Adibzadeh, Sara ORCID: https://orcid.org/0009-0003-3656-916X, Fernandes, Patricia ORCID: https://orcid.org/0009-0000-9720-2829, Agrawal, Mayur ORCID: https://orcid.org/0009-0000-7878-2274, Dadashi Serej, Nasim ORCID: https://orcid.org/0000-0002-2898-1926, Gheitasy, Ali ORCID: https://orcid.org/0009-0008-4090-5249 and Zolgharni, Massoud ORCID: https://orcid.org/0000-0003-0904-2904 (2025) A Clinician-Centred interface for AI-Powered echocardiographic image quality feedback. In: International Conference on AI in Healthcare, 8-10 September 2025, Cambridge, United Kingdom.

PDF 292-305.pdf - Draft Version Restricted to Repository staff only until 25 August 2026. Download (2MB) | Request a copy

Abstract

Echocardiography is a widely used, non-invasive imaging technique for cardiac assessment, but its effectiveness is highly dependent on the operator’s expertise. Variability in image acquisition can compromise diagnostic accuracy, highlighting the need for consistent, real-time feedback to support clinicians during scanning. Although recent advances in artificial intelligence have enabled automated assessment of image quality, these tools often fail to deliver feedback in a format that is interpretable, actionable, and seamlessly integrated into clinical workflows. We present the design and evaluation of a clinician-centred interface that provides visual feedback on image quality during echocardiographic examinations. The interface overlays quality assessments onto the imaging screen using intuitive visual elements, guiding the operator to improve the visibility of key cardiac structures while also addressing image foreshortening. The system was developed through a human-centred design process involving clinician input, ethical safeguards, and iterative prototyping. A three-phase evaluation involving peer reviewers, expert cardiologists, and clinical practitioners assessed usability and interpretability through qualitative feedback and structured usability metrics. Results confirmed the interface’s effectiveness in enhancing user experience, supporting clinical decision-making, and preserving clinician autonomy. The findings demonstrate the potential of this approach to improve consistency and confidence in echocardiographic image acquisition.

Item Type:	Conference or Workshop Item (Paper)
ISBN:	9783032006561
Identifier:	10.1007/978-3-032-00656-1_21
Page Range:	pp. 283-296
Identifier:	10.1007/978-3-032-00656-1_21
Keywords:	human-computer interaction; user-centered design; human-artificial intelligence interaction; echocardiography
Subjects:	Computing > Intelligent systems
Date Deposited:	03 Oct 2025
URI:	https://repository.uwl.ac.uk/id/eprint/14144
Sustainable Development Goals:	Goal 3: Good Health and Well-Being

Actions (login required)

View Item