The software could take into account availability and employee preferences to create an ideal schedule – alleviating Dyear Langevin. “That is my main managerial task. If I free up that time, I will be able to focus on something else,” emphasizes the doctor.
Manage time better
Artificial intelligence to generate… Plans? Isn’t that too simple a task for such a specialized tool? “Emergency plans are very complicated,” D repliesyear Langevin. Some doctors work full-time, others part-time. Sometimes they have related tasks so we can’t make them work in the evening or at night. We have to balance weekday and weekend work. » Not to mention the difference in performance between newly arrived doctors, who see fewer patients during their shift, and their more experienced colleagues.
But the ambitions of both collaborators do not end there. In addition to creating plans based on staff availability, why not also add an indicator: on-call traffic. “We thought we could use historical emergency data to create tailor-made schedules,” explains Mr Ahabchane. For example, we see that the emergency department is always busiest on Monday and Tuesday mornings. » The tool could take this information into account and assign more experienced doctors to that shift to minimize patient wait times.
Quebec has a goldmine of data: the Med-Urge software, implemented since the early 2000s in emergencies across the province. Some basic information is noted about each patient, including the reason for the consultation, in addition to arrival and departure times, time spent in the emergency department and priority for triage. “We have a lot of data, but it is underutilized,” says Mr. Ahabchane, who sees huge potential. This information was used as input for a machine learning tool.
The result: from November 2023, emergency plans at Rouyn-Noranda Hospital are designed by artificial intelligence – under the strict supervision of D.year Langevin. “The algorithm has a different style than mine,” he notes with a smile. Example: “I usually do one or two shifts and then two days off. Instead, the algorithm forces people to work four or five days, but gives them longer rest periods. » A survey was conducted among emergency service workers to measure their satisfaction with this new way of working and to optimize the tool accordingly. Other improvements could also be made. “I would like people to be able to enter their preferences, for example the number of days in a row they want to work, and for the schedule to be created to reflect that,” says the doctor.
Support the doctor
Although their project is still in its infancy, both colleagues are already thinking about what will happen next. “If we can develop a standardized program, we could export it elsewhere in Quebec,” Justin Langevin points out. Confidentiality issues will need to be resolved before this can be achieved. Fortunately, there is very little information about patients’ health in Med-Urge. “Patient data is in paper form in the card file,” explains the head of the ambulance service.
One thing is clear: doctors need all the support they can get. “Emergency medicine is notoriously difficult, and atypical hours contribute to that,” recalls Dr.year Langevin. If we can optimize this aspect to improve the quality of life of doctors, we may be able to increase retention. »
This content was created by the Special Publications team at Obligation, relating to marketing. Writing about Obligation did not participate.