• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

用于代谢功能障碍相关脂肪性肝炎评分的基于人工智能的病理学工具的临床验证

Clinical validation of an AI-based pathology tool for scoring of metabolic dysfunction-associated steatohepatitis.

作者信息

Pulaski Hanna, Harrison Stephen A, Mehta Shraddha S, Sanyal Arun J, Vitali Marlena C, Manigat Laryssa C, Hou Hypatia, Madasu Christudoss Susan P, Hoffman Sara M, Stanford-Moore Adam, Egger Robert, Glickman Jonathan, Resnick Murray, Patel Neel, Taylor Cristin E, Myers Robert P, Chung Chuhan, Patterson Scott D, Sejling Anne-Sophie, Minnich Anne, Baxi Vipul, Subramaniam G Mani, Anstee Quentin M, Loomba Rohit, Ratziu Vlad, Montalto Michael C, Anderson Nick P, Beck Andrew H, Wack Katy E

机构信息

PathAI, Inc., Boston, MA, USA.

Pinnacle Clinical Research, San Antonio, TX, USA.

出版信息

Nat Med. 2025 Jan;31(1):315-322. doi: 10.1038/s41591-024-03301-2. Epub 2024 Nov 4.

DOI:10.1038/s41591-024-03301-2
PMID:39496972
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11750710/
Abstract

Metabolic dysfunction-associated steatohepatitis (MASH) is a major cause of liver-related morbidity and mortality, yet treatment options are limited. Manual scoring of liver biopsies, currently the gold standard for clinical trial enrollment and endpoint assessment, suffers from high reader variability. This study represents the most comprehensive multisite analytical and clinical validation of an artificial intelligence (AI)-based pathology system, AI-based measurement of metabolic dysfunction-associated steatohepatitis (AIM-MASH), to assist pathologists in MASH trial histology scoring. AIM-MASH demonstrated high repeatability and reproducibility compared to manual scoring. AIM-MASH-assisted reads by expert MASH pathologists were superior to unassisted reads in accurately assessing inflammation, ballooning, MAS ≥ 4 with ≥1 in each score category and MASH resolution, while maintaining non-inferiority in steatosis and fibrosis assessment. These findings suggest that AIM-MASH could mitigate reader variability, providing a more reliable assessment of therapeutics in MASH clinical trials.

摘要

代谢功能障碍相关脂肪性肝炎（MASH）是肝脏相关发病和死亡的主要原因，但治疗选择有限。肝活检的人工评分目前是临床试验入组和终点评估的金标准，存在较高的阅片者变异性。本研究是对基于人工智能（AI）的病理学系统——基于AI的代谢功能障碍相关脂肪性肝炎测量（AIM-MASH）——进行的最全面的多中心分析和临床验证，以协助病理学家进行MASH试验组织学评分。与人工评分相比，AIM-MASH表现出高重复性和再现性。在准确评估炎症、气球样变、MAS≥4且各评分类别中至少有1项、以及MASH缓解方面，由MASH专家病理学家进行的AIM-MASH辅助阅片优于非辅助阅片，同时在脂肪变性和纤维化评估方面保持非劣效性。这些发现表明，AIM-MASH可以减少阅片者变异性，为MASH临床试验中的治疗提供更可靠的评估。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6136/11750710/8e1abeba4227/41591_2024_3301_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6136/11750710/0b8eeda47642/41591_2024_3301_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6136/11750710/62903f7c5c8c/41591_2024_3301_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6136/11750710/dcac2ed4d4cc/41591_2024_3301_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6136/11750710/8e1abeba4227/41591_2024_3301_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6136/11750710/0b8eeda47642/41591_2024_3301_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6136/11750710/62903f7c5c8c/41591_2024_3301_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6136/11750710/dcac2ed4d4cc/41591_2024_3301_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6136/11750710/8e1abeba4227/41591_2024_3301_Fig4_HTML.jpg

相似文献

1
Clinical validation of an AI-based pathology tool for scoring of metabolic dysfunction-associated steatohepatitis.用于代谢功能障碍相关脂肪性肝炎评分的基于人工智能的病理学工具的临床验证
Nat Med. 2025 Jan;31(1):315-322. doi: 10.1038/s41591-024-03301-2. Epub 2024 Nov 4.
2
Utility of AI digital pathology as an aid for pathologists scoring fibrosis in MASH.人工智能数字病理学在协助病理学家对MASH中的纤维化进行评分方面的效用。
J Hepatol. 2025 May;82(5):898-908. doi: 10.1016/j.jhep.2024.11.032. Epub 2024 Nov 28.
3
AI-based automation of enrollment criteria and endpoint assessment in clinical trials in liver diseases.基于人工智能的临床试验入组标准和终点评估自动化在肝脏疾病中的应用。
Nat Med. 2024 Oct;30(10):2914-2923. doi: 10.1038/s41591-024-03172-7. Epub 2024 Aug 7.
4
Noninvasive identification of metabolic dysfunction-associated steatohepatitis (INFORM MASH): a retrospective cohort and disease modeling study.代谢功能障碍相关脂肪性肝炎的非侵入性识别（INFORM MASH）：一项回顾性队列和疾病建模研究。
Expert Rev Gastroenterol Hepatol. 2025 Apr;19(4):427-435. doi: 10.1080/17474124.2025.2477249. Epub 2025 Mar 21.
5
A metabolome-derived score predicts metabolic dysfunction-associated steatohepatitis and mortality from liver disease.代谢组衍生评分可预测代谢功能障碍相关脂肪性肝炎及肝病死亡率。
J Hepatol. 2025 May;82(5):781-793. doi: 10.1016/j.jhep.2024.10.015. Epub 2024 Oct 16.
6
Validation of a whole slide image management system for metabolic-associated steatohepatitis for clinical trials.用于临床试验的代谢相关脂肪性肝炎的全切片图像管理系统的验证。
J Pathol Clin Res. 2024 Sep;10(5):e12395. doi: 10.1002/2056-4538.12395.
7
NAFLD (MASLD)/NASH (MASH): Does It Bother to Label at All? A Comprehensive Narrative Review.非酒精性脂肪性肝病（MASLD）/非酒精性脂肪性肝炎（MASH）：是否有必要进行标记？全面的叙述性综述。
Int J Mol Sci. 2024 Aug 2;25(15):8462. doi: 10.3390/ijms25158462.
8
The use of simple tests to predict biopsy-proven steatohepatitis in people with type 2 diabetes.使用简单测试预测2型糖尿病患者经活检证实的脂肪性肝炎。
Eur J Gastroenterol Hepatol. 2025 Mar 1;37(3):320-326. doi: 10.1097/MEG.0000000000002890. Epub 2025 Jan 29.
9
NIS2+ as a screening tool to optimize patient selection in metabolic dysfunction-associated steatohepatitis clinical trials.NIS2+ 作为一种筛选工具，可优化代谢功能障碍相关脂肪性肝炎临床试验中的患者选择。
J Hepatol. 2024 Feb;80(2):209-219. doi: 10.1016/j.jhep.2023.10.038. Epub 2023 Dec 5.
10
Mixed active metabolites of the SNP-6 series of novel compounds mitigate metabolic dysfunction-associated steatohepatitis and fibrosis: promising results from pre-clinical and clinical trials.新型 SNP-6 系列化合物的混合活性代谢物可改善代谢功能障碍相关的脂肪性肝炎和纤维化：临床前和临床试验的可喜结果。
J Transl Med. 2024 Oct 14;22(1):936. doi: 10.1186/s12967-024-05686-7.

引用本文的文献

1
Digital pathology and lipid droplet size as a key determinant of discrepancies between histology and MRI gradings in steatotic liver disease.数字病理学与脂滴大小作为脂肪性肝病组织学与MRI分级差异的关键决定因素
Eur Radiol. 2025 Aug 8. doi: 10.1007/s00330-025-11919-0.
2
AI-based Hepatic Steatosis Detection and Integrated Hepatic Assessment from Cardiac CT Attenuation Scans Enhances All-cause Mortality Risk Stratification: A Multi-center Study.基于人工智能的心脏CT衰减扫描检测肝脂肪变性及综合肝脏评估可增强全因死亡风险分层：一项多中心研究
medRxiv. 2025 Jun 11:2025.06.09.25329157. doi: 10.1101/2025.06.09.25329157.
3
Clinical Validation and Post-Implementation Performance Monitoring of a Neural Network-Assisted Approach for Detecting Chronic Lymphocytic Leukemia Minimal Residual Disease by Flow Cytometry.

本文引用的文献

1
Validation of a whole slide image management system for metabolic-associated steatohepatitis for clinical trials.用于临床试验的代谢相关脂肪性肝炎的全切片图像管理系统的验证。
J Pathol Clin Res. 2024 Sep;10(5):e12395. doi: 10.1002/2056-4538.12395.
2
AI-based automation of enrollment criteria and endpoint assessment in clinical trials in liver diseases.基于人工智能的临床试验入组标准和终点评估自动化在肝脏疾病中的应用。
Nat Med. 2024 Oct;30(10):2914-2923. doi: 10.1038/s41591-024-03172-7. Epub 2024 Aug 7.
3
A Phase 3, Randomized, Controlled Trial of Resmetirom in NASH with Liver Fibrosis.
用于通过流式细胞术检测慢性淋巴细胞白血病微小残留病的神经网络辅助方法的临床验证及实施后性能监测
Cancers (Basel). 2025 May 17;17(10):1688. doi: 10.3390/cancers17101688.
4
Digital Pathology Tailored for Assessment of Liver Biopsies.专为肝活检评估量身定制的数字病理学
Biomedicines. 2025 Apr 1;13(4):846. doi: 10.3390/biomedicines13040846.
5
Artificial Intelligence-Powered Quality Assurance: Transforming Diagnostics, Surgery, and Patient Care-Innovations, Limitations, and Future Directions.人工智能驱动的质量保证：变革诊断、手术及患者护理——创新、局限与未来方向
Life (Basel). 2025 Apr 16;15(4):654. doi: 10.3390/life15040654.
6
Metabolic dysfunction-associated steatotic liver disease in adults.成人代谢功能障碍相关脂肪性肝病
Nat Rev Dis Primers. 2025 Mar 6;11(1):14. doi: 10.1038/s41572-025-00599-1.
一项评估 Resmetirom 治疗伴有肝纤维化的 NASH 的 3 期随机对照试验。
N Engl J Med. 2024 Feb 8;390(6):497-509. doi: 10.1056/NEJMoa2309000.
4
Utility of pathologist panels for achieving consensus in NASH histologic scoring in clinical trials: Data from a phase 3 study.病理学家小组在临床试验中实现 NASH 组织学评分共识的效用：来自 3 期研究的数据。
Hepatol Commun. 2023 Dec 22;8(1). doi: 10.1097/HC9.0000000000000325. eCollection 2024 Jan 1.
5
A multisociety Delphi consensus statement on new fatty liver disease nomenclature.多学会专家组关于新的脂肪肝疾病命名的德尔菲共识声明。
J Hepatol. 2023 Dec;79(6):1542-1556. doi: 10.1016/j.jhep.2023.06.003. Epub 2023 Jun 24.
6
Histological assessment based on liver biopsy: the value and challenges in NASH drug development.基于肝活检的组织学评估：在 NASH 药物研发中的价值和挑战。
Acta Pharmacol Sin. 2022 May;43(5):1200-1209. doi: 10.1038/s41401-022-00874-x. Epub 2022 Feb 14.
7
Complexity of ballooned hepatocyte feature recognition: Defining a training atlas for artificial intelligence-based imaging in NAFLD.气球样变肝细胞特征识别的复杂性：为非酒精性脂肪性肝病基于人工智能的成像定义一个训练图谱。
J Hepatol. 2022 May;76(5):1030-1041. doi: 10.1016/j.jhep.2022.01.011. Epub 2022 Jan 25.
8
An independent assessment of an artificial intelligence system for prostate cancer detection shows strong diagnostic accuracy.一项针对前列腺癌检测人工智能系统的独立评估显示出较强的诊断准确性。
Mod Pathol. 2021 Aug;34(8):1588-1595. doi: 10.1038/s41379-021-00794-x. Epub 2021 Mar 29.
9
Approval of artificial intelligence and machine learning-based medical devices in the USA and Europe (2015-20): a comparative analysis.美国和欧洲对人工智能和基于机器学习的医疗器械的审批（2015-20）：比较分析。
Lancet Digit Health. 2021 Mar;3(3):e195-e203. doi: 10.1016/S2589-7500(20)30292-2. Epub 2021 Jan 18.
10
Suboptimal reliability of liver biopsy evaluation has implications for randomized clinical trials.肝活检评估的可靠性欠佳对随机临床试验有影响。
J Hepatol. 2020 Dec;73(6):1322-1332. doi: 10.1016/j.jhep.2020.06.025. Epub 2020 Jun 28.