Key result
Deep learning integrating CT and vitals predicts hemodynamic instability with ~0.84 AUC, outperforming clinical models.
Why the study?
Does a multimodal deep learning framework integrating CT features and vital signs improve the prediction of hemodynamic instability compared to clinical variables alone in patients undergoing elective abdominal and pelvic cancer surgery?
Cohort (n=456)
Yes
Does a multimodal deep learning framework integrating CT features and vital signs improve the prediction of hemodynamic instability compared to clinical variables alone in patients undergoing elective abdominal and pelvic cancer surgery?
A multimodal AI framework combining preoperative CT features and peri-induction vital signs significantly improves the prediction of intraoperative hemodynamic instability compared to clinical variables alone.
We developed and externally validated an interpretable multimodal deep learning framework for predicting Hemodynamic instability (HDI) in patients undergoing elective abdominal and pelvic cancer surgery under general anesthesia, integrating (1) radiomic features and deep imaging representations from preoperative contrast-enhanced computed tomography (CT), and (2) peri-induction vital-sign summaries. This retrospective multicenter cohort study enrolled 456 patients across three centers (training/validation: n = 312, Centers 1–2; external test: n = 144, Center 3). HDI was defined as sustained MAP < 65 mmHg for > 5 min or a > 20% MAP reduction requiring vasopressor intervention. Four feature modalities were evaluated: (1) a clinical-only benchmark (L2-regularized logistic regression on seven preoperative variables), (2) radiomic-only CT features, (3) deep imaging features from four pretrained backbone architectures (ConvNeXt-Base, Swin-V2-B, EfficientNetV2-L, ViT-L/16), and (4) a full multimodal combination of CT features and peri-induction vital-sign statistics. Imaging modalities were evaluated across four tabular deep learning (DL) classifiers (TabNet, FT-Transformer, SAINT, DANet) and four feature-selection strategies (LASSO, Boruta, mRMR, SHAP-RFE), yielding 16 configurations per imaging modality. HDI occurred in 138 patients (30.3%), with comparable prevalence across centers ( χ 2 = 0.04, p = 0.98). The clinical-only L2-LR benchmark achieved an external test AUC-ROC of 0.728 (95% CI 0.667–0.787). Radiomic-only models improved performance to AUC 0.786 (0.726–0.842; ΔAUC + 0.058, p = 0.031). Deep feature-only models with the ViT-L/16 backbone achieved AUC 0.805 (0.746–0.859; ΔAUC + 0.077, p = 0.008). The primary multimodal model (SAINT + ViT-L/16 + mRMR) achieved the highest external test AUC of 0.836 (0.784–0.884) (ΔAUC + 0.108 vs clinical-only L2-LR; Westfall–Young p < 0.001), with sensitivity 0.726, specificity 0.798, Brier score 0.174, and MCC 0.511. A perioperative multimodal framework integrating preoperative CT radiomic and deep imaging features with peri-induction vital-sign data significantly outperforms clinical-only risk stratification for HDI prediction.
No takes yet. Share an insight, caveat, or question.
Xu et al. (2026) conducted a cohort in Elective abdominal and pelvic cancer surgery under general anesthesia (n=456). Multimodal deep learning framework (CT features and vital signs) vs. Clinical-only benchmark was evaluated on Hemodynamic instability (sustained MAP < 65 mmHg for > 5 min or > 20% MAP reduction requiring vasopressor) (AUC 0.836, 95% CI 0.784-0.884, p=<0.001). A multimodal deep learning framework integrating CT features and vital signs outperformed a clinical-only model for predicting hemodynamic instability (AUC 0.836 vs 0.728; P<0.001).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: