从实验室到临床:人工智能如何改变甲状腺结节诊断的系统综述
本系统综述检索2015年1月1日至2023年1月1日PubMed和IEEE Xplore的英文文献,纳入使用人工智能对疑似甲状腺结节进行诊断测试的研究,共61项研究,均进行外部验证,其中16项为前瞻性研究,33项将模型与医生对基准真值的预测进行比较。研究归纳出5个高层级结局:结节定位、超声风险评分、分子状态、恶性和长期预后,并指出模型主要使用超声图像预测恶性,4个FDA批准产品中仅S-Detect得到广泛验证。
要点
- 共纳入61项研究,均进行外部验证,其中16项为前瞻性研究。
- 50篇论文报告了统计验证,33项研究比较了模型与医生对基准真值的预测。
- 模型主要使用超声图像预测恶性,4个FDA批准产品中仅S-Detect得到广泛验证。
核心结论
- 模型主要使用超声图像预测恶性。
- 4个FDA批准产品中仅S-Detect得到广泛验证。
- 在本地实施AI模型需要数据清洗和重新验证以确保适当的临床性能。
研究设计与样本
- 系统综述,检索PubMed和IEEE Xplore中2015年1月1日至2023年1月1日发表的英文文献。
- 纳入使用人工智能对疑似甲状腺结节进行诊断测试的研究,排除无前瞻性或外部验证、非原始文献、重复、非结节性甲状腺疾病、未使用AI以及偶然使用AI支持标准临床实践之外的实验性诊断的研究。
- 共纳入61项研究,均进行外部验证,其中16项为前瞻性研究,33项比较模型与医生对基准真值的预测,50篇论文报告统计验证。
- 质量按牛津证据等级分级。
主要发现
- 共纳入61项研究,所有研究均进行外部验证。
- 16项研究为前瞻性研究,33项研究比较模型与医生对基准真值的预测。
- 50篇论文报告了统计验证。
- 归纳出5个高层级结局:结节定位、超声风险评分、分子状态、恶性和长期预后。
- 7项前瞻性研究验证了单一商业AI,优势包括从超声自动评估结节特征和辅助医生预测恶性风险,弱点包括自动边缘预测和观察者间变异。
关键数值与推荐
- 质量按牛津证据等级分级(原文未报告具体等级分布)。
临床怎么用
- 在本地实施AI模型需要数据清洗和重新验证以确保适当的临床性能。
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
CONTEXT: Use of artificial intelligence (AI) to predict clinical outcomes in thyroid nodule diagnostics has grown exponentially over the past decade. The greatest challenge is in understanding the best model to apply to one's own patient population, and how to operationalize such a model in practice. EVIDENCE ACQUISITION: A literature search of PubMed and IEEE Xplore was conducted for English-language publications between January 1, 2015 and January 1, 2023, studying diagnostic tests on suspected thyroid nodules that used AI. We excluded articles without prospective or external validation, nonprimary literature, duplicates, focused on nonnodular thyroid conditions, not using AI, and those incidentally using AI in support of an experimental diagnostic outside standard clinical practice. Quality was graded by Oxford level of evidence. EVIDENCE SYNTHESIS: A total of 61 studies were identified; all performed external validation, 16 studies were prospective, and 33 compared a model to physician prediction of ground truth. Statistical validation was reported in 50 papers. A diagnostic pipeline was abstracted, yielding 5 high-level outcomes: (1) nodule localization, (2) ultrasound (US) risk score, (3) molecular status, (4) malignancy, and (5) long-term prognosis. Seven prospective studies validated a single commercial AI; strengths included automating nodule feature assessment from US and assisting the physician in predicting malignancy risk, while weaknesses included automated margin prediction and interobserver variability. CONCLUSION: Models predominantly used US images to predict malignancy. Of 4 Food and Drug Administration-approved products, only S-Detect was extensively validated. Implementing an AI model locally requires data sanitization and revalidation to ensure appropriate clinical performance.
引用
- Sant VR, Radhachandran A, Ivezic V, et al. From Bench-to-Bedside: How Artificial Intelligence is Changing Thyroid Nodule Diagnostics, a Systematic Review. J Clin Endocrinol Metab. 2024. PMID: 38679750. doi:10.1210/clinem/dgae277
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。