In the Journals

Clinical, biomarker score predicts PAD

A score consisting of one clinical variable and six biomarkers accurately predicted the presence of peripheral artery disease, researchers reported in Clinical Cardiology.

The score comprised presence of hypertension plus six biomarkers: midkine, kidney injury molecule-1, interleukin-23, follicle-stimulating hormone, angiopoietin-1 and eotaxin-1 and can be derived from a blood test (HART PAD, Prevencio).

“This blood test may allow for the diagnosis and treatment of many more patients with PAD,” James L. Januzzi, MD, Roman W. DeSanctis Endowed Distinguished Clinical Scholar in Medicine and director of the Dennis and Marilyn Barry Fellowship in Cardiovascular Research at Massachusetts General Hospital and professor of medicine at Harvard Medical School, said in a press release. “As well as giving physicians the opportunity to provide patients with more appropriate care, we believe the test could also benefit clinical trials by saving time and thereby lowering overall trial costs.”

Januzzi and colleagues analyzed 354 patients from the CASABLANCA study referred for diagnostic peripheral and/or coronary angiography; 132 had obstructive PAD, defined as at least 50% stenosis in at least one peripheral vessel. After analyzing more than 50 clinical variables and 109 biomarkers, machine learning identified the seven predictors of obstructive PAD.

The model that Januzzi and colleagues created had an in-sample area under the receiver operating characteristic curve of 0.85 and a cross-validated area under the curve of 0.84 for obstructive PAD. The higher the score, the greater the severity of angiographic stenosis.

At optimal cutoff, for obstructive PAD, the score had a sensitivity of 65%, a specificity of 88%, a positive predictive value of 76% and a negative predictive value of 81%, Januzzi and colleagues wrote, noting the score performed consistently across different vascular beds.

When the cohort was stratified into quintiles based on the score, the score had a positive predictive value of 86% for the highest quintile and a negative predictive value of 98% for the lowest quintile, according to the researchers.

At 4.3 years of follow-up, higher score was associated with shorter time to revascularization, Januzzi and colleagues wrote.

“The combination of biomarkers and clinical variable might be useful to clinicians,” Januzzi and colleagues wrote. “Given a range of score values that provides both strong [positive and negative predictive values], one could theoretically argue that the use of a clinical/biomarker tool such as this could act as a gatekeeper to imaging or invasive testing, thereby reducing costs and exposures to intravenous contrast and/or ionizing radiation by avoiding expensive imaging modalities when unwarranted.” – by Erik Swain

Disclosure: The study was supported by a grant from Prevencio. Januzzi reports he has received grant support from Critical Diagnostics, Novartis, Philips and Roche Diagnostics and has participated in clinical endpoint committees and or data safety monitoring boards for Abbvie, Amgen, Bayer, Boehringer Ingelheim, Janssen, Novartis and Pfizer. Please see the study for the other authors’ relevant financial disclosures.

A score consisting of one clinical variable and six biomarkers accurately predicted the presence of peripheral artery disease, researchers reported in Clinical Cardiology.

The score comprised presence of hypertension plus six biomarkers: midkine, kidney injury molecule-1, interleukin-23, follicle-stimulating hormone, angiopoietin-1 and eotaxin-1 and can be derived from a blood test (HART PAD, Prevencio).

“This blood test may allow for the diagnosis and treatment of many more patients with PAD,” James L. Januzzi, MD, Roman W. DeSanctis Endowed Distinguished Clinical Scholar in Medicine and director of the Dennis and Marilyn Barry Fellowship in Cardiovascular Research at Massachusetts General Hospital and professor of medicine at Harvard Medical School, said in a press release. “As well as giving physicians the opportunity to provide patients with more appropriate care, we believe the test could also benefit clinical trials by saving time and thereby lowering overall trial costs.”

Januzzi and colleagues analyzed 354 patients from the CASABLANCA study referred for diagnostic peripheral and/or coronary angiography; 132 had obstructive PAD, defined as at least 50% stenosis in at least one peripheral vessel. After analyzing more than 50 clinical variables and 109 biomarkers, machine learning identified the seven predictors of obstructive PAD.

The model that Januzzi and colleagues created had an in-sample area under the receiver operating characteristic curve of 0.85 and a cross-validated area under the curve of 0.84 for obstructive PAD. The higher the score, the greater the severity of angiographic stenosis.

At optimal cutoff, for obstructive PAD, the score had a sensitivity of 65%, a specificity of 88%, a positive predictive value of 76% and a negative predictive value of 81%, Januzzi and colleagues wrote, noting the score performed consistently across different vascular beds.

When the cohort was stratified into quintiles based on the score, the score had a positive predictive value of 86% for the highest quintile and a negative predictive value of 98% for the lowest quintile, according to the researchers.

At 4.3 years of follow-up, higher score was associated with shorter time to revascularization, Januzzi and colleagues wrote.

“The combination of biomarkers and clinical variable might be useful to clinicians,” Januzzi and colleagues wrote. “Given a range of score values that provides both strong [positive and negative predictive values], one could theoretically argue that the use of a clinical/biomarker tool such as this could act as a gatekeeper to imaging or invasive testing, thereby reducing costs and exposures to intravenous contrast and/or ionizing radiation by avoiding expensive imaging modalities when unwarranted.” – by Erik Swain

Disclosure: The study was supported by a grant from Prevencio. Januzzi reports he has received grant support from Critical Diagnostics, Novartis, Philips and Roche Diagnostics and has participated in clinical endpoint committees and or data safety monitoring boards for Abbvie, Amgen, Bayer, Boehringer Ingelheim, Janssen, Novartis and Pfizer. Please see the study for the other authors’ relevant financial disclosures.