Wu Yifan, Liu Yang, Yang Yue, Yao Michael S, Yang Wenli, Shi Xuehui, Yang Lihong, Li Dongjun, Liu Yueming, Yin Shiyi, Lei Chunyan, Zhang Meixia, Gee James C, Yang Xuan, Wei Wenbin, Gu Shi
University of Pennsylvania, Philadelphia, PA, USA.
University of Electronic Science and Technology of China, Chengdu, China.
Nat Commun. 2025 Apr 13;16(1):3504. doi: 10.1038/s41467-025-58801-7.
Diagnosing rare diseases remains a critical challenge in clinical practice, often requiring specialist expertise. Despite the promising potential of machine learning, the scarcity of data on rare diseases and the need for interpretable, reliable artificial intelligence (AI) models complicates development. This study introduces a multimodal concept-based interpretable model tailored to distinguish uveal melanoma (0.4-0.6 per million in Asians) from hemangioma and metastatic carcinoma following the clinical practice. We collected a comprehensive dataset on Asians to date on choroid neoplasm imaging with radiological reports, encompassing over 750 patients from 2013 to 2019. Our model integrates domain expert insights from radiological reports and differentiates between three types of choroidal tumors, achieving an F score of 0.91. This performance not only matches senior ophthalmologists but also improves the diagnostic accuracy of less experienced clinicians by 42%. The results underscore the potential of interpretable AI to enhance rare disease diagnosis and pave the way for future advancements in medical AI.
在临床实践中，诊断罕见病仍然是一项严峻挑战，通常需要专家专业知识。尽管机器学习具有广阔前景，但罕见病数据稀缺以及对可解释、可靠的人工智能（AI）模型的需求使开发工作变得复杂。本研究引入了一种基于多模态概念的可解释模型，专门用于在临床实践中区分葡萄膜黑色素瘤（亚洲人发病率为百万分之0.4 - 0.6）与血管瘤和转移性癌。我们收集了截至目前关于亚洲人脉络膜肿瘤成像及放射学报告的综合数据集，涵盖2013年至2019年的750多名患者。我们的模型整合了放射学报告中的领域专家见解，区分了三种类型的脉络膜肿瘤，F分数达到0.91。这一表现不仅与资深眼科医生相当，还将经验不足的临床医生的诊断准确率提高了42%。结果凸显了可解释人工智能在增强罕见病诊断方面的潜力，并为医学人工智能的未来发展铺平了道路。
