Predicting abnormal epicardial adipose tissue in psoriasis patients by integrating radiomics from non-contrast chest CT with serological biomarkers

Abstract

Background: Psoriasis patients frequently present with cardiovascular comorbidities, which maybe associated with abnormal epicardial adipose tissue (EAT). This study aimed to evaluate the predictive value of radiomics features derived from non-contrast chest CT (NCCT) combined with serological parameters for identifying abnormal EAT in psoriasis.

Methods: In this retrospective case-control study, we enrolled consecutive psoriasis patients who underwent chest NCCT between September 2021 and February 2024, along with a matched healthy control group. Psoriasis patients were stratified into mild-to-moderate (PASI ≤ 10) and severe (PASI > 10) groups based on the Psoriasis Area and Severity Index (PASI). Using TIMESlice, we extracted EAT volume, CT values, and 86 radiomics features. The cohort was randomly divided into a training (70%) and test (30%) set. LASSO regression selected radiomic features to calculate the Rad_Score. Serum uric acid (UA) and C-reactive protein (CRP) levels were collected. We compared EAT volume, CT values, Rad_Score, UA, and CRP between groups and developed three models: Model A (UA, CRP, EAT CT values), Model B (Rad_Score), and Model C (UA, CRP, EAT CT values, Rad_Score). Model accuracy was evaluated using ROC curves (P < 0.05).

Results: The study included 77 psoriasis patients and 76 matched controls. Psoriasis patients had higher UA and CRP levels than controls (both P < 0.001). EAT CT value was higher in psoriasis (P = 0.020), with no volume difference. Eight radiomics features and Rad_Score significantly differed between groups (P < 0.001), and Rad_Score also higher in severe group than that in mild-to-moderate group (P < 0.001). Model C showed the highest AUC in both sets: training 0.947 and test 0.895, indicating superior predictive performance.

Conclusions: Combining radiomics features, EAT CT values, UA, and CRP in a predictive model accurately predicts EAT abnormalities in psoriasis, potentially improving cardiovascular comorbidity diagnosis.

Clinical trial number: Not applicable.

Keywords: Computed tomography; Epicardial adipose tissue; Psoriasis; Radiomics.

Fig. 1

Extraction flow chart of EAT related features

Fig. 2

Lasso regression analysis and feature selection. (a) The features set in lasso model is depicted, with the vertical dashed lines indicating the Lambda value selected after cross-validation, the left dashed line represents the Lambda corresponding to the lowest horizontal classification error rate, while the right dashed line is the Lambda corresponding to the lowest average classification error rate of 1 times the labeling difference. (b) Eight valuable features were identified to evaluate the abnormal EAT in patients with psoriasis. 2c The waterfall diagram of the 8-features Rad_Score illustrates concentrated colors distribution, suggestting good identification efficiency.(psoriasis group = 1, healthy control group = 0)

Fig. 3

Boxplots of Rad-Score values. Boxplots of Rad_Score values for the psoriasis group and control group in the training set (a) and test set (b) are presented. There were statistically significant differences in Rad-Score values between psoriasis group and control group. (psoriasis group = 1, healthy control group = 0). ****:P < 0.001,*:P < 0.05

Fig. 4

Model Performance Evaluation. ROC curves, model calibration curves (abscissa represents the predicted probability, ordinate represents the actual probability of occurrence; the diagonal dotted line in the figure indicates that the predicted probability and the actual probability are always equal), and decision curve analysis (DCA) of the three regression models for the training set (a ~ c) and test set (d ~ f) are shown. The curves demonstrate practical significance as they are higher than the all-line and none-line, indicating the models’ utility in predicting outcomes