Integrating artificial intelligence into an echocardiography department: Feasibility and comparative study of automated versus human measurements in a high-volume clinical setting - 08/05/25

Doi : 10.1016/j.acvd.2025.04.051

Stéphane Lafitte ^a,^b,⁎ , Louis Lafitte ^a, Melchior Jonveaux ^b, Zoe Pascual ^b, Julien Ternacle ^b, Marina Dijos ^b, Guillaume Bonnet ^a,^b, Patricia Reant ^a,^b, Anne Bernard ^c,^d
^a Bordeaux University, 33000 Bordeaux, France
^b Unité médicochirurgicale des valvulopathies, CHU de Bordeaux, 33000 Bordeaux, France
^c Inserm U1327 ISCHEMIA ‘Membrane signaling and inflammation in reperfusion injuries’, Université de Tours, 37000 Tours, France
^d Service de Cardiologie, CHU de Tours, 37000 Tours, France

^⁎Corresponding author at: Hôpital Cardiologique, avenue Magellan, 33600 Pessac, France.Hôpital Cardiologiqueavenue MagellanPessac33600France

Sous presse. Épreuves corrigées par l'auteur. Disponible en ligne depuis le Thursday 08 May 2025

Graphical abstract

Le texte complet de cet article est disponible en PDF.

Highlights

•	The AI system was successfully integrated into the hospital's infrastructure within 4weeks.
•	The AI system is vendor neutral and therefore broadly scalable.
•	Very good agreement between AI and human measurements was highlighted for key parameters.
•	Higher concordance was found for expert echocardiographers and residents vs. nurses.

Le texte complet de cet article est disponible en PDF.

Abstract

Background

Echocardiography is an important diagnostic tool in cardiology as it is essential for heart disease treatment. However, its time-consuming nature and reliance on user expertise constitutes a challenge for its use in high-volume clinics. Artificial intelligence (AI) offers the potential to automate tasks performed manually by echocardiographers and promises to improve efficiency and diagnostic consistency.

Aims

To evaluate the integration of AI-based tools in a high-volume echocardiography department and assess the concordance of AI-generated measurements with manually-performed measurements.

Methods

The study was conducted in the echocardiography department of Bordeaux University Hospital. Over 2months, 894 echocardiograms were performed by operators with three experience levels (nurses, residents and experts), with measurements performed by AI and humans. The statistical analyses assessed measurement agreement between both.

Results

The AI system was successfully integrated into the hospital's infrastructure within 6weeks. Concordance analysis revealed good to very good agreement between AI and human measurements for most parameters, especially for ejection fraction (intraclass correlation coefficient [ICC]: 0.81, 95% confidence interval [95% CI]: 0.78–0.85) and Doppler-based flow measurements (mitral E wave velocity: ICC 0.97, 95% CI 0.95–0.98). Bland-Altman analysis showed a global mean difference of −4% with a standard deviation of 15%. Subgroup analysis revealed higher concordance for experts and residents compared with nurses (mean ICCs: 0.78 and 0.79 vs. 0.72, respectively).

Conclusion

AI can be effectively integrated into clinical echocardiography practice, with high agreement between AI and human measurements. Further research is needed to investigate the long-term impact on clinical outcomes and efficiency.

Le texte complet de cet article est disponible en PDF.

Keywords : Echocardiography, Artificial intelligence, Deep learning, Agreement analysis, Cardiac parameters