01
Starting with a gap in access
An ultrasound machine is a starting point. Acquiring and interpreting cardiac images still requires specialist skills. Where specialists are scarce, local teams need ways to connect an examination with appropriate assessment and referral.
EasyEF is being developed to add information at this point in the care journey. We aim to make existing images more useful to care teams, while evaluating how the workflow affects time, workload, and referrals.
References and further reading
02
Building on existing equipment
A healthcare professional records the echocardiography display with a smartphone and submits the clip through the app for AI assessment. The ultrasound examination produces the cardiac image; the phone captures and sends it.
This approach lets us build around equipment that clinical teams already know. The suitability of different displays, phones, and working environments still needs testing with users.
References and further reading
03
What EasyEF looks for in a heart video
Our focus is the left ventricle (LV). The studied model uses the sequence of heart movement to classify function, adding information for clinical assessment.
The output is a function category, not a precise EF percentage or a complete cardiac examination. Valve and pericardial abnormalities require separate research.
References and further reading
04
Supporting assessment and clinical decisions
EasyEF is Clinical Decision Support: a tool that adds information to clinical decisions. It focuses on screening left ventricular contraction, with clinicians interpreting the result alongside symptoms, history, and other investigations.
AI results have a defined scope and can be wrong. Patient care continues to depend on clinical assessment and further investigation when appropriate.
References and further reading
05
Designed for clinical teams
Our intended users include general practitioners, internists, family physicians, cardiac nurses, and trained healthcare professionals. The workflow covers selecting a view, recording a clip, submitting it, and understanding the result.
We plan approximately 1–2 hours of application training, alongside checks of clip quality and user readiness. Echocardiographic acquisition skills remain an essential foundation that requires training and supervision.
References and further reading
06
Learning through research and practice
The 2024 study tested video-clip classification. A later Rayong Hospital study evaluated 218 participants during December 2025–January 2026. Together, these studies help us understand both the potential and the areas needing improvement.
Intermediate cardiac-function categories remain a key challenge. We use subgroup findings to guide development, with methods and detailed results available on the research pages.
References and further reading
07
The next step with partners
The next phase connects application and platform development, multisite evaluation, and medical-software readiness. Our goal is a system that can be evaluated rigorously and fits real care workflows.
We welcome hospitals, researchers, technology developers, and supporters to help define questions and test what matters to users.
References and further reading
SOURCE NOTES
Sources and published project summaries
- The cardiac-assessment journey — by the EasyEF team
- From an idea to the platform — by the EasyEF team
- 2024 published study — original journal article ↗
- EasyEF team: Rayong study report
- EasyEF team: project scope and development roadmap
Project content is compiled and published by the EasyEF team from development records, presentations and study reports. Internal links lead to the team’s summaries, not additional independent evidence. Published research links to its original journal; study status and limitations are stated in the relevant articles.
Explore the source library →