• Risk Prediction of Major Adver...

Treffer: Risk Prediction of Major Adverse Cardiovascular Events Within One Year After Percutaneous Coronary Intervention in Patients With Acute Coronary Syndrome: Machine Learning-Based Time-to-Event Analysis.

Title:
Risk Prediction of Major Adverse Cardiovascular Events Within One Year After Percutaneous Coronary Intervention in Patients With Acute Coronary Syndrome: Machine Learning-Based Time-to-Event Analysis.
Authors:
Choi HJ; Department of Thoracic and Cardiovascular Surgery, Seoul Metropolitan Government-Seoul National University Boramae Medical Center, Seoul National University College of Medicine, Seoul, Republic of Korea., Lee C; Department of Artificial Intelligence, Korea University, Seoul, Republic of Korea., Kim HL; Division of Cardiology, Department of Internal Medicine, Seoul Metropolitan Government-Seoul National University Boramae Medical Center, Seoul National University College of Medicine, Seoul, Republic of Korea., Son YJ; Red Cross College of Nursing, Chung-Ang University, Seoul, Republic of Korea.
Source:
JMIR medical informatics [JMIR Med Inform] 2025 Nov 27; Vol. 13, pp. e81778. Date of Electronic Publication: 2025 Nov 27.
Publication Type:
Journal Article; Observational Study
Language:
English
Journal Info:
Publisher: JMIR Publications Country of Publication: Canada NLM ID: 101645109 Publication Model: Electronic Cited Medium: Internet ISSN: 2291-9694 (Electronic) Linking ISSN: 22919694 NLM ISO Abbreviation: JMIR Med Inform Subsets: MEDLINE
Imprint Name(s):
Original Publication: Toronto : JMIR Publications, [2013]-
MeSH Terms:
Acute Coronary Syndrome*/complications , Acute Coronary Syndrome*/surgery , Percutaneous Coronary Intervention*/adverse effects , Percutaneous Coronary Intervention*/statistics & numerical data , Cardiovascular Diseases*/epidemiology , Cardiovascular Diseases*/etiology , Postoperative Complications*/epidemiology , Postoperative Complications*/etiology , Time Factors* , Predictive Learning Models*, Humans ; Male ; Female ; Middle Aged ; Aged ; Predictive Value of Tests ; Republic of Korea/epidemiology ; Follow-Up Studies ; Severity of Illness Index ; Glomerular Filtration Rate ; Risk Assessment/methods ; Risk Factors
References:
J Saudi Heart Assoc. 2022 Jun 11;34(2):100-109. (PMID: 36237223)
Clin Interv Aging. 2020 May 21;15:715-722. (PMID: 32546989)
PLoS One. 2021 Aug 2;16(8):e0254894. (PMID: 34339432)
BMJ. 2024 Apr 16;385:e078378. (PMID: 38626948)
J Geriatr Cardiol. 2015 Nov;12(6):626-33. (PMID: 26788039)
J Korean Soc Radiol. 2022 Nov;83(6):1219-1228. (PMID: 36545410)
Medicina (Kaunas). 2020 Sep 08;56(9):. (PMID: 32911665)
J Stat Softw. 2012 Sep;50(11):1-23. (PMID: 25317082)
Circulation. 2023 Aug 29;148(9):e9-e119. (PMID: 37471501)
J Clin Med. 2022 Apr 23;11(9):. (PMID: 35566504)
Sci Rep. 2023 Mar 1;13(1):3447. (PMID: 36859606)
Ann Pharmacother. 2004 Sep;38(9):1369-76. (PMID: 15266038)
EuroIntervention. 2024 Feb 05;20(3):e198-e206. (PMID: 38343370)
BMC Nephrol. 2018 Dec 22;19(1):374. (PMID: 30577763)
PLoS One. 2019 May 16;14(5):e0216805. (PMID: 31095602)
Basic Clin Pharmacol Toxicol. 2021 Feb;128(2):305-314. (PMID: 32991776)
Comput Inform Nurs. 2024 May 01;42(5):388-395. (PMID: 39248449)
Crit Care Nurse. 2017 Feb;37(1):13-26. (PMID: 28148611)
Appl Clin Inform. 2022 May;13(3):720-740. (PMID: 35617971)
J Cardiol. 2019 Aug;74(2):95-101. (PMID: 31053505)
Sci Rep. 2020 Jul 21;10(1):12028. (PMID: 32694522)
J Clin Med. 2021 Oct 01;10(19):. (PMID: 34640592)
BMC Med Res Methodol. 2021 Nov 6;21(1):241. (PMID: 34742250)
Am J Cardiol. 2019 May 1;123(9):1387-1392. (PMID: 30797559)
Comput Math Methods Med. 2021 Jul 5;2021:7252280. (PMID: 34285708)
Adv Exp Med Biol. 2020;1177:37-73. (PMID: 32246443)
Dig Dis Sci. 2017 Feb;62(2):543-549. (PMID: 27933471)
Stat Med. 2019 Mar 30;38(7):1276-1296. (PMID: 30357870)
Ann Med. 2021 Dec;53(1):817-823. (PMID: 34080496)
Int J Environ Res Public Health. 2022 May 07;19(9):. (PMID: 35565087)
J Epidemiol Glob Health. 2021 Jun;11(2):169-177. (PMID: 33605111)
Clin Kidney J. 2021 Oct 22;15(2):338-346. (PMID: 35145648)
J Clin Med. 2021 May 22;10(11):. (PMID: 34067233)
Stat Med. 2013 Jun 15;32(13):2173-84. (PMID: 23172755)
BMC Complement Med Ther. 2023 Jan 19;23(1):16. (PMID: 36658513)
J Am Coll Cardiol. 2022 Jan 18;79(2):197-215. (PMID: 34895951)
Eur Heart J. 2021 Apr 7;42(14):1289-1367. (PMID: 32860058)
BMC Geriatr. 2024 Apr 12;24(1):337. (PMID: 38609875)
Catheter Cardiovasc Interv. 2018 Oct 1;92(4):717-731. (PMID: 29691963)
Eur Heart J. 2020 Jan 14;41(3):407-477. (PMID: 31504439)
PLoS One. 2021 Jun 11;16(6):e0249338. (PMID: 34115750)
J Am Coll Cardiol. 2022 Jul 26;80(4):348-372. (PMID: 35863852)
Eur Heart J. 2024 Sep 29;45(36):3415-3537. (PMID: 39210710)
Eur Heart J. 2023 Oct 12;44(38):3720-3826. (PMID: 37622654)
Medicine (Baltimore). 2022 Aug 26;101(34):e30100. (PMID: 36042595)
Circulation. 2018 Feb 27;137(9):961-972. (PMID: 29483172)
J Korean Med Sci. 2023 Apr 17;38(15):e119. (PMID: 37069813)
BMJ. 2022 May 25;377:e059818. (PMID: 35613721)
Clin Kidney J. 2023 Sep 01;16(12):2626-2638. (PMID: 38046040)
Contributed Indexing:
Keywords: acute coronary syndrome; machine learning; major adverse cardiovascular events; percutaneous coronary intervention; predictive models; survival analysis
Entry Date(s):
Date Created: 20251127 Date Completed: 20251210 Latest Revision: 20251215
Update Code:
20251215
PubMed Central ID:
PMC12699253
DOI:
10.2196/81778
PMID:
41308188
Database:
MEDLINE

Weitere Informationen

Background: Patients with acute coronary syndrome (ACS) who undergo percutaneous coronary intervention (PCI) remain at high risk for major adverse cardiovascular events (MACE). Conventional risk scores may not capture dynamic or nonlinear changes in postdischarge MACE risk, whereas machine learning (ML) approaches can improve predictive performance. However, few ML models have incorporated time-to-event analysis to reflect changes in MACE risk over time.
Objective: This study aimed to develop a time-to-event ML model for predicting MACE after PCI in patients with ACS and to identify the risk factors with time-varying contributions.
Methods: We analyzed electronic health records of 3159 patients with ACS who underwent PCI at a tertiary hospital in South Korea between 2008 and 2020. Six time-to-event ML models were developed using 54 variables. Model performance was evaluated using the time-dependent concordance index and Brier score. Variable importance was assessed using permutation importance and visualized with partial dependence plots to identify variables contributing to MACE risk over time.
Results: During a median follow-up of 3.8 years, 626 (19.8%) patients experienced MACE. The best-performing model achieved a time-dependent concordance index of 0.743 at day 30 and 0.616 at 1 year. Time-dependent Brier scores increased and remained stable across all ML models. Key predictors included contrast volume, age, medication adherence, coronary artery disease severity, and glomerular filtration rate. Contrast volume ≥300 mL, age ≥60 years, and medication adherence score ≥30 were associated with early postdischarge risk, whereas coronary artery disease severity and glomerular filtration rate became more influential beyond 60 days.
Conclusions: The proposed time-to-event ML model effectively captured dynamic risk patterns after PCI and identified key predictors with time-varying effects. These findings may support individualized postdischarge management and early intervention strategies to prevent MACE in high-risk patients.
(©Hong-Jae Choi, Changhee Lee, Hack-Lyoung Kim, Youn-Jung Son. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 27.11.2025.)