AI-driven enhancements in rare disease diagnosis and support system optimization

• 資料種別: 記事
• タイトル: AI-driven enhancements in rare disease diagnosis and support system optimization
• 著者標目: Wang Xin; He Da; Jin Chunlin
• 出版年月日等: 2025-11-30
• 出版年（W3CDTF）: 2025-11-30
• タイトル（掲載誌）: Intractable & Rare Diseases Research
• 巻号年月日等（掲載誌）: 14 4
• 掲載巻: 14
• 掲載号: 4
• 掲載ページ: 306-308
• 掲載年月日（W3CDTF）: 2025-11-30
• ISSN（掲載誌）: 21863644
• 出版事項（掲載誌）: International Research and Cooperation Association for Bio & Socio-Sciences Advancement
• 本文の言語コード: en
• 件名標目: rare disease; artificial intelligence; diagnosis; support system
• 対象利用者: 一般
• DOI: 10.5582/irdr.2025.01079; https://doi.org/10.5582/irdr.2025.01079
• 関連情報（URI）: https://www.jstage.jst.go.jp/article/irdr/14/4/14_2025.01079/_pdf
• 参照: Artificial intelligence and perspective for rare genetic kidney diseases; https://cir.nii.ac.jp/crid/1360025034121836288; Improving AI models for rare thyroid cancer subtype by text guided diffusion models; https://cir.nii.ac.jp/crid/1360025034122560896; Enhancing diagnostic accuracy in rare and common fundus diseases with a knowledge-rich vision-language model; https://cir.nii.ac.jp/crid/1360025034122563328; A fully open AI foundation model applied to chest radiography; https://cir.nii.ac.jp/crid/1360025034122576128; Predicting expression-altering promoter mutations with deep learning; https://cir.nii.ac.jp/crid/1360306504329444352; Machine learning in rare disease; https://cir.nii.ac.jp/crid/1360306504604235008; A guide for the diagnosis of rare and undiagnosed disease: beyond the exome; https://cir.nii.ac.jp/crid/1360861294964706944; Few shot learning for phenotype-driven diagnosis of patients with rare genetic diseases; https://cir.nii.ac.jp/crid/1360869454548025216
• 連携機関・データベース: 国立情報学研究所 : CiNii Research; https://cir.nii.ac.jp/
• 提供元機関・データベース: Japan Link Center; https://japanlinkcenter.org/top; Crossref; https://www.crossref.org

• 要約等: <p>Rare diseases are characterized by an extremely low prevalence, high phenotypic heterogeneity, and complex pathogenesis. This combination of factors presents significant challenges, including prolonged diagnostic delays, lack of standardized care, and difficulties in pathological interpretation. The integration of artificial intelligence (AI) offers a transformative approach to overcoming these barriers. In recent years, researchers worldwide have been actively exploring the use of AI to diagnose and manage rare diseases. Key advances include few-shot learning algorithms designed to tackle data scarcity, clinically validated foundation models that enhance diagnostic consistency across institutions, and multimodal AI frameworks that integrate imaging, genomic, and phenotypic data to improve diagnostic accuracy. In addition, there is growing recognition that AI can enhance diagnostic efficiency and thereby optimize support systems for rare diseases. As challenges such as AI model interpretability and data equity are addressed, AI is expected to make significant strides in the diagnosis and treatment of rare diseases.</p>
• DOI: 10.5582/irdr.2025.01079
• オンライン閲覧公開範囲: インターネット公開
• 連携機関・データベース: 科学技術振興機構 : J-STAGE; http://www.jstage.jst.go.jp