Table 1_Interpretable hybrid deep learning features of pectoralis on low-dose chest CT for detecting type 2 diabetes.docx

Objective<p>To develop an explainable hybrid deep learning features framework using low-dose chest CT (LDCT)-derived pectoralis features for opportunistic type 2 diabetes mellitus (T2DM) opportunistic screening, evaluating its incremental value over conventional biomarkers.</p>Methods<p>This multi-center study analyzed LDCT images from 1,209 individuals. Following automated MedSAM segmentation, conventional metrics (e.g., Mean_HU, SMI) and deep learning (DL) features (ResNet152) were extracted.

To prevent data leakage, PCA, LASSO selection, and ExtraTrees model optimization were strictly confined to the training set. A hybrid (COM) model integrating both feature types was compared against a baseline Muscle model. SHapley Additive exPlanations (SHAP) provided clinical interpretability.</p>Results<p>The COM model achieved an area under the curve (AUC) of 0.830 (training), 0.759 (internal validation), and 0.746 (external validation).