基于人工智能的代谢功能障碍相关脂肪性肝炎临床试验入组标准与终点评估自动化
研究开发了用于代谢功能障碍相关脂肪性肝炎(MASH)组织学评分的AI测量工具AIM-MASH,其预测可重复(κ=1),与专家病理学家共识评分一致(κ=0.62-0.74),在NASH临床研究网络评分和纤维化分期上与病理学家平均一致性相当。连续评分与非侵袭性生物标志物相关,并强预测3期(P<0.0001)和4期(P=0.03)纤维化患者的无进展生存;在ATLAS试验回顾性分析中,治疗应答者纤维化连续变化大于安慰剂(P=0.02)。
要点
- AIM-MASH对MASH组织学评分的预测可重复(κ=1),与专家共识评分一致(κ=0.62-0.74)。
- AIM-MASH与共识的一致性在NASH临床研究网络评分(82% vs 81%)和纤维化(97% vs 96%)上与病理学家平均相当。
- AIM-MASH连续评分强预测3期(P<0.0001)和4期(P=0.03)纤维化患者的无进展生存。
核心结论
- AIM-MASH可能辅助病理学家对MASH临床试验进行组织学审阅,减少终点评估的评分者间变异,并提供更敏感且可重复的患者反应测量。
研究设计与样本
- 开发基于人工智能的测量工具AIM-MASH,用于MASH组织学评分。
- 在ATLAS试验(NCT03449446)中进行回顾性分析。
主要发现
- AIM-MASH对MASH临床研究网络坏死性炎症分级和纤维化分期的预测可重复(κ=1),与专家病理学家共识评分一致(κ=0.62-0.74)。
- AIM-MASH与共识的一致性在MASH临床研究网络评分上为82% vs 病理学家平均81%,在纤维化上为97% vs 96%。
- AIM-MASH对MASH关键组织学特征的连续评分与病理学家平均评分和非侵袭性生物标志物相关。
- AIM-MASH连续评分强预测3期纤维化(P<0.0001)和4期纤维化(P=0.03)患者的无进展生存。
- 在ATLAS试验回顾性分析中,接受研究治疗的反应者纤维化连续变化大于安慰剂(P=0.02)。
关键数值与推荐
- AIM-MASH预测可重复性κ=1。
- AIM-MASH与专家病理学家共识评分一致性κ=0.62-0.74。
- AIM-MASH与共识一致性:MASH临床研究网络评分82%,纤维化97%;病理学家平均:MASH临床研究网络评分81%,纤维化96%。
- AIM-MASH连续评分预测无进展生存:3期纤维化P<0.0001,4期纤维化P=0.03。
- ATLAS试验中治疗应答者 vs 安慰剂纤维化连续变化P=0.02。
临床怎么用
- AIM-MASH可能辅助病理学家对MASH临床试验进行组织学审阅。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
Clinical trials in metabolic dysfunction-associated steatohepatitis (MASH, formerly known as nonalcoholic steatohepatitis) require histologic scoring for assessment of inclusion criteria and endpoints. However, variability in interpretation has impacted clinical trial outcomes. We developed an artificial intelligence-based measurement (AIM) tool for scoring MASH histology (AIM-MASH). AIM-MASH predictions for MASH Clinical Research Network necroinflammation grades and fibrosis stages were reproducible (κ = 1) and aligned with expert pathologist consensus scores (κ = 0.62-0.74). The AIM-MASH versus consensus agreements were comparable to average pathologists for MASH Clinical Research Network scores (82% versus 81%) and fibrosis (97% versus 96%). Continuous scores produced by AIM-MASH for key histological features of MASH correlated with mean pathologist scores and noninvasive biomarkers and strongly predicted progression-free survival in patients with stage 3 (P < 0.0001) and stage 4 (P = 0.03) fibrosis. In a retrospective analysis of the ATLAS trial (NCT03449446), responders receiving study treatment showed a greater continuous change in fibrosis compared with placebo (P = 0.02). Overall, these results suggest that AIM-MASH may assist pathologists in histologic review of MASH clinical trials, reducing inter-rater variability on trial outcomes and offering a more sensitive and reproducible measure of patient responses.
引用
- Iyer JS, Juyal D, Le Q, et al. AI-based automation of enrollment criteria and endpoint assessment in clinical trials in liver diseases. Nat Med. 2024. PMID: 39112795. doi:10.1038/s41591-024-03172-7
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。