Inagaki Masayasu, Uchiyama Makoto, Yoshikawa-Kawabe Kanae, Ito Masafumi, Murakami Hideki, Gunji Masaharu, Minoshima Makoto, Kohnoh Takashi, Ito Ryota, Kodama Yuta, Tanaka-Sakai Mari, Nakase Atsushi, Goto Nozomi, Tsushima Yusuke, Mori Shoich, Kozuka Masahiro, Otomo Ryo, Hirai Mitsuharu, Fujino Masahiko, Yokoyama Toshihiko
Department of Respiratory Medicine, Japanese Red Cross Aichi Medical Center Nagoya Daiichi Hospital, 3-35 Michishita-Cho, Nakamura-Ku, Nagoya, Aichi, 453-8511, Japan.
Research and Development Division, ARKRAY, Inc., Yousuien-Nai, 59 Gansuin-Cho, Kamigyo-Ku, Kyoto, 602-0008, Japan.
J Cancer Res Clin Oncol. 2023 Sep;149(11):8297-8305. doi: 10.1007/s00432-023-04728-9. Epub 2023 Apr 19.
Less-invasive early diagnosis of lung cancer is essential for improving patient survival rates. The purpose of this study is to demonstrate that serum comprehensive miRNA profile is high sensitive biomarker to early-stage lung cancer in direct comparison to the conventional blood biomarker using next-generation sequencing (NGS) technology combined with automated machine learning (AutoML).
We first evaluated the reproducibility of our measurement system using Pearson's correlation coefficients between samples derived from a single pooled RNA sample. To generate comprehensive miRNA profile, we performed NGS analysis of miRNAs in 262 serum samples. Among the discovery set (57 patients with lung cancer and 57 healthy controls), 1123 miRNA-based diagnostic models for lung cancer detection were constructed and screened using AutoML technology. The diagnostic faculty of the best performance model was evaluated by inspecting the validation samples (74 patients with lung cancer and 74 healthy controls).
The Pearson's correlation coefficients between samples derived from the pooled RNA sample ≥ 0.98. In the validation analysis, the best model showed a high AUC score (0.98) and a high sensitivity for early stage lung cancer (85.7%, n = 28). Furthermore, in comparison to carcinoembryonic antigen (CEA), a conventional blood biomarker for adenocarcinoma, the miRNA-based model showed higher sensitivity for early-stage lung adenocarcinoma (CEA, 27.8%, n = 18; miRNA-based model, 77.8%, n = 18).
The miRNA-based diagnostic model showed a high sensitivity for lung cancer, including early-stage disease. Our study provides the experimental evidence that serum comprehensive miRNA profile can be a highly sensitive blood biomarker for early-stage lung cancer.
肺癌的微创早期诊断对于提高患者生存率至关重要。本研究的目的是通过使用下一代测序（NGS）技术结合自动机器学习（AutoML），直接与传统血液生物标志物进行比较，证明血清综合miRNA谱是早期肺癌的高灵敏度生物标志物。
我们首先使用来自单个混合RNA样本的样本之间的Pearson相关系数评估了我们测量系统的重现性。为了生成综合miRNA谱，我们对262份血清样本中的miRNA进行了NGS分析。在发现集（57例肺癌患者和57例健康对照）中，使用AutoML技术构建并筛选了1123个基于miRNA的肺癌检测诊断模型。通过检查验证样本（74例肺癌患者和74例健康对照）来评估最佳性能模型的诊断能力。
来自混合RNA样本的样本之间的Pearson相关系数≥0.98。在验证分析中，最佳模型显示出高AUC分数（0.98）和对早期肺癌的高灵敏度（85.7%，n = 28）。此外，与腺癌的传统血液生物标志物癌胚抗原（CEA）相比，基于miRNA的模型对早期肺腺癌显示出更高的灵敏度（CEA，27.8%，n = 18；基于miRNA的模型，77.8%，n = 18）。
基于miRNA的诊断模型对肺癌（包括早期疾病）显示出高灵敏度。我们的研究提供了实验证据，表明血清综合miRNA谱可以是早期肺癌的高灵敏度血液生物标志物。
