Citations

Clear

6729 citation(s) found for "Li, Mark".

Unsupervised Machine Learning for Adaptive Immune Receptors with immuneML
Pavlović, Milena , Würtzen, Charlotte , Kanduri, Chakravarthi , Mamica, Maria , Scheffer, Lonneke , Lund‐Andersen, Christin , Gubatan, John Mark , Ullmann, Theresa , Greiff, Victor , Sandve, G K , Gubatan, John

Mayo Clinic

No container title available | April 18, 2026 | Volume: No volume available | Issue: No issue available | Pages: No page available

10.64898/2026.04.15.718648 Get It

Abstract Machine learning (ML) enables adaptive immune receptor repertoires (AIRRs) analyses for biomarker identification and therapeutic development. With the majority of AIRR data partially or imperfectly labeled, unsupervised ML is essential for motif discovery, biologically meaningful clustering, and generation of novel receptor sequences. However, no unified framework for unsupervised ML exists in the AIRR field, hindering the assessment of model robustness and generalizability. Here, we present an immuneML release advancing unsupervised ML in the AIRR field through unified clustering workflows, interpretable generative modeling, integration with protein language model embeddings, dimensionality reduction, and visualization. We demonstrate immuneML’s utility in three use cases: (i) benchmarking generative models for epitope-specific sequence generation, assessing specificity and novelty, (ii) systematic evaluation of clustering approaches on experimental receptor sequences against biological properties, such as epitope specificity and MHC, and (iii) unsupervised analysis of an experimental AIRR dataset to examine potential confounding, a practice widespread in related fields but unexplored in AIRR analyses.
Low titer group O whole blood inventory conservation: The effect of implementing group A whole blood at a simulated civilian trauma center
Jochumsen, Emil Ainsworth , Gurney, Jennifer, Jenkins, Donald, Seheult, Jansen N. , Spinella, Philip C. , Yazer, Mark H. , Jochumsen, Emilie A , Yazer, Mark H , Spinella, Philip C , Seheult, Jansen N , Gurney, Jennifer M. , Jenkins, Donald, Sprogøe, Ulrik

Mayo Clinic

Transfusion | April 18, 2026 | Volume: 66 | Issue: 7 | Pages: 1289-1298

10.1111/trf.70235 | PMID 41999095 Get It

Abstract Background Substituting group A whole blood (GAWB) might relieve some of the burden on the low titer group O whole blood (LTOWB) inventory. This simulation examined the effect of implementing GAWB at a large trauma hospital. Study Design and Methods A civilian trauma center with LTOWB and GAWB par levels set to 22 and 10 units, respectively, was modeled as the baseline. The average daily number of WB recipients was 0.5 who received an average of four WB units per patient. LTOWB was issued in packages of five and all had to be consumed before a group A patient could be switched to GAWB. Several variations on the baseline simulation were also modeled. Results In the baseline simulation, there was a median (interquartile range, IQR) of 1 (0–2) GAWB and 16 (13–19) LTOWB recipients per month. The median (IQR) GAWB and LTOWB units transfused per month was 2 (0–9) and 56 (42–72), respectively. Fourteen percent of group A patients received any quantity of GAWB. The variations that had the most impact on GAWB usage included increasing the number of WB recipients to 2.5 per day where the median (IQR) monthly number of GAWB recipients and units transfused increased to 4 (3–5) recipients and 21 (12–29) units, respectively, and when the average WB requirements increased to eight units per patient resulting in transfusing a median (IQR) of 10 (5–15) GAWB units per month to 3 (1–4) recipients. Discussion Under routine civilian hospital circumstances, implementing GAWB will have a modest impact on LTOWB inventory.
Abstract CT017: Neoadjuvant IL-1β and PD-1 inhibition in localized clear-cell renal cell carcinoma: Clinical and correlative analyses of the phase 1b SPARC-1 trial
McCann, Patrick J., Obradovic, Aleksandar, Ager, Casey R. , Rahiman, Chelsea L., Campbell, Kaitlyn R., Laplaca, Caroline, Johnston, Peyton C., Kim, Amanda, Gomez, Katherine, Manjrekar, Kriti Bagri , Stein, Mark N. , Drake, Charles G. , Runcie, Karie , Dallos, Matthew, McCann, Patrick J., Obradović, Aleksandar , Aggen, David H , Spina, Catherine S. , Rahiman, Chelsea L., Dallos, Matthew C. , McCann, Patrick J.

Mayo Clinic

Cancer Research | April 17, 2026 | Volume: 86 | Issue: 8_Supplement | Pages: CT017-CT017

10.1158/1538-7445.am2026-ct017 Get It

Abstract Background: Despite efficacy in metastatic clear cell renal cell carcinoma (ccRCC), immunotherapy currently has no role in the neoadjuvant setting. Suppressive tumor-associated macrophages (TAMs) are known to mediate resistance to immune checkpoint blockade (ICB) in ccRCC. In preclinical studies, IL-1β blockade reprograms TAMs toward an anti-tumor phenotype and promotes T cell activation, creating a tumor microenvironment (TME) more sensitive to ICB. To test this in patients, we conducted a correlative-rich neoadjuvant trial of IL-1β + PD-1 inhibition in localized ccRCC. Methods: SPARC-1 is a single-center, phase 1b study assessing the safety and feasibility of neoadjuvant canakinumab (αIL-1β) and spartalizumab (αPD-1) in patients with localized ccRCC (T1b-T4NanyM0 or TanyN1M0). All patients received 2 doses of canakinumab (300mg IV, Q4w) and spartalizumab (400mg IV, Q4w), 6 weeks (±7 days) prior to nephrectomy. The primary endpoint was safety and feasibility. Key secondary and exploratory endpoints included 12-month metastasis-free survival rate, pathologic response rate, and quantification of immune cell infiltration. To characterize immunologic reprogramming, fresh tumor specimens were collected at nephrectomy for single-cell RNA sequencing (scRNAseq) and multiparametric flow cytometry. Tissue from a treatment naïve cohort was collected for comparative analysis (n=16). Results: From August 15th, 2018, to January 30th, 2025, 14 patients were enrolled. There were no severe treatment-related adverse events (Grade ≥ 3) attributed to canakinumab or spartalizumab. At a median follow-up of 12.0 months (range, 6.3-12.0 months), the 12-month metastasis-free survival was 100%. Based on the ASSURE nomogram, the mean predicted 12-month recurrence risk was 16.7% (range, 4.7-46.5%). ScRNAseq revealed that treatment with αIL-1β + αPD-1 increased the frequency of TREM2+APOE+ TAMs (p=0.035), a population typically associated with immune suppression. However, these TAMs exhibited a phenotypic shift toward a less immunosuppressive state, with reduced IL-1β expression and increased CXCL9:SPP1 ratio, consistent with anti-tumor TAM polarization. Immune profiling revealed an increased CD8/CD4 T cell ratio (p=0.042) with modest enrichment of activated CD8+ T cells after treatment, supporting a more pro-inflammatory TME. Conclusions: The neoadjuvant combination of canakinumab (αIL-1β) and spartalizumab (αPD-1) is well-tolerated, feasible, and demonstrated promising clinical activity with no progression of disease observed in a localized ccRCC population at high risk of recurrence. Correlative analyses demonstrated that combined IL-1β and PD-1 blockade reprograms immunosuppressive TAMs, providing evidence that dual IL-1β and PD-1 inhibition can overcome myeloid-driven resistance in ccRCC. Clinical Trial Information: NCT04028245 Citation Format: Patrick J. McCann, Aleksandar Obradovic, Casey R. Ager, David H. Aggen, Catherine S. Spina, Chelsea L. Rahiman, Kaitlyn R. Campbell, Caroline Laplaca, Peyton C. Johnston, Amanda Kim, Katherine Gomez, Kriti Bagri Manjrekar, Mark N. Stein, Charles G. Drake, Karie Runcie, Matthew Dallos. Neoadjuvant IL-1β and PD-1 inhibition in localized clear-cell renal cell carcinoma: Clinical and correlative analyses of the phase 1b SPARC-1 trial [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(8_Suppl):Abstract nr CT017.
Patient's Age Impact on Stroke Risk and Intracranial Aneurysm Occlusion: SCENT Flow Diverter Study—A Nonrandomized Clinical Trial on Large and Giant Aneurysms
Wakhloo, Ajay K. , Jenkins, Paul, Meyers, Philip M. , Coon, A , Kan, Peter T., Puri, Ajit S., Vries, Joost de, Lanzino, Giuseppe, Bain, Mark D., Ebersole, Koji , Welch, B, Dog⫧an, Aclan , Jabbour, Pascal M., Mocco, J., Siddiqui, Adnan H., Turk, Aquilla S., Taussky, Philipp, Hanel, Ricardo A., Investigators, for the SHaRe and IPHCC, Siddiqui, Adnan H. , Siddiqui, Adnan H , Coon, Alexander Lewis , Kan, Peter , Puri, Ajit S., Vries, Joost de , Lanzino, Giuseppe , Welch, Babu G. , Jabbour, Pascal , Turk, Aquilla S , Taussky, Philipp , Hanel, Ricardo A.

Mayo Clinic

Neurosurgery Practice | April 17, 2026 | Volume: 7 | Issue: 2 | Pages: No page available

10.1227/neuprac.0000000000000222 | PMID 42007246 Get It

BACKGROUND AND OBJECTIVES: The prospective single-arm nonrandomized SCENT (Surpass Intracranial Aneurysm Embolization System Pivotal) trial on flow diverter treatment of large and giant intracranial aneurysms (IA) was analyzed for patients' age and IA characteristics affecting stroke and occlusion rates over 5 years (Trial registration NCT01716117). METHODS: Impact on major ipsilateral stroke and IA occlusion was studied by stratifying age as 65 years and younger vs older than 65. Kaplan–Meier estimates of time to both endpoints, stratified by age, were created. Univariate predictors of time-to-stroke were analyzed using univariable proportional hazards regression models. Limited bivariable modeling was also attempted. RESULTS: Of 180 patients with large or giant IA enrolled, 119 were 65 years and younger, whereas 61 were older than 65 years. The 3-year risk of stroke for the older than 65 years group (19.7%) was more than double that of the 65 years and younger group (9.2%), P = .047. No new strokes were reported between 3 and 5 years. Four patients (2.2%) experienced aneurysm rupture within the first week post-treatment, 3 being 65 years and younger and the fourth older than 65 (>.99). Complete IA occlusion within age strata at 1 year was: older than 65 60% (33/55), 65 years and younger 79.1% (87/110), P = .009, 3 years: older than 65 67.6% (25/37), 65 years and younger 82.5% (66/80), P = .071, and 5 years: older than 65 85.7% (18/21), 65 years and younger 91.8% (56/61), P = .417. CONCLUSION: Age older than 65 was associated with an increased risk of stroke and predictive of incomplete healing and increased time to healing.
RATE OF PATCH TESTS REACTION TO A DERMATOPHAGOIDES MIX CURRENTLY ON THE MARKET: 29
Davis, Mark D. P. , Ahmed, Debra F, Davis, Mark D.P. , Ahmed, Debra D. F.

Mayo Clinic

American Journal of Contact Dermatitis | April 17, 2026 | Volume: 12 | Issue: 2 | Pages: 129-129

10.1053/ajcd.2001.3151 Get It

Patch Test Results for the Plastics and Glues Series at Mayo Clinic, 2000–2007
Shmidt, Eugenia , Davis, Mark D.

Mayo Clinic

Dermatitis® | April 16, 2026 | Volume: 20 | Issue: 4 | Pages: 226-226

10.2310/6620.2009.00005i Get It

Differentiating Immunoglobulin G4-Related Sclerosing Cholangitis From Primary Sclerosing Cholangitis: A Comprehensive Systematic Review and Meta-Analysis of Diagnostic Features
Wang, Mark C. , Chong, Albert C. , Grave, Erick Cruz , Tarakji, Andrew, Rahal, Kabir , Nastaskin, Lucas, Kunitsky, Abby, Saric, Karin , Lee, Helen, Sahakian, Ara , Buxbaum, James , Saric, Karin J , Nastaskin, Lucas

Mayo Clinic

American Journal of Gastroenterology | April 16, 2026 | Volume: No volume available | Issue: No issue available | Pages: No page available

10.14309/ajg.0000000000004024 | PMID 41989037 Get It

INTRODUCTION: Immunoglobulin G4-related sclerosing cholangitis (IgG4-SC) and primary sclerosing cholangitis (PSC) are cholestatic disorders, which may be difficult to differentiate. Importantly, PSC is an untreatable progressive fibroinflammatory disease, whereas IgG4-SC responds to immunosuppression if recognized in a timely manner. This systematic review and meta-analysis aimed to identify and define the performance of clinical, biochemical, radiographic, and histologic features to differentiate between these 2 diseases. METHODS: A systematic search for comparative studies of IgG4-SC and PSC through November 2023 (with repeat evaluation for interval literature in December 2024) was performed and data extraction performed in duplicate. Pooled proportions, odds ratios, means, and standardized mean differences of pertinent diagnostic features were calculated using random-effects inverse-variance models. RESULTS: We identified 38 studies comparing patients with IgG4-SC and PSC. IgG4-SC patients were more likely to have pancreatic disease ( P < 0.001) but less likely to have inflammatory bowel disease ( P < 0.001) than those with PSC. Serum IgG4 was significantly higher in IgG4-SC ( P < 0.001), as anticipated. Radiographically, IgG4-SC demonstrated long distal strictures ( P = 0.02) and symmetric ductal thickening ( P < 0.001), whereas PSC showed a beaded appearance ( P = 0.038). With the exception of IgG4 staining, histologic features including periductal fibrosis were similar between these entities, although sample size was limited for these features. DISCUSSION: Our meta-analysis shows that IgG4-SC and PSC present with similar clinical and radiographic features and possibly comparable histology. A history of unusual pancreatitis and elevated IgG4 (serum or tissue) prompts assessment for more specific radiographic features which if present warrant a therapeutic treatment trial.
Impact of preoperative radiotherapy on the risk of postpancreatectomy haemorrhage and major morbidity after resection of pancreatic adenocarcinoma including arterial divestment or arterial resection
Stoop, Thomas F, Land, Freek R. van ‘t , Seelen, Leonard W F, Ali, Mahsoem , Sultan, Ahmer , Javed, Ammar A, Eijck, van, Thiels, Cornelius A, Hewitt, D Brock, Sparrelid, Ernesto, Uzunoglu, Faik G, Gehrisch, O H Fiete, Daams, Freek, Ishida, Hiroyuki, Santvoort, Hjalmar C van, Molenaar, I Quintus, Leiting, Jennifer L. , Cappelle, Marie, Ginesini, Michael, Kendrick, Michael L, Franklin, Oskar , Ghorbani, Poya, Schulick, Richard D, Dankha, Rimon , Wilde, R F de, Welsch, Thilo , Riele, Wouter te, Wolfgang, Christopher L, Koerkamp, Bas Groot , Boggi, Ugo, Truty, Mark J, Chiaro, Marco Del, Hackert, T, Croce, C, Kazemier, G, Rompen, I F, Larsson, P, Franco, S Rodriguez, Sugawara, T, van 't Land, Freek R , Erdmann, Joris I , Busch, Olivier R , Franklin, Oskar , Besselink, Marc G , Groot Koerkamp, Bas , Hackert, Thilo , Sultan, Ahmer , Stoop, Thomas F. , Seelen, Leonard W. F. , Javed, Ammar A. , Thiels, Cornelius A. , Hewitt, D. Brock , Sparrelid, Ernesto , Uzunoglu, Faik Güntac , Gehrisch, O. H. Fiete, Daams, F, Ishida, Hiroyuki, Santvoort, Hjalmar C. van , Molenaar, I. Quintus , Erdmann, Joris I. , Cappelle, Marie , Ginesini, Michael , Kendrick, Michael L. , Napoli, Niccolò , Ghorbani, Poya , Schulick, Richard D. , Wilde, Roeland De, Riele, Wouter W. te , Wolfgang, Christopher L. , Boggi, Ugo , Truty, Mark J. , Chiaro, Marco Del , Hackert, Thilo , Kazemier, Geert , Rompen, Ingmar Florin , Larsson, Patrik , Franco, Salvador Rodriguez

Mayo Clinic

BJS Open | April 16, 2026 | Volume: 10 | Issue: 3 | Pages: No page available

10.1093/bjsopen/zrag058 | PMID 42263218 Get It

Abstract Background Some centres advocate preoperative radiotherapy in patients with pancreatic cancer and arterial involvement despite a lack of Level 1 evidence on survival benefit. Although it has been suggested that preoperative radiotherapy may increase the risk of postpancreatectomy haemorrhage (PPH) and morbidity, evidence is again lacking. This study investigated the association between preoperative radiotherapy and both PPH and major morbidity following arterial divestment/resection during pancreatic adenocarcinoma resection after chemotherapy. Methods Consecutive patients diagnosed with pancreatic adenocarcinoma and &gt; 180° arterial involvement who were treated with preoperative chemotherapy with or without radiotherapy followed by pancreatic resection with arterial divestment/resection were included in the study. Logistic regression analyses including propensity score-based overlap weighting were performed to investigate associations between radiotherapy and in-hospital PPH grade B/C and major morbidity, expressed as adjusted risk differences (aRDs). Results Overall, 246 patients undergoing pancreatic resection with arterial resection (169, 69%) or divestment (77, 31%) were included. Radiotherapy was not associated with PPH (aRD 6%; 95% confidence interval (c.i.) −3 to 14), regardless of arterial divestment (aRD 3%; 95% c.i. −5 to 11) or arterial resection (aRD 12%; 95% c.i. 1 to 23; Pinteraction = 0.189). Radiotherapy was associated with a 14% (95% c.i. 2 to 25) higher risk of major morbidity, especially after arterial resection (aRD 27%; 95% c.i. 11 to 43) compared with arterial divestment (aRD −12%; 95% c.i. −35 to 11; Pinteraction = 0.006) and after external beam radiotherapy (aRD 21%; 95% c.i. 8 to 32) compared with stereotactic body radiotherapy (aRD −12%; 95% c.i. −27 to 6; Pinteraction = 0.0001). Ninety-day mortality was increased, albeit not significantly, after preoperative radiotherapy (10 (8%) versus 3 (3%) deaths with versus without preoperative radiotherapy, respectively; P = 0.067). Conclusions Radiotherapy before resection of pancreatic cancer with &gt; 180° arterial involvement was associated with an increased risk of postoperative major morbidity when arterial resection, but not arterial divestment, was performed. This risk should be taken into account when considering preoperative radiotherapy in patients who may require arterial resection.
Neurogenic diarrhoea after superior mesenteric artery divestment or resection for pancreatic adenocarcinoma following preoperative chemotherapy: international multicentre retrospective study
Stoop, Thomas F, Crocè, C , Ishida, Hiroyuki, Ali, Mahsoem , Halimi, Asif , Oba, Atsushi , Koerkamp, Bas Groot , Leonhardt, Carl-Stephan , Thiels, Cornelius A, Rangelova, Elena , Sparrelid, Ernesto, Sotirova, Ira , Leiting, Jennifer L. , Tauchi, Jun, Kobayashi, Kosuke, Klos, Marit, Beuk, Lysanne P M, Genova, Luana , Kendrick, Michael L, Mughal, Nabiha A, Franklin, Oskar , Larsson, P, Klaiber, Ulla , Schulick, Richard D, Theijse, Rutger T., Strobel, Oliver, Ghorbani, Poya, Wilde, R F de, Wilmink, Johanna W, Messersmith, Wells, Wolfgang, Christopher L, Inoue, Yosuke, Truty, Mark J, Chiaro, Marco Del, Kazemier, G, Rompen, I F, Erdmann, J I, Daams, F, Strobel, Oliver , Oba, Atsushi , Groot Koerkamp, Bas , Leonhardt, Carl-Stephan , Mastronardi, Manuela , Busch, Olivier R , Franklin, Oskar , Klaiber, Ulla , Sugawara, Toshitaka , Besselink, Marc G , Strobel, Oliver , Stoop, Thomas F. , Javed, Ammar A. , Thiels, Cornelius A. , Sparrelid, Ernesto , Kobayashi, Kosuke , Beuk, Lysanne P.M. , Kendrick, Michael L. , Mughal, Nabiha Akhlaq, Larsson, Patrik , Schulick, Richard D. , Ghorbani, Poya , Wilde, Roeland De, Franco, Salvador Rodriguez , Wilmink, Johanna W., Messersmith, Wells A. , Wolfgang, Christopher L. , Inoue, Yosuke , Truty, Mark J. , Chiaro, Marco Del , Kazemier, Geert , Rompen, Ingmar Florin

Mayo Clinic

BJS Open | April 16, 2026 | Volume: 10 | Issue: 3 | Pages: No page available

10.1093/bjsopen/zrag057 | PMID 42263216 Get It

Abstract Background The increased use of superior mesenteric artery (SMA) divestment has been a driver behind the increased resection rate for locally advanced pancreatic cancer following preoperative therapy. This has also resulted in an increase in the rate of postoperative neurogenic diarrhoea, but knowledge about postoperative neurogenic diarrhoea is lacking. The aims of this study were to determine the incidence, risk factors, management, and outcomes of neurogenic diarrhoea after SMA divestment/resection for pancreatic adenocarcinoma. Methods This multicentre retrospective study included consecutive patients undergoing pancreatic adenocarcinoma resection, including SMA divestment/resection, after preoperative chemotherapy with or without radiotherapy between 2016 and 2022. Primary endpoints were the incidence of postoperative neurogenic diarrhoea, associated factors, treatment strategies, and outcomes. Secondary endpoints were the rate of adjuvant chemotherapy and the impact of neurogenic diarrhoea on overall survival (OS). Results Overall, 291 patients who underwent pancreatic resection with concomitant SMA divestment (240, 82%) or resection (51, 18%) were included in the study. Postoperative neurogenic diarrhoea was diagnosed in 193 patients. The adjusted risk of developing neurogenic diarrhoea was 59% (95% confidence interval (c.i.) 46 to 73) after ≤ 180° SMA divestment, 80% (95% c.i. 67 to 93) after &gt; 180° SMA divestment, and 77% (95% c.i. 66 to 88) after SMA resection. Postoperative neurogenic diarrhoea was treated with non-opioid drugs (29, 15%), non-opium opioids (140, 73%), opium tincture (69, 36%), and/or octreotide (49, 25%), and normalized in 51% of patients. After adjusting for confounders, neurogenic diarrhoea was not significantly associated with OS (hazard ratio 0.83; 95% c.i. 0.55 to 1.25). Conclusion Neurogenic diarrhoea occurred in two-thirds of patients following resection of pancreatic adenocarcinoma with concomitant SMA divestment/resection, particularly after &gt; 180° SMA divestment or SMA resection. Although challenging to manage, neurogenic diarrhoea is not associated with impaired OS. Evidence-based treatment strategies are needed for adequate management.
Hidden risk in normal myocardial perfusion scans: AI-detected proximal coronary calcium on CT attenuation maps improves prognosis
Zhou, Jianhang, Miller, Robert JH, Shanbhag, Aakash , Killekar, Aditya , Han, D, Patel, Krishna K., Pieszko, Konrad , Yi, Jirong , Urs, Meghana , Ramirez, Giselle, Lemley, M A R K, Kavanagh, P A U L, Liang, Joanna X , Kamagate, Assiata, Builoff, V A L E R I, Einstein, A N D R E W, Feher, Attila, Sinusas, AJ, Le, Viet T, Mason, Steve, Wopperer, Samuel, Alexanderson, Erick, Carvajal-Juarez, Isabel, Rosamond, Thomas, Travin, Mark I. , Packard, René RS, deKemp, Robert A. , Buechel, Ronny R. , Berman, Daniel S. , Carli, Marcelo F. Di , Carvajal-Juarez, Isabel , Carvajal-Juarez, Isabel , Buechel, Ronny R , Shanbhag, Aakash , Zhou, Jianhang , Miller, Robert J.H. , Lemley, Mark , Kavanagh, Paul , Liang, Joanna X. , Builoff, Valerie , Einstein, Andrew Jeffrey , Feher, Attila , Miller, Edward J , Sinusas, Albert J. , Ruddy, Terrence D , Knight, Stacey , Le, Viet T. , Mason, Steve, Chareonthaitawee, Panithaya , Wopperer, Samuel, Alexanderson, Erick , Slipczuk, Leandro , Packard, René R. Sevag , Acampa, Wanda , Al‐Mallah, Mouaz H. , Dey, Damini , Slomka, Piotr J

Mayo Clinic

No container title available | April 15, 2026 | Volume: No volume available | Issue: No issue available | Pages: No page available

10.64898/2026.04.14.26350808 Get It

Abstract Purpose Spatial distribution of coronary artery calcium (CAC) may provide additional prognostic value in patients undergoing SPECT and PET myocardial perfusion imaging (MPI). We aimed to automatically identify CAC in proximal segments from attenuation correction CT (CTAC) scans using artificial intelligence (AI) and to evaluate prognostic significance in two large international multicenter registries. Methods From hybrid MPI/CT imaging (N=43,099) across 15 sites, we included 4,552 most relevant patients with 1) no prior coronary artery disease; 2) AI-derived mild CAC scores (1-99); and 3) normal perfusion (stress total perfusion deficit <5%). The independent associations between AI-identified proximal CAC and major adverse cardiovascular events (MACE) and all-cause mortality (ACM) were evaluated using multivariable Cox regression, likelihood ratio test (LRT), and continuous net reclassification index (NRI). Results Among the patients with mild CAC and normal perfusion (mean age 65±12 years, 51% male), 1,730 (38%) had proximal CAC. Over 3.6 (inter-quartile interval 2.1, 5.2) years follow-up, 599 (13%) and 444 (10%) patients had MACE or ACM, respectively. Proximal CAC was associated with an increased risk of MACE (adjusted hazard ratio [HR] 1.24, 95% CI 1.03–1.48, P=0.02) and ACM (adjusted HR 1.25, 95% CI 1.01–1.53, P=0.04) after the adjustment of CAC score and density, clinical risk factors, and perfusion deficit. Proximal CAC improved the risk stratification of MACE (LRT P=0.02; NRI 12%) and ACM (LRT P=0.04; NRI 12%). Conclusion In patients with mild CAC and normal perfusion, AI detection of proximal CAC identified a higher-risk group for adverse outcomes, highlighting its prognostic utility. Graphical Abstract From patients who underwent hybrid myocardial perfusion imaging (MPI) from 15 sites, we analyzed those without prior coronary artery disease (CAD), mild coronary artery calcium (CAC) scores (1-99), and normal perfusion (stress total perfusion deficit <5%). A previously developed AI model was used to identify CAC lesions in proximal coronary segments on CT attenuation correction maps (CTAC). We evaluated associations with major adverse cardiovascular events (MACE) and all-cause mortality (ACM), showing risk stratification of proximal CAC and improvement by net reclassification index (NRI). CAC lesion color: green, left anterior descending artery (LAD) with left main artery; red, left circumflex artery (LCX); yellow, right coronary artery (RCA). Adjusted hazard ratios (HRs) are shown with 95% confidence intervals.