Impact of symptom duration and mechanical circulatory support on prognosis in cardiogenic shock complicating acute myocardial infarction.

BACKGROUND: Mortality rates in patients with cardiogenic shock complicating acute myocardial infarction (AMICS) remain high despite advancements in AMI care. Our study aimed to investigate the impact of prehospital symptom duration on the prognosis of AMICS patients and those receiving mechanical circulatory support (MCS). METHODS AND RESULTS: We conducted a retrospective cohort study with data registered in the Netherlands Heart Registration. A total of 1,363 patients with AMICS who underwent percutaneous coronary intervention between 2017 and 2021 were included. Patients presenting after out-of-hospital cardiac arrest were excluded. Most patients were male (68%), with a median age of 69 years (IQR 61-77), predominantly presenting with ST-elevation myocardial infarction (86%). The overall 30-day mortality was 32%. Longer prehospital symptom duration was associated with a higher 30-day mortality with the following rates: < 3 h, 26%; 3-6 h, 29%; 6-24 h, 36%; ≥ 24 h, 46%; p < 0.001. In a subpopulation of AMICS patients with MCS (n = 332, 24%), symptom duration of > 24 h was associated with significantly higher mortality compared to symptom duration of < 24 h (59% vs 45%, p = 0.029). Multivariate analysis identified > 24 h symptom duration, age and in-hospital cardiac arrest as predictors of 30-day mortality in MCS patients. CONCLUSION: Prolonged prehospital symptom duration was associated with significantly increased 30-day mortality in patients presenting with AMICS. In AMICS patients treated with MCS, a symptom duration of > 24 h was an independent predictor of poor survival. These results emphasise the critical role of early recognition and intervention in the prognosis of AMICS patients.

Characteristics and Outcome in Cardiogenic Shock according to Vascular Access Site for PCI.

BACKGROUND: The optimal vascular access site for percutaneous coronary interventions (PCI) in patients with acute myocardial infarction (AMI) complicated by cardiogenic shock (CS) remains uncertain. While observational data favor transradial access (TRA) due to lower complication rates and mortality, transfemoral (TFA) PCI offers advantages such as shorter access and procedure times, along with quicker escalation to mechanical circulatory support (MCS). In this study, we aimed to investigate factors associated with a transfemoral approach and compare mortality rates between TRA and TFA in AMI-CS patients undergoing PCI. METHODS: Data from a nationwide registry of AMI-CS patients undergoing PCI (2017-2021) were analyzed. We compared patient demographics, procedural details, and outcomes between TRA and TFA groups. Logistic regression identified access site factors and radial-to-femoral cross-over predictors. Propensity score matched (PSM) analysis examined the impact of access site on mortality. RESULTS: Of 1562 patients, 45% underwent TRA PCI, with an increasing trend over time. TFA patients were more often female, had a history of coronary artery bypass grafting (CABG), lower blood pressure, higher resuscitation and intubation rates, and elevated lactate levels. After PSM, 30-day mortality was lower in TRA (33% vs. 46%, p <0.001). Predictors for cross-over included left coronary artery interventions, multivessel PCI, and MCS initiation. CONCLUSION: Significant differences exist between TRA and TFA PCI in AMI-CS. TFA was more common in patients with worse hemodynamics and was associated with higher 30-day mortality compared to TRA. This mortality difference persisted in the propensity score matched analysis.

Low muscle quality on a procedural computed tomography scan assessed with deep learning as a practical useful predictor of mortality in patients with severe aortic valve stenosis.

BACKGROUND & AIMS: Accurate diagnosis of sarcopenia requires evaluation of muscle quality, which refers to the amount of fat infiltration in muscle tissue. In this study, we aim to investigate whether we can independently predict mortality risk in transcatheter aortic valve implantation (TAVI) patients, using automatic deep learning algorithms to assess muscle quality on procedural computed tomography (CT) scans. METHODS: This study included 1199 patients with severe aortic stenosis who underwent transcatheter aortic valve implantation (TAVI) between January 2010 and January 2020. A procedural CT scan was performed as part of the preprocedural-TAVI evaluation, and the scans were analyzed using deep-learning-based software to automatically determine skeletal muscle density (SMD) and intermuscular adipose tissue (IMAT). The association of SMD and IMAT with all-cause mortality was analyzed using a Cox regression model, adjusted for other known mortality predictors, including muscle mass. RESULTS: The mean age of the participants was 80 ± 7 years, 53% were female. The median observation time was 1084 days, and the overall mortality rate was 39%. We found that the lowest tertile of muscle quality, as determined by SMD, was associated with an increased risk of mortality (HR 1.40 [95%CI: 1.15-1.70], p < 0.01). Similarly, low muscle quality as defined by high IMAT in the lowest tertile was also associated with increased mortality risk (HR 1.24 [95%CI: 1.01-1.52], p = 0.04). CONCLUSIONS: Our findings suggest that deep learning-assessed low muscle quality, as indicated by fat infiltration in muscle tissue, is a practical, useful and independent predictor of mortality after TAVI.

Ten-Year Outcome of Recanalization or Medical Therapy for Concomitant Chronic Total Occlusion After Myocardial Infarction.

BACKGROUND: The EXPLORE (Evaluating Xience and Left Ventricular Function in PCI on Occlusions After STEMI) trial was the first and only randomized trial investigating chronic total occlusion (CTO) percutaneous coronary intervention (PCI) early after primary PCI for ST-segment-elevation myocardial infarction, compared with medical therapy for the CTO. We performed a 10-year follow-up of EXPLORE to investigate long-term safety and clinical impact of CTO PCI after ST-segment-elevation myocardial infarction, compared with no-CTO PCI. METHODS AND RESULTS: In EXPLORE, 302 patients post-ST-segment-elevation myocardial infarction with concurrent CTO were randomized to CTO PCI within ≈1 week or no-CTO PCI. We performed an extended clinical follow-up for the primary end point of major adverse cardiac events, consisting of cardiovascular death, coronary artery bypass grafting, or myocardial infarction. Secondary end points included all-cause death, angina, and dyspnea. Median follow-up was 10 years (interquartile range, 8-11 years). The primary end point occurred in 25% of patients with CTO PCI and in 24% of patients with no-CTO PCI (hazard ratio [HR], 1.11 [95% CI, 0.70-1.76]). Cardiovascular mortality was higher in the CTO PCI group (HR, 2.09 [95% CI, 1.10-2.50]), but all-cause death was similar (HR, 1.53 [95% CI, 0.93-2.50]). Dyspnea relief was more frequent after CTO PCI (83% versus 65%, P=0.005), with no significant difference in angina. CONCLUSIONS: This 10-year follow-up of patients post-ST-segment-elevation myocardial infarction randomized to CTO PCI or no-CTO PCI demonstrated no clinical benefit of CTO PCI in major adverse cardiac events or overall mortality. However, CTO PCI was associated with a higher cardiovascular mortality compared with no-CTO PCI. Our long-term data support a careful weighing of effective symptom relief against an elevated cardiovascular mortality risk in CTO PCI decisions. REGISTRATION: URL: https://www.trialregister.nl; Unique identifier: NTR1108.

Same-day discharge after large-bore access in percutaneous coronary intervention of chronic total coronary occlusions.

BACKGROUND: Same-day discharge (SDD) in patients undergoing percutaneous coronary intervention (PCI) of a chronic total occlusion (CTO) is appealing because of the increased patient comfort. However, data on SDD following large-bore vascular access are scarce. AIMS: We investigated the feasibility and safety of SDD in patients undergoing large-bore CTO PCI. METHODS: Between 2013 and 2023, 948 patients were prospectively enrolled in a single-centre CTO registry and underwent CTO PCI. SDD was pursued in all patients. Large-bore access was defined as the use of ≥7 French (Fr) sheaths in ≥1 access site. A logistic regression analysis was used to identify predictors for non-SDD. Clinical follow-up was obtained at 30 days. RESULTS: SDD was observed in 62% of patients. Large-bore access was applied in 99% of the cohort. SDD patients were younger and more often male, with lower rates of renal insufficiency and prior coronary artery bypass grafting. Local access site bleeding (odds ratio [OR] 8.53, 95% confidence interval [CI]: 5.24-13.87) and vascular access complications (OR 7.23, 95% CI: 1.98-26.32) made hospitalisation more likely, with vascular access complications occurring in 3%. At 30 days, the hospital readmission rate was low in both SDD and non-SDD patients (5% vs 7%; p=non-significant). Finally, SDD was not a predictor for major adverse cardiovascular events (MACE) at follow-up. CONCLUSIONS: Same-day discharge can be achieved in the majority of patients undergoing CTO PCI with large-bore (≥7 Fr) access. Similar low hospital readmission and MACE rates between SDD and non-SDD patients at 30 days demonstrate the feasibility and safety of SDD.

Biomarker patterns in patients with cardiogenic shock versus septic shock.

Background: In cardiogenic shock (CS), contractile failure is often accompanied by a systemic inflammatory response syndrome. In contrast, many patients with septic shock (SS) develop cardiac dysfunction. A similar hemodynamic support strategy is often deployed in both syndromes but it is unclear whether this is justified based on profiles of biomarkers expressing neurohormonal activation and cardiovascular stress. Methods: In this prospective, multicenter cohort, 111 patients with acute myocardial infarction related CS were identified, and matched to patients with SS. Clinical parameters were collected and blood samples were obtained on day 1-3 of Intensive Care admission. Results: In this shock cohort comprising 222 patients, with a mean age of 61 (±13.5) years and of whom 161 (37 %) were male, we found that despite obvious clinical disparities on admission, mortality at 30-days did not differ (CS: 40.5 % vs. SS 43.1 %, p = 0.56). Overall, plasma concentrations of all biomarkers were higher in SS patients, with the largest difference on the first day. However, only in CS patients the biomarker concentrations were associated with mortality. Conclusion: In this prospective, multicenter cohort SS and CS patients showed similarities in baseline conditions and had similar mortality. However, several biomarkers only showed prognostic value in CS.

Graph neural networks for automatic extraction and labeling of the coronary artery tree in CT angiography.

Purpose: Automatic comprehensive reporting of coronary artery disease (CAD) requires anatomical localization of the coronary artery pathologies. To address this, we propose a fully automatic method for extraction and anatomical labeling of the coronary artery tree using deep learning. Approach: We include coronary CT angiography (CCTA) scans of 104 patients from two hospitals. Reference annotations of coronary artery tree centerlines and labels of coronary artery segments were assigned to 10 segment classes following the American Heart Association guidelines. Our automatic method first extracts the coronary artery tree from CCTA, automatically placing a large number of seed points and simultaneous tracking of vessel-like structures from these points. Thereafter, the extracted tree is refined to retain coronary arteries only, which are subsequently labeled with a multi-resolution ensemble of graph convolutional neural networks that combine geometrical and image intensity information from adjacent segments. Results: The method is evaluated on its ability to extract the coronary tree and to label its segments, by comparing the automatically derived and the reference labels. A separate assessment of tree extraction yielded an F1 score of 0.85. Evaluation of our combined method leads to an average F1 score of 0.74. Conclusions: The results demonstrate that our method enables fully automatic extraction and anatomical labeling of coronary artery trees from CCTA scans. Therefore, it has the potential to facilitate detailed automatic reporting of CAD.

Correction: van Veelen et al. First-in-Human Drug-Eluting Balloon Treatment of Vulnerable Lipid-Rich Plaques: Rationale and Design of the DEBuT-LRP Study. J. Clin. Med. 2023, 12, 5807.

In the original publication [...].

Impact of a Chronic Total Coronary Occlusion on the Incidence of Appropriate Implantable Cardioverter-Defibrillator Shocks and Mortality: A Substudy of the Dutch Outcome in ICD Therapy (DO-IT)) Registry.

BACKGROUND: Chronic total coronary occlusions (CTO) substantially increase the risk for sudden cardiac death. Among patients with chronic ischemic heart disease at risk for sudden cardiac death, an implantable cardioverter defibrillator (ICD) is the favored therapy for primary prevention of sudden cardiac death. This study sought to investigate the impact of CTOs on the risk for appropriate ICD shocks and mortality within a nationwide prospective cohort. METHODS AND RESULTS: This is a subanalysis of the nationwide Dutch-Outcome in ICD Therapy (DO-IT) registry of primary prevention ICD recipients in The Netherlands between September 2014 and June 2016 (n=1442). We identified patients with chronic ischemic heart disease (n=663) and assessed available coronary angiograms for CTO presence (n=415). Patients with revascularized CTOs were excluded (n=79). The primary end point was the composite of all-cause mortality and appropriate ICD shocks. Clinical follow-up was conducted for at least 2 years. A total of 336 patients were included, with an average age of 67±9 years, and 20.5% was female (n=69). An unrevascularized CTO was identified in 110 patients (32.7%). During a median follow-up period of 27 months (interquartile range, 24-32), the primary end point occurred in 21.1% of patients with CTO (n=23) compared with 11.9% in patients without CTO (n=27; P=0.034). Corrected for baseline characteristics including left ventricular ejection fraction, and the presence of a CTO was an independent predictor for the primary end point (hazard ratio, 1.82 [95% CI, 1.03-3.22]; P=0.038). CONCLUSIONS: Within this nationwide prospective registry of primary prevention ICD recipients, the presence of an unrevascularized CTO was an independent predictor for the composite outcome of all-cause mortality and appropriate ICD shocks.

Impact of sex on myocardial perfusion following percutaneous coronary intervention of chronic total coronary occlusions.

OBJECTIVES: We sought to investigate the impact of sex on myocardial perfusion changes following chronic total coronary occlusion (CTO) percutaneous coronary intervention (PCI) as measured by [15O]H2O positron-emission tomography (PET) perfusion imaging. BACKGROUND: CTO PCI has been associated with an increase in myocardial perfusion, yet females are less likely to undergo revascularization. As such, data on the impact of sex on myocardial perfusion following CTO PCI is scarce. METHODS: A total of 212 patients were prospectively enrolled and underwent CTO PCI combined with [15O]H2O PET perfusion imaging prior to and 3 months after PCI. Hyperemic myocardial blood flow (hMBF, mL·min-1·g-1) and coronary flow reserve (CFR) allocated to the CTO territory were quantitatively assessed. RESULTS: This study comprised 34 (16 %) females and 178 (84 %) males. HMBF at baseline did not differ between sexes. Females showed a higher increase in hMBF than males (Δ1.34 ± 0.67 vs. Δ1.06 ± 0.74, p = 0.044), whereas post-PCI hMBF was comparable (2.59 ± 0.85 in females vs. 2.28 ± 0.84 in males, p = 0.052). Female sex was independently associated with a higher increase in hMBF after correction for clinical covariates. CFR increase after revascularization was similar in females and males (Δ1.47 ± 0.99 vs. Δ1.30 ± 1.14, p = 0.711). CONCLUSIONS: The present study demonstrates a greater recovery of stress perfusion in females compared to males as measured by serial [15O]H2O PET imaging. In addition, a comparable increase in CFR was found in females and males. These results emphasize the benefit of performing CTO PCI in both sexes. CLINICAL PERSPECTIVE: What is new? What are the clinical implications?

Native coronary artery or bypass graft percutaneous coronary intervention in patients after previous coronary artery bypass surgery: A large nationwide analysis from the Netherlands Heart Registration.

BACKGROUND: Patients with previous coronary artery bypass surgery (CABG) who require repeat revascularization frequently undergo percutaneous coronary intervention (PCI). We sought to identify factors associated with the decision to intervene on the native vessel versus a bypass graft and investigate their outcomes in a large nationwide prospective registry. METHODS: We identified patients who underwent PCI with a history of prior CABG from the Netherlands Heart Registration between 2017 and 2021 and stratified them by isolated native vessel PCI versus PCI including at least one venous- or arterial graft. The primary endpoint of major adverse cardiac events (MACE) was a composite of all-cause death and target vessel revascularization (TVR) at one-year post PCI. The key secondary endpoint was a composite of all-cause death, myocardial infarction (MI), and TVR at 30 days. RESULTS: Out of 154,146 patients who underwent PCI, 12,822 (8.3%) had a prior CABG. Isolated native vessel PCI was most frequently performed (75.2%), while an acute coronary syndrome (ACS) presentation was most strongly associated with graft interventions. The primary outcome of MACE at one-year post PCI occurred more frequently in interventions including grafts compared with native vessels alone (19.7% vs. 14.3%; adjOR 1.267; 95% CI 1.101-1.457); p < 0.001) driven by TVR. There was however no difference in mortality or the key secondary endpoint between the two groups. CONCLUSION: In this nationwide prospective registry, ACS presentation was strongly associated with bypass graft PCI. At one year after PCI, interventions including bypass grafts had a higher composite of MACE compared with isolated native vessel interventions.

Impact of coronary hyperemia on collateral flow correction of coronary microvascular resistance indices.

Recently, a novel method to estimate wedge pressure (Pw)-corrected minimal microvascular resistance (MR) was introduced. However, this method has not been validated since, and there are some theoretical concerns regarding the impact of different physiological conditions on the derivation of Pw measurements. This study sought to validate the recently introduced method to estimate Pw-corrected MR in a Doppler-derived study population and to evaluate the impact of different physiological conditions on the Pw measurements and the derivation of Pw-corrected MR. The method to derive "estimated" hyperemic microvascular resistance (HMR) without the need for Pw measurements was validated by estimating the coronary fractional flow reserve (FFRcor) from myocardial fractional flow reserve (FFRmyo) in a Doppler-derived study population (N = 53). From these patients, 24 had hyperemic Pw measurements available for the evaluation of hyperemic conditions on the derivation of Pw and its effect on the derivation of both "true" (with measured Pw) and "estimated" Pw-corrected HMR. Nonhyperemic Pw differed significantly from Pw measured in hyperemic conditions (26 ± 14 vs. 35 ± 14 mmHg, respectively, P < 0.005). Nevertheless, there was a strong linear relationship between FFRcor and FFRmyo in nonhyperemic conditions (R2 = 0.91, P < 0.005), as well as in hyperemic conditions (R2 = 0.87, P < 0.005). There was a strong linear relationship between "true" HMR and "estimated" HMR using either nonhyperemic (R2 = 0.86, P < 0.005) or hyperemic conditions (R2 = 0.85, P < 0.005) for correction. In contrast to a modest agreement between nonhyperemic Pw-corrected HMR and apparent HMR (R2 = 0.67, P < 0.005), hyperemic Pw-corrected HMR showed a strong agreement with apparent HMR (R2 = 0.88, P < 0.005). We validated the calculation method for Pw-corrected MR in a Doppler velocity-derived population. In addition, we found a significant impact of hyperemic conditions on the measurement of Pw and the derivation of Pw-corrected HMR.NEW & NOTEWORTHY The following are what is known: 1) wedge-pressure correction is often considered for the derivation of indices of minimal microvascular resistance, and 2) the Yong method for calculating wedge pressure-corrected index of microvascular resistance (IMR) without balloon inflation has never been validated in a Doppler-derived population and has not been tested under different physiological conditions. This study 1) adds validation for the Yong method for calculated wedge-pressure correction in a Doppler-derived study population and 2) shows significant influence of the physiological conditions on the derivation of coronary wedge pressure.

Treatment stability with bonded versus vacuum-formed retainers after 12 months: A randomized clinical trial.

OBJECTIVE: To compare the clinical effectiveness of V-bend bonded retainers (BR) versus vacuum-formed retainers (VFR) regarding their capacity to maintain treatment stability and survival rates after 12 months. MATERIALS AND METHODS: Patients finishing orthodontic treatment were randomly allocated into two groups. The BR group received maxillary and mandibular BRs in the lingual surfaces of the anterior teeth. The VFR group received VFRs right after fixed appliances removal. The patients were evaluated at four time-points: at fixed appliances removal (T0), after 3 (T1), 6 (T2) and 12 months (T3). In each time-point digital models were obtained and analysed with the OrthoAnalyzer™ software. Treatment stability based on occlusal outcomes and retainers' survival rates were evaluated. Intergroup comparisons were performed using Mann-Whitney U-tests. The Kaplan-Meier survival plot and the log-rank test were employed to assess the retainers' survival. RESULTS: Both BR and VFR groups included 25 patients. The groups were comparable regarding their baseline characteristics. Up to 6 months, both retainers were equally effective; however, after 12 months, BRs were more effective in maintaining the incisors' alignment in the maxilla and the mandible compared to the VFRs. No differences were noticed in the intercanine and intermolar widths, overjet and overbite. There were no differences regarding the retainers' survivability in both arches. CONCLUSIONS: BRs were more effective in maintaining the alignment of the incisors in the maxilla and mandible compared to VFRs after 12 months. Both retainers presented the same survival rates after the same period.

Higher Edmonton Frail Scale prior to transcatheter Aortic Valve Implantation is related to longer hospital stay and mortality.

BACKGROUND: International guidelines for the management of valvular heart disease recommend frailty assessment prior to Transcatheter Aortic Valve Implantation (TAVI), however there is no consensus how to assess frailty. We investigated whether frailty status assessed with the Edmonton Frail Scale (EFS, range 0-17 points) relates to length of stay (LOS), short- and long-term mortality and adverse outcomes after TAVI. METHODS: In this study we included 357 patients between April 2016 till December 2018. EFS was assessed at baseline. Patients were classified into low (0-3), intermediate (4-7) or high frailty status (8-17). LOS was defined as the number of days between admission and discharge. Mortality data were obtained up to four years after TAVI. Adverse events were defined by Valve Academic Research Consortium (VARC)-2 criteria and collected <30 days after TAVI. RESULTS: Patients with higher frailty status had longer median LOS (days (IQR): low 5 (3), intermediate 6 (4) and high 7 (5), p < 0.001) and higher mortality: low vs intermediate vs high at 30 days 0.5%, 2.2%, 7.0% (p = 0.050), 1 year 3.7%, 10.0%, 15.2% (p = 0.052), 2 years 9.2%, 17.8%, 31.7% (p = 0.003), 3 years 17.2%, 24.0, 47.0% (p = 0.001) and 4 years 19.6%, 30.8%, 55.6% (p < 0.001). Frail patients received more often a pacemaker (2.6%, 6.6%, 13.5%, p = 0.048). CONCLUSION: In clinical practice, the EFS is a useful tool to screen for frailty in TAVI patients. This tool may possibly be expanded to determine benefit versus harm-risk in these patients and whether specific pre-procedurally interventions are needed in order to reduce mortality.

Treatment of Class II malocclusion with 2-maxillary premolar extractions: Monthly vs biweekly appointments, which is more efficient?

INTRODUCTION: This study compared whether there is a difference in treatment time (TT) and efficiency when appointments are held once a month or at 2-week intervals in patients with Class II malocclusion treated with 2-premolar extractions METHODS: The patients of this retrospective sample were treated with the same orthodontic mechanics and divided into 2 groups according to frequencies of orthodontic appointments. Group 1 consisted of 18 patients (10 males, 8 females), with an initial mean age of 14.38 ± 1.38 years and appointments once a month. Group 2 consisted of 19 patients (9 males, 10 females), with an initial mean age of 14.12 ± 1.38 years and biweekly appointments. Edgewise fixed appliances with a slot size of 0.022 × 0.028 mm were used, and the anterior teeth were retracted en-masse with a rectangular wire and elastic chains. The Peer Assessment Rating and Objective Grading System indexes were measured in the dental models at the beginning and the end of treatment. Efficiency was assessed by dividing the percentage of improvement of each occlusal index concerning the multiplication of TT and the number of appointments. RESULTS: Both groups presented similar Peer Assessment Rating and Objective Grading System indexes at the end of treatment. Groups 1 and 2 presented different TTs (28.06 and 22.05 months, respectively); however, there were no differences regarding the efficiency of both protocols. CONCLUSIONS: Patients with Class II malocclusion treated with 2-maxillary premolars had significantly shorter treatment times when seen on biweekly appointments than those with monthly appointments; however, there was no difference in efficiency between protocols.

Automatic Coronary Artery Plaque Quantification and CAD-RADS Prediction Using Mesh Priors.

Coronary artery disease (CAD) remains the leading cause of death worldwide. Patients with suspected CAD undergo coronary CT angiography (CCTA) to evaluate the risk of cardiovascular events and determine the treatment. Clinical analysis of coronary arteries in CCTA comprises the identification of atherosclerotic plaque, as well as the grading of any coronary artery stenosis typically obtained through the CAD-Reporting and Data System (CAD-RADS). This requires analysis of the coronary lumen and plaque. While voxel-wise segmentation is a commonly used approach in various segmentation tasks, it does not guarantee topologically plausible shapes. To address this, in this work, we propose to directly infer surface meshes for coronary artery lumen and plaque based on a centerline prior and use it in the downstream task of CAD-RADS scoring. The method is developed and evaluated using a total of 2407 CCTA scans. Our method achieved lesion-wise volume intraclass correlation coefficients of 0.98, 0.79, and 0.85 for calcified, non-calcified, and total plaque volume respectively. Patient-level CAD-RADS categorization was evaluated on a representative hold-out test set of 300 scans, for which the achieved linearly weighted kappa ( κ ) was 0.75. CAD-RADS categorization on the set of 658 scans from another hospital and scanner led to a κ of 0.71. The results demonstrate that direct inference of coronary artery meshes for lumen and plaque is feasible, and allows for the automated prediction of routinely performed CAD-RADS categorization.