A Classifier for Improving Early Lung Cancer Diagnosis Incorporating Artificial Intelligence and Liquid Biopsy

Abstract

Lung cancer is the leading cause of cancer-related deaths worldwide and in China. Screening for lung cancer by low dose computed tomography (LDCT) can reduce mortality but has resulted in a dramatic rise in the incidence of indeterminate pulmonary nodules, which presents a major diagnostic challenge for clinicians regarding their underlying pathology and can lead to overdiagnosis. To address the significant gap in evaluating pulmonary nodules, we conducted a prospective study to develop a prediction model for individuals at intermediate to high risk of developing lung cancer. Univariate and multivariate logistic analyses were applied to the training cohort (n = 560) to develop an early lung cancer prediction model. The results indicated that a model integrating clinical characteristics (age and smoking history), radiological characteristics of pulmonary nodules (nodule diameter, nodule count, upper lobe location, malignant sign at the nodule edge, subsolid status), artificial intelligence analysis of LDCT data, and liquid biopsy achieved the best diagnostic performance in the training cohort (sensitivity 89.53%, specificity 81.31%, area under the curve [AUC] = 0.880). In the independent validation cohort (n = 168), this model had an AUC of 0.895, which was greater than that of the Mayo Clinic Model (AUC = 0.772) and Veterans’ Affairs Model (AUC = 0.740). These results were significantly better for predicting the presence of cancer than radiological features and artificial intelligence risk scores alone. Applying this classifier prospectively may lead to improved early lung cancer diagnosis and early treatment for patients with malignant nodules while sparing patients with benign entities from unnecessary and potentially harmful surgery.Clinical Trial Registration NumberChiCTR1900026233, URL: http://www.chictr.org.cn/showproj.aspx?proj=43370.

Integrative Serum Metabolic Fingerprints Based Multi‐Modal Platforms for Lung Adenocarcinoma Early Detection and Pulmonary Nodule Classification

“…[ 22 ] We developed a deep learning‐based Image Artificial Intelligence software (Image‐AI) previously. [ 23 ] As shown in Figure 3D and Table 3 , the obtained AUC of MP‐NN was significantly higher than Image‐AI in the test set ( p = 0.026) and MP‐NN was highly sensitive, but showed poor specificity, while Image‐AI was highly specific, thus a comprehensive intelligent model integrating MP‐NN and Image‐AI will be significantly valuable.…”

“…Researchers have previously discussed the feasibility of incorporating blood test with routine image scan to improve early cancer screening/diagnosis performance and pulmonary nodule classification. [ 18 , 23 ] We constructed a tri modal model integrated SMFs, tumor marker CEA, and Image‐AI via RF classifier (MPI‐RF), which is more robust and accurate for nodule risk stratification than dual modal MP‐NN and single modal Image‐AI (Figure 4 ). RF is an ensemble tree‐based algorithm involving multiple decision trees which are combined to yield a single prediction that is collective and consensus of multiple trees.…”

“…Deep convolutional neural network model based artificial intelligence software (Image‐AI) for lung nodule detection and classification was developed by Sanmed Biotech and clinical validated previously. [ 23 ] A 3D‐Unet was used for the nodule detection and segmentation, while downstream tasks including the nodule type classification and cancer risk score prediction network were realized with 3D Resnet. A total of 480 cases of raw chest CT data were transferred to the workstation, and the software system automatically performed lung nodule identification and labeling in batch.…”

Correlation between lung cancer probability and number of pulmonary nodules in baseline computed tomography lung cancer screening: A retrospective study based on the Chinese population

“…A few studies suggest that the number of nodules does not differentiate benign from malignant nodules, but more in-depth research is still required ( 18 , 19 ). At present, only a few risk-prediction models have considered the number of nodules as a risk factor ( 20 , 21 ). This study innovatively stratified nodules according to the nodule size and determined the correlation between the nodule number and the probability of LC.…”

The Third Joint Meeting on Lung Cancer of the FHU OncoAge (University Côte d’Azur, Nice, France) and the University of Texas MD Anderson Cancer Center (Houston, TX, USA). Understanding New Therapeutic Options and Promising Predictive Biomarkers for Lung Cancer Patients

“…Despite the different therapeutic advances in the framework of care for lung cancer patients, studies focusing on the early detection of these cancers still need to be considered through the development of liquid biopsies and circulating biomarkers [ 27 , 28 , 29 , 30 , 31 ]. Along with early detection of lung cancer, we must also focus on preventive measures and identifying populations at risk of developing lung cancer, which could help to quickly reduce the number of deaths from lung cancers [ 9 , 29 , 32 ].…”