Perioperative medicine & outcomes
Digital Stethoscope–Derived Single-Lead Electrocardiogram and Artificial Intelligence to Detect Low Ejection Fraction: A Multicenter Observational Study
Authors' conclusion
The Eko digital stethoscope shows promise as a clinical decision-making tool for preoperative assessment.
Study context
- Population
- Preoperative patients referred for 2-dimensional echocardiogram, 10 tertiary care hospitals across India867 analysed
- Participants
- 981 patients
- Comparison
- Stethoscope-derived single-lead ECG AI algorithm vs echocardiogram-derived left ventricular ejection fraction (LVEF) ≤ 40%
- Outcome
- Detection of LVEF ≤ 40% (vs echocardiogram-derived LVEF ≤ 40%)
Methodological detailsmulticentre, prospective, observational
- Multicentre
- Prospective
- Observational
Performance
As reported in the abstract
| Test or model | AUC-ROC | Sensitivity | Specificity |
|---|---|---|---|
| Algorithm | 0.73 (95% CI, 0.67-0.78) | 60.1% (95% CI, 51.8%-67.9%) | 81.3% (95% CI, 78.4%-84.0%) |
Algorithm
AUC-ROC0.73 (95% CI, 0.67-0.78)
Sensitivity60.1% (95% CI, 51.8%-67.9%)
Specificity81.3% (95% CI, 78.4%-84.0%)
Further findings
| Outcome | Noncardiac | Cardiac |
|---|---|---|
| Detection of LVEF ≤ 40% by type of surgery (subgroup) | ||
| AUC | 0.75 (95% CI 0.59-0.92) | 0.70 (95% CI 0.64-0.75) |
Detection of LVEF ≤ 40% by type of surgery (subgroup)
- Performance superior in the noncardiac group
Parts of this Brief are withheld: the automatic checks could not confirm them against the abstract.
Original publication
Digital Stethoscope–Derived Single-Lead Electrocardiogram and Artificial Intelligence to Detect Low Ejection Fraction: A Multicenter Observational Study. J Cardiothorac Vasc Anesth. Published 4 March 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →