临床医学进展 Pub Date : 2025-12-19 DOI: 10.25259/warm_21_2025

Tariq Zayan, Heba Abouelyazied Khafagy

{"title":"Artificial intelligence-powered digital pathology: A potential gold standard for kidney biopsy interpretation?","authors":"Tariq Zayan, Heba Abouelyazied Khafagy","doi":"10.25259/warm_21_2025","DOIUrl":"https://doi.org/10.25259/warm_21_2025","url":null,"abstract":"Renal biopsy remains the cornerstone for diagnosing and managing kidney diseases. However, the inherent subjectivity and variability in traditional histopathological assessment pose significant challenges to diagnostic consistency and reproducibility. The advent of digital pathology, coupled with rapid advancements in artificial intelligence (AI), offers a transformative paradigm for renal pathology. This comprehensive review explores the revolutionary potential of AI in redefining kidney biopsy interpretation, aiming to establish a potential new gold standard. We delve into AI’s capabilities across the entire diagnostic pipeline, from standardizing sample adequacy and objectively quantifying key histological features such as glomerulosclerosis and interstitial fibrosis, to enhancing the reproducibility of established scoring systems such as Banff and Mesangial hypercellularity, Endocapillary hypercellularity, Segmental glomerulosclerosis, Tubular atrophy/interstitial fibrosis, and Crescents. Furthermore, we discuss AI’s emerging role in discovering novel histologic patterns that correlate with disease progression and patient outcomes, thereby facilitating personalized medicine. By bridging the gap between pathologists, nephrologists, and data scientists, this review provides a definitive guide to the state-of-the-art applications and future prospects of AI in interpreting the foundational diagnostic tests in nephrology, highlighting its high impact on clinical practice, research, and patient care. This article aims to serve as a critical resource for the nephrology and pathology communities, fostering collaboration and accelerating the integration of AI into routine renal pathology workflows.","PeriodicalId":63379,"journal":{"name":"临床医学进展","volume":"1 1","pages":"72-79"},"PeriodicalIF":0.0,"publicationDate":"2025-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://warmjournal.org/content/194/2025/1/3/pdf/WARM-1-072.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147911961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}