Application of artificial intelligence quantitative analysis in prognostic evaluation of patients with connective tissue disease-associated interstitial lung disease
10.3969/j.issn.1002-1671.2025.07.011
- VernacularTitle:人工智能定量分析在结缔组织病相关间质性肺疾病患者预后评估中的应用
- Author:
Jingyu XU
1
;
Chen CHU
;
Shengnan ZHAO
;
Ying WEI
;
Feng SHI
;
Zhengyang ZHOU
Author Information
1. 南京大学医学院附属鼓楼医院医学影像科,江苏 南京 210008
- Publication Type:Journal Article
- Keywords:
interstitial lung disease;
connective tissue disease;
artificial intelligence;
high-resolution computed tomography
- From:
Journal of Practical Radiology
2025;41(7):1129-1133
- CountryChina
- Language:Chinese
-
Abstract:
Objective To explore the application of artificial intelligence quantitative analysis in the prognostic assessment of patients with connective tissue disease-associated interstitial lung disease(CTD-ILD).Methods A total of 67 patients with CTD-ILD were retrospectively selected.All subjects underwent high-resolution computed tomography(HRCT)scanning and were categorized into three groups,namely mild,moderate and severe groups,based on the results of pulmonary function tests.The survival rates of patients in each group were compared using Kaplan-Meier curves and analysis of variance.The univariate analysis was employed to assess the rela-tionships between artificial intelligence parameters and patient prognosis.Significant results were then incorporated into a multifacto-rial Cox regression model to construct the most accurate predictive model.Results A significant difference in survival rate was observed among the three groups(P<0.05).Univariate analysis revealed that the volume and percentage of lung infection in deceased patients were significantly greater than those in surviving patients,while the lung volume in deceased patients was significantly smaller than that in surviving patients.The analysis showed left lung volume and the percentage of lesion components CT value≤-750 HU as risk factors for prognosis,and the combination of these two factors as the most effective predictive model.Conclusion The artificial intelligence analysis system for lung lesions provides a new systematic and quantitative method for the prognostic assessment of CTD-ILD patients,which can be used for the prognostic assessment and follow-up of CTD-ILD patients.
