Objectives This study developed deep neural network (DNN) models capable of accurately classifying major adverse cardiac events (MACE) in patients with acute myocardial infarction (AMI) after hospital discharge, across 3 follow-up intervals: 1, 6, and 12 months. Methods: DNN models were constructed to predict post-discharge MACE across 4 categories. Multiple traditional machine learning models were implemented as controls to benchmark the performance of our DNN approach. All models were evaluated based on their ability to predict MACE occurrence during the specified follow-up periods. Results: The DNN models demonstrated superior predictive performance over conventional machine learning methods, achieving high accuracies of 0.922, 0.884, and 0.913 for the 1-month, 6-month, and 12-month follow-up periods, respectively. Conclusion: The high accuracy of our DNN models highlights their practical advantages for AMI diagnosis and guidance of follow-up treatment. These models can serve as valuable decision support tools, enabling clinicians to optimize the overall management of AMI patients and potentially enhance their hospitalization experience.
Citations
Citations to this article as recorded by
Artificial intelligence and biohealth: the Republic of Korea’s emerging priorities in health care R&D Jong-Koo Lee Osong Public Health and Research Perspectives.2025; 16(4): 309. CrossRef
<sec>
<title>Objectives</title>
<p>The aim of this research was to determine intra-oral factors that affect halitosis in young women.</p></sec>
<sec>
<title>Methods</title>
<p>This study was performed between March 2014 to May 2014, and included 35 women in their 20s with good oral health. Correlation and logistic regression analyses were performed to investigate the change in halitosis immediately, and 1 hour after scaling.</p></sec>
<sec>
<title>Results</title>
<p>In both oral gas (OG) and extraoral gas (EG) groups, halitosis was reduced after scaling compared to before scaling. The logistic regression analysis of oral state factors in OG showed that as oral fluid [odds ratio (OR) = 0.792, <italic>p</italic> = 0.045] and dental plaque (OR = 0.940, <italic>p</italic> = 0.016) decreased by 1 unit, the OR in the OG group decreased (> 50). In addition, as glucose levels in the oral cavity (OR = 1.245, <italic>p</italic> = 0.075) and tongue coating index (OR = 2.912, <italic>p</italic> = 0.064) increased by 1 unit, the OR in the OG group increased (> 50). Furthermore, in the EG group, as oral fluid (OR = 0.66, <italic>p</italic> = 0.01) and dental plaque (OR = 0.95, <italic>p</italic> = 0.04) decreased, the OR in the EG group decreased (> 50) significantly.</p></sec>
<sec>
<title>Conclusion</title>
<p>To control halitosis, it is necessary to increase oral fluid and decrease the amount of tongue plaque. Furthermore, maintaining a healthy oral environment, aided by regular scaling and removal of dental plaque, may significantly control halitosis.</p></sec>
Citations
Citations to this article as recorded by
Prevalence and associated factors of self‐reported halitosis among institutionalized adolescents: Cross‐sectional study Francisco Wilker Mustafa Gomes Muniz, Laura Barreto Moreno, Taciane Menezes da Silviera, Cassiano Kuchenbecker Rösing, Paulo Roberto Grafitti Colussi International Journal of Dental Hygiene.2023; 21(2): 409. CrossRef
Validation of the Romanian Version of the Halitosis Associated Life-Quality Test (HALT) in a Cross-Sectional Study among Young Adults Raluca Briceag, Aureliana Caraiane, Gheorghe Raftu, Melania Lavinia Bratu, Roxana Buzatu, Liana Dehelean, Mariana Bondrescu, Felix Bratosin, Bogdan Andrei Bumbu Healthcare.2023; 11(19): 2660. CrossRef
Role of Probiotics in Halitosis of Oral Origin: A Systematic Review and Meta-Analysis of Randomized Clinical Studies Nansi López-Valverde, Antonio López-Valverde, Bruno Macedo de Sousa, Cinthia Rodríguez, Ana Suárez, Juan Manuel Aragoneses Frontiers in Nutrition.2022;[Epub] CrossRef
Microbiota in intra-oral halitosis – characteristics, effects of antibacterial mouth rinse treatment D. S. Vikina, I. N. Antonova, V. V. Tec, T. E. Lazareva Parodontologiya.2020; 25(1): 4. CrossRef
<p>N-terminal pro-brain natriuretic peptide (NT-proBNP) is a well-known biomarker for the diagnosis and prognosis of heart failure, and is directly associated with myocardial dysfunction. We evaluated the prognostic value of NT-proBNP for major adverse cardiac events (MACEs) among patients with non-ST-segment elevation myocardial infarction (NSTEMI) from the Korea Acute Myocardial Infarction Registry during their mid-term follow-up period. In this paper, we analyzed NT-proBNP according to various MACE and level of NT-proBNP. We used multivariate logistic regression to determine the risk factors according to MACE type and NT-proBNP levels, and to identify the cutoff value for each MACE by using the receiver operating characteristic (ROC) curve. NT-proBNP was a significant variable among cardiac deaths (<italic>p</italic> = 0.016), myocardial infarction (<italic>p</italic> = 0.000), and coronary artery bypass grafting (CABG) (<italic>p</italic> = 0.000) in patients with MACE compared with those without MACE. Two-vessel coronary artery disease (CAD) (<italic>p</italic> = 0.037) and the maximum creatinine kinase (max-CK) (<italic>p</italic> = 0.031) produced significant results in repeat percutaneous coronary intervention. The area under the ROC curve was found to be statistically significant for cardiac death and CABG. NT-proBNP is a useful predictor for 12-month MACEs among patients with NSTEMI and in those with heart failure. We propose that a new index incorporating NT-proBNP, max-CK, and CAD vessel will be useful as a prognostic indicator of MACEs in the future.</p>
Citations
Citations to this article as recorded by
The association between the NT-pro-BNP/eGFR ratio and coronary artery disease severity in Non-ST elevation myocardial infarction Nazlı Turan Şerifler, Funda Başyiğit, Hamza Sunman, Ayşe Nur Özkaya İbiş, Belma Yaman Irish Journal of Medical Science (1971 -).2026;[Epub] CrossRef
Senescence-related Genes as Prognostic Markers for STEMI Patients: LASSO Regression-Based Bioinformatics and External Validation Xing-jie Wang, Lei Huang, Min Hou, Jie Guo Journal of Cardiovascular Translational Research.2025; 18(2): 354. CrossRef
Prognostic value of NT-proBNP and uric acid in acute ST-segment elevation myocardial infarction patients after complete revascularization Li Kang American Journal of Translational Research.2024; 16(8): 4182. CrossRef
Serum IL-38 Level Was Associated with Incidence of MACE in the STEMI Patients Chengbo Lu, Fanghui Zhou, Huimin Xian, Siyuan Sun, Jingkun Yue, Ying Zhang, Qi Zhao, Xing Luo, Yang Li International Journal of General Medicine.2023; Volume 16: 2987. CrossRef
Nomogram M Prognostic Value for Major Adverse Cardiac and Cerebral Events after Elective Cardiac Surgery with Cardiopulmonary Bypass L. B. Berikashvili, A. N. Kuzovlev, M. Yа. Yadgarov, K. K. Kadantseva, E. A. Ozhiganova, V. V. Likhvantsev Messenger of ANESTHESIOLOGY AND RESUSCITATION.2022; 19(2): 6. CrossRef
Association of N-terminal pro-brain natriuretic peptide level with adverse outcomes in patients with acute myocardial infarction: A meta-analysis Shenghui Shen, Jianhua Ye, Xiangzhong Wu, Xiaoling Li Heart & Lung.2021; 50(6): 863. CrossRef
Effect of phenylacetamide isolated from lepidium apetalum on myocardial injury in spontaneously hypertensive rats and its possible mechanism Qi Zhang, Peipei Yuan, Meng Li, Yang Fu, Ying Hou, Yaping Sun, Liyuan Gao, Yaxin Wei, Weisheng Feng, Xiaoke Zheng Pharmaceutical Biology.2020; 58(1): 597. CrossRef
Toward analyzing and synthesizing previous research in early prediction of cardiac arrest using machine learning based on a multi-layered integrative framework Samaneh Layeghian Javan, Mohammad Mehdi Sepehri, Hassan Aghajani Journal of Biomedical Informatics.2018; 88: 70. CrossRef
Objectives
Predicting protein function from the protein–protein interaction network is challenging due to its complexity and huge scale of protein interaction process along with inconsistent pattern. Previously proposed methods such as neighbor counting, network analysis, and graph pattern mining has predicted functions by calculating the rules and probability of patterns inside network. Although these methods have shown good prediction, difficulty still exists in searching several functions that are exceptional from simple rules and patterns as a result of not considering the inconsistent aspect of the interaction network. Methods
In this article, we propose a novel approach using the sequential pattern mining method with gap-constraints. To overcome the inconsistency problem, we suggest frequent functional patterns to include every possible functional sequence—including patterns for which search is limited by the structure of connection or level of neighborhood layer. We also constructed a tree-graph with the most crucial interaction information of the target protein, and generated candidate sets to assign by sequential pattern mining allowing gaps. Results
The parameters of pattern length, maximum gaps, and minimum support were given to find the best setting for the most accurate prediction. The highest accuracy rate was 0.972, which showed better results than the simple neighbor counting approach and link-based approach. Conclusion
The results comparison with other approaches has confirmed that the proposed approach could reach more function candidates that previous methods could not obtain.
Citations
Citations to this article as recorded by
Mining DNA Sequence Patterns with Constraints Using Hybridization of Firefly and Group Search Optimization Kuruva Lakshmanna, Neelu Khare Journal of Intelligent Systems.2018; 27(3): 349. CrossRef
First
Prev
