Performance evaluation of domain-specific and general-purpose AI models for chest radiograph interpretation: a comparative study.
Authors
Affiliations (5)
Affiliations (5)
- Department of Radiology, Chosun University Hospital and Chosun University College of Medicine, 365 Pilmun-Daero, Dong-Gu, Gwangju, 61453, Republic of Korea.
- Deepnoid Inc., Seoul, 08376, Republic of Korea.
- Department of Pulmonology and Critical Care Medicine, Chosun University Hospital, Gwangju, Republic of Korea.
- Medical Science Research Institute, Kyung Hee University Hospital, Seoul, 02447, Republic of Korea.
- Department of Radiology, Chosun University Hospital and Chosun University College of Medicine, 365 Pilmun-Daero, Dong-Gu, Gwangju, 61453, Republic of Korea. [email protected].
Abstract
Chest radiography remains the most widely used imaging modality worldwide; however, its interpretation is inherently challenging because of overlapping anatomical structures and subtle findings. Recent advances in multimodal large language models (LLMs) have enabled automated radiology report generation, yet their clinical performance relative to domain-specific medical AI systems remains insufficiently validated. This study aimed to evaluate the performance and clinical applicability of a domain-specific multimodal AI model (M4CXR) compared with a general-purpose LLM (ChatGPT-4o) for chest radiograph interpretation. In this retrospective study, 500 anonymized chest radiographs from a single tertiary care center were analyzed. Four board-certified radiologists independently evaluated AI-generated reports from both models. Key outcomes included key finding detection (categorized as complete, partial, or inconsistent), report generation time, and report discrepancies assessed using the RADPEER scoring system. Agreement between original and M4CXR-assisted RADPEER scores was assessed using intraclass correlation coefficients and weighted Cohen's kappa. Statistical analyses included paired t-tests, and chi-square tests. M4CXR demonstrated significantly higher report consistency than GPT-4o, with complete concordance observed in 55.8% versus 19.8% of cases, and lower inconsistency rates (25.2% vs. 46.4%, P<.001). The use of M4CXR significantly reduced report generation time compared with unaided interpretation (16.3 ± 12.9 s vs. 179.2 ± 50.4 s, P<.001). RADPEER-based discrepancy analysis revealed no significant differences between original and AI-assisted interpretations. Agreement between original and M4CXR-assisted RADPEER scores showed good reliability (ICC = 0.701), and weighted kappa analysis showed substantial agreement (κ<sub>w</sub> = 0.652). Domain-specific multimodal AI model evaluated in this study demonstrated higher diagnostic consistency than the general-purpose LLM evaluated under the study conditions. These findings suggest the potential of specialized AI models as viable assistive tools, while highlighting the complementary utility of general-purpose LLMs in broader clinical contexts. Future integration should prioritize human-AI collaboration and prospective multi-center validation.