Hospitals are increasingly implementing artificial intelligence (AI) into their operations, particularly predictive algorithms. Writing for MedCity News, Katie Adams explains how two major health systems, Geisinger and UNC Health, are using predictive AI to manage chronic diseases, improve patient care, and more.
According to Karen Murphy, Geisinger's chief innovation and digital transformation officer, many of the organization's innovation efforts focus on "the problem of chronic disease management and population health."
To address this issue, Geisinger developed a risk stratification model to identify patients with chronic diseases who have the highest risk of an adverse event or ED admission. The model allows case managers to identify which patients require more serious medical intervention and when.
"We developed a risk stratification model that incorporates over 800 factors. The prediction we're trying to make is which patients are at the highest risk for admission over the next 30 days," Murphy said. "And that model is then shared with the assigned case manager: these are your patients that are at the highest risk, reach out, explain why, and then implement the necessary interventions to prevent that ED or hospital admission."
Murphy also noted that since Geisinger is an integrated delivery network, which includes a clinical enterprise and health plan, the organization made sure the model could "work hand in hand" with both the health plans' case managers and population health managers.
According to Murphy, a recent analysis of the model's impact over 60 days showed that it reduced avoidable ED visits and hospital admissions among patients with chronic conditions by 10%.
At UNC Health, predictive AI is being used to quickly identify and treat patients with sepsis, which can rapidly become fatal if clinicians do not intervene as soon as possible. According to Adams, around 11 million people worldwide die from sepsis-related issues every year.
Rachini Moosavi, UNC Health's chief analytics officer, said the organization has been testing predictive models to flag sepsis since 2018.
"We were looking at the models that were already available to us, and some of them triggered an alert 10 times within our EHR system that a patient might actually have sepsis," Moosavi said. "That kind of level of false positive alerting starts to add to alert fatigue."
To prevent alert fatigue, as well as clinician burnout, UNC created a custom model to detect sepsis. According to Moosavi, health systems often need to create their own predictive algorithms since in-house data teams will have the best knowledge of clinicians' workflows compared to commercial models. (Adams, MedCity News, 7/28)
Generative artificial intelligence offers life science leaders an unprecedented opportunity to revolutionize the drug development process. Explore how life science leaders can leverage generative AI to increase diversity in clinical trials, identify better targets for drug discovery, and reduce drug development timelines — all while promoting equity and improved health outcomes.
Create your free account to access 1 resource, including the latest research and webinars.
You have 1 free members-only resource remaining this month.
1 free members-only resources remaining
1 free members-only resources remaining
Never miss out on the latest innovative health care content tailored to you.