1
|
Tan MC, Dinh D, Gayed D, Liang D, Brennan A, Duffy SJ, Clark D, Ajani A, Oqueli E, Roberts L, Reid C, Freeman M, Chandrasekhar J. Associations Between Dual Antiplatelet Therapy Score and Long-Term Mortality After Percutaneous Coronary Intervention: Analysis of More Than 27,000 Patients. Can J Cardiol 2024; 40:2045-2053. [PMID: 39084254 DOI: 10.1016/j.cjca.2024.06.030] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/11/2023] [Revised: 06/12/2024] [Accepted: 06/30/2024] [Indexed: 08/02/2024] Open
Abstract
BACKGROUND The dual antiplatelet therapy (DAPT) score was developed to identify patients undergoing percutaneous coronary intervention (PCI) who are likely to derive benefit (score ≥ 2) or harm (score < 2) from extended DAPT beyond 1 year after PCI in terms of ischemic and bleeding outcomes. We examined the associations between DAPT score at index PCI and long-term mortality from an all-comers PCI registry in patients receiving DAPT according to the standard of care. METHODS We retrospectively examined prospectively collected data from the Melbourne Interventional Group PCI database (2005-2018) and grouped patients as having DAPT score ≥ 2 or < 2. Long-term mortality was assessed from the Australian National Death Index linkage. The primary end point was long-term mortality as determined using survival analysis. Secondary end points included in-hospital events and 30-day major adverse cardiac events (MACE), a composite of death, myocardial infarction, or target vessel revascularisation. RESULTS Of 27,740 study patients, 9402 (33.9%) had DAPT score ≥ 2. Patients with DAPT score ≥ 2 were younger, included more women, and had a higher prevalence of cardiovascular risk factors. Patients with DAPT score ≥ 2 had higher in-hospital mortality (3.0% vs 1.0%), major bleeding (2.3% vs 1.6%), 30-day MACE (7.1% vs 3.1%), and long-term mortality at a median follow-up of 5.17 years (21.9% vs 16.5%) P < 0.001 for all. CONCLUSIONS One-third of all-comer patients undergoing PCI had a DAPT score ≥ 2 with greater short-term ischemic and bleeding risk, and higher long-term mortality. Risk assessment with the DAPT score may guide the duration and intensity of DAPT beyond the early post-PCI period.
Collapse
Affiliation(s)
- Mae Chyi Tan
- Department of Cardiology, Eastern Health, Box Hill, Victoria, Australia
| | - Diem Dinh
- Centre of Cardiovascular Research and Education in Therapeutics, Monash University, Melbourne, Victoria, Australia
| | - Daniel Gayed
- Department of Cardiology, Eastern Health, Box Hill, Victoria, Australia
| | - Danlu Liang
- Department of Cardiology, Eastern Health, Box Hill, Victoria, Australia
| | - Angela Brennan
- Centre of Cardiovascular Research and Education in Therapeutics, Monash University, Melbourne, Victoria, Australia
| | | | - David Clark
- University of Melbourne, Melbourne, Victoria, Australia; Department of Cardiology, Austin Health, Heidelberg, Victoria, Australia
| | - Andrew Ajani
- Department of Cardiology, Royal Melbourne Hospital, Parkville, Victoria, Australia
| | - Ernesto Oqueli
- Department of Cardiology, Grampians Health Ballarat, Ballarat, Victoria, Australia
| | - Louise Roberts
- Department of Cardiology, Eastern Health, Box Hill, Victoria, Australia; Eastern Health Clinical School, Monash University, Clayton, Victoria, Australia
| | - Christopher Reid
- University of Melbourne, Melbourne, Victoria, Australia; Curtin University, Perth, Western Australia, Australia
| | - Melanie Freeman
- Department of Cardiology, Eastern Health, Box Hill, Victoria, Australia
| | - Jaya Chandrasekhar
- Department of Cardiology, Eastern Health, Box Hill, Victoria, Australia; Eastern Health Clinical School, Monash University, Clayton, Victoria, Australia.
| |
Collapse
|
2
|
Li F, Rasmy L, Xiang Y, Feng J, Abdelhameed A, Hu X, Sun Z, Aguilar D, Dhoble A, Du J, Wang Q, Niu S, Dang Y, Zhang X, Xie Z, Nian Y, He J, Zhou Y, Li J, Prosperi M, Bian J, Zhi D, Tao C. Dynamic Prognosis Prediction for Patients on DAPT After Drug-Eluting Stent Implantation: Model Development and Validation. J Am Heart Assoc 2024; 13:e029900. [PMID: 38293921 PMCID: PMC11056175 DOI: 10.1161/jaha.123.029900] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/20/2023] [Accepted: 12/01/2023] [Indexed: 02/01/2024]
Abstract
BACKGROUND The rapid evolution of artificial intelligence (AI) in conjunction with recent updates in dual antiplatelet therapy (DAPT) management guidelines emphasizes the necessity for innovative models to predict ischemic or bleeding events after drug-eluting stent implantation. Leveraging AI for dynamic prediction has the potential to revolutionize risk stratification and provide personalized decision support for DAPT management. METHODS AND RESULTS We developed and validated a new AI-based pipeline using retrospective data of drug-eluting stent-treated patients, sourced from the Cerner Health Facts data set (n=98 236) and Optum's de-identified Clinformatics Data Mart Database (n=9978). The 36 months following drug-eluting stent implantation were designated as our primary forecasting interval, further segmented into 6 sequential prediction windows. We evaluated 5 distinct AI algorithms for their precision in predicting ischemic and bleeding risks. Model discriminative accuracy was assessed using the area under the receiver operating characteristic curve, among other metrics. The weighted light gradient boosting machine stood out as the preeminent model, thus earning its place as our AI-DAPT model. The AI-DAPT demonstrated peak accuracy in the 30 to 36 months window, charting an area under the receiver operating characteristic curve of 90% [95% CI, 88%-92%] for ischemia and 84% [95% CI, 82%-87%] for bleeding predictions. CONCLUSIONS Our AI-DAPT excels in formulating iterative, refined dynamic predictions by assimilating ongoing updates from patients' clinical profiles, holding value as a novel smart clinical tool to facilitate optimal DAPT duration management with high accuracy and adaptability.
Collapse
Affiliation(s)
- Fang Li
- McWilliams School of Biomedical InformaticsUniversity of Texas Health Science Center at HoustonHoustonTXUSA
- Department of Artificial Intelligence and InformaticsMayo ClinicJacksonvilleFLUSA
| | - Laila Rasmy
- McWilliams School of Biomedical InformaticsUniversity of Texas Health Science Center at HoustonHoustonTXUSA
| | - Yang Xiang
- Peng Cheng LaboratoryShenzhenGuangdongChina
| | - Jingna Feng
- McWilliams School of Biomedical InformaticsUniversity of Texas Health Science Center at HoustonHoustonTXUSA
- Department of Artificial Intelligence and InformaticsMayo ClinicJacksonvilleFLUSA
| | - Ahmed Abdelhameed
- McWilliams School of Biomedical InformaticsUniversity of Texas Health Science Center at HoustonHoustonTXUSA
- Department of Artificial Intelligence and InformaticsMayo ClinicJacksonvilleFLUSA
| | - Xinyue Hu
- McWilliams School of Biomedical InformaticsUniversity of Texas Health Science Center at HoustonHoustonTXUSA
- Department of Artificial Intelligence and InformaticsMayo ClinicJacksonvilleFLUSA
| | - Zenan Sun
- McWilliams School of Biomedical InformaticsUniversity of Texas Health Science Center at HoustonHoustonTXUSA
| | - David Aguilar
- Department of Internal Medicine, McGovern Medical SchoolUniversity of Texas Health Science Center at HoustonHoustonTXUSA
- LSU School of Medicine, LSU Health New OrleansNew OrleansLAUSA
| | - Abhijeet Dhoble
- Department of Internal Medicine, McGovern Medical SchoolUniversity of Texas Health Science Center at HoustonHoustonTXUSA
| | - Jingcheng Du
- McWilliams School of Biomedical InformaticsUniversity of Texas Health Science Center at HoustonHoustonTXUSA
| | - Qing Wang
- McWilliams School of Biomedical InformaticsUniversity of Texas Health Science Center at HoustonHoustonTXUSA
| | - Shuteng Niu
- McWilliams School of Biomedical InformaticsUniversity of Texas Health Science Center at HoustonHoustonTXUSA
| | - Yifang Dang
- McWilliams School of Biomedical InformaticsUniversity of Texas Health Science Center at HoustonHoustonTXUSA
| | - Xinyuan Zhang
- McWilliams School of Biomedical InformaticsUniversity of Texas Health Science Center at HoustonHoustonTXUSA
| | - Ziqian Xie
- McWilliams School of Biomedical InformaticsUniversity of Texas Health Science Center at HoustonHoustonTXUSA
| | - Yi Nian
- McWilliams School of Biomedical InformaticsUniversity of Texas Health Science Center at HoustonHoustonTXUSA
| | - JianPing He
- McWilliams School of Biomedical InformaticsUniversity of Texas Health Science Center at HoustonHoustonTXUSA
| | - Yujia Zhou
- McWilliams School of Biomedical InformaticsUniversity of Texas Health Science Center at HoustonHoustonTXUSA
| | - Jianfu Li
- McWilliams School of Biomedical InformaticsUniversity of Texas Health Science Center at HoustonHoustonTXUSA
- Department of Artificial Intelligence and InformaticsMayo ClinicJacksonvilleFLUSA
| | - Mattia Prosperi
- Data Intelligence Systems Lab, Department of Epidemiology, College of Public Health and Health Professions & College of MedicineUniversity of FloridaGainesvilleFLUSA
| | - Jiang Bian
- Department of Health Outcomes and Biomedical Informatics, College of MedicineUniversity of FloridaGainesvilleFLUSA
| | - Degui Zhi
- McWilliams School of Biomedical InformaticsUniversity of Texas Health Science Center at HoustonHoustonTXUSA
| | - Cui Tao
- McWilliams School of Biomedical InformaticsUniversity of Texas Health Science Center at HoustonHoustonTXUSA
- Department of Artificial Intelligence and InformaticsMayo ClinicJacksonvilleFLUSA
| |
Collapse
|
3
|
Persampieri S, Castini D, Lupi A, Guazzi M. Untangling the difficult interplay between ischemic and hemorrhagic risk: The role of risk scores. World J Cardiol 2022; 14:96-107. [PMID: 35316974 PMCID: PMC8900521 DOI: 10.4330/wjc.v14.i2.96] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/17/2021] [Revised: 08/01/2021] [Accepted: 01/23/2022] [Indexed: 02/06/2023] Open
Abstract
BACKGROUND Bleedings are an independent risk factor for subsequent mortality in patients with acute coronary syndromes (ACS) and in those undergoing percutaneous coronary intervention. This represents a hazard equivalent to or greater than that for recurrent ACS. Dual antiplatelet therapy (DAPT) represents the cornerstone in the secondary prevention of thrombotic events, but the benefit of such therapy is counteracted by the increased hemorrhagic complications. Therefore, an early and individualized patient risk stratification can help to identify high-risk patients who could benefit the most from intensive medical therapies while minimizing unnecessary treatment complications in low-risk patients.
AIM To review existing literature and gain better understanding of the role of ischemic and hemorrhagic risk scores in patients with ischemic heart disease (IHD).
METHODS We used a combination of terms potentially used in literature describing the most common ischemic and hemorrhagic risk scores to search in PubMed as well as references of full-length articles.
RESULTS In this review we briefly describe the most important ischemic and bleeding scores that can be adopted in patients with IHD, focusing on GRACE, CHA2DS2-Vasc, PARIS CTE, DAPT, CRUSADE, ACUITY, HAS-BLED, PARIS MB and PRECISE-DAPT score. In the second part of this review, we try to define a possible approach to the IHD patient, using the most suitable scores to stratify patient risk and decide the most appropriate patient treatment.
CONCLUSION It becomes evident that risk scores by themselves can’t be the solution to balance the ischemic/bleeding risk of an IHD patient. Instead, some risk factors that are commonly associated with an elevated risk profile and that are already included in risk scores should be the focus of the clinician while he/she is taking care of a patient affected by IHD.
Collapse
Affiliation(s)
| | - Diego Castini
- Division of Cardiology, Ospedale San Paolo, Milan 20142, Italy
- Department of Clinical Sciences, University of Milan, Milan 20122, Italy
| | - Alessandro Lupi
- Division of Cardiology, Ospedale San Biagio, Verbania 28845, Italy
| | - Marco Guazzi
- Department of Clinical Sciences, University of Milan, Milan 20122, Italy
- Division of Cardiology, San Paolo Hospital, ASST Santi Paolo e Carlo, Milan 20142, Italy
| |
Collapse
|
4
|
Yokoi H, Oda E, Kaneko K, Matsubayashi K. Duration and clinical outcome of dual antiplatelet therapy after percutaneous coronary intervention: a retrospective cohort study using a medical information database from Japanese hospitals. Cardiovasc Interv Ther 2022; 37:465-474. [PMID: 35141843 PMCID: PMC9197891 DOI: 10.1007/s12928-021-00833-z] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/03/2021] [Accepted: 12/09/2021] [Indexed: 01/01/2023]
Abstract
In this real-world, retrospective cohort study of 9753 patients in Japan prescribed dual antiplatelet therapy (DAPT) following percutaneous coronary intervention (PCI), we investigated DAPT duration and determined factors associated with early DAPT discontinuation and with event rates in patients who discontinued DAPT. The study period was April 1, 2012–March 31, 2018; endpoints comprised composite efficacy [death, myocardial infarction (MI), and stroke] and bleeding (intracranial, gastrointestinal, and requiring transfusion) endpoints. Overall, 68.8% of patients were continuing DAPT at 3 months post-PCI. Patients without major efficacy or safety events within 3 months after index PCI were included in a landmark analysis set (LAS; n = 7056), and categorized as DAPT ≥ 3 months (continuation) versus < 3 months (discontinuation). In the two LAS analysis groups, there was no difference in the composite bleeding endpoint (P = 0.067), although the incidence of the composite efficacy endpoint was higher in the discontinuation group (P < 0.001). In multivariate regression analysis, age ≥ 75 years, minor bleeding after PCI, history of cerebral infarction, history of cerebral or gastrointestinal bleeding, atrial fibrillation, dialysis, and anticoagulant use after PCI were associated with early DAPT discontinuation. Acute coronary syndrome, history of MI, kidney disorder, and anticoagulant use after PCI were associated with the composite efficacy endpoint in the discontinuation group. In conclusion, early DAPT discontinuation is more likely in patients at high bleeding risk, but may influence the occurrence of ischemic events in these patients. Determination of DAPT duration should take into account potential ischemic risk, even in patients at high bleeding risk.
Collapse
Affiliation(s)
- Hiroyoshi Yokoi
- Cardiovascular Medicine Center, Fukuoka Sanno Hospital, 3-6-45 Momochihama, Sawara-ku, Fukuoka, 814-0001, Japan. .,International University of Health and Welfare, Tochigi, Japan.
| | - Eisei Oda
- StatLink Medical Statistics Consulting Service, Tokyo, Japan
| | - Kazuki Kaneko
- EBM Unit, Medical Data Vision Co., Ltd., Tokyo, Japan
| | - Kenta Matsubayashi
- Clinical Development Department II, Daiichi Sankyo Co., Ltd., Tokyo, Japan
| |
Collapse
|