Key result
Automated AI analysis cuts test-retest LVEF variability ~45% vs manual expert measurement.
Why the study?
Serial cardiotoxicity screening requires measurement precision, and automated AI techniques could reduce variability and increase confidence in detecting true interval change.
Does fully automated AI analysis improve measurement precision of LVEF and GLS in cancer patients undergoing cardiotoxicity surveillance compared to expert manual analysis?
Observational (n=60)
Blinded manual analysis
No
Does fully automated AI analysis improve measurement precision of LVEF and GLS in cancer patients undergoing cardiotoxicity surveillance compared to expert manual analysis?
Absolute Event Rate: 3.6% vs 6.6%
p-value: p=0.011
Fully automated AI analysis of 2D echocardiograms provides superior measurement precision for LVEF and GLS compared to expert manual analysis, potentially improving the reliability of cardiotoxicity surveillance.
May improve LVEF precision in cardiotoxicity surveillance; leaves open need for prospective outcome trials before practice change.
Aims Serial imaging demands measurement precision – particularly for cardiotoxicity screening where small changes gatekeeper major management decisions. Automated measurement using artificial intelligence (AI)-based techniques should reduce variability and increase confidence for detection of true interval change. We directly compared the precision of fully-automated AI versus expert manual analysis of left ventricular function by echocardiography. Methods and Results Consecutive cancer patients referred for cardiotoxicity monitoring underwent same day repeat 2D echocardiography (n=60, 83% female, mean age 52±12years, mean LVEF 57±7%), with 3D acquisition where feasible (n=45). All 2D images underwent blinded manual analysis by fully automated analysis software and four individual experts. Quantitative 2D LVEF measurement was feasible in 97% scans by both methods. Mean absolute difference (MAD) between repeat scans was significantly lower for AI than experts for both 2D LVEF (3.6% [CI 2.8–4.4] vs 6.6% [CI 5.3–7.9], p=0.011) and global longitudinal strain (1.5% [CI 1.1–1.9] vs 2.5% [CI 2.0–3.0], p=0.006). In participants with 3DE datasets, 3D LVEF MAD was lower than manual 2D LVEF (3.6% [CI 2.8-4.6] vs 6.4% [CI 5.0-8.0], p=0.006) but comparable to AI-derived 2D LVEF (3.5% [CI 2.9-4.2], p=0.4). In a subset (n=48) also with same day cardiovascular magnetic resonance studies (CMR), AI 2DE analysis demonstrated stronger agreement with CMR than expert 2DE analysis (LVEF MAD 5.0% [CI 4.1-5.9] vs 7.8% ([CI 6.6-9.0] p=0.006). Conclusions In cancer patients at risk of cardiotoxicity, the precision of 2D echocardiographic AI analysis exceeds that of experts, matching that of 3D LVEF assessment.
No takes yet. Share an insight, caveat, or question.
Dowsing et al. (2026) conducted an observational in Cancer patients referred for cardiotoxicity monitoring (n=60). Fully automated AI analysis of 2D echocardiography vs. Expert manual analysis was evaluated on Mean absolute difference (MAD) in 2D LVEF between same-day repeat scans (p=0.011). Fully automated AI analysis of 2D echocardiograms significantly reduced the mean absolute difference in LVEF between same-day repeat scans compared to expert manual analysis (3.6% vs 6.6%, p=0.011).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: