开发一个基于miRNA的模型来检测肺癌
Kai Chin Poh1, Toh Ming Ren1, Goh Liuh Ling2
1Division of Respiratory Medicine, Sengkang General Hospital, Singapore 544886, Singapore.
Cancers
|March 28, 2025
概括
这项研究表明,将血清microRNA (miRNA) 生物标志物与肺结节大小相结合,可显著提高肺癌检测准确度. 这种综合方法为增强当前肺癌查方案提供了一个有前途的工具.
科学领域:
- 在瘤学瘤学.
- 生物标志物发现发现
- 医学诊断 医学诊断 医学诊断
背景情况:
- 肺癌仍然是全球癌症死亡的主要原因,通常在晚期被诊断出来.
- 目前的低剂量计算机断层扫描 (LDCT) 查具有诸如高错误阳性率等局限性.
- 血清微RNA (miRNA) 生物标志物为早期肺癌检测提供了潜在的非侵入性辅助.
研究的目的:
- 评估血清miRNA生物标志物用于肺癌检测的预测能力.
- 使用机器学习技术识别关键miRNA生物标志物.
- 评估miRNA生物标志物和肺结节特征的联合预测能力.
主要方法:
- 一项涉及82名肺癌患者和123名对照者的病例控制研究.
- 文献审查选择25个候选miRNAs,其中16个显示显著差异表达.
- 机器学习算法 (随机森林,KNN,NN,SVM) 用于识别前六个miRNAs.
主要成果:
- 一个使用6个miRNA的预测模型实现了0.78-0.86.6的AUC.
- 将肺结节大小纳入模型显著提高了性能 (AUC 0.96-0.99).
- 综合模型的高灵敏度 (92-98%) 和高特异性 (93-98%) 得到了实现.
结论:
- 血清miRNAs和结节大小的综合预测模型显示了肺癌检测的高准确性.
- 这种综合模型有可能在现有的查计划中改善患者的治疗结果.
相关概念视频
MicroRNAs
MicroRNA (miRNA) are short, regulatory RNA transcribed from introns—non-coding regions of a gene—or intergenic regions—stretches of DNA present between genes. Several processing steps are required to form biologically active, mature miRNA. The initial transcript, called primary miRNA (pri-mRNA), base-pairs with itself forming a stem-loop structure. Within the nucleus, an endonuclease enzyme, called Drosha, shortens the stem-loop structure into hairpin-shaped pre-miRNA. After the pre-miRNA ends...
MicroRNAs
MicroRNA (miRNA) are short, regulatory RNA transcribed from introns (non-coding regions of a gene) or intergenic regions (stretches of DNA present between genes). Several processing steps are required to form biologically active, mature miRNA. The initial transcript, called primary miRNA (pri-mRNA), base-pairs with itself, forming a stem-loop structure. Within the nucleus, an endonuclease enzyme, called Drosha, shortens the stem-loop structure into hairpin-shaped pre-miRNA. After the pre-miRNA...


