| Literature DB >> 34455736 |
Zhaojue Wang1, Jing Zhao1, Mengzhao Wang1.
Abstract
With the popularization of computed tomography (CT) examinations, the incidence of solitary pulmonary nodules (SPNs) has increased significantly. The assessment of benign and malignant pulmonary nodules is crucial to the diagnosis and treatment of lung nodules. Many models for predicting the malignant probability of lung nodules have been developed. These models assess the malignant probability of lung nodules based on the clinical and imaging characteristics of patients. In recent years, malignant probability prediction models have gradually attracted attention in China. Based on the researches on the malignant probability prediction model of pulmonary nodule, focusing on the establishment or verification of the model in the Chinese patient population, this paper reviews the research progress and clinical application of the malignant probability prediction model of pulmonary nodule, and proposes ideas for the future development. .Entities:
Keywords: Lung neoplasms; Models; Pulmonary nodules
Mesh:
Year: 2021 PMID: 34455736 PMCID: PMC8503979 DOI: 10.3779/j.issn.1009-3419.2021.102.29
Source DB: PubMed Journal: Zhongguo Fei Ai Za Zhi ISSN: 1009-3419
Mayo模型、VA模型、Brock模型和PKUPH模型在国内的外部验证研究
External verification of Mayo model, VA model, Brock model and PKUPH model in China
| Central location | Malignant rate | AUC | |||
| Mayo model | VA model | Brock model | PKUPH model | ||
| AUC: area under the curve | |||||
| Sichuan[ | 76.0% | 0.705 | 0.646 | 0.575 | 0.675 |
| Hubei[ | 78.4% | 0.626 | 0.621 | 0.600 | 0.630 |
| Guangdong[ | 60.0% | 0.752 | 0.730 | 0.878 | 0.833 |
| Beijing[ | 86.5% | 0.739 | 0.715 | 0.709 | 0.755 |
| Jiangsu[ | 86.4% | 0.597 | 0.538 | 0.430 | 0.623 |
| Xi’an[ | 48.8% | 0.655 | 0.603 | 0.521 | |
| Zhejiang[ | 67.2% | 0.789 | 0.746 | ||
| Chongqing[ | 68.0% | 0.649 | 0.599 | ||
| Guangdong[ | 81.2% | 0.753 | 0.728 | 0.800 | |
| Shanghai[ | 78.7% | 0.701 | 0.729 | 0.773 | |
| Jiangsu[ | 55.0% | 0.764 | 0.715 | ||
| Guangdong[ | 68.9% | 0.685 | 0.646 | ||
| Jiangxi[ | 56.7% | 0.745 | 0.825 | ||