A group of researchers from the United States has developed a tool to predict well in advance risks of individuals developing a rare, chronic lung condition called idiopathic pulmonary fibrosis.
The tool uses algorithms to sift through an individual’s health records and identify whether the person risks developing the serious lung condition.
Called Zero-burden Co-Morbidity Risk Score for IPF (ZCoR-IPF), the algorithm captures an individual’s past medical interventions to cull out a risk score for the disease. It has been tested on more than three million individuals, 54,000 of whom had IPF. .
The test does not require any traditional diagnostic sampling procedures, and has been built upon US electronic health records data.
Helpful head start
Currently it takes about three years to diagnose the disease after the onset of its symptoms, making it hard to treat individuals who have IPF.
In their testing, the researchers found that the algorithm was 85 per cent accurate in diagnosing the condition four years before it was detected through conventional methods.
“Running the tool as soon as one makes an appointment with the doctor could actually give the individual’s test results even before [the person] walks into the clinic,” told co-author of the study, Ishanu Chattopadhyay, who is an assistant professor of medicine at the University of Chicago to Happiest Health.
The algorithm, he adds, can work as a point of care tool for this condition.
Hard to detect
Idiopathic pulmonary fibrosis is a chronic lung tissue disorder that largely affects individuals in the age group of 50 to 70 years. This condition falls into the category of interstitial lung diseases (ILD) that are often characterised by inflammation and scarring of lung tissues.
It causes shortness of breath and dry cough and is often misdiagnosed as chronic obstructive pulmonary disease.
“IPF is a rare disorder with varying clinical manifestations and challenging diagnostic criteria,” according to co-author Fernando J Martinez, who is chief of the Division of Pulmonary and Critical Care Medicine at Weill Cornell Medicine.
Current methods to diagnose IPF are time consuming, requiring multiple CT scans and lung tissue biopsies. “Lung biopsy is not done unless a reason exists for it. This further delays the diagnosis of IPF,” says Chattopadhyay.
The results are extremely promising given that IPF presents itself non-specifically, meaning that not every patient with the condition would experience the same symptoms. Further, the tool also performed well despite known inconsistencies in electronic medical records.
“When you work with electronic health record data, one of the first pushbacks you often hear is, ‘How accurate is it?’,” says Chattopadhyay. “So, we were very pleased with our results. It seems to be a very accurate screening test.”
The researchers from the University of Chicago, Mayo Clinic, Weill Cornell Medicine, New York-Presbyterian, and Brigham and Women’s Hospital said using this algorithm, they would conduct studies on a larger population and in real-time settings to enhance its efficacy.
They also hope to implement the tool for diagnosing other disease conditions as well.