Certified into the record
The exact text we saved
This is the version exactly as it was saved, character for character. The SHA-256 hash below is a 64-character code worked out from that text. Run the same text through SHA-256 and you get the same code; change a single letter and the code comes out completely different. Each version also stores the previous version’s hash, which chains them together so no version can be swapped out quietly.
TRUVACE RECORD VERSION record: TRV-2026-3087 version: 1 kind: certified reason: Certified into the record timestamp: 2026-11-21T00:02:47.919087Z status: published lens: g_space sector: health headline: Fully Automated, Explainable AI Analysis of Coronary CTA Improves Prediction of Major Cardiovascular Events dek: Coronary artery disease (CAD) remains a major global cause of morbidity and mortality. Coronary computed tomography angiography (CCTA) is central to noninvasive diagnosis and risk assessment, yet current workflows are labor-intensive and depend on semiquantitative scoring systems that do not fully leverage prognostic information in CCTA. The objectives of the study were to develop and validate a fully automated, explainable artificial intelligence (AI) system (AI-automated coronary analysis [ACA]) for comprehens… gain_title: In a retrospective study of 1,702 patients, a fully automated AI analysis of coronary CT scans predicted major cardiovascular events with an AUC of 0.81, versus 0.76 for the Agatston calcium score and 0.67 for demographic risk markers. problem_title: (none) trace_subject: (none) gain_reading: In a retrospective study of 1,702 patients, a fully automated AI analysis of coronary CT scans predicted major cardiovascular events with an AUC of 0.81, versus 0.76 for the Agatston calcium score and 0.67 for demographic risk markers. gain_evidence: AI-ACA demonstrated higher predictive performance (area under the curve [AUC]: 0.81) than Agatston score (AUC: 0.76) and demographic markers (AUC: 0.67) problem_reading: (none) problem_evidence: (none) quick_read: Researchers developed and validated a fully automated, explainable AI system for analysing coronary CT angiography scans, called AI-ACA, and tested it on a retrospective cohort of 1,702 patients. It predicted major adverse cardiovascular events with an AUC of 0.81, compared with 0.76 for the Agatston score and 0.67 for demographic markers. The system also separated patients' event-free survival more clearly than the Agatston score: its Harrell C-index was 0.791 versus 0.742, and the Kaplan-Meier log-rank statistic was 31.79 versus 13.71. Its performance matched an AI-derived CAD-RADS score at an AUC of 0.81. Current CCTA workflows are labor-intensive and rely on semiquantitative scoring. The authors say the platform offers transparent, biomarker-based risk assessment and scalable analysis that may help bring quantitative CCTA into wider clinical use. limitation: Prognostic performance was comparable to AI-CADRADS and only modestly higher than the Agatston score, and the study was a retrospective cohort rather than a prospective trial. tag: Evidence-backed gain key_points: The cohort was retrospective and included 1,702 patients. | AI-ACA reached an AUC of 0.81 for major adverse cardiovascular events, against 0.76 for the Agatston score and 0.67 for demographic markers. | Harrell C-index was 0.791 for AI-ACA versus 0.742 for the Agatston score. | Kaplan-Meier log-rank statistic for event-free survival was 31.79 for AI-ACA versus 13.71 for the Agatston score. | The system extracts stenosis severity, plaque burden and composition, AI-derived CAD-RADS, coronary tortuosity and subtended myocardial mass. | Shapley Additive Explanations analysis ranked total plaque volume and burden, maximum stenosis severity and AI-CADRADS as the strongest contributors to risk estimates. rundown: The study set out to build a fully automated system that analyses coronary CT angiography without manual intervention. The AI-ACA tool pulls out a set of imaging biomarkers, including stenosis severity, plaque burden and composition, an AI-derived CAD-RADS category, coronary tortuosity and the mass of heart muscle supplied by each vessel, and combines them into interpretable risk estimates. In the 1,702-patient retrospective cohort, AI-ACA was compared with the Agatston score, standard demographic risk markers and AI-CADRADS. It outperformed the Agatston score and demographic markers on AUC, C-index and survival separation, but matched AI-CADRADS at an AUC of 0.81. Explainability was assessed with Shapley Additive Explanations. Total plaque volume and burden, maximum stenosis severity and AI-CADRADS contributed most to the risk estimates, which the authors say makes the assessment transparent. sources: - peer_reviewed | JACC: Advances | https://doi.org/10.1016/j.jacadv.2026.103461 | 2026-11-19 prev: 0000000000000000000000000000000000000000000000000000000000000000
- SHA-256 hash
- f163b0e702b98918678e021472c85feaaba33838622288866683f2b036069ac4
- Previous version’s hash
- 0000000000000000000000000000000000000000000000000000000000000000
How to check it yourself, without trusting this page
Download any version from /api/record/TRV-2026-3087 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.
ace