How AI is helping to predict death and complications after heart procedures

AI model predicts death, complications for patients undergoing angioplasty, stents

1:00 PM

View Transcript

It showed high levels of accuracy at predicting death, major bleeding events and the need for blood transfusion. Visit Health Lab to read the full story. The BMC2 Probability of Events Following PCI application can be found here.

Transcript

Host: 

Welcome to Health Lab, your destination for news and stories about the future of healthcare. Today: How AI is helping to predict death and complications after heart procedures. A new AI-driven model showed high levels of accuracy at predicting death, major bleeding events and the need for blood transfusion for patients undergoing angioplasty and stent placement.

When a person has one or more blocked arteries, providers may choose to conduct a minimally invasive procedure known as a percutaneous coronary intervention, or PCI. 

By inflating a balloon and potentially placing a stent, blood can flow more freely from the heart. 

Despite carrying less risk than open surgery, stenting and balloon angioplasty can result in complications like bleeding and kidney injury. 

Researchers at Michigan Medicine developed an AI-driven algorithm that accurately predicts death and complications after PCI — which could emerge as a tool for clinicians as they determine treatment for blocked heart arteries.

The results are published in the European Heart Journal.

“The risks for patients undergoing percutaneous coronary intervention vary greatly depending on the individual patient, and both patients and clinicians have historically both over and underestimated the harms associated with PCI,” said lead David E. Hamilton, M.D., a cardiology-critical care fellow at Michigan Medicine. 

“Precise risk prediction is critical to treatment selection and the shared decision-making process. Our tool can be used by care providers and patients together to decide the best course of treatment.”

While other risk stratification tools have been created to identify risk after PCI, researchers say, many have modest accuracy and were made without involving a key party: the patients. 

The Michigan Medicine team collected data from all adult patients who underwent PCI procedures between April 2018 and the end of 2021 using the Blue Cross Blue Shield of Michigan Cardiovascular Consortium, or BMC2, registry. 

The consortium is comprised of hospitals across the state of Michigan that use data they collect to inform quality projects, and improve care and patient outcomes.

Researchers used that data — including more than 20 pre-procedural characteristics, such as age, blood pressure and total cholesterol — to create a risk prediction model with the machine learning software “XGBoost”.

The AI-driven model showed high levels of accuracy at predicting death, major bleeding events and the need for blood transfusion. It outperformed other models that used the same pre-procedural characteristics.

“We combined the predictive model with patient feedback from the PCI Patient Advisory Council to transform machine learning into this patient-centered, individualized risk prediction tool,” said senior author Hitinder Gurm, MBBS, interim chief medical officer at U of M Health. 

“In the age of widespread smartphones and electronic medical records, this computerized risk score could be integrated into electronic health systems and made easy to use at the bedside. It would not only help relay complex information to the provider quickly, but it could also be used to enhance patient education on the risks related to PCI.”

The innovative technology has been harnessed into a computer and phone application to allow for free and widespread use.

For more on this story and for others like it, visit michiganmedicine.org/health-lab. Health Lab is a part of the Michigan Medicine Podcast Network, and is produced by the Michigan Medicine Department of Communication. You can subscribe to Health Lab wherever you listen to podcasts.


More Articles About: Cardiovascular: Diseases & Conditions Michigan Medicine podcast
Health Lab Podcast in brackets with a background with a dark blue translucent layers over cells
Health Lab Podcast

Listen to more Health Lab podcasts - a part of the Michigan Medicine Podcast Network.

Featured News & Stories Health Lab Podcast in brackets with a background with a dark blue translucent layers over cells
Health Lab Podcast
Study finds bipolar disorder surpasses smoking in mortality risk
A large study shows having bipolar disorder is associated with a four- to six-fold risk of dying prematurely, suggesting more preventive efforts needed. Visit Health Lab to read the full story.
purple gloves close up holding piece
Health Lab
Recycled pacemakers function as well as new devices, international study suggests
Recycled pacemakers can function as well as new devices, a University of Michigan-led study suggests. These used and reconditioned devices have the potential to increase access to pacemaker therapy in low- and middle-income countries, where many patients cannot afford the treatment.
Minding Memory with a microphone and a shadow of a microphone on a blue background
Minding Memory
Can a personalized music intervention reduce behavioral disturbances in dementia?
While memory loss is generally thought of as the hallmark of dementia, behavioral and psychological symptoms of dementia like agitation, aggression, anxiety, and hallucinations are nearly universal, affecting almost all patients with advanced dementia. These behavioral disturbances are often the trigger for nursing home placement, and they can be highly distressing for both patients and their care partners. In today’s episode, Matt and Lauren speak with Dr. Ellen McCreedy, a researcher from the Brown School of Public Health who has conducted a study of personalized music intervention called Music & Memory for people living with dementia in nursing homes. Dr. McCreedy is a gerontologist and health services researcher who focuses on evaluation of non-pharmacologic interventions for managing behavioral disturbances of people living with dementia.
clinical team and patient standing together
Health Lab
Planting a tree, and hope, for a heart healthy future
A complex mitral valve repair by Michigan Medicine cardiac specialists helps restore health and happiness to one Michigan patient and his family.
Minding Memory with a microphone and a shadow of a microphone on a blue background
Minding Memory
The Impact of Partner Plan Choices among Older Adults Enrolled in Medicare Advantage (MMs4)
In this episode, Matt & Lauren speak with Dr. Lianlian Lei, an Assistant Professor in the Department of Psychiatry at the University of Michigan. Dr. Lei discusses a recent study that looks at the impact of partner’s plan choice on the likelihood of Medicare Advantage disenrollment and how that may impact older adults living with dementia. Unlike traditional Medicare that's administered by the federal government, Medicare Advantage are healthcare plans that are administered by private health insurance companies. These plans can vary a lot and typically cover additional services not covered by traditional Medicare. Navigating the various plan options can be a challenge for older adults, and it's not uncommon for individuals to change plans depending on their current needs.
Health Lab Podcast in brackets with a background with a dark blue translucent layers over cells
Health Lab Podcast
The “chemical nudges” approach to chronic pain
In this episode, you will get to hear Dr. Boehnke, in his own words, talk about his experiences, and the “chemical nudges” approach to chronic pain; reframing the role of medications in chronic pain management, and why solely relying on pain relievers “disempowers patients, clinicians and the drugs themselves.”