AI Model Predicting Two-Year Risk of Common Heart Disorder can Easily be Integrated into Healthcare Workflow

AFib (short for atrial fibrillation), a common heart rhythm disorder in adults, can have disastrous consequences including life-threatening blood clots and stroke if left undetected or untreated. A new study demonstrates that UNAFIED, a highly accurate artificial intelligence (AI) prediction model which uses machine learning to parse information acquired from a patient's electronic health record (EHR) to predict whether a patient has or might develop detectable AFib within the following two years, can be easily integrated into the healthcare workflow.

UNAFIED is an acronym for Undiagnosed Atrial Fibrillation prediction using Electronic health Data.

Testing implementation and performance in real world conditions, the researchers reported that physicians in a busy medical practice in the Eskenazi Health system in Indianapolis who regularly used the UNAFIED risk prediction model found it easy to use and not time consuming. Most significantly, physicians participating in the study indicated that they believed it helped improve patient care. The non-invasive, inexpensive approach provides a practical option for proactive screening of patients, especially the large number of individuals at elevated risk for AFib.

Individuals at higher risk for AFib include adults living with obesity, many types of heart disease, Type 2 diabetes or sleep apnea, as well those who are smokers or binge alcohol drinkers or have a family history of the disease.

"Unfortunately, atrial fibrillation can be silent until it's disastrous. We developed and validated this risk prediction model to find the instances where atrial fibrillation was silent but still occurring or likely to occur," said Regenstrief Institute Research Scientist Randall Grout, M.D., M.S. "The primary goals of the UNAFIED model are preventing very significant negative medical outcomes and even death.

"Using such indicators as sex, height and weight, prior diagnoses of heart or kidney disease - information already easily available to the clinician - our model performed at the leading edge. It doesn't require extra steps, making it easy for clinicians to integrate into their practice."

Dr. Grout is the first author of the UNAFIED clinical implementation study, a co-author of the national validation study and the first author of the development study. In addition to his Regenstrief appointment, Dr. Grout is a faculty member of the Indiana University School of Medicine and chief health informatics officer at Eskenazi Health.

In the study of clinical implementation, UNAFIED was integrated into the EHR system of a busy cardiology clinic, enabling the algorithm upon which UNAFIED is based to calculate the predicted risk for each patient individually. If the risk factor was found to be above a certain threshold, the model provided visual indicators to the cardiologist that the patient might have an elevated risk of undetected AFib or of developing AFib within the next two years. The workflow also provides recommendations such as performing follow-up heart rhythm and other testing as well as presenting ways to document within the EHR for higher risk or that a patient may actually be experiencing AFib, even if the condition had been previously ruled out. Respectful of professional expertise and experience, the model offers the physician the option of overriding or bypassing the prompts.

According to the Centers for Disease Control and Prevention, there are more than 454,000 hospitalizations with AFib as the primary diagnosis in the U.S. annually. The condition contributes to an estimated 158,000 deaths in the U.S. each year.

Dr. Grout notes that while the algorithm on which UNAFIED is based was built to predict undetected AFib, lessons learned from the development of this model could be employed to develop algorithms for models focused on other conditions as well as specific populations or geographic areas. While some of the predictor variables used may be the same in many or most models - for instance age of patient - others, such as a history of a certain diagnoses, could be customized for the specific disease under scrutiny.

Grout RW, Ateya M, DiRenzo B, Hart S, King C, Rajkumar J, Sporrer S, Torabi A, Walroth TA, Kovacs RJ.
Screening for undiagnosed atrial fibrillation using an electronic health record‒based clinical prediction model: clinical pilot implementation initiative.
BMC Med Inform Decis Mak. 2024 Dec 18;24(1):388. doi: 10.1186/s12911-024-02773-z

Most Popular Now

AI-Powered CRISPR could Lead to Faster G…

Stanford Medicine researchers have developed an artificial intelligence (AI) tool to help scientists better plan gene-editing experiments. The technology, CRISPR-GPT, acts as a gene-editing “copilot” supported by AI to help...

Groundbreaking AI Aims to Speed Lifesavi…

To solve a problem, we have to see it clearly. Whether it’s an infection by a novel virus or memory-stealing plaques forming in the brains of Alzheimer’s patients, visualizing disease processes...

AI Spots Hidden Signs of Depression in S…

Depression is one of the most common mental health challenges, but its early signs are often overlooked. It is often linked to reduced facial expressivity. However, whether mild depression or...

AI Model Forecasts Disease Risk Decades …

Imagine a future where your medical history could help predict what health conditions you might face in the next two decades. Researchers have developed a generative AI model that uses...

AI Tools Help Predict Severe Asthma Risk…

Mayo Clinic researchers have developed artificial intelligence (AI) tools that help identify which children with asthma face the highest risk of serious asthma exacerbation and acute respiratory infections. The study...

AI Model Indicates Four out of Ten Breas…

A project at Lund University in Sweden has trained an AI model to identify breast cancer patients who could be spared from axillary surgery. The model analyses previously unutilised information...

Smart Device Uses AI and Bioelectronics …

As a wound heals, it goes through several stages: clotting to stop bleeding, immune system response, scabbing, and scarring. A wearable device called "a-Heal," designed by engineers at the University...

AI Distinguishes Glioblastoma from Look-…

A Harvard Medical School–led research team has developed an AI tool that can reliably tell apart two look-alike cancers found in the brain but with different origins, behaviors, and treatments. The...

ChatGPT 4o Therapeutic Chatbot 'Ama…

One of the first randomized controlled trials assessing the effectiveness of a large language model (LLM) chatbot 'Amanda' for relationship support shows that a single session of chatbot therapy...

Overcoming the AI Applicability Crisis a…

Opinion Article by Harry Lykostratis, Chief Executive, Open Medical. The government’s 10 Year Health Plan makes a lot of the potential of AI-software to support clinical decision making, improve productivity, and...

Dartford and Gravesham Implements Clinis…

Dartford and Gravesham NHS Trust has taken a significant step towards a more digital future by rolling out electronic test ordering using Clinisys ICE. The trust deployed the order communications...