Objective

The aim of this study was to create the preoperative predictive model on mediastinal lymph-node metastasis based on artificial intelligence in surgically resected lung adenocarcinoma.

Methods

We enrolled 301 surgical resections of patients with clinical stage N0-1 lung adenocarcinoma, who received positron emission tomography preoperatively between 2015 and 2019. We randomly assigned the patients into two groups: the training (n = 201) and validation groups (n = 100). The training group was used to obtain basic data for learning by artificial intelligence, whereas the validation group was used to verify the constructed algorithm. We used an automatic machine learning platform, to create artificial intelligence model. For comparison, multivariate analysis was performed in the training group, whereas for calculating and verifying the prediction accuracy rate, significant predicting factors were applied to the validation group.

Results

Of the 301 patients, 41 patients were diagnosed as mediastinal lymph node metastasis. In multivariate analysis, the maximum standardized uptake value was an individual predictive factor. The accuracy rate of artificial intelligence model was 84%, and the specificity was 98% which were higher than those of the maximum standardized uptake value (61% and 57%). However, in terms of sensitivity, artificial intelligence model remarked low at 12%.

Conclusions

An artificial intelligence-based diagnostic algorithm showed remarkable specificity compared with the maximum standardized uptake value. Although this model is not ready to practical use and the result was preliminary because of poor sensitivity, artificial intelligence could be able to complement the shortcomings of existing diagnostic modalities.

中文翻译：

---

人工智能对纵隔淋巴结转移的预测能力

客观的

本研究的目的是建立基于人工智能的手术切除肺腺癌纵隔淋巴结转移的术前预测模型。

方法

我们招募了 301 例手术切除的临床分期 N0-1 肺腺癌患者，这些患者在 2015 年至 2019 年期间术前接受了正电子发射断层扫描。我们将患者随机分为两组：训练组（n  = 201）和验证组（n  = 100 ）。训练组用于获取人工智能学习的基础数据，验证组用于验证构建的算法。我们使用自动机器学习平台，创建人工智能模型。为了比较，在训练组中进行多变量分析，而为了计算和验证预测准确率，将显着的预测因素应用于验证组。

结果

301例患者中，41例确诊为纵隔淋巴结转移。在多变量分析中，最大标准化摄取值是个体预测因素。人工智能模型的准确率为84%，特异性为98%，高于最大标准化摄取值（61%和57%）。但在敏感度方面，人工智能模型评价低至12%。

结论

与最大标准化摄取值相比，基于人工智能的诊断算法显示出显着的特异性。尽管该模型尚未准备好投入实际使用，并且由于敏感性差而得出的结果是初步的，但人工智能可以弥补现有诊断方式的不足。