Computer researchers at the University of Ottawa Heart Institute (UOHI) have developed and tested a clinical model to accurately predict the risk of death and unplanned cardiac hospitalization for patients awaiting heart surgery.
Unplanned cardiac hospitalization refers to non-selective (acute) hospitalization for heart failure, myocardial infarction (heart attack), unstable angina (unexpected chest pain) or endocarditis (an infection of the heart’s inner lining or heart valves) while on the waiting list.
This model is intended to facilitate patient-centered decision-making, improve patient outcomes, and work with other models developed by the group to maximize the allocation of important health resources.
An additional tool in the box for GPs and administrators
“Given the medical complexity of cardiac patients and the risk of becoming ill while awaiting surgery, this data-driven approach promotes individualized waiting times and confirms safe and timely triage decisions,” explains Dr. Louise Sun, who spearheaded the project, an anesthesiologist and computer scientist at UOHI and an adjunct scientist at the Institute for Clinical Evaluative Sciences (ICES).
“Our model is an extra tool in the box to support referring physicians and the operating team as well as health administrators through time-dependent, individualized risk prediction.”
– Dr. Louise Sun.
A robust population study with deep consequences for patient care
Using data sets from the CorHealth Ontario Clinical Registry and population-level administrative health databases from ICES, Dr. Sun and her team conducted a population-based, retrospective cohort study to develop and test the calculator. The results are highlighted in the Canadian Medical Association Journal (CMAJ).
More than 60,000 residents across Ontario were included in the study, all of whom were over 18 and on the waiting list for either aortic, mitral or tricuspid valve surgery, coronary bypass grafting (CABG) or thoracic aortic surgery between October 2008 and September 2019.
Researchers randomly divide the study cohort into two groups: two-thirds to inform the model, and the remaining third to validate it.
In analyzing the data, study authors identified functions in patients that they say are “most at risk” for death or unplanned cardiac hospitalization while on the waiting list after surgery.
“Our analysis showed that patients who were men, lived in urban areas, had more severe heart symptoms, were treated in teaching hospitals and waited for surgery for specific procedures, such as CABG, had an increased risk of death or unplanned hospitalization,” said Dr. Sun.
Understanding who is at greatest risk helps nursing teams determine who is most likely to benefit from rapid surgery.
Decision support also benefits administrators.
Carmel Coleman, a surgical triage coordinator and registered nurse at UOHI, has been using variations of the waiting list score for heart surgery since March 2020.
“This tool has become such a fundamental component of mine every day,” she said. “Every time a patient is referred for heart surgery, our team runs them through the application before entering the system and prioritizing their booking.”
Using the tool, Coleman and her staff can also distinguish between review cases and those that may require longer hospital stays, and they can plan all cases in such a way as to maintain flow and capacity in the intensive care intensive care unit, which means more patients can be admitted for surgery without sap vital resources or keeping them in the queue.
Among the things Coleman values most about the tool is how it provides an effective and quantifiable means of supporting which candidates are selected and planned for the operating room.
“You can’t argue with numbers,” she said. “When administrators can provide full reasoning and rationality for each patient they plan for surgery, and can back up their choices with hard data, they are relieved of the stress associated with making such important care decisions.”
Planned cases are routinely discussed and agreed upon in meetings with heads of cardiac surgery and anaesthesiology.
Do machines and algorithms take over?
The calculator’s waiting list calculator, said Dr. Sun, is intended to increase and not replace human intelligence or intuition.
“Clinical judgment is based on many years of education and practical experience in medicine. It is an art form that simply cannot and will not be completely replaced by machines, ”she said. “Using data-driven support tools, we can allocate resources allocated and make informed decisions about who is selected for surgery and when.”
Coleman agrees. “Assistive devices like these guarantee the care team, the patient and their family that decisions about the next day’s cases are fully justified because they are supported by real evidence.”
So far, Dr. Sun and her team at UOHI and ICES developed point-of-care apps and integrated software platforms for waiting list management, capacity planning, and planning to share with hospitals and health jurisdictions during the COVID-19 crisis and beyond.
“Our clinical service team has used a calculator to predict the length of stay in our intensive care unit and a waiting list tool to triage each patient who comes through the surgical referral pipeline,” said Dr. Sun.
“While other centers reduced their annual procedure volumes, we were able to perform close to our usual cardiac surgery volumes while still keeping enough ICU beds open for COVID.”