Highlights & Key Findings

​

• Peripheral artery disease (PAD) is an increasing global health problem with 202 million people diagnosed. A need exists for alternative means for evaluating Peripheral artery disease (PAD).

• A prospective cohort of 355 patients referred for diagnostic peripheral angiography and/orcoronary angiography to Massachusetts General Hospital were enrolled in the CASABLANCA Study (Clinical Trials.Gov NCT00842868). Predictors of ≥50% stenosis in at least one peripheral vessel were identified from over fifty clinical variables and 109 biomarkers.

• Machine Learning (Subset of AI) & Big Data. Candidate panels of biomarkers and clinical variables were generated and evaluated with machine learning statistical techniques, a subset of Artificial Intelligence (AI). The ultimate result of this process was a final test panel and scoring system.

• Final score has 1 clinical variable (History of hypertension) and 6 biomarkers (Angiopoietin-1, Eotaxin-1, Follicle Stimulating Hormone, Interleukin-23, Kidney Injury Molecule-1, and Midkine).

• Low risk patients (score = 1) had NPV of 98%; high risk patients (score = 5) had PPV of 86%.

​

​

​

Conclusions

​

• In a prospective cohort study, we describe a novel method to predict angiographically significant PAD, also lending potential prognostic information regarding need for revascularization.

​

• The biomarkers in this model all have plausible biologic links to atherosclerosis.

​

• Clinically, use of a tool such as this could act as a gatekeeper prior to imaging or invasive testing, thus reducing cost and exposures to intravenous contrast and/or ionizing radiation.

​

• The score may also be used to evaluate at-risk patients for risk of vascular complications. Enriching clinical trials for PAD-related events or identifying patients at risk for adverse effects of drug therapies could be effective.

​

• Prevencio has also developed HART   AMP, a panel specifically for identifying patients at risk for amputation.

​

​

​

Scroll Down for the Clinical Cardiology publication

TM