A multimodal deep learning system integrating automated CAD-RADS, anatomy, and demographics predicted 30-day MACE with AUROC 0.82, outperforming RCRI and human CAD-RADS.
Does a fully automated multimodal deep learning system integrating CCTA and clinical data improve 30-day MACE prediction compared to RCRI and CAD-RADS alone in patients undergoing elective non-cardiac surgery?
A fully automated deep learning system combining CCTA imaging features with clinical data significantly improves 30-day perioperative MACE prediction compared to standard clinical risk scores.
Absolute Event Rate: 0% vs 0%
Abstract Aims Major adverse cardiac events (MACE) significantly impact perioperative morbidity and mortality. We aimed to develop a fully automated multimodal deep learning (DL) system integrating patient demographics, comorbidities, and coronary computed tomography angiography (CCTA) findings to optimize risk prediction. Methods We included 639 patients undergoing CCTA as part of perioperative risk assessment for elective non-cardiac surgery. Convolutional neural networks automatically identified coronary artery disease reporting and data system (CAD-RADS) scores and segmented the left ventricle, aorta, and heart. These imaging features were combined with patient demographics and comorbidities to predict MACE risk. We evaluated the performance of our multimodal model against the revised cardiac risk index (RCRI) using gradient boosting decision tree modelling and area under the receiver operating characteristic (AUROC) curves. Results Among 639 patients (mean age 70±9 years, 56% males, median RCRI 1), 61% underwent orthopaedic surgery, 27% vascular surgery and the rest abdominal/pelvic or spine surgery. 45 patients experienced MACE within 30 days. Automated CAD-RADS (AUROC = 0.69) demonstrated comparable performance to human analysis (AUROC=0.67, p=0.77). The multimodal DL system (AUROC = 0.82) outperformed CAD-RADS (delta-AUROC = 0.13, CI: 0.02, 0.26, p=0.02, ), and RCRI (delta-AUROC =0.22, CI: 0.05, 0.46; p=0.001 in predicting MACE and demonstrated robust sensitivity (83%) and specificity (79%). Conclusion Our multimodal system built using automated CAD-RADS, anatomical segmentations and patient demographics outperforms both human expert and automated CAD-RADS for MACE prediction. This approach has the potential to enhance patient outcomes by leveraging the synergy between automated imaging and clinical data.
Lu et al. (Tue,) reported a other. A multimodal deep learning system integrating automated CAD-RADS, anatomy, and demographics predicted 30-day MACE with AUROC 0.82, outperforming RCRI and human CAD-RADS.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: