Background
Transthoracic echocardiography (TTE) is critical for detecting and managing cardiac dysfunction. However, its dependence on expert acquisition means its accessibility in rural areas may be limited, leading to potential missed diagnoses and delayed management. AGILE-Echo is a trial of Artificial intelligence-guided (AI)-TTE for permitting non-expert image acquisition in rural and remote Australia.
Aims
We aimed to assess markers of image quality to determine 1) Rates of diagnostic image acquisition at sites, 2) Whether a learning curve exists, 3) Whether patient demographic details influence the diagnostic quality of images?.
Methods
109 participants (51% male, age 66±15, BMI 30±7) from six sites were assessed for exercise intolerance (73%) or heart valve disease. We also assessed whether images were of “diagnostic” quality. Studies were also graded if each study's parasternal long axis (PLAX), parasternal short axis (PSAX), and apical 4-chamber (AP4CH) were visible. Regression models were used to determine the significance of the patient's clinical background to diagnostic image quality.
Results
Participants had high rates of smoking (65%), hypertension (57%), and atrial fibrillation (13%), with 4-year ARIC-HF risk of 7.3±11.9%. Parasternal windows showed higher success rates than apical windows, with AP2CH having the lowest. Increased BMI, hypertension, and ARIC-HF score correlated with non-diagnostic images (Table 1). No significant difference in diagnostic image rates was observed between personnel with >10 studies and those with fewer, or between first 10 and subsequent studies.
Conclusions
AI-TTE image acquisition success varied by window type, with PLAX most successful. Patient demographics (including age, BMI, and HF risk) influenced image quality (Table 2). No clear learning curve was observed after 10 studies.