Clinical Edge

Summaries of Must-Read Clinical Literature, Guidelines, and FDA Actions

Machine learning–derived risk score predicts heart failure risk in diabetes patients

Key clinical point: A machine learning–derived risk score based on 10 common clinical variables (WATCH-DM) can identify high-risk diabetes patients facing a heart failure risk of up to nearly 20% over the ensuing 5 years.

Major finding: The 5-year risk of heart failure was 1.1% for patients with WATCH-DM scores in the lowest quintile, increasing in a graded fashion to 17.4% in the highest quintile.

Study details: Machine-learning analysis using data from 8,756 high-risk diabetes patients (from the ACCORD study) with no heart failure at baseline.

Disclosures: Dr. Vaduganathan said he is supported by an award from Harvard Catalyst. He provided disclosures related to Amgen, AstraZeneca, Baxter Healthcare, Bayer AG, Boehringer Ingelheim (advisory boards), and with Novartis and the National Institutes of Health (participation on clinical endpoint committees).

Citation:

HFSA 2019; Segar MW, Vaduganathan M et al. Diabetes Care. doi: 10.2337/dc19-0587.