JMIR Publications

ABSTRACT

Background:

Standard echocardiography reports use complex terminology, limiting patient comprehension and exacerbating preconsultation anxiety. Large language models (LLMs) can transform technical data into patient-friendly narratives by incorporating longitudinal comparisons with prior examinations.

Objective:

To develop an LLM-based patient-friendly echocardiography reporting system and evaluate its professional safety, patient comprehension, and impact on short-term anxiety.

Methods:

This study consisted of two stages. In the retrospective development stage, 60 patients with baseline hospitalization and follow-up echocardiography reports were included. Clinical diagnosis, hospitalization records, and serial echocardiographic data were integrated as model inputs using DeepSeek-V3.2. Generated reports followed a standardized four-module structure. Report quality was independently evaluated by two clinicians and an external LLM (Kimi 2.5, Moonshot AI) across four domains: data accuracy, information completeness, appropriateness of interpretation, and reasonableness of recommendations. In the prospective clinical evaluation stage, 100 patients undergoing echocardiography and 85 family members were enrolled between January 2026 and March 2026. Participants received both conventional and LLM-generated patient-friendly reports. A 5-point Likert scale assessed helpfulness in understanding results, effectiveness in addressing concerns, helpfulness in improving disease-related knowledge, and anxiety relief. Anxiety was measured using the STAI-6 at three time points: after echocardiography (APost-ECHO), after conventional report release (APost-CR), and after reading the patient-friendly report (APost-PFR).

Results:

All 60 reports in the retrospective stage were successfully generated. Professional evaluation showed high overall quality scores from both clinicians and the external LLM, with no significant difference between evaluators (mean total scores 18.15 [SD 1.36] vs 18.28 [SD 1.26]; P>.05). One hallucination event was identified. In the prospective stage, all 100 patients received patient-friendly reports. Both patients and family members rated the reports highly, with mean scores above 4.3 across all domains and no significant between-group difference in total scores (17.61 [SD 1.60] vs 17.62 [SD 1.03]; P>.05). Subgroup analyses showed greater perceived benefit among older patients and outpatients, particularly in report comprehension and overall evaluation (both P<.001). Patients with chronic heart failure, reduced left ventricular ejection fraction (≤40%), and left ventricular enlargement (>55 mm) reported higher scores for addressing concerns (all P<.001). Anxiety scores increased significantly after conventional report release (APost-CR vs APost-ECHO) and decreased significantly after reading the patient-friendly report (APost-PFR vs APost-CR; both P<.001). Older patients (>60 years) and outpatients showed significantly higher anxiety change rates than their counterparts (CR1 and CR2: both P<.001). The reduction in anxiety was positively correlated with subjective anxiety relief ratings (r=0.531; P<.001).

Conclusions:

The LLM-based patient-friendly echocardiography reporting system with longitudinal comparison demonstrated good feasibility and promising preliminary clinical utility. While maintaining high professional quality, it improved patient understanding of echocardiographic findings and was associated with reduced short-term anxiety, particularly among older adults and outpatients.