Establishment and validation of a combined diagnostic model for aldosterone-producing adenoma of the adrenal gland based on CT radiomics and clinical features
Objective To establish a combined diagnostic model based on CT radiomics and clinical features, and to investigate the value of the model in the diagnosis of aldosterone-producing adenoma (APA) of the adrenal gland. Methods This study was conducted among 229 patients with a unilateral solitary adren...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Journal of Precision Medicine
2025-06-01
|
| Series: | 精准医学杂志 |
| Subjects: | |
| Online Access: | https://jpmed.qdu.edu.cn/fileup/2096-529X/PDF/1750385743619-1002841492.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Objective To establish a combined diagnostic model based on CT radiomics and clinical features, and to investigate the value of the model in the diagnosis of aldosterone-producing adenoma (APA) of the adrenal gland. Methods This study was conducted among 229 patients with a unilateral solitary adrenal mass who were admitted to The Affiliated Hospital of Qingdao University from January 2018 to December 2023 and 50 patients with a unilateral solitary adrenal mass who were admitted to Qilu Hospital of Shandong University from January 2016 to March 2024, and according to whether they were diagnosed with APA, each batch of patients was divided into APA group and non-APA group. Based on the time-series segmentation method, the 229 patients (104 in the APA group and 125 in the non-APA group) from The Affiliated Hospital of Qingdao University were divided into a training set (n=160) and an internal validation set (n=69) according to the order of operation time at a ratio of 7∶3, and the 50 patients (18 in the APA group and 32 in the non-APA group) from Qilu Hospital of Shandong University were set as an external validation group. Clinical and imaging data were collected from all patients, and univariate and multivariate logistic regression analyses were used to investigate the independent influencing factors for the onset of unilateral solitary APA and establish a clinical feature model based on these factors. The Pearson correlation coefficient and the least absolute shrinkage and selection ope-rator (LASSO) algorithm were used to identify the radiomic features on the plain CT and contrast-enhanced CT images of the adrenal gland, and a CT radiomic model was established. The indepen-dent influencing factors and the radiomic features were used to establish a combined diagnostic model for unilateral solitary APA, and a nomogram was plotted. The receiver operating characteristic (ROC) curve and the area under the ROC curve (AUC) were used to evaluate the performance of the model, and the clinical decision analysis (DCA) and the calibration curve were used to assess the clinical application value of the nomogram. Results The univariate and multivariate logistic regression analyses showed that preoperative serum potassium level, the maximum diameter of the lesion, and the highest CT value (plain scan) of the lesion were independent influencing factors for the onset of unilateral solitary APA, and a clinical feature model was established based on these three indicators, while the 23 radiomic features identified by plain CT scan of the adrenal gland were used to establish a radiomic model. A combined diagnostic model was established based on the independent influencing factors and the radiomic features and was represented by a nomogram, and the results showed that it had good diagnostic efficacy. In the training set, the clinical model, the CT radiomic model, and the combined diagnostic model had an AUC of 0.761, 0.867, and 0.949, respectively, in the internal validation group, they had an AUC of 0.733, 0.718, and 0.895, respectively, and in the external validation group, they had an AUC of 0.739, 0.716, and 0.929, respectively, suggesting that the combined diagnostic model had a significantly greater AUC than the other two models in the training group, the internal validation group, and the external validation group (Z=2.495-5.327,P<0.05). The DCA showed that the combined diagnostic model had the maximum net clinical benefit, and the calibration curve showed that the combined diagnostic model had good calibration. Conclusion In this study, a diagnostic model is established for unilateral solitary APA based on clinical and radiomic features, which has excellent diagnostic efficacy and a good generalization ability for APA, and therefore, it is expected to become an ideal noninvasive diagnostic method for unilateral solitary APA in clinical practice. |
|---|---|
| ISSN: | 2096-529X |