Department of Family Medicine, Kyungpook National University Chilgok Hospital, 807 Hoguk-ro, Buk-gu, Daegu 41404, Republic of Korea.
BIOINFRA Life Science Inc., Jongno-gu, Seoul 03127, Republic of Korea.
Breast J. 2023 Dec 27;2023:9117047. doi: 10.1155/2023/9117047. eCollection 2023.
The objective of this study was to determine whether multi-microRNA analysis using a combination of four microRNA biomarkers (miR-1246, 202, 21, and 219B) could improve the diagnostic performance of mammography in determining breast cancer risk by age group (under 50 vs. over 50) and distinguish breast cancer from benign breast diseases and other cancers (thyroid, colon, stomach, lung, liver, and cervix cancers). To verify breast cancer classification performance of the four miRNA biomarkers and whether the model providing breast cancer risk score could distinguish between benign breast disease and other cancers, the model was verified using nonlinear support vector machine (SVM) and generalized linear model (GLM) and age and four miRNA qRT-PCR analysis values (dCt) were input to these models. Breast cancer risk scores for each Breast Imaging-Reporting and Data System (BI-RADS) category in multi-microRNA analysis were analyzed to examine the correlation between breast cancer risk scores and mammography categories. We generated two models using two classification algorithms, SVM and GLM, with a combination of four miRNA biomarkers showing high performance and sensitivities of 84.5% and 82.1%, a specificity of 85%, and areas under the curve (AUCs) of 0.967 and 0.965, respectively, which showed consistent performance across all stages of breast cancer and patient ages. The results of this study showed that this multi-microRNA analysis using the four miRNA biomarkers was effective in classifying breast cancer in patients under the age of 50, which is challenging to accurately diagnose. In addition, breast cancer and benign breast diseases can be classified, showing the possibility of helping with diagnosis by mammography. Verification of the performance of the four miRNA biomarkers confirmed that multi-microRNA analysis could be used as a new breast cancer screening aid to improve the accuracy of mammography. However, many factors must be considered for clinical use. Further validation with an appropriate screening population in large clinical trials is required. This trial is registered with (KNUCH 2022-04-036).
本研究旨在确定四种 microRNA 标志物（miR-1246、202、21 和 219B）的多 microRNA 分析是否可以通过年龄组（<50 岁与>50 岁）提高乳腺摄影在确定乳腺癌风险方面的诊断性能，并区分乳腺癌与良性乳腺疾病和其他癌症（甲状腺、结肠、胃、肺、肝和宫颈癌）。为了验证四种 microRNA 生物标志物的乳腺癌分类性能以及提供乳腺癌风险评分的模型是否可以区分良性乳腺疾病和其他癌症，使用非线性支持向量机（SVM）和广义线性模型（GLM）以及年龄和四个 microRNA qRT-PCR 分析值（dCt）来验证该模型。分析多 microRNA 分析中每个乳腺影像报告和数据系统（BI-RADS）类别的乳腺癌风险评分，以检查乳腺癌风险评分与乳腺摄影类别之间的相关性。我们使用两种分类算法（SVM 和 GLM）生成了两个模型，使用四个 microRNA 标志物的组合具有 84.5%和 82.1%的高性能和灵敏度、85%的特异性和 0.967 和 0.965 的曲线下面积（AUCs），这在所有乳腺癌阶段和患者年龄中均表现出一致的性能。本研究结果表明，使用四种 microRNA 标志物的这种多 microRNA 分析可有效分类 50 岁以下患者的乳腺癌，这对于准确诊断具有挑战性。此外，还可以对乳腺癌和良性乳腺疾病进行分类，显示出通过乳腺摄影进行诊断的可能性。对四种 microRNA 生物标志物性能的验证证实，多 microRNA 分析可作为新的乳腺癌筛查辅助手段，提高乳腺摄影的准确性。然而，临床应用还需要考虑许多因素。需要在大型临床试验中使用适当的筛查人群进行进一步验证。该试验在（KNUCH 2022-04-036）注册。
