Hu Wenteng, Zhang Xu, Saber Ali, Cai Qianqian, Wei Min, Wang Mingyuan, Da Zijian, Han Biao, Meng Wenbo, Li Xun
The First Clinical Medical School of Lanzhou University, Lanzhou, Gansu, China.
Department of Thoracic Surgery, The First Hospital of Lanzhou University, Lanzhou, Gansu, China.
Front Oncol. 2023 Mar 29;13:1132514. doi: 10.3389/fonc.2023.1132514. eCollection 2023.
Artificial intelligence AI) discrimination models using single radioactive variables in recognition algorithms of lung nodules cannot predict lung cancer accurately. Hence, we developed a clinical model that combines AI with blood test variables to predict lung cancer.
Between 2018 and 2021, 584 individuals (358 patients with lung cancer and 226 individuals with lung nodules other than cancer as control) were enrolled prospectively. Machine learning algorithms including lasso regression and random forest (RF) were used to select variables from blood test data, Logistic regression analysis was used to reconfirm the features to build the nomogram model. The predictive performance was assessed by performing the receiver operating characteristic (ROC) curve analysis as well as calibration, clinical decision and impact curves. A cohort of 48 patients was used to independently validate the model. The subgroup application was analyzed by pathological diagnosis.
A total of 584 patients were enrolled (358 lung cancers, 61.30%,226 patients for the control group) to establish the model. The integrated model identified eight potential factors including carcinoembryonic antigen (CEA), AI score, Pro-Gastrin Releasing Peptide (ProGRP), cytokeratin 19 fragment antigen21-1(CYFRA211), squamous cell carcinoma antigen(SCC), indirect bilirubin(IBIL), activated partial thromboplastin time(APTT) and age. The area under the curve (AUC) of the nomogram was 0.907 (95% CI, 0.881-0.929). The decision and clinical impact curves showed good predictive accuracy of the model. An AUC of 0.844 (95% CI, 0.710 - 0.932) was obtained for the external validation group.
The nomogram model integrating AI and clinical data can accurately predict lung cancer, especially for the squamous cell carcinoma subtype.
在肺结节识别算法中使用单一放射性变量的人工智能（AI）判别模型无法准确预测肺癌。因此，我们开发了一种将AI与血液检测变量相结合来预测肺癌的临床模型。
在2018年至2021年期间，前瞻性纳入了584例个体（358例肺癌患者和226例非癌性肺结节个体作为对照）。使用包括套索回归和随机森林（RF）在内的机器学习算法从血液检测数据中选择变量，采用逻辑回归分析重新确认特征以构建列线图模型。通过进行受试者操作特征（ROC）曲线分析以及校准、临床决策和影响曲线来评估预测性能。使用48例患者的队列对模型进行独立验证。通过病理诊断分析亚组应用情况。
共纳入584例患者（358例肺癌，占61.30%，226例作为对照组）以建立模型。综合模型确定了八个潜在因素，包括癌胚抗原（CEA）、AI评分、胃泌素释放肽前体（ProGRP）、细胞角蛋白19片段抗原21-1（CYFRA211）、鳞状细胞癌抗原（SCC）、间接胆红素（IBIL）、活化部分凝血活酶时间（APTT）和年龄。列线图的曲线下面积（AUC）为0.907（95%CI，0.881-0.929）。决策曲线和临床影响曲线显示该模型具有良好的预测准确性。外部验证组的AUC为0.844（95%CI，0.710-0.932）。
整合AI和临床数据的列线图模型能够准确预测肺癌，尤其是对于鳞状细胞癌亚型。
