Quantitative Comparison of Coronary Artery Calcium and AI-Based Plaque Burden: Agreement, Discordance, and Clinical Implications

Quantitative Comparison of Coronary Artery Calcium and AI-Based Plaque Burden: Agreement, Discordance, and Clinical Implications | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Quantitative Comparison of Coronary Artery Calcium and AI-Based Plaque Burden: Agreement, Discordance, and Clinical Implications kyvan Irannejad, ruben Mora, Balaphanidhar Mogga, Beshoy Iskander, and 6 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8604663/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Background Coronary artery calcium (CAC) scoring quantifies calcified atherosclerosis but does not capture non-calcified plaque. Artificial intelligence (AI) – based quantitative coronary CT angiography (CCTA) enables the measurement of total plaque burden (TPB), reflecting both calcified and non-calcified components. The degree of agreement between CAC and TPB categories remains unclear. Methods We retrospectively analyzed 1,955 subjects who underwent both CAC scoring and quantitative CCTA. Subjects with CAC = 0 were excluded. CAC was categorized as 1–99, 100–299, and ≥ 300 Agatston units, while TPB was categorized as 0, 1–250, 251–750, and > 750 mm³. Agreement between CAC and TPB categories was assessed using Cohen’s weighted Kappa, and Spearman correlation evaluated the continuous relationship between CAC and TPB. Analyses were stratified by age, sex, diabetes, hypertension, and use of statins. Results Participants had a mean age of 66.5 ± 10.4 years, and 69% were male. CAC distribution was 1–99 (39%), 100–299 (20%), and ≥ 300 (41%); TPB distribution was 1–250 (67%), 251–750 (27%), and > 750 mm³ (12%). Weighted Kappa was 0.495 (95% CI 0.471–0.519), indicating moderate categorical agreement, while Spearman correlation was robust (ρ = 0.92). Agreement improved modestly when CAC cutoffs were adjusted to 1–99, 100–399, and ≥ 400 (κ = 0.535). Concordance was higher in males (κ = 0.53) than in females (κ = 0.37). Conclusions CAC and AI-derived total plaque burden demonstrate moderate categorical agreement but very strong continuous correlation, highlighting that quantitative plaque analysis captures complementary non-calcified atherosclerosis not reflected by CAC alone. Coronary calcium Computed tomography angiography Artificial intelligence Plaque quantification Atherosclerosis Cardiovascular imaging Figures Figure 1 1. Introduction Coronary artery calcium (CAC) scoring, derived from non-contrast CT, is a well-validated marker of coronary atherosclerosis and a powerful predictor of cardiovascular risk ( 1 , 2 ). CAC quantifies the extent of calcified plaque using the Agatston method and is widely used in clinical practice to refine risk stratification and guide primary prevention. However, CAC scoring detects only calcified plaque and overlooks non-calcified or lipid-rich components, which are associated with plaque vulnerability and future events ( 3 ). As a result, CAC may underestimate the overall atherosclerotic burden in populations with predominantly non-calcified disease, particularly younger individuals, women, and patients treated with statins ( 4 – 6 ). Coronary computed tomography angiography (CCTA) complements CAC scoring by visualizing both calcified and non-calcified plaques and assessing luminal stenosis ( 7 , 8 ). Recent advances in artificial intelligence (AI) have transformed CCTA interpretation, enabling automated, quantitative plaque analysis. FDA-cleared AI software such as Cleerly allows volumetric measurement of total plaque burden (TPB) across the coronary tree, providing detailed characterization of plaque morphology, composition, and distribution. These methods are reproducible, rapid, and suitable for large-scale clinical and research applications ( 9 – 12 ). Although both CAC and TPB reflect atherosclerotic burden, they quantify distinct aspects of disease biology: CAC measures the calcified end-stage component, while TPB represents the aggregate of calcified and non-calcified plaque volume. Whether CAC categories correspond closely to TPB categories remains uncertain. Prior work has demonstrated that individuals with zero or low CAC may still harbor significant non-calcified plaque, yet the categorical concordance between these measures across broader CAC ranges has not been systematically examined ( 12 – 14 ). This study aimed to evaluate the agreement between CAC score categories and AI-derived TPB categories in a large real-world cohort. We hypothesized that CAC and TPB would show strong continuous correlation but only moderate categorical agreement, reflecting the additional contribution of non-calcified plaque. Secondary analyses explored whether agreement varied by demographic or clinical characteristics, including sex, age, diabetes mellitus, hypertension, and statin use. 2. Methods 2.1 Study Population This retrospective analysis included 1,955 consecutive subjects who underwent both CAC scanning and CCTA at the Lundquist Institute at Harbor-UCLA Medical Center. Patients were referred for evaluation of coronary atherosclerosis or risk assessment. Exclusion criteria included prior coronary revascularization (percutaneous coronary intervention or bypass surgery), incomplete imaging data, or technically inadequate studies. To focus on individuals with measurable calcification, subjects with CAC = 0 were excluded. Clinical variables, including age, sex, diabetes mellitus (DM), hypertension (HTN), and statin use, were extracted from medical records. The study was approved by the institutional review board, and informed consent was waived due to the retrospective design. 2.2 Imaging Protocols All scans were performed using 256 GE Revolution CT scanners with prospective ECG-gating. CAC scoring was acquired with non-contrast imaging (120 kVp, 2.5 mm slice thickness) and quantified using the Agatston method. CCTA was performed using iodinated contrast (80–100 mL) with dose-modulated protocols optimized for heart rate control (target < 65 bpm) using oral or intravenous beta-blockers. Sublingual nitroglycerin was administered before image acquisition. 2.3 Quantitative Plaque Analysis AI-based quantitative analysis was conducted using Cleerly (Cleerly Inc., New York, NY), which automatically segments coronary arteries, identifies plaque components, and quantifies volumetric plaque measures (mm³). TPB was defined as the sum of all calcified, fibrous, and lipid-rich plaque volumes across major coronary vessels. The software has been previously validated against expert manual assessment and intravascular reference standards. 2.4 Categorization of CAC and Total Plaque Burden CAC was categorized as 1–99, 100–299, and ≥ 300 Agatston units. A secondary analysis was performed with adjusted cutoffs of 1–99, 100–399, and ≥ 400. TPB was categorized as 0, 1–250, 251–750, or > 750 mm³. Continuous variables were expressed as mean ± standard deviation, and categorical variables as counts and percentages. Agreement between CAC and TPB categories was evaluated using Cohen’s weighted Kappa (κ) with 95% confidence intervals. The strength of agreement was defined as poor ( 0.80). The continuous relationship between CAC and TPB was assessed using Spearman’s rank correlation coefficient (ρ). Subgroup analyses were performed stratified by age, sex, diabetes, hypertension, and statin use. Statistical significance was set at a two-tailed p < 0.05. 2.5 Statistical Analysis Continuous variables were expressed as mean ± standard deviation (SD), and categorical variables as frequencies and percentages. Agreement between CAC and TPB categories was quantified using Cohen’s weighted Kappa (κ) with 95% confidence intervals. Kappa values were interpreted as follows: poor ( 0.80). The correlation between continuous CAC and TPB values was assessed using Spearman’s rank correlation coefficient (ρ). Subgroup analyses were conducted by age (≤ 63.9 vs > 63.9 years), sex, presence of diabetes or hypertension, and statin use. All analyses were performed using SPSS version 29 (IBM Corp., Armonk, NY). A two-tailed p-value < 0.05 was considered statistically significant. 3. Results 3.1 Baseline Characteristics Among 1,955 subjects, the mean age was 66.5 ± 10.4 years, and 69% were male. Diabetes mellitus was present in 16%, hypertension in 54%, and 68% were on statin therapy. Demographic and clinical characteristics are summarized in Table 1 . Table 1 Baseline Demographic and Clinical Characteristics of the Study Population (N = 1,955) Characteristic Value Age, years 66.5 ± 10.4 Male sex 1,350 (69%) Diabetes mellitus 304 (16%) Hypertension 1,048 (54%) Statin therapy 1,327 (68%) Non-statin therapy 627 (32%) CAC score categories 1–99 765 (39%) 100–299 391 (20%) ≥300 799 (41%) Total plaque burden categories 1–250 mm³ 1,309 (67%) 251–750 mm³ 528 (27%) > 750 mm³ 118 (6%) 3.2 Distribution of CAC and Total Plaque Burden The categorical distributions of Coronary Artery Calcium (CAC) and Total Plaque Burden (TPB) are summarized in Table 2 . Among the study population, 39% had CAC scores between 1–99, 20% fell within the 100–299 range, and 41% had scores ≥ 300. In comparison, TPB was distributed as follows: 67% of individuals had a burden between 1–250 mm³, 27% fell within the 251–750 mm³ range, and 12% had total plaque volumes exceeding 750 mm³. Table 2 Distribution of Coronary Artery Calcium (CAC) and Total Plaque Burden (TPB) Categories Measure Category Frequency (%) CAC 1–99 765 (39%) CAC 100–299 391 (20%) CAC ≥ 300 799 (41%) TPB 1–250 mm³ 1,309 (67%) TPB 251–750 mm³ 528 (27%) TPB > 750 mm³ 118 (6%) 3.3 Agreement Between CAC and TPB Categories Overall, weighted Kappa was 0.495 (95% CI 0.471–0.519), representing moderate agreement between CAC and TPB categories. When CAC thresholds were adjusted to 1–99, 100–399, and ≥ 400, Kappa increased modestly to 0.535 (95% CI 0.511–0.559). Spearman correlation between continuous CAC and TPB was very strong (ρ = 0.92, p < 0.001). 3.4 Subgroup Analyses We assessed the categorical agreement between Coronary Artery Calcium (CAC) categories and AI-derived Total Plaque Burden (TPB) across clinically relevant subgroups using Cohen’s weighted Kappa statistic. The overall agreement was moderate (κ ≈ 0.50), with notable variability based on age, sex, and cardiovascular risk factors. Agreement was slightly higher in older individuals (age > 63.9 years) compared to those ≤ 63.9 years, suggesting better concordance between calcification and total plaque burden in more advanced disease. Patients on statin therapy also demonstrated higher Kappa values than those not receiving statins, consistent with statin-associated promotion of plaque calcification. Conversely, individuals without statin use, diabetes, or hypertension exhibited wider confidence intervals and lower Kappa values, indicating greater discordance between CAC and total plaque burden. Sex-based differences were particularly prominent. Female participants showed the lowest categorical agreement (κ < 0.45), reflecting the higher prevalence of non-calcified plaque in women and reinforcing the limitations of relying solely on CAC for risk assessment in this population. These subgroup differences are visually summarized in Fig. 1 , which displays Kappa estimates with 95% confidence intervals for each clinical category. 4. Discussion 4.1 Principal Findings In this large, single-center study of nearly 2,000 patients undergoing both CAC scoring and AI-enabled quantitative CCTA, we observed a moderate categorical agreement (κ ≈ 0.50) but very strong continuous correlation (ρ = 0.92) between CAC scores and total plaque burden (TPB). This dichotomy highlights an important clinical insight: although CAC and TPB both aim to quantify the extent of coronary atherosclerosis, they do so through fundamentally different lenses. The moderate categorical overlap implies that applying discrete risk thresholds (e.g., CAC > 100, TPB > 250 mm³) may not reliably classify the same individuals into concordant risk categories, underscoring the potential for clinically meaningful discordance in plaque assessment ( 15 , 16 ). 4.2 Interpretation The discrepancy in categorical agreement stems from the inherent limitation of CAC: it detects only calcified plaque, neglecting the fibrous and lipid-rich components that characterize earlier and potentially more vulnerable stages of atherosclerosis ( 17 , 18 ). Consequently, two patients with identical CAC scores (e.g., CAC = 100) may have markedly different atherosclerotic burdens if one harbors predominantly non-calcified plaque. This limitation is especially pertinent in younger individuals and women, where non-calcified plaque tends to predominate ( 19 – 21 ). The strong continuous correlation (ρ = 0.92) suggests that overall plaque accumulation, both calcified and non-calcified, tends to progress in tandem, but the observed categorical misalignment indicates that a single metric may miss important nuances in disease characterization ( 22 , 23 ). Importantly, these findings reaffirm that CAC and TPB are complementary rather than interchangeable. CAC provides a surrogate of disease chronicity and stability, while AI-based TPB offers a more nuanced, volumetric, and compositional view of the full atherosclerotic landscape. 4.3 Sex and Statin Differences Sex-specific analysis revealed lower agreement in women, consistent with known differences in plaque biology. Prior research has demonstrated that women tend to exhibit less calcified and more non-calcified plaque than men at equivalent levels of overall atherosclerosis. This contributes to the underestimation of risk when relying solely on CAC scores in female populations ( 24 – 27 ). Similarly, statin therapy may alter the CAC–TPB relationship. Statins promote plaque stabilization and calcification, a phenomenon referred to as the “statin paradox,” where CAC increases due to plaque healing, despite overall risk reduction. This transformation of non-calcified plaque into denser, more calcified forms can lead to an apparent “discrepancy” between high CAC and low-risk morphology. Conversely, patients on long-term statin therapy may show elevated CAC despite relatively modest TPB. Recognizing these modifying effects is critical when interpreting imaging results in both clinical and research settings ( 28 – 31 ). 4.4 Comparison with Previous Literature Our results corroborate prior observations from the Multi-Ethnic Study of Atherosclerosis (MESA), which revealed that up to 15% of individuals with CAC = 0 may still harbor non-calcified plaque detectable by CCTA. Similarly, Budoff et al. and Williams et al. demonstrated that total plaque burden assessed by CCTA, especially lipid-rich or low-attenuation plaque, is independently predictive of major adverse cardiovascular events (MACE), even in the absence of CAC ( 32 , 33 ). By explicitly quantifying categorical agreement using weighted Kappa statistics, our study extends this literature, offering a formal metric for the degree of concordance between these two commonly used imaging biomarkers. This benchmark may help frame future studies assessing integrated risk models that combine CAC and AI-derived plaque metrics. 4.5 Clinical Implications Our findings have several important clinical implications. First, they validate the incremental value of AI-enabled CCTA in detecting subclinical atherosclerosis that may be invisible to calcium scoring alone. In an era of precision prevention, where cardiovascular risk stratification increasingly guides therapeutic intensity, failing to identify patients with high non-calcified plaque burden could delay timely intervention. Second, in patients with discordant findings, for instance, low or zero CAC but elevated TPB, physicians may consider intensifying lifestyle or pharmacologic therapy. Conversely, high CAC with low TPB may prompt further evaluation of plaque morphology or stability, rather than immediate escalation of therapy. This nuanced interpretation allows for a more tailored approach to preventive cardiology, avoiding both over- and under-treatment. Finally, with growing availability and regulatory approval of AI-based tools, integration of TPB analysis into routine clinical workflows may become feasible and cost-effective, especially when bundled with routine CCTA performed for other indications (e.g., evaluation of chest pain). Combining CAC and TPB may enable multi-dimensional risk profiling, which better captures both plaque quantity and quality ( 34 – 36 ). 4.6 Limitations Several limitations merit consideration. This was a retrospective, single-center study without follow-up outcomes; thus, prognostic implications could not be assessed. CAC = 0 subjects were excluded, limiting generalizability to early subclinical disease. Imaging was performed on different CT systems, although standardized acquisition protocols were used. AI-derived plaque quantification depends on image quality and reconstruction parameters, which could introduce variability. Future multicenter studies should validate these findings across diverse populations and correlate CAC–TPB discordance with cardiovascular events. 4.7 Future Directions Defining plaque volume thresholds corresponding to “low-risk” or “trivial” disease, analogous to CAC = 0, could enhance the interpretation of AI-derived metrics. Longitudinal analyses integrating CAC and TPB progression may further elucidate how plaque transformation, from non-calcified to calcified, relates to clinical outcomes. Combining AI-based plaque quantification with traditional calcium scoring has the potential to refine risk prediction models and optimize preventive therapy allocation. 5. Conclusion Although CAC and AI-derived TPB demonstrate a strong continuous correlation, their categorical agreement is only moderate, highlighting important differences in what each metric captures. CAC quantifies only calcified atherosclerosis, whereas AI-enabled CCTA offers a comprehensive volumetric assessment of both calcified and non-calcified plaque. This discrepancy is particularly relevant in populations such as women, younger individuals, and statin users, where non-calcified plaque may predominate, or calcification may not reflect overall disease burden. Our findings underscore the complementary nature of CAC and AI-based TPB assessment. While CAC remains a valuable screening tool, particularly for asymptomatic risk stratification, quantitative plaque analysis via CCTA provides additional insights into early and potentially high-risk atherosclerotic disease that may be missed by calcium scoring alone. Incorporating both modalities into clinical practice and research frameworks may lead to more personalized, accurate cardiovascular risk assessment and prevention strategies. Declarations Ethics Approval and Consent to Participate: This study was conducted in accordance with the ethical principles outlined in the Declaration of Helsinki. The study protocol was reviewed and approved by the Institutional Review Board of The Lundquist Institute at Harbor-UCLA Medical Center. Given the retrospective nature of the study and use of de-identified data, the requirement for informed consent was waived by the Institutional Review Board. Conflicts of Interest: The authors declare no conflicts of interest . Funding: This research received no external funding . Author Contribution K.I. conceived and designed the study, performed data analysis and interpretation, and drafted the initial manuscript.R.M., B.M., B.I., and N.P. contributed to data acquisition and curation.A.K. assisted with data management and statistical support.S.K., S.L., and S.R. contributed to the interpretation of results and critically revised the manuscript for important intellectual content.M.B. provided overall study supervision, conceptual guidance, and critical revision of the manuscript.All authors reviewed and approved the final manuscript and agree to be accountable for all aspects of the work. Acknowledgments The authors acknowledge institutional support from The Lundquist Institute for Biomedical Innovation at Harbor-UCLA Medical Center . No external grants or funding were received for this study. Data Availability The data that support the findings of this study are available from the corresponding author upon reasonable request. The data are not publicly available due to institutional restrictions and the inclusion of protected health information. References Budoff M, Backlund J-YC, Bluemke DA, Polak J, Bebu I, Schade D et al (2019) The association of coronary artery calcification with subsequent incidence of cardiovascular disease in type 1 diabetes: the DCCT/EDIC trials. JACC Cardiovasc Imaging 12(7 Pt 2):1341–1349 Masrouri S, Shapiro MD, Khalili D, Hadaegh F (2024) Impact of coronary artery calcium on mortality and cardiovascular events in metabolic syndrome and diabetes among younger adults. Eur J Prev Cardiol 31(6):744–753 Theofilis P, Sagris M, Antonopoulos AS, Oikonomou E, Tsioufis K, Tousoulis D (2022) Non-Invasive Modalities in the Assessment of Vulnerable Coronary Atherosclerotic Plaques. Tomography 8(4):1742–1758 Suzuki K, Kinoshita D, Yuki H, Niida T, Sugiyama T, Yonetsu T et al (2024) Higher noncalcified plaque volume is associated with increased plaque vulnerability and vascular inflammation. Circ Cardiovasc Imaging 17(1):e015769 Alyami B, Santer M, Seetharam K, Velu D, Gadde E, Patel B et al (2023) Non-Calcified Coronary Artery Plaque on Coronary Computed Tomography Angiogram: Prevalence and Significance. Tomography 9(5):1755–1771 Onnis C, Virmani R, Kawai K, Nardi V, Lerman A, Cademartiri F et al (2024) Coronary artery calcification: current concepts and clinical implications. Circulation 149(3):251–266 Weng T, Ding D, Li G, Guan S, Han W, Gan Q et al (2024) Accuracy of coronary computed tomography angiography-derived quantitative flow ratio for onsite assessment of coronary lesions. EuroIntervention 20(20):e1288–e1297 Vatsa N, Faaborg-Andersen C, Dong T, Blaha MJ, Shaw LJ, Quintana RA (2024) Coronary atherosclerotic plaque burden assessment by computed tomography and its clinical implications. Circ Cardiovasc Imaging 17(8):e016443 Wang T-W, Tzeng Y-H, Wu K-T, Liu H-R, Hong J-S, Hsu H-Y et al (2024) Meta-analysis of deep learning approaches for automated coronary artery calcium scoring: Performance and clinical utility AI in CAC scoring: A meta-analysis: AI in CAC scoring: A meta-analysis. Comput Biol Med 183:109295 Khan H, Bansal K, Griffin WF, Cantlay C, Sidahmed A, Nurmohamed NS et al (2024) Assessment of atherosclerotic plaque burden: comparison of AI-QCT versus SIS, CAC, visual and CAD-RADS stenosis categories. Int J Cardiovasc Imaging 40(6):1201–1209 Nurmohamed NS, Bom MJ, Jukema RA, de Groot RJ, Driessen RS, van Diemen PA et al (2024) AI-Guided Quantitative Plaque Staging Predicts Long-Term Cardiovascular Outcomes in Patients at Risk for Atherosclerotic CVD. JACC Cardiovasc Imaging 17(3):269–280 Choi AD, Marques H, Kumar V, Griffin WF, Rahban H, Karlsberg RP et al (2021) CT ​Evaluation ​by ​Artificial ​Intelligence ​for ​Atherosclerosis, Stenosis and Vascular ​Morphology ​(CLARIFY): ​A ​Multi-center, international study. J Cardiovasc Comput Tomogr 15(6):470–476 Ghazal R, Bawa D, Ahmed A, Lakkireddy D, Singh V (2024) The zero calcium score paradox. JACC Case Rep 29(5):102233 Blaha MJ, Cainzos-Achirica M, Greenland P, McEvoy JW, Blankstein R, Budoff MJ et al (2016) Role of Coronary Artery Calcium Score of Zero and Other Negative Risk Markers for Cardiovascular Disease: The Multi-Ethnic Study of Atherosclerosis (MESA). Circulation 133(9):849–858 Kambalapalli S, Bhandari M, Punnanithinont N, Iskander B, Khan MA, Budoff M (2025) Bridging prevention and imaging: the influence of statins on CAC and CCTA findings. Curr Atheroscler Rep 27(1):50 Nezarat N, Budoff MJ, Luo Y, Darabian S, Nakanishi R, Li D et al (2017) Presence, characteristics, and volumes of coronary plaque determined by computed tomography angiography in young type 2 diabetes mellitus. Am J Cardiol 119(10):1566–1571 Detrano R, Guerci AD, Carr JJ, Bild DE, Burke G, Folsom AR et al (2008) Coronary calcium as a predictor of coronary events in four racial or ethnic groups. N Engl J Med 358(13):1336–1345 Chartrand-Lefebvre C, Cadrin-Chênevert A, Bordeleau E, Ugolini P, Ouellet R, Sablayrolles J-L et al (2007) Coronary computed tomography angiography: overview of technical aspects, current concepts, and perspectives. Can Assoc Radiol J 58(2):92–108 Osborne-Grinter M, Kwiecinski J, Doris M, McElhinney P, Cadet S, Adamson PD et al (2022) Association of coronary artery calcium score with qualitatively and quantitatively assessed adverse plaque on coronary CT angiography in the SCOT-HEART trial. Eur Heart J Cardiovasc Imaging 23(9):1210–1221 Blaha MJ, Nasir K, Rivera JJ, Choi E-K, Chang S-A, Yoon YE et al (2009) Gender differences in coronary plaque composition by coronary computed tomography angiography. Coron Artery Dis 20(8):506–512 Hecht HS (2015) Coronary artery calcium scanning: past, present, and future. JACC Cardiovasc Imaging 8(5):579–596 Dey D, Schepis T, Marwan M, Slomka PJ, Berman DS, Achenbach S (2010) Automated three-dimensional quantification of noncalcified coronary plaque from coronary CT angiography: comparison with intravascular US. Radiology 257(2):516–522 Ambale-Venkatesh B, Yang X, Wu CO, Liu K, Hundley WG, McClelland R et al (2017) Cardiovascular Event Prediction by Machine Learning: The Multi-Ethnic Study of Atherosclerosis. Circ Res 121(9):1092–1101 Plank F, Beyer C, Friedrich G, Wildauer M, Feuchtner G (2019) Sex differences in coronary artery plaque composition detected by coronary computed tomography: quantitative and qualitative analysis. Neth Heart J 27(5):272–280 Lansky AJ, Ng VG, Maehara A, Weisz G, Lerman A, Mintz GS et al (2012) Gender and the extent of coronary atherosclerosis, plaque composition, and clinical outcomes in acute coronary syndromes. JACC Cardiovasc Imaging 5(3 Suppl):S62–72 Garg K, Patel TR, Kanwal A, Villines TC, Aggarwal NR, Nasir K et al (2022) The evolving role of coronary computed tomography in understanding sex differences in coronary atherosclerosis. J Cardiovasc Comput Tomogr 16(2):138–149 Chandrasekhar J, Mehran R (2016) Sex-Based Differences in Acute Coronary Syndromes: Insights From Invasive and Noninvasive Coronary Technologies. JACC Cardiovasc Imaging 9(4):451–464 Puri R, Nicholls SJ, Shao M, Kataoka Y, Uno K, Kapadia SR et al (2015) Impact of statins on serial coronary calcification during atheroma progression and regression. J Am Coll Cardiol 65(13):1273–1282 Henein MY, Owen A (2011) Statins moderate coronary stenoses but not coronary calcification: results from meta-analyses. Int J Cardiol 153(1):31–35 Ueki Y, Itagaki T, Kuwahara K (2024) Lipid-lowering Therapy and Coronary Plaque Regression. J Atheroscler Thromb 31(11):1479–1495 Ferencik M, Chatzizisis YS (2015) Statins and the coronary plaque calcium paradox: Insights from non-invasive and invasive imaging. Atherosclerosis 241(2):783–785 Williams MC, Kwiecinski J, Doris M, McElhinney P, D’Souza MS, Cadet S et al (2020) Low-Attenuation Noncalcified Plaque on Coronary Computed Tomography Angiography Predicts Myocardial Infarction: Results From the Multicenter SCOT-HEART Trial (Scottish Computed Tomography of the HEART). Circulation 141(18):1452–1462 Budoff MJ, Dowe D, Jollis JG, Gitter M, Sutherland J, Halamert E et al (2008) Diagnostic performance of 64-multidetector row coronary computed tomographic angiography for evaluation of coronary artery stenosis in individuals without known coronary artery disease: results from the prospective multicenter ACCURACY (Assessment by Coronary Computed Tomographic Angiography of Individuals Undergoing Invasive Coronary Angiography) trial. J Am Coll Cardiol 52(21):1724–1732 Ihdayhid AR, Tzimas G, Peterson K, Ng N, Mirza S, Maehara A et al (2024) Diagnostic Performance of AI-enabled Plaque Quantification from Coronary CT Angiography Compared with Intravascular Ultrasound. Radiol Cardiothorac Imaging 6(6):e230312 Tsiachristas A, Chan K, Wahome E, Kearns B, Patel P, Lyasheva M et al (2025) Cost-effectiveness of a novel AI technology to quantify coronary inflammation and cardiovascular risk in patients undergoing routine coronary computed tomography angiography. Eur Heart J Qual Care Clin Outcomes 11(4):434–444 van Velzen SGM, Dobrolinska MM, Knaapen P, van Herten RLM, Jukema R, Danad I et al (2023) Automated cardiovascular risk categorization through AI-driven coronary calcium quantification in cardiac PET acquired attenuation correction CT. J Nucl Cardiol 30(3):955–969 Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8604663","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":577700803,"identity":"2c14f56c-e497-4037-906b-1bdc5b8eb90b","order_by":0,"name":"kyvan Irannejad","email":"data:image/png;base64,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","orcid":"","institution":"The Lundquist Institute","correspondingAuthor":true,"prefix":"","firstName":"kyvan","middleName":"","lastName":"Irannejad","suffix":""},{"id":577700805,"identity":"5ae15c2d-733e-4480-857d-bc92b17e9d8e","order_by":1,"name":"ruben Mora","email":"","orcid":"","institution":"The Lundquist Institute","correspondingAuthor":false,"prefix":"","firstName":"ruben","middleName":"","lastName":"Mora","suffix":""},{"id":577700806,"identity":"d25087f9-67c4-4c1c-80be-f111dc1e3e59","order_by":2,"name":"Balaphanidhar Mogga","email":"","orcid":"","institution":"The Lundquist Institute","correspondingAuthor":false,"prefix":"","firstName":"Balaphanidhar","middleName":"","lastName":"Mogga","suffix":""},{"id":577700807,"identity":"1a1f6e9b-acbb-4308-866a-165972426450","order_by":3,"name":"Beshoy Iskander","email":"","orcid":"","institution":"The Lundquist Institute","correspondingAuthor":false,"prefix":"","firstName":"Beshoy","middleName":"","lastName":"Iskander","suffix":""},{"id":577700808,"identity":"5d84f11a-8cba-459a-b6dd-ae6752428074","order_by":4,"name":"Natdanai punnanithinont","email":"","orcid":"","institution":"The Lundquist Institute","correspondingAuthor":false,"prefix":"","firstName":"Natdanai","middleName":"","lastName":"punnanithinont","suffix":""},{"id":577700809,"identity":"a4a9f85b-1107-4f7c-8e51-f5e32e180c44","order_by":5,"name":"April Kinninger","email":"","orcid":"","institution":"The Lundquist Institute","correspondingAuthor":false,"prefix":"","firstName":"April","middleName":"","lastName":"Kinninger","suffix":""},{"id":577700810,"identity":"234f7b59-d19d-46e0-a2f4-37bd2fdf315d","order_by":6,"name":"Srikanth Krishnan","email":"","orcid":"","institution":"The Lundquist Institute","correspondingAuthor":false,"prefix":"","firstName":"Srikanth","middleName":"","lastName":"Krishnan","suffix":""},{"id":577700813,"identity":"1e7d7f70-fd65-4471-ad52-b7ffd31d67ac","order_by":7,"name":"Suvasini Lakshmanan","email":"","orcid":"","institution":"The Lundquist Institute","correspondingAuthor":false,"prefix":"","firstName":"Suvasini","middleName":"","lastName":"Lakshmanan","suffix":""},{"id":577700814,"identity":"234b188f-5e07-4d2c-a2ef-3e9e16554745","order_by":8,"name":"Sion Roy","email":"","orcid":"","institution":"The Lundquist Institute","correspondingAuthor":false,"prefix":"","firstName":"Sion","middleName":"","lastName":"Roy","suffix":""},{"id":577700815,"identity":"dc23f788-78af-4813-9562-735e881ac6a5","order_by":9,"name":"Matthew Budoff","email":"","orcid":"","institution":"The Lundquist Institute","correspondingAuthor":false,"prefix":"","firstName":"Matthew","middleName":"","lastName":"Budoff","suffix":""}],"badges":[],"createdAt":"2026-01-14 19:23:05","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8604663/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8604663/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":100951028,"identity":"44753ec5-9e33-4237-a9d5-6c552efff15c","added_by":"auto","created_at":"2026-01-23 07:09:51","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3217147,"visible":true,"origin":"","legend":"","description":"","filename":"EditedCACCleerlyManuscript.docx","url":"https://assets-eu.researchsquare.com/files/rs-8604663/v1/8d5cc1b2dafeaee22c8f85fb.docx"},{"id":100896807,"identity":"71f43fa6-28da-4351-a9f6-3c38fb67a7a2","added_by":"auto","created_at":"2026-01-22 14:17:35","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":11303,"visible":true,"origin":"","legend":"","description":"","filename":"2aaaa4eaa5674bfe8e4f7c1b0f222140.json","url":"https://assets-eu.researchsquare.com/files/rs-8604663/v1/1e540c0b54ae96ad732b8fba.json"},{"id":100896810,"identity":"b23fd17e-3cbb-49a5-8662-a7a0f979d1c0","added_by":"auto","created_at":"2026-01-22 14:17:35","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":90457,"visible":true,"origin":"","legend":"","description":"","filename":"2aaaa4eaa5674bfe8e4f7c1b0f2221401enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8604663/v1/bdc77438134f994f132f6312.xml"},{"id":100951011,"identity":"98ee4af1-1b6f-437c-adde-89a7ab423c2b","added_by":"auto","created_at":"2026-01-23 07:09:50","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":24779,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8604663/v1/9af97306499e09a39f13edfa.png"},{"id":100949809,"identity":"ac0b61e7-1f6a-4d76-b15b-bf3f8ef1070a","added_by":"auto","created_at":"2026-01-23 07:05:49","extension":"xml","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":88694,"visible":true,"origin":"","legend":"","description":"","filename":"2aaaa4eaa5674bfe8e4f7c1b0f2221401structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8604663/v1/8365261283da3a81eb3dd8d3.xml"},{"id":100896808,"identity":"c2a4e74e-ca69-443a-a0e4-8acc160886a0","added_by":"auto","created_at":"2026-01-22 14:17:35","extension":"html","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":99172,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8604663/v1/381e6ea1faa8bdc1ccfc1016.html"},{"id":100949780,"identity":"4474ac8f-4bcb-40d7-a0d1-f9de52320233","added_by":"auto","created_at":"2026-01-23 07:05:37","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":112112,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eQuantitative Comparison of Coronary Artery Calcium and AI-Based Plaque Burden: Agreement, Discordance, and Clinical Implications\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8604663/v1/05ec8de2b897db2bf7405a8f.png"},{"id":101704177,"identity":"60206e63-3920-47ef-b6d1-2df65738ac8d","added_by":"auto","created_at":"2026-02-02 18:55:26","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":925876,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8604663/v1/c0c3c4d0-6c7b-48c1-a313-c7840e2fc8ff.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Quantitative Comparison of Coronary Artery Calcium and AI-Based Plaque Burden: Agreement, Discordance, and Clinical Implications","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eCoronary artery calcium (CAC) scoring, derived from non-contrast CT, is a well-validated marker of coronary atherosclerosis and a powerful predictor of cardiovascular risk (\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e). CAC quantifies the extent of calcified plaque using the Agatston method and is widely used in clinical practice to refine risk stratification and guide primary prevention. However, CAC scoring detects only calcified plaque and overlooks non-calcified or lipid-rich components, which are associated with plaque vulnerability and future events (\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e). As a result, CAC may underestimate the overall atherosclerotic burden in populations with predominantly non-calcified disease, particularly younger individuals, women, and patients treated with statins (\u003cspan additionalcitationids=\"CR5\" citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eCoronary computed tomography angiography (CCTA) complements CAC scoring by visualizing both calcified and non-calcified plaques and assessing luminal stenosis (\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e). Recent advances in artificial intelligence (AI) have transformed CCTA interpretation, enabling automated, quantitative plaque analysis. FDA-cleared AI software such as Cleerly allows volumetric measurement of total plaque burden (TPB) across the coronary tree, providing detailed characterization of plaque morphology, composition, and distribution. These methods are reproducible, rapid, and suitable for large-scale clinical and research applications (\u003cspan additionalcitationids=\"CR10 CR11\" citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eAlthough both CAC and TPB reflect atherosclerotic burden, they quantify distinct aspects of disease biology: CAC measures the calcified end-stage component, while TPB represents the aggregate of calcified and non-calcified plaque volume. Whether CAC categories correspond closely to TPB categories remains uncertain. Prior work has demonstrated that individuals with zero or low CAC may still harbor significant non-calcified plaque, yet the categorical concordance between these measures across broader CAC ranges has not been systematically examined (\u003cspan additionalcitationids=\"CR13\" citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eThis study aimed to evaluate the agreement between CAC score categories and AI-derived TPB categories in a large real-world cohort. We hypothesized that CAC and TPB would show strong continuous correlation but only moderate categorical agreement, reflecting the additional contribution of non-calcified plaque. Secondary analyses explored whether agreement varied by demographic or clinical characteristics, including sex, age, diabetes mellitus, hypertension, and statin use.\u003c/p\u003e"},{"header":"2. Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003e2.1 Study Population\u003c/h2\u003e \u003cp\u003eThis retrospective analysis included 1,955 consecutive subjects who underwent both CAC scanning and CCTA at the Lundquist Institute at Harbor-UCLA Medical Center. Patients were referred for evaluation of coronary atherosclerosis or risk assessment. Exclusion criteria included prior coronary revascularization (percutaneous coronary intervention or bypass surgery), incomplete imaging data, or technically inadequate studies. To focus on individuals with measurable calcification, subjects with CAC\u0026thinsp;=\u0026thinsp;0 were excluded.\u003c/p\u003e \u003cp\u003eClinical variables, including age, sex, diabetes mellitus (DM), hypertension (HTN), and statin use, were extracted from medical records. The study was approved by the institutional review board, and informed consent was waived due to the retrospective design.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e2.2 Imaging Protocols\u003c/h2\u003e \u003cp\u003eAll scans were performed using 256 GE Revolution CT scanners with prospective ECG-gating. CAC scoring was acquired with non-contrast imaging (120 kVp, 2.5 mm slice thickness) and quantified using the Agatston method. CCTA was performed using iodinated contrast (80\u0026ndash;100 mL) with dose-modulated protocols optimized for heart rate control (target\u0026thinsp;\u0026lt;\u0026thinsp;65 bpm) using oral or intravenous beta-blockers. Sublingual nitroglycerin was administered before image acquisition.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003e2.3 Quantitative Plaque Analysis\u003c/h2\u003e \u003cp\u003eAI-based quantitative analysis was conducted using Cleerly (Cleerly Inc., New York, NY), which automatically segments coronary arteries, identifies plaque components, and quantifies volumetric plaque measures (mm\u0026sup3;). TPB was defined as the sum of all calcified, fibrous, and lipid-rich plaque volumes across major coronary vessels. The software has been previously validated against expert manual assessment and intravascular reference standards.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003e2.4 Categorization of CAC and Total Plaque Burden\u003c/h2\u003e \u003cp\u003eCAC was categorized as 1\u0026ndash;99, 100\u0026ndash;299, and \u0026ge;\u0026thinsp;300 Agatston units. A secondary analysis was performed with adjusted cutoffs of 1\u0026ndash;99, 100\u0026ndash;399, and \u0026ge;\u0026thinsp;400. TPB was categorized as 0, 1\u0026ndash;250, 251\u0026ndash;750, or \u0026gt;\u0026thinsp;750 mm\u0026sup3;.\u003c/p\u003e \u003cp\u003eContinuous variables were expressed as mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation, and categorical variables as counts and percentages. Agreement between CAC and TPB categories was evaluated using Cohen\u0026rsquo;s weighted Kappa (κ) with 95% confidence intervals. The strength of agreement was defined as poor (\u0026lt;\u0026thinsp;0.20), fair (0.21\u0026ndash;0.40), moderate (0.41\u0026ndash;0.60), substantial (0.61\u0026ndash;0.80), or almost perfect (\u0026gt;\u0026thinsp;0.80). The continuous relationship between CAC and TPB was assessed using Spearman\u0026rsquo;s rank correlation coefficient (ρ). Subgroup analyses were performed stratified by age, sex, diabetes, hypertension, and statin use. Statistical significance was set at a two-tailed p\u0026thinsp;\u0026lt;\u0026thinsp;0.05.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003e2.5 Statistical Analysis\u003c/h2\u003e \u003cp\u003eContinuous variables were expressed as mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation (SD), and categorical variables as frequencies and percentages. Agreement between CAC and TPB categories was quantified using Cohen\u0026rsquo;s weighted Kappa (κ) with 95% confidence intervals. Kappa values were interpreted as follows: poor (\u0026lt;\u0026thinsp;0.20), fair (0.21\u0026ndash;0.40), moderate (0.41\u0026ndash;0.60), substantial (0.61\u0026ndash;0.80), and almost perfect (\u0026gt;\u0026thinsp;0.80). The correlation between continuous CAC and TPB values was assessed using Spearman\u0026rsquo;s rank correlation coefficient (ρ). Subgroup analyses were conducted by age (\u0026le;\u0026thinsp;63.9 vs\u0026thinsp;\u0026gt;\u0026thinsp;63.9 years), sex, presence of diabetes or hypertension, and statin use. All analyses were performed using SPSS version 29 (IBM Corp., Armonk, NY). A two-tailed p-value\u0026thinsp;\u0026lt;\u0026thinsp;0.05 was considered statistically significant.\u003c/p\u003e \u003c/div\u003e"},{"header":"3. Results","content":"\u003cdiv id=\"Sec9\" class=\"Section2\"\u003e \u003ch2\u003e3.1 Baseline Characteristics\u003c/h2\u003e \u003cp\u003eAmong 1,955 subjects, the mean age was 66.5\u0026thinsp;\u0026plusmn;\u0026thinsp;10.4 years, and 69% were male. Diabetes mellitus was present in 16%, hypertension in 54%, and 68% were on statin therapy. Demographic and clinical characteristics are summarized in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eBaseline Demographic and Clinical Characteristics of the Study Population (N\u0026thinsp;=\u0026thinsp;1,955)\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"2\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCharacteristic\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eValue\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge, years\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e66.5\u0026thinsp;\u0026plusmn;\u0026thinsp;10.4\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMale sex\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1,350 (69%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDiabetes mellitus\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e304 (16%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHypertension\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1,048 (54%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eStatin therapy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1,327 (68%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNon-statin therapy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e627 (32%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eCAC score categories\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e1\u0026ndash;99\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e765 (39%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e100\u0026ndash;299\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e391 (20%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026ge;300\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e799 (41%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eTotal plaque burden categories\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e1\u0026ndash;250 mm\u0026sup3;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1,309 (67%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e251\u0026ndash;750 mm\u0026sup3;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e528 (27%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026gt;\u0026thinsp;750 mm\u0026sup3;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e118 (6%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec10\" class=\"Section2\"\u003e \u003ch2\u003e3.2 Distribution of CAC and Total Plaque Burden\u003c/h2\u003e \u003cp\u003eThe categorical distributions of Coronary Artery Calcium (CAC) and Total Plaque Burden (TPB) are summarized in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. Among the study population, 39% had CAC scores between 1\u0026ndash;99, 20% fell within the 100\u0026ndash;299 range, and 41% had scores\u0026thinsp;\u0026ge;\u0026thinsp;300. In comparison, TPB was distributed as follows: 67% of individuals had a burden between 1\u0026ndash;250 mm\u0026sup3;, 27% fell within the 251\u0026ndash;750 mm\u0026sup3; range, and 12% had total plaque volumes exceeding 750 mm\u0026sup3;.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eDistribution of Coronary Artery Calcium (CAC) and Total Plaque Burden (TPB) Categories\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMeasure\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCategory\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eFrequency (%)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCAC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1\u0026ndash;99\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e765 (39%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCAC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e100\u0026ndash;299\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e391 (20%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCAC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e\u0026ge;\u0026thinsp;300\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e799 (41%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTPB\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1\u0026ndash;250 mm\u0026sup3;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1,309 (67%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTPB\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e251\u0026ndash;750 mm\u0026sup3;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e528 (27%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTPB\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e\u0026gt;\u0026thinsp;750 mm\u0026sup3;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e118 (6%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec11\" class=\"Section2\"\u003e \u003ch2\u003e3.3 Agreement Between CAC and TPB Categories\u003c/h2\u003e \u003cp\u003eOverall, weighted Kappa was 0.495 (95% CI 0.471\u0026ndash;0.519), representing moderate agreement between CAC and TPB categories. When CAC thresholds were adjusted to 1\u0026ndash;99, 100\u0026ndash;399, and \u0026ge;\u0026thinsp;400, Kappa increased modestly to 0.535 (95% CI 0.511\u0026ndash;0.559).\u003c/p\u003e \u003cp\u003eSpearman correlation between continuous CAC and TPB was very strong (ρ\u0026thinsp;=\u0026thinsp;0.92, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001).\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec12\" class=\"Section2\"\u003e \u003ch2\u003e3.4 Subgroup Analyses\u003c/h2\u003e \u003cp\u003e We assessed the categorical agreement between Coronary Artery Calcium (CAC) categories and AI-derived Total Plaque Burden (TPB) across clinically relevant subgroups using Cohen\u0026rsquo;s weighted Kappa statistic. The overall agreement was moderate (κ\u0026thinsp;\u0026asymp;\u0026thinsp;0.50), with notable variability based on age, sex, and cardiovascular risk factors.\u003c/p\u003e \u003cp\u003eAgreement was slightly higher in older individuals (age\u0026thinsp;\u0026gt;\u0026thinsp;63.9 years) compared to those\u0026thinsp;\u0026le;\u0026thinsp;63.9 years, suggesting better concordance between calcification and total plaque burden in more advanced disease. Patients on statin therapy also demonstrated higher Kappa values than those not receiving statins, consistent with statin-associated promotion of plaque calcification. Conversely, individuals without statin use, diabetes, or hypertension exhibited wider confidence intervals and lower Kappa values, indicating greater discordance between CAC and total plaque burden.\u003c/p\u003e \u003cp\u003eSex-based differences were particularly prominent. Female participants showed the lowest categorical agreement (κ\u0026thinsp;\u0026lt;\u0026thinsp;0.45), reflecting the higher prevalence of non-calcified plaque in women and reinforcing the limitations of relying solely on CAC for risk assessment in this population.\u003c/p\u003e \u003cp\u003eThese subgroup differences are visually summarized in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, which displays Kappa estimates with 95% confidence intervals for each clinical category.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"4. Discussion","content":"\u003cdiv id=\"Sec14\" class=\"Section2\"\u003e \u003ch2\u003e4.1 Principal Findings\u003c/h2\u003e \u003cp\u003eIn this large, single-center study of nearly 2,000 patients undergoing both CAC scoring and AI-enabled quantitative CCTA, we observed a moderate categorical agreement (κ\u0026thinsp;\u0026asymp;\u0026thinsp;0.50) but very strong continuous correlation (ρ\u0026thinsp;=\u0026thinsp;0.92) between CAC scores and total plaque burden (TPB). This dichotomy highlights an important clinical insight: although CAC and TPB both aim to quantify the extent of coronary atherosclerosis, they do so through fundamentally different lenses. The moderate categorical overlap implies that applying discrete risk thresholds (e.g., CAC\u0026thinsp;\u0026gt;\u0026thinsp;100, TPB\u0026thinsp;\u0026gt;\u0026thinsp;250 mm\u0026sup3;) may not reliably classify the same individuals into concordant risk categories, underscoring the potential for clinically meaningful discordance in plaque assessment (\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e, \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e).\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec15\" class=\"Section2\"\u003e \u003ch2\u003e4.2 Interpretation\u003c/h2\u003e \u003cp\u003eThe discrepancy in categorical agreement stems from the inherent limitation of CAC: it detects only calcified plaque, neglecting the fibrous and lipid-rich components that characterize earlier and potentially more vulnerable stages of atherosclerosis (\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e, \u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e). Consequently, two patients with identical CAC scores (e.g., CAC\u0026thinsp;=\u0026thinsp;100) may have markedly different atherosclerotic burdens if one harbors predominantly non-calcified plaque. This limitation is especially pertinent in younger individuals and women, where non-calcified plaque tends to predominate (\u003cspan additionalcitationids=\"CR20\" citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e). The strong continuous correlation (ρ\u0026thinsp;=\u0026thinsp;0.92) suggests that overall plaque accumulation, both calcified and non-calcified, tends to progress in tandem, but the observed categorical misalignment indicates that a single metric may miss important nuances in disease characterization (\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e, \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eImportantly, these findings reaffirm that CAC and TPB are complementary rather than interchangeable. CAC provides a surrogate of disease chronicity and stability, while AI-based TPB offers a more nuanced, volumetric, and compositional view of the full atherosclerotic landscape.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec16\" class=\"Section2\"\u003e \u003ch2\u003e4.3 Sex and Statin Differences\u003c/h2\u003e \u003cp\u003eSex-specific analysis revealed lower agreement in women, consistent with known differences in plaque biology. Prior research has demonstrated that women tend to exhibit less calcified and more non-calcified plaque than men at equivalent levels of overall atherosclerosis. This contributes to the underestimation of risk when relying solely on CAC scores in female populations (\u003cspan additionalcitationids=\"CR25 CR26\" citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eSimilarly, statin therapy may alter the CAC\u0026ndash;TPB relationship. Statins promote plaque stabilization and calcification, a phenomenon referred to as the \u0026ldquo;statin paradox,\u0026rdquo; where CAC increases due to plaque healing, despite overall risk reduction. This transformation of non-calcified plaque into denser, more calcified forms can lead to an apparent \u0026ldquo;discrepancy\u0026rdquo; between high CAC and low-risk morphology. Conversely, patients on long-term statin therapy may show elevated CAC despite relatively modest TPB. Recognizing these modifying effects is critical when interpreting imaging results in both clinical and research settings (\u003cspan additionalcitationids=\"CR29 CR30\" citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e).\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec17\" class=\"Section2\"\u003e \u003ch2\u003e4.4 Comparison with Previous Literature\u003c/h2\u003e \u003cp\u003eOur results corroborate prior observations from the Multi-Ethnic Study of Atherosclerosis (MESA), which revealed that up to 15% of individuals with CAC\u0026thinsp;=\u0026thinsp;0 may still harbor non-calcified plaque detectable by CCTA. Similarly, Budoff et al. and Williams et al. demonstrated that total plaque burden assessed by CCTA, especially lipid-rich or low-attenuation plaque, is independently predictive of major adverse cardiovascular events (MACE), even in the absence of CAC (\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e, \u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eBy explicitly quantifying categorical agreement using weighted Kappa statistics, our study extends this literature, offering a formal metric for the degree of concordance between these two commonly used imaging biomarkers. This benchmark may help frame future studies assessing integrated risk models that combine CAC and AI-derived plaque metrics.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec18\" class=\"Section2\"\u003e \u003ch2\u003e4.5 Clinical Implications\u003c/h2\u003e \u003cp\u003eOur findings have several important clinical implications. First, they validate the incremental value of AI-enabled CCTA in detecting subclinical atherosclerosis that may be invisible to calcium scoring alone. In an era of precision prevention, where cardiovascular risk stratification increasingly guides therapeutic intensity, failing to identify patients with high non-calcified plaque burden could delay timely intervention.\u003c/p\u003e \u003cp\u003eSecond, in patients with discordant findings, for instance, low or zero CAC but elevated TPB, physicians may consider intensifying lifestyle or pharmacologic therapy. Conversely, high CAC with low TPB may prompt further evaluation of plaque morphology or stability, rather than immediate escalation of therapy. This nuanced interpretation allows for a more tailored approach to preventive cardiology, avoiding both over- and under-treatment.\u003c/p\u003e \u003cp\u003eFinally, with growing availability and regulatory approval of AI-based tools, integration of TPB analysis into routine clinical workflows may become feasible and cost-effective, especially when bundled with routine CCTA performed for other indications (e.g., evaluation of chest pain). Combining CAC and TPB may enable multi-dimensional risk profiling, which better captures both plaque quantity and quality (\u003cspan additionalcitationids=\"CR35\" citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e).\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec19\" class=\"Section2\"\u003e \u003ch2\u003e4.6 Limitations\u003c/h2\u003e \u003cp\u003eSeveral limitations merit consideration. This was a retrospective, single-center study without follow-up outcomes; thus, prognostic implications could not be assessed. CAC\u0026thinsp;=\u0026thinsp;0 subjects were excluded, limiting generalizability to early subclinical disease. Imaging was performed on different CT systems, although standardized acquisition protocols were used. AI-derived plaque quantification depends on image quality and reconstruction parameters, which could introduce variability. Future multicenter studies should validate these findings across diverse populations and correlate CAC\u0026ndash;TPB discordance with cardiovascular events.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec20\" class=\"Section2\"\u003e \u003ch2\u003e4.7 Future Directions\u003c/h2\u003e \u003cp\u003eDefining plaque volume thresholds corresponding to \u0026ldquo;low-risk\u0026rdquo; or \u0026ldquo;trivial\u0026rdquo; disease, analogous to CAC\u0026thinsp;=\u0026thinsp;0, could enhance the interpretation of AI-derived metrics. Longitudinal analyses integrating CAC and TPB progression may further elucidate how plaque transformation, from non-calcified to calcified, relates to clinical outcomes. Combining AI-based plaque quantification with traditional calcium scoring has the potential to refine risk prediction models and optimize preventive therapy allocation.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"5. Conclusion","content":"\u003cp\u003eAlthough CAC and AI-derived TPB demonstrate a strong continuous correlation, their categorical agreement is only moderate, highlighting important differences in what each metric captures. CAC quantifies only calcified atherosclerosis, whereas AI-enabled CCTA offers a comprehensive volumetric assessment of both calcified and non-calcified plaque. This discrepancy is particularly relevant in populations such as women, younger individuals, and statin users, where non-calcified plaque may predominate, or calcification may not reflect overall disease burden.\u003c/p\u003e \u003cp\u003eOur findings underscore the complementary nature of CAC and AI-based TPB assessment. While CAC remains a valuable screening tool, particularly for asymptomatic risk stratification, quantitative plaque analysis via CCTA provides additional insights into early and potentially high-risk atherosclerotic disease that may be missed by calcium scoring alone. Incorporating both modalities into clinical practice and research frameworks may lead to more personalized, accurate cardiovascular risk assessment and prevention strategies.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e \u003ch2\u003eEthics Approval and Consent to Participate:\u003c/h2\u003e \u003cp\u003e This study was conducted in accordance with the ethical principles outlined in the Declaration of Helsinki. The study protocol was reviewed and approved by the Institutional Review Board of The Lundquist Institute at Harbor-UCLA Medical Center. Given the retrospective nature of the study and use of de-identified data, the requirement for informed consent was waived by the Institutional Review Board.\u003c/p\u003e \u003c/p\u003e\u003cp\u003e \u003ch2\u003eConflicts of Interest:\u003c/h2\u003e \u003cp\u003eThe authors declare \u003cb\u003eno conflicts of interest\u003c/b\u003e.\u003c/p\u003e \u003c/p\u003e\u003ch2\u003eFunding:\u003c/h2\u003e \u003cp\u003eThis research received \u003cb\u003eno external funding\u003c/b\u003e.\u003c/p\u003e\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eK.I. conceived and designed the study, performed data analysis and interpretation, and drafted the initial manuscript.R.M., B.M., B.I., and N.P. contributed to data acquisition and curation.A.K. assisted with data management and statistical support.S.K., S.L., and S.R. contributed to the interpretation of results and critically revised the manuscript for important intellectual content.M.B. provided overall study supervision, conceptual guidance, and critical revision of the manuscript.All authors reviewed and approved the final manuscript and agree to be accountable for all aspects of the work.\u003c/p\u003e\u003ch2\u003eAcknowledgments\u003c/h2\u003e \u003cp\u003eThe authors acknowledge institutional support from \u003cb\u003eThe Lundquist Institute for Biomedical Innovation at Harbor-UCLA Medical Center\u003c/b\u003e. No external grants or funding were received for this study.\u003c/p\u003e\u003ch2\u003eData Availability\u003c/h2\u003e\u003cp\u003eThe data that support the findings of this study are available from the corresponding author upon reasonable request. The data are not publicly available due to institutional restrictions and the inclusion of protected health information.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eBudoff M, Backlund J-YC, Bluemke DA, Polak J, Bebu I, Schade D et al (2019) The association of coronary artery calcification with subsequent incidence of cardiovascular disease in type 1 diabetes: the DCCT/EDIC trials. JACC Cardiovasc Imaging 12(7 Pt 2):1341\u0026ndash;1349\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMasrouri S, Shapiro MD, Khalili D, Hadaegh F (2024) Impact of coronary artery calcium on mortality and cardiovascular events in metabolic syndrome and diabetes among younger adults. Eur J Prev Cardiol 31(6):744\u0026ndash;753\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTheofilis P, Sagris M, Antonopoulos AS, Oikonomou E, Tsioufis K, Tousoulis D (2022) Non-Invasive Modalities in the Assessment of Vulnerable Coronary Atherosclerotic Plaques. Tomography 8(4):1742\u0026ndash;1758\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSuzuki K, Kinoshita D, Yuki H, Niida T, Sugiyama T, Yonetsu T et al (2024) Higher noncalcified plaque volume is associated with increased plaque vulnerability and vascular inflammation. Circ Cardiovasc Imaging 17(1):e015769\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAlyami B, Santer M, Seetharam K, Velu D, Gadde E, Patel B et al (2023) Non-Calcified Coronary Artery Plaque on Coronary Computed Tomography Angiogram: Prevalence and Significance. Tomography 9(5):1755\u0026ndash;1771\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOnnis C, Virmani R, Kawai K, Nardi V, Lerman A, Cademartiri F et al (2024) Coronary artery calcification: current concepts and clinical implications. Circulation 149(3):251\u0026ndash;266\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWeng T, Ding D, Li G, Guan S, Han W, Gan Q et al (2024) Accuracy of coronary computed tomography angiography-derived quantitative flow ratio for onsite assessment of coronary lesions. EuroIntervention 20(20):e1288\u0026ndash;e1297\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVatsa N, Faaborg-Andersen C, Dong T, Blaha MJ, Shaw LJ, Quintana RA (2024) Coronary atherosclerotic plaque burden assessment by computed tomography and its clinical implications. Circ Cardiovasc Imaging 17(8):e016443\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang T-W, Tzeng Y-H, Wu K-T, Liu H-R, Hong J-S, Hsu H-Y et al (2024) Meta-analysis of deep learning approaches for automated coronary artery calcium scoring: Performance and clinical utility AI in CAC scoring: A meta-analysis: AI in CAC scoring: A meta-analysis. Comput Biol Med 183:109295\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKhan H, Bansal K, Griffin WF, Cantlay C, Sidahmed A, Nurmohamed NS et al (2024) Assessment of atherosclerotic plaque burden: comparison of AI-QCT versus SIS, CAC, visual and CAD-RADS stenosis categories. Int J Cardiovasc Imaging 40(6):1201\u0026ndash;1209\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNurmohamed NS, Bom MJ, Jukema RA, de Groot RJ, Driessen RS, van Diemen PA et al (2024) AI-Guided Quantitative Plaque Staging Predicts Long-Term Cardiovascular Outcomes in Patients at Risk for Atherosclerotic CVD. JACC Cardiovasc Imaging 17(3):269\u0026ndash;280\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChoi AD, Marques H, Kumar V, Griffin WF, Rahban H, Karlsberg RP et al (2021) CT ​Evaluation ​by ​Artificial ​Intelligence ​for ​Atherosclerosis, Stenosis and Vascular ​Morphology ​(CLARIFY): ​A ​Multi-center, international study. J Cardiovasc Comput Tomogr 15(6):470\u0026ndash;476\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGhazal R, Bawa D, Ahmed A, Lakkireddy D, Singh V (2024) The zero calcium score paradox. JACC Case Rep 29(5):102233\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBlaha MJ, Cainzos-Achirica M, Greenland P, McEvoy JW, Blankstein R, Budoff MJ et al (2016) Role of Coronary Artery Calcium Score of Zero and Other Negative Risk Markers for Cardiovascular Disease: The Multi-Ethnic Study of Atherosclerosis (MESA). Circulation 133(9):849\u0026ndash;858\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKambalapalli S, Bhandari M, Punnanithinont N, Iskander B, Khan MA, Budoff M (2025) Bridging prevention and imaging: the influence of statins on CAC and CCTA findings. Curr Atheroscler Rep 27(1):50\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNezarat N, Budoff MJ, Luo Y, Darabian S, Nakanishi R, Li D et al (2017) Presence, characteristics, and volumes of coronary plaque determined by computed tomography angiography in young type 2 diabetes mellitus. Am J Cardiol 119(10):1566\u0026ndash;1571\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDetrano R, Guerci AD, Carr JJ, Bild DE, Burke G, Folsom AR et al (2008) Coronary calcium as a predictor of coronary events in four racial or ethnic groups. N Engl J Med 358(13):1336\u0026ndash;1345\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChartrand-Lefebvre C, Cadrin-Ch\u0026ecirc;nevert A, Bordeleau E, Ugolini P, Ouellet R, Sablayrolles J-L et al (2007) Coronary computed tomography angiography: overview of technical aspects, current concepts, and perspectives. Can Assoc Radiol J 58(2):92\u0026ndash;108\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOsborne-Grinter M, Kwiecinski J, Doris M, McElhinney P, Cadet S, Adamson PD et al (2022) Association of coronary artery calcium score with qualitatively and quantitatively assessed adverse plaque on coronary CT angiography in the SCOT-HEART trial. Eur Heart J Cardiovasc Imaging 23(9):1210\u0026ndash;1221\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBlaha MJ, Nasir K, Rivera JJ, Choi E-K, Chang S-A, Yoon YE et al (2009) Gender differences in coronary plaque composition by coronary computed tomography angiography. Coron Artery Dis 20(8):506\u0026ndash;512\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHecht HS (2015) Coronary artery calcium scanning: past, present, and future. JACC Cardiovasc Imaging 8(5):579\u0026ndash;596\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDey D, Schepis T, Marwan M, Slomka PJ, Berman DS, Achenbach S (2010) Automated three-dimensional quantification of noncalcified coronary plaque from coronary CT angiography: comparison with intravascular US. Radiology 257(2):516\u0026ndash;522\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAmbale-Venkatesh B, Yang X, Wu CO, Liu K, Hundley WG, McClelland R et al (2017) Cardiovascular Event Prediction by Machine Learning: The Multi-Ethnic Study of Atherosclerosis. Circ Res 121(9):1092\u0026ndash;1101\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePlank F, Beyer C, Friedrich G, Wildauer M, Feuchtner G (2019) Sex differences in coronary artery plaque composition detected by coronary computed tomography: quantitative and qualitative analysis. Neth Heart J 27(5):272\u0026ndash;280\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLansky AJ, Ng VG, Maehara A, Weisz G, Lerman A, Mintz GS et al (2012) Gender and the extent of coronary atherosclerosis, plaque composition, and clinical outcomes in acute coronary syndromes. JACC Cardiovasc Imaging 5(3 Suppl):S62\u0026ndash;72\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGarg K, Patel TR, Kanwal A, Villines TC, Aggarwal NR, Nasir K et al (2022) The evolving role of coronary computed tomography in understanding sex differences in coronary atherosclerosis. J Cardiovasc Comput Tomogr 16(2):138\u0026ndash;149\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChandrasekhar J, Mehran R (2016) Sex-Based Differences in Acute Coronary Syndromes: Insights From Invasive and Noninvasive Coronary Technologies. JACC Cardiovasc Imaging 9(4):451\u0026ndash;464\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePuri R, Nicholls SJ, Shao M, Kataoka Y, Uno K, Kapadia SR et al (2015) Impact of statins on serial coronary calcification during atheroma progression and regression. J Am Coll Cardiol 65(13):1273\u0026ndash;1282\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHenein MY, Owen A (2011) Statins moderate coronary stenoses but not coronary calcification: results from meta-analyses. Int J Cardiol 153(1):31\u0026ndash;35\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eUeki Y, Itagaki T, Kuwahara K (2024) Lipid-lowering Therapy and Coronary Plaque Regression. J Atheroscler Thromb 31(11):1479\u0026ndash;1495\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFerencik M, Chatzizisis YS (2015) Statins and the coronary plaque calcium paradox: Insights from non-invasive and invasive imaging. Atherosclerosis 241(2):783\u0026ndash;785\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWilliams MC, Kwiecinski J, Doris M, McElhinney P, D\u0026rsquo;Souza MS, Cadet S et al (2020) Low-Attenuation Noncalcified Plaque on Coronary Computed Tomography Angiography Predicts Myocardial Infarction: Results From the Multicenter SCOT-HEART Trial (Scottish Computed Tomography of the HEART). Circulation 141(18):1452\u0026ndash;1462\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBudoff MJ, Dowe D, Jollis JG, Gitter M, Sutherland J, Halamert E et al (2008) Diagnostic performance of 64-multidetector row coronary computed tomographic angiography for evaluation of coronary artery stenosis in individuals without known coronary artery disease: results from the prospective multicenter ACCURACY (Assessment by Coronary Computed Tomographic Angiography of Individuals Undergoing Invasive Coronary Angiography) trial. J Am Coll Cardiol 52(21):1724\u0026ndash;1732\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eIhdayhid AR, Tzimas G, Peterson K, Ng N, Mirza S, Maehara A et al (2024) Diagnostic Performance of AI-enabled Plaque Quantification from Coronary CT Angiography Compared with Intravascular Ultrasound. Radiol Cardiothorac Imaging 6(6):e230312\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTsiachristas A, Chan K, Wahome E, Kearns B, Patel P, Lyasheva M et al (2025) Cost-effectiveness of a novel AI technology to quantify coronary inflammation and cardiovascular risk in patients undergoing routine coronary computed tomography angiography. Eur Heart J Qual Care Clin Outcomes 11(4):434\u0026ndash;444\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003evan Velzen SGM, Dobrolinska MM, Knaapen P, van Herten RLM, Jukema R, Danad I et al (2023) Automated cardiovascular risk categorization through AI-driven coronary calcium quantification in cardiac PET acquired attenuation correction CT. J Nucl Cardiol 30(3):955\u0026ndash;969\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Coronary calcium, Computed tomography angiography, Artificial intelligence, Plaque quantification, Atherosclerosis, Cardiovascular imaging","lastPublishedDoi":"10.21203/rs.3.rs-8604663/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8604663/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eCoronary artery calcium (CAC) scoring quantifies calcified atherosclerosis but does not capture non-calcified plaque. Artificial intelligence (AI) \u0026ndash; based quantitative coronary CT angiography (CCTA) enables the measurement of total plaque burden (TPB), reflecting both calcified and non-calcified components. The degree of agreement between CAC and TPB categories remains unclear.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eWe retrospectively analyzed 1,955 subjects who underwent both CAC scoring and quantitative CCTA. Subjects with CAC\u0026thinsp;=\u0026thinsp;0 were excluded. CAC was categorized as 1\u0026ndash;99, 100\u0026ndash;299, and \u0026ge;\u0026thinsp;300 Agatston units, while TPB was categorized as 0, 1\u0026ndash;250, 251\u0026ndash;750, and \u0026gt;\u0026thinsp;750 mm\u0026sup3;. Agreement between CAC and TPB categories was assessed using Cohen\u0026rsquo;s weighted Kappa, and Spearman correlation evaluated the continuous relationship between CAC and TPB. Analyses were stratified by age, sex, diabetes, hypertension, and use of statins.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eParticipants had a mean age of 66.5\u0026thinsp;\u0026plusmn;\u0026thinsp;10.4 years, and 69% were male. CAC distribution was 1\u0026ndash;99 (39%), 100\u0026ndash;299 (20%), and \u0026ge;\u0026thinsp;300 (41%); TPB distribution was 1\u0026ndash;250 (67%), 251\u0026ndash;750 (27%), and \u0026gt;\u0026thinsp;750 mm\u0026sup3; (12%). Weighted Kappa was 0.495 (95% CI 0.471\u0026ndash;0.519), indicating moderate categorical agreement, while Spearman correlation was robust (ρ\u0026thinsp;=\u0026thinsp;0.92). Agreement improved modestly when CAC cutoffs were adjusted to 1\u0026ndash;99, 100\u0026ndash;399, and \u0026ge;\u0026thinsp;400 (κ\u0026thinsp;=\u0026thinsp;0.535). Concordance was higher in males (κ\u0026thinsp;=\u0026thinsp;0.53) than in females (κ\u0026thinsp;=\u0026thinsp;0.37).\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e \u003cp\u003eCAC and AI-derived total plaque burden demonstrate moderate categorical agreement but very strong continuous correlation, highlighting that quantitative plaque analysis captures complementary non-calcified atherosclerosis not reflected by CAC alone.\u003c/p\u003e","manuscriptTitle":"Quantitative Comparison of Coronary Artery Calcium and AI-Based Plaque Burden: Agreement, Discordance, and Clinical Implications","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-22 14:17:30","doi":"10.21203/rs.3.rs-8604663/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"bb8c5128-ac99-4c2f-9624-753c6f886e19","owner":[],"postedDate":"January 22nd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-02-02T18:55:13+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-22 14:17:30","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8604663","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8604663","identity":"rs-8604663","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}