Once someone has a stroke, the likelihood for a second stroke jumps up. And that recurrent stroke may cause further damage to the already injured brain, boosting the chance it leads to disability or death. A major risk factor for a second stroke is a form of heart arrhythmia called atrial fibrillation. It’s usual to monitor people for atrial fibrillation while they are in the hospital but once they go home, most stroke patients aren’t monitored.
In part, that’s because home monitoring for atrial fibrillation for every stroke patient would be prohibitively expensive, Stanford researcher Nigam Shah, MBBS, PhD, told me. But what if you could figure out which patients are most likely to have atrial fibrillation?
That’s exactly what a team of researchers — led by Shah, who is an associate professor of biomedical data science, and Susan Zhao, MD, of Valley Medical Center — did recently, publishing their research in the journal Cardiology today.
As I explained in my news release about the study:
The team did a retrospective cohort study using data from thousands of stroke patients from Stanford’s Translational Research Integrated Database Environment. Of the 9,589 stroke patients in the database, 482 of them, or 5 percent, went on to be diagnosed with atrial fibrillation.
The team had already developed a text-processing pipeline for analyzing clinical data and clinical-diagnosis coding. Using that pipeline, the team extracted information from clinical notes, flagging, for example, phrases such as ‘ruled out stroke’ and classifying data according to whether it referred to the patient or came from a family history section. The result was a list of biomedical facts about each patient — including age, body mass index and so on.
The result is an scoring system that a physician can use to estimate how likely an individual patient is to experience atrial fibrillation and a second stroke. That information allows physicians to intervene with treatments that reduce the risk — providing a classic example of precision health in action.