A team of researchers at the Stanford University School of Medicine and Santa Clara Valley Medical Center in the US have developed an algorithm that analyses data from electronic health records (EHRs) to predict the chance of a patient having a reoccurring stroke.
The algorithm specifically identifies the likelihood of a patient experiencing an irregular heartbeat – atrial fibrillation, after either a cryptogenic stroke or a transient ischemic attack.
By being able to identify the heart abnormality in stroke patients, doctors will be able to stay one step ahead by providing treatment to prevent a second stroke from occurring.
It’s generally difficult and costly to predict the likelihood of a second stroke in patients because even though patients are monitored for atrial fibrillation while they’re still in the hospital, once they go home they aren’t monitored closely enough to detect any abnormalities that could lead to a stroke.
In June the researchers published a paper describing their work in Cardiology. The senior authors are Nigam Shah, MBBS, PhD, associate professor of biomedical data science at Stanford, and Susan Zhao, MD, of Valley Medical Center. Stanford graduate student, Albee Ling, and Valley Medical Center internist, Calvin Kwong, MD, share lead authorship.
“This work resulted from a unique collaboration where a need for risk stratification was identified by Dr Zhao, and followed up jointly by an informatics student and a clinical fellow to derive a risk estimate for a population for which we don’t have good scoring methods,” said Shah.
Shah and his colleagues developed a way to predict which patients were at high risk for atrial fibrillation and should therefore be further monitored. This was achieved by doing 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 went on to be diagnosed with atrial fibrillation.
The team then used a text-processing pipeline they already developed to analyse the clinical data and clinical-diagnosis coding. From this they were able to extract 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 such as age and body mass index.
By ranking the clinical attributes of patients whose medical records indicated they went on to be diagnosed with atrial fibrillation, the team was able to determine a set of seven risk factors that, when combined, predicted which stroke patients were the most likely to develop the condition and should be monitored after hospitalisation. The risk factors are: age, obesity, congestive heart failure, hypertension, coronary artery disease, peripheral vascular disease and disease of the heart valves.
The scoring system can be used by physicians to determine which patients have a high risk of atrial fibrillation and should be monitored at home, and even be prescribed the appropriate medication to try and prevent a second stroke.
“Our system needs to be further validated in studies using other independent data sources,” said Ling.
Ling added that she expects that clinicians and researchers will further validate and improve the scoring system and that hopefully it will one day be adopted in everyday practice.
“On the other hand, there will surely be more clinical studies conducted using EHRs, not just at Stanford but in other medical institutions, as well,” concluded Ling.