Truace
Subscribe

A randomized controlled trial of a novel AI-based prognostic decision support tool integrated into the electronic health record for ischemic heart disease: Rationale and design of the PM Heart trial

Background Ischemic heart disease (IHD) is the leading global cause of years of life lost. Although the clinical presentation and progression of IHD differ widely, clinical management is relatively uniform. To improve risk stratification and clinical management, we developed a decision support tool - the PMHeart IHD Algorithm (also named PMHNet) - based on extensive clinical, registry and biochemical data. This algorithm automatically calculates one-year survival following an IHD event. We hypothesize that prese…

By the Truvace desk2 min read1 sourcePeer-reviewedTRV-2026-2147· cite & verify
A randomized controlled trial of a novel AI-based prognostic decision support tool integrated into the electronic health record for ischemic heart disease: Rationale and design of the PM Heart trial
Cardio Surgery 1 by Dominique Cappronnier. CC BY-SA 3.0 · https://creativecommons.org/licenses/by-sa/3.0

In brief

The article describes the rationale and design of the PM Heart trial in Denmark. Researchers built the PMHeart IHD Algorithm from clinical, registry and biochemical data and connected it to the Epic-based electronic health record used in two Danish regions.

The trial matters because it will give controlled evidence on whether an AI prognosis changes care for coronary artery disease patients, rather than relying on assumptions. It is a protocol, so no results exist yet, and any benefit remains a hypothesis until follow-up ends.

Main points

  1. The algorithm automatically estimates one-year survival after an ischemic heart disease event.
  2. The trial is multicenter, prospective, randomized and open-label, with 1:1 randomization immediately after coronary angiography.
  3. Patients are randomized to have the calculated prognosis shown or hidden in the electronic health record.
  4. The primary outcome combines re-admission within 30 days and one-year survival after randomization.
  5. A secondary aim is to learn how cardiology decision support tools are implemented, received and used in practice.

The gain

An AI algorithm integrated into the hospital record calculates one-year survival after an ischemic heart disease event, and a randomized trial is testing whether showing it to physicians improves patient outcomes.

The rundown

Ischemic heart disease is described as the leading global cause of years of life lost. Presentation and progression vary widely, yet clinical management is relatively uniform, which motivated a tool to improve risk stratification.

The algorithm is integrated into the Sundhedsplatformen EPIC system. The trial automatically enrolls and randomizes hospitalized coronary artery disease patients at cardiology departments in the Capital Region and Region Zealand.

Inclusion began in September 2023 and follow-up is expected to finish in 2026. The article presents the design, so it reports no measured effect on patient outcomes.

Sources

  1. Peer-reviewedAmerican Heart Journal2026-10-18

The debate