基于图像的AI用于甲状腺眼病诊断与活动度分级:系统综述与荟萃分析
诊断合并敏感度0.93、特异度0.84、AUC 0.93;活动度分级合并敏感度0.82、特异度0.87、AUC 0.90。AI诊断和分级的敏感度均高于现有眼科医生对照,但证据确定性低,不支持即刻自主临床应用。
要点
- 基于图像的AI对TED诊断的合并AUC为0.93,敏感度0.93、特异度0.84。
- AI对CAS≥3活动度分级的合并AUC为0.90,敏感度0.82、特异度0.87。
- AI敏感度高于现有眼科医生对照,但证据确定性低、异质性大,不能自主部署。
核心结论
- 基于图像的AI在TED诊断和基于CAS的活动度分级中显示出有前景的准确性。
- 证据支持在临床监督下将AI作为诊断排除辅助工具,阴性结果需结合症状和临床背景解读。
- 基于CAS的活动度分级不应据此排除低CAS的活动性TED。
- 低确定性、显著异质性和图像比较的局限性妨碍了AI即刻自主临床应用。
- 疑似TED患者仍应转诊进行眼科评估,并需前瞻性、多中心、多族裔验证。
研究设计与样本
- 系统综述与荟萃分析,检索PubMed、Embase、Web of Science和Cochrane Library至2025年11月13日。
- 诊断评估8项研究(11个验证集,n=4662),活动度分级评估11项研究(11个验证集,n=4082)。
- 使用PROBAST+AI评估偏倚风险,采用GRADE评估证据确定性,双变量随机效应模型合并敏感度、特异度和AUC。
主要发现
- 诊断合并敏感度0.93(95%CI 0.86-0.96),特异度0.84(95%CI 0.78-0.88),AUC 0.93(95%CI 0.90-0.95)。
- 诊断排除离群值后敏感度0.90、特异度0.82、AUC 0.92。
- 活动度分级合并敏感度0.82(95%CI 0.77-0.85),特异度0.87(95%CI 0.82-0.91),AUC 0.90(95%CI 0.88-0.91)。
- 活动度分级排除离群值后敏感度0.80、特异度0.84、AUC 0.89。
- AI诊断敏感度高于现有眼科医生对照(P=0.01),活动度分级敏感度亦高于对照(P=0.003);诊断阴性似然比0.09,活动度分级阴性似然比0.21。
关键数值与推荐
- TED诊断的AI合并敏感度0.93、特异度0.84、AUC 0.93(95%CI 0.90-0.95)。
- CAS≥3活动度分级的AI合并敏感度0.82、特异度0.87、AUC 0.90(95%CI 0.88-0.91)。
- 诊断阴性似然比0.09,活动度分级阴性似然比0.21。
- PROBAST+AI评定12.5%的诊断研究和36.4%至54.5%的活动度分级研究为高偏倚风险,GRADE证据确定性为低。
临床怎么用
- 可在临床监督下将基于图像的AI用作TED诊断排除辅助工具,阴性结果需结合症状和临床背景解读。
- 基于CAS的活动度分级不应使用AI排除低CAS的活动性TED。
- 疑似TED患者仍应转诊进行眼科评估,不应仅依赖AI结果。
局限性
- GRADE证据确定性为低。
- 存在显著异质性。
- 图像比较存在局限性。
- 与眼科医生的比较涉及选定的阅片者且临床背景有限。
- 部分研究存在高偏倚风险,需前瞻性、多中心、多族裔验证。
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
TOPIC: To evaluate image-based artificial intelligence (AI) accuracy for thyroid eye disease (TED) diagnosis and clinical activity grading (Clinical Activity Score [CAS] ≥ 3 vs. <3) and compare AI with ophthalmologists. CLINICAL RELEVANCE: TED diagnosis and activity grading are challenging because of overlapping signs and subjective CAS (interrater variability up to 30%). Its consolidated accuracy is unquantified. METHODS: We searched PubMed, Embase, Web of Science, and Cochrane Library through November 13, 2025, for studies of TED diagnosis or activity grading using image-based AI. Risk of bias was assessed with PROBAST+AI and certainty with Grading of Recommendations Assessment, Development, and Evaluation (GRADE). Bivariate random-effects models pooled sensitivity, specificity, and area under the curve (AUC). RESULTS: Nineteen studies (n = 8744) were included: 8 evaluated diagnosis (11 validation sets; n = 4662) and 11 activity grading (11 validation sets; n = 4082). For diagnosis, sensitivity was 0.93 (95% confidence interval [CI], 0.86-0.96), specificity 0.84 (95% CI, 0.78-0.88), and AUC 0.93 (95% CI, 0.90-0.95); after outlier exclusion, 0.90, 0.82, and 0.92, respectively. For activity grading, sensitivity was 0.82 (95% CI, 0.77-0.85), specificity 0.87 (95% CI, 0.82-0.91), and AUC 0.90 (95% CI, 0.88-0.91); after outlier exclusion, 0.80, 0.84, and 0.89, respectively. AI showed higher sensitivity than available ophthalmologist comparators for diagnosis (P = 0.01) and activity grading (P = 0.003), but comparisons involved selected readers and limited clinical context. Negative likelihood ratio was 0.09 for diagnosis and 0.21 for activity grading. PROBAST+AI rated 12.5% of diagnosis studies and 36.4% to 54.5% of activity-grading studies at high risk of bias; GRADE certainty was low. CONCLUSION: Image-based AI showed promising accuracy for TED diagnosis and CAS-based activity grading. Evidence supports cautious use as a diagnosis rule-out aid under clinical supervision when negative results are interpreted with symptoms and clinical context; however, CAS-based activity grading should not rule out low-CAS active TED. Low certainty, substantial heterogeneity, and limitations of image-based comparisons preclude immediate autonomous clinical deployment. Patients with suspected TED should still be referred for ophthalmologic assessment. Prospective, multicenter, multiethnic validation is required. FINANCIAL DISCLOSURE(S): The author has no/the authors have no proprietary or commercial interest in any materials discussed in this article.
引用
- Hu R, Zhao J, Li GY, et al. Image-Based Artificial Intelligence for Automated Diagnosis and Clinical Activity Grading in Thyroid Eye Disease: A Systematic Review and Meta-Analysis. Ophthalmology. 2026. PMID: 42556434. doi:10.1016/j.ophtha.2026.07.038
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。