基于超声的机器学习方法检测非酒精性脂肪性肝病
在24例平衡测试集中,AutoML模型敏感度72.2%、特异度94.6%、PPV 93.1%、准确率83.4%。结论认为该超声机器学习模型具有高特异度和PPV,未来可能作为高危人群NAFLD的无创筛查工具。
要点
- 以MRI PDFF>6.4%为参考标准,超声机器学习模型检测NAFLD特异度94.6%、PPV 93.1%。
- 测试集敏感度72.2%,阴性预测值77.3%,提示阴性者仍需结合其他指标。
- 模型基于肝左右叶10个标准位置超声图像,个体平均一致率92%。
核心结论
- 基于超声的机器学习模型识别NAFLD在本次前瞻性试验中表现出高特异度和高阳性预测值。
- 该方法未来可能作为高危患者NAFLD的无创、低成本筛查工具。
研究设计与样本
- 以MRI质子密度脂肪分数(PDFF)>6.4%作为NAFLD参考标准,将受试者分为NAFLD和非NAFLD。
- 按标准方案采集肝右叶和左叶10个不同位置的超声图像,开发监督机器学习模型。
- 使用24例受试者的平衡测试数据集验证模型性能,计算敏感度、特异度、PPV、NPV和总准确率及95%CI。
诊断标准与关键数值
- MRI PDFF>6.4%定义为NAFLD。
- 模型开发使用106名参与者的1119张图像,内部评估平均精确率0.941、召回率88.2%、精确率89.0%。
- 测试集AutoML敏感度72.2%(63.1%-80.1%)、特异度94.6%(88.7%-98.0%)。
- 测试集PPV 93.1%(86.0%-96.7%)、NPV 77.3%(71.6%-82.1%)、准确率83.4%(77.9%-88.0%)。
- 个体受试者平均一致率为92%。
临床应用与阅片要点
- 超声机器学习模型高特异度和高PPV,阳性结果对NAFLD有较高确认价值。
- 敏感度72.2%和NPV 77.3%,阴性结果不能完全排除NAFLD,需结合临床或其他检查。
- 图像采集需遵循标准方案,覆盖肝右叶和左叶共10个位置。
局限性
- 测试集仅24例受试者,样本量较小。
- 研究为单中心前瞻性设计,外部推广性需进一步验证。
- 原文未报告模型在不同设备或操作者间的一致性数据。
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)。
英文原文(摘要)· 点击展开
OBJECTIVES: Current diagnosis of nonalcoholic fatty liver disease (NAFLD) relies on biopsy or MR-based fat quantification. This prospective study explored the use of ultrasound with artificial intelligence for the detection of NAFLD.
METHODS: One hundred and twenty subjects with clinical suspicion of NAFLD and 10 healthy volunteers consented to participate in this institutional review board-approved study. Subjects were categorized as NAFLD and non-NAFLD according to MR proton density fat fraction (PDFF) findings. Ultrasound images from 10 different locations in the right and left hepatic lobes were collected following a standard protocol. MRI-based liver fat quantification was used as the reference standard with >6.4% indicative of NAFLD. A supervised machine learning model was developed for assessment of NAFLD. To validate model performance, a balanced testing dataset of 24 subjects was used. Sensitivity, specificity, positive predictive value, negative predictive value, and overall accuracy with 95% confidence interval were calculated.
RESULTS: A total of 1119 images from 106 participants was used for model development. The internal evaluation achieved an average precision of 0.941, recall of 88.2%, and precision of 89.0%. In the testing set AutoML achieved a sensitivity of 72.2% (63.1%-80.1%), specificity of 94.6% (88.7%-98.0%), positive predictive value (PPV) of 93.1% (86.0%-96.7%), negative predictive value of 77.3% (71.6%-82.1%), and accuracy of 83.4% (77.9%-88.0%). The average agreement for an individual subject was 92%.
CONCLUSIONS: An ultrasound-based machine learning model for identification of NAFLD showed high specificity and PPV in this prospective trial. This approach may in the future be used as an inexpensive and noninvasive screening tool for identifying NAFLD in high-risk patients.
引用
- Tahmasebi, Wang, Wessner, et al. Ultrasound-Based Machine Learning Approach for Detection of Nonalcoholic Fatty Liver Disease. J Ultrasound Med. 2023. PMID: 36807314. doi:10.1002/jum.16194
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。