The use of big data—referring to the use of computational programs to generate statistics—is pervasive in medicine and technology, but nurses are a growing part of this movement to translate data into protocols that profoundly benefit patient care and outcomes.
And while assistant professor Jessica Keim-Malpass holds two previous grants—$119,177 from the Lucile Packard Foundation for Children’s Health, and $30,000 from the American Cancer Society—her most recent award from the Translational Health Research Institute of Virginia will enable her to show how information that nurses collect from patients is central to creating predictive models from big data.
Because they are constantly at the bedside, nurses are perfectly positioned to contribute real-time information to these predictive models. Nurses are the “eyes and ears and first responders,” explains Keim-Malpass, as well as the “gatekeepers of patients’ safety.”
She’ll work with UVA’s Surgical Trauma Intensive Care Unit (STICU), where a program called Continuous Monitoring of Event Trajectories, or CoMET—created by School of Medicine professor J. Randall Moorman—calculates an overall picture of a STICU patient’s risk level, yielding an illustration of this risk that looks like a comet shooting across the sky. With the addition of vital sign data that nurses collect, including respiratory rate, pulse oximetry, heart rate, and blood pressure, the picture on CoMET of a patient’s overall health will be more complete, providing a consistent image of their status.
While the focus for a patient in intensive care is rehabilitation, these patients are also at great risk for decompensation, unplanned-for complications, and long hospital stays. When nurses’ observations are included in analyses like those by CoMET, the protocol improves, complications decrease and patients’ quality of life increases.
Over the study’s three years, Keim-Malpass will use nurse involvement in clinical trials and protocols to develop models to improve patient-centered outcomes. So when a nurse observes that a patient is experiencing increased heart rate, for example, and the information is included in a computational system like CoMET, the result is evidence-based care and a wider portrait of a patient’s status, prognosis, and risk, which informs protocols that drive treatment plans.
When nurses finally have a seat at the big data table, the benefit to patients will be immense, says Keim-Malpass, because the picture cast by big data will be richer and more detailed in scope, allowing big data to reflect what is happening in real time.
When more structures are in place to include nurses’ observations and assessments, says Keim-Malpass, big data will deepen clinicians’ understanding, broadening and enriching analyses overall.
“We [nurses] are central to moving this technology forward,” she says.