基于CT影像组学与临床生化特征的机器学习模型预测原发性醛固酮增多症患者亚型
本研究回顾性纳入158例2014年1月至2021年3月间接受肾上腺静脉采血的PA患者,利用三期腹部CT影像组学与临床生化特征构建两阶段神经网络模型,分别判别单侧或双侧PA及单侧PA的优势侧;最终模型在亚型诊断与侧别判定上的准确率和F1分数均优于放射科医生的常规影像评估(p < .05)。
要点
- 联合CT影像组学与临床生化特征的模型在第一阶段(单侧 vs 双侧PA)准确率80.6%±3.0%、AUC 0.778±0.050,优于单独影像组学或单独临床生化模型。
- 第二阶段(单侧PA优势侧判定)基于影像组学的模型准确率88%±4.9%、AUC 0.831±0.087。
- 最终联合模型在亚型诊断与侧别判定中准确率77.5%±3.9%、F1分数70.5%±7.1%、AUC 0.771±0.046,优于放射科医生常规影像评估(p < .05)。
核心结论
- 所提出的机器学习模型能够预测PA的亚型及侧别,结果优于常规影像评估,并可能辅助PA的诊断流程。
研究设计与样本
- 回顾性纳入158例接受肾上腺静脉采血(AVS)的PA患者,采用两阶段分析构建神经网络机器学习模型,输入为三期腹部CT影像组学特征与临床生化特征,以AVS为参考标准,采用重复分层五折交叉验证评估性能,并与放射科医生常规影像评估进行配对t检验比较。
诊断标准与关键数值
- 第一阶段(单侧 vs 双侧PA):联合CT影像组学与临床生化特征的整合模型准确率80.6%±3.0%、F1分数74.8%±5.2%、AUC 0.778±0.050,优于单独影像组学模型和单独临床生化模型。
- 第二阶段(单侧PA优势侧判定):基于影像组学的模型准确率88%±4.9%、F1分数81.9%±6.2%、AUC 0.831±0.087。
- 最终联合模型(亚型诊断与侧别判定):准确率77.5%±3.9%、F1分数70.5%±7.1%、AUC 0.771±0.046,优于放射科医生常规影像评估(p < .05)。
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)。
英文原文(摘要)· 点击展开
RATIONALE AND OBJECTIVES: Adrenal venous sampling (AVS) is the primary method for differentiating between primary aldosterone (PA) subtypes. The aim of study is to develop prediction models for subtyping of patients with PA using computed tomography (CT) radiomics and clinicobiochemical characteristics associated with PA.
MATERIALS AND METHODS: This study retrospectively enrolled 158 patients with PA who underwent AVS between January 2014 and March 2021. Neural network machine learning models were developed using a two-stage analysis of triple-phase abdominal CT and clinicobiochemical characteristics. In the first stage, the models were constructed to classify unilateral or bilateral PA; in the second stage, they were designed to determine the predominant side in patients with unilateral PA. The final proposed model combined the best-performing models from both stages. The model's performance was evaluated using repeated stratified five-fold cross-validation. We employed paired t-tests to compare its performance with the conventional imaging evaluations made by radiologists, which categorize patients as either having bilateral PA or unilateral PA on one side.
RESULTS: In the first stage, the integrated model that combines CT radiomic and clinicobiochemical characteristics exhibited the highest performance, surpassing both the radiomic-alone and clinicobiochemical-alone models. It achieved an accuracy and F1 score of 80.6% ± 3.0% and 74.8% ± 5.2% (area under the receiver operating curve [AUC] = 0.778 ± 0.050). In the second stage, the accuracy and F1 score of the radiomic-based model were 88% ± 4.9% and 81.9% ± 6.2% (AUC=0.831 ± 0.087). The proposed model achieved an accuracy and F1 score of 77.5% ± 3.9% and 70.5% ± 7.1% (AUC=0.771 ± 0.046) in subtype diagnosis and lateralization, surpassing the accuracy and F1 score achieved by radiologists' evaluation (p < .05).
CONCLUSION: The proposed machine learning model can predict the subtypes and lateralization of PA. It yields superior results compared to conventional imaging evaluation and has potential to supplement the diagnostic process in PA.
引用
- Chen PT, Li PY, Liu KL, et al. Machine Learning Model with Computed Tomography Radiomics and Clinicobiochemical Characteristics Predict the Subtypes of Patients with Primary Aldosteronism. Acad Radiol. 2023. PMID: 38042624. doi:10.1016/j.acra.2023.10.015
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。