A deep learning model can analyze routine chest CTs to predict major adverse cardiac event risk, outperforming traditional methods.
Key Details
- 1Researchers developed a 3D convolutional neural network to assess MACE risk directly from chest CT images.
- 2The AI model leverages 'causal intervention' to improve generalizability across diverse patient populations.
- 3Performance metrics included AUCs of 0.73 (internal test set) and 0.69 (external test set), surpassing existing clinical models.
- 4Traditional risk estimations do not incorporate imaging data and underperform when applied externally.
Why It Matters
Incorporating imaging data with AI could enable more accurate, widely generalizable cardiac risk prediction, improving proactive patient management. Broad deployment of such models in routine chest CTs could significantly expand radiologists' role in population health.
Source
AuntMinnie
Related News
•AuntMinnie
Deep Learning AI Outperforms Radiologists in Detecting ENE on CT
A deep learning tool, DeepENE, exceeded radiologist performance in identifying lymph node extranodal extension in head and neck cancers using preoperative CT scans.
•Radiology Business
Patients Favor AI in Imaging Diagnostics, Hesitate on Triage Use
Survey finds most patients support AI in diagnostic imaging but are reluctant about its use in triage decisions.
•Radiology Business
FDA Clears Multi-Disease AI Screening Platform for CT Imaging
HeartLung Corporation's AI-CVD platform receives FDA clearance to detect multiple diseases from a single CT scan.