AUTHOR=Hu Wenteng , Zhang Xu , Saber Ali , Cai Qianqian , Wei Min , Wang Mingyuan , Da Zijian , Han Biao , Meng Wenbo , Li Xun 

TITLE=Development and validation of a nomogram model for lung cancer based on radiomics artificial intelligence score and clinical blood test data

JOURNAL=Frontiers in Oncology

VOLUME=Volume 13 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2023.1132514

DOI=10.3389/fonc.2023.1132514

ISSN=2234-943X

ABSTRACT=Summary
Background: Artificial intelligence (AI) discrimination models using single radioactive variables in lung nodules recognition algorithms can not predict lung cancer accurately. Hence, we developed a clinical model that combined AI with blood test variables to predict lung cancer.
Methods: During 2018 and 2021, 554 people 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 and build the model. The predictive performance was assessed by recruiting the receiver operating characteristic (ROC) curve as well as calibration, clinical decision and impact curves. External validation with 54 patients was used to validate the model. The subgroup application was analyzed in pathological diagnosis.
Findings: A total of 554 patients were enrolled (358 lung cancers, 64.62%,196 patients for the control group) to build the model. The integrated model identified eight potential predictors including CEA, AI score, serum ProGRP, CYFRA211, SCC, IBIL, 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 0.939 (95% CI, 0.931 - 0.981) was obtained for the external group.
Conclusions: The model combined with AI and clinical data can accurately predict lung cancer, especially for the squamous cell carcinoma subtype.
 
Keywords: pulmonary nodule, lung cancer, artificial intelligence, prediction model