1
|
Xu F, Dirsch O, Dahmen U. Causal Relationship between Angina and Hepatic Failure as Revealed by Mendelian Randomization. J Clin Med 2024; 13:449. [PMID: 38256583 PMCID: PMC10816156 DOI: 10.3390/jcm13020449] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/04/2023] [Revised: 01/07/2024] [Accepted: 01/11/2024] [Indexed: 01/24/2024] Open
Abstract
BACKGROUND Patients with angina are often suffering from comorbidities such as varying degrees of hepatic dysfunction. However, the impact of angina on the incidence of hepatic failure (HF) remains unclear. METHODS The genetic data were retrieved from genome-wide association studies. Five Mendelian randomization methods were used to investigate the causal relationship between unstable angina (UA), stable angina (SA), and HF. The result of the Inverse variance weighted (IVW) method was deemed the principal result. In addition, we performed a comprehensive sensitivity analysis to verify the robustness of the results. RESULTS The IVW results showed that UA (Odds ratio (OR): 2.055, 95% confidence interval (CI): 1.171-3.606, p = 0.012) was causally associated with the incidence of HF. SA (OR: 1.122, 95% CI: 0.738-1.706, p = 0.591) was not causally associated with the incidence of HF. Sensitivity analysis did not identify any bias in the results. CONCLUSIONS UA turned out to be a risk factor for HF. SA does not have a significant causal effect on HF. Therefore, it is highly recommended that patients with chronic liver disease seek prompt medical attention and undergo regular monitoring of liver function when experiencing UA. This may help them to reduce the risk of HF.
Collapse
Affiliation(s)
- Fengming Xu
- Department of Infectious Diseases, The First Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou 310006, China;
- Else Kröner Graduate School for Medical Students “JSAM”, Jena University Hospital, 07747 Jena, Germany
| | - Olaf Dirsch
- Institute of Pathology, Klinikum Chemnitz gGmbH, 09111 Chemnitz, Germany;
| | - Uta Dahmen
- Department of General, Visceral and Vascular Surgery, Jena University Hospital, 07747 Jena, Germany
| |
Collapse
|
2
|
Guldogan E, Yagin FH, Pinar A, Colak C, Kadry S, Kim J. A proposed tree-based explainable artificial intelligence approach for the prediction of angina pectoris. Sci Rep 2023; 13:22189. [PMID: 38092844 PMCID: PMC10719282 DOI: 10.1038/s41598-023-49673-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/12/2023] [Accepted: 12/11/2023] [Indexed: 12/17/2023] Open
Abstract
Cardiovascular diseases (CVDs) are a serious public health issue that affects and is responsible for numerous fatalities and impairments. Ischemic heart disease (IHD) is one of the most prevalent and deadliest types of CVDs and is responsible for 45% of all CVD-related fatalities. IHD occurs when the blood supply to the heart is reduced due to narrowed or blocked arteries, which causes angina pectoris (AP) chest pain. AP is a common symptom of IHD and can indicate a higher risk of heart attack or sudden cardiac death. Therefore, it is important to diagnose and treat AP promptly and effectively. To forecast AP in women, we constructed a novel artificial intelligence (AI) method employing the tree-based algorithm known as an Explainable Boosting Machine (EBM). EBM is a machine learning (ML) technique that combines the interpretability of linear models with the flexibility and accuracy of gradient boosting. We applied EBM to a dataset of 200 female patients, 100 with AP and 100 without AP, and extracted the most relevant features for AP prediction. We then evaluated the performance of EBM against other AI methods, such as Logistic Regression (LR), Categorical Boosting (CatBoost), eXtreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), and Light Gradient Boosting Machine (LightGBM). We found that EBM was the most accurate and well-balanced technique for forecasting AP, with accuracy (0.925) and Youden's index (0.960). We also looked at the global and local explanations provided by EBM to better understand how each feature affected the prediction and how each patient was classified. Our research showed that EBM is a useful AI method for predicting AP in women and identifying the risk factors related to it. This can help clinicians to provide personalized and evidence-based care for female patients with AP.
Collapse
Affiliation(s)
- Emek Guldogan
- Department of Biostatistics and Medical Informatics, Faculty of Medicine, Inonu University, 44280, Malatya, Turkey
| | - Fatma Hilal Yagin
- Department of Biostatistics and Medical Informatics, Faculty of Medicine, Inonu University, 44280, Malatya, Turkey.
| | - Abdulvahap Pinar
- Department of Biostatistics and Medical Informatics, Faculty of Medicine, Inonu University, 44280, Malatya, Turkey
| | - Cemil Colak
- Department of Biostatistics and Medical Informatics, Faculty of Medicine, Inonu University, 44280, Malatya, Turkey
| | - Seifedine Kadry
- Noroff University College, Kristiansand, Norway
- Artificial Intelligence Research Center (AIRC), Ajman University, 346, Ajman, United Arab Emirates
- Department of Electrical and Computer Engineering, Lebanese American University, Byblos, Lebanon
| | - Jungeun Kim
- Department of Software, Kongju National University, Cheonan, 31080, Korea.
| |
Collapse
|
3
|
Ciliberti G, Guerra F, Pizzi C, Merlo M, Zilio F, Bianco F, Mancone M, Zaffalon D, Gioscia R, Bergamaschi L, Compagnucci P, Armillotta M, Casella M, Sansonetti A, Marini M, Paolisso P, Stronati G, Gallina S, Dello Russo A, Perna GP, Fedele F, Bonmassari R, De Luca G, Tritto I, Piva T, Sinagra G, Ambrosio G, Kaski JC, Verdoia M. Characteristics of patients with recurrent acute myocardial infarction after MINOCA. Prog Cardiovasc Dis 2023; 81:42-47. [PMID: 37852517 DOI: 10.1016/j.pcad.2023.10.006] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/15/2023] [Accepted: 10/15/2023] [Indexed: 10/20/2023]
Abstract
BACKGROUND Myocardial infarction (MI) with non-obstructed coronary arteries (MINOCA) is an increasingly recognized condition with challenging management. Some MINOCA patients ultimately experience recurrent acute MI (re-AMI) during follow-up; however, clinical and angiographic factors predisposing to re-AMI are still poorly defined. METHODS In this retrospective multicenter cohort study we enrolled consecutive patients fulfilling diagnostic criteria of MINOCA according to the IV universal definition of myocardial infarction; characteristics of patients experiencing re-AMI during the follow-up were compared to a group of MINOCA patients without re-AMI. RESULTS 54 patients (mean age 66 ± 13) experienced a subsequent re-AMI after MINOCA and follow-up was available in 44 (81%). Compared to MINOCA patients without re-AMI (n = 695), on first invasive coronary angiography (ICA) MINOCA patients with re-AMI showed less frequent angiographically normal coronaries (37 versus 53%, p = 0.032) and had a higher prevalence of atherosclerosis involving 3 vessels or left main stem (17% versus 8%, p = 0.049). Twenty-four patients (44%) with re-AMI underwent a new ICA: 25% had normal coronary arteries, 12.5% had mild luminal irregularities (<30%), 20.8% had moderate coronary atherosclerosis (30-49%), and 41.7% showed obstructive coronary atherosclerosis (≥50% stenosis). Among patients undergoing new ICA, atherosclerosis progression was observed in 11 (45.8%), 37.5% received revascularization, only 4.5% had low-density lipoprotein cholesterol (LDL_C) under 55 mg/dL and 33% experienced a new cardiovascular disease (CVD) event (death, AMI, heart failure, stroke) at subsequent follow-up. CONCLUSIONS In the present study, only a minority of MINOCA patients with re-AMI underwent a repeated ICA, nearly one out of two showed atherosclerosis progression, often requiring revascularization. Recommended LDL-C levels were achieved only in a minority of the cases, indicating a possible underestimation of CVD risk in this population.
Collapse
Affiliation(s)
- Giuseppe Ciliberti
- Cardiology and Arrhythmology Clinic, Marche Polytechnic University, Azienda Ospedaliero Universitaria delle Marche, Ancona, Italy.
| | - Federico Guerra
- Cardiology and Arrhythmology Clinic, Marche Polytechnic University, Azienda Ospedaliero Universitaria delle Marche, Ancona, Italy
| | - Carmine Pizzi
- Cardiology Unit, IRCCS Azienda Ospedaliera-Universitaria di Bologna; Department of Medical and Surgical Sciences - DIMEC - Alma Mater Studiorum, University of Bologna, Bologna, Italy
| | - Marco Merlo
- Cardiovascular Department, Azienda Sanitaria Universitaria Integrata, University of Trieste, Italy
| | - Filippo Zilio
- Department of Cardiology, S. Chiara Hospital, Trento, Italy
| | - Francesco Bianco
- Department of Pediatric and Congenital Cardiology and Cardiac Surgery, Azienda Ospedaliero-Universitaria "Ospedali Riuniti", Ancona, Italy
| | - Massimo Mancone
- Department of Cardiovascular, Respiratory, Nephrology, Anesthesiology and Geriatric Sciences, Sapienza University of Rome, Rome, Italy
| | - Denise Zaffalon
- Cardiovascular Department, Azienda Sanitaria Universitaria Integrata, University of Trieste, Italy
| | | | - Luca Bergamaschi
- Cardiology Unit, IRCCS Azienda Ospedaliera-Universitaria di Bologna; Department of Medical and Surgical Sciences - DIMEC - Alma Mater Studiorum, University of Bologna, Bologna, Italy
| | - Paolo Compagnucci
- Cardiology and Arrhythmology Clinic, Marche Polytechnic University, Azienda Ospedaliero Universitaria delle Marche, Ancona, Italy
| | - Matteo Armillotta
- Cardiology Unit, IRCCS Azienda Ospedaliera-Universitaria di Bologna; Department of Medical and Surgical Sciences - DIMEC - Alma Mater Studiorum, University of Bologna, Bologna, Italy
| | - Michela Casella
- Cardiology and Arrhythmology Clinic, Marche Polytechnic University, Azienda Ospedaliero Universitaria delle Marche, Ancona, Italy
| | - Angelo Sansonetti
- Cardiology Unit, IRCCS Azienda Ospedaliera-Universitaria di Bologna; Department of Medical and Surgical Sciences - DIMEC - Alma Mater Studiorum, University of Bologna, Bologna, Italy
| | - Marco Marini
- Cardiology and Coronary Care Unit, Marche University Hospital, Ancona, Italy
| | - Pasquale Paolisso
- Cardiovascular Center Aalst, OLV-Clinic, Aalst, Belgium; Dept. of Advanced Biomedical Sciences, University Federico II, Naples, Italy
| | - Giulia Stronati
- Cardiology and Arrhythmology Clinic, Marche Polytechnic University, Azienda Ospedaliero Universitaria delle Marche, Ancona, Italy
| | - Sabina Gallina
- Department of Neuroscience, Imaging and clinical Sciences, "G. d'Annunzio" University, Chieti, Italy
| | - Antonio Dello Russo
- Cardiology and Arrhythmology Clinic, Marche Polytechnic University, Azienda Ospedaliero Universitaria delle Marche, Ancona, Italy
| | - Gian Piero Perna
- Cardiology and Coronary Care Unit, Marche University Hospital, Ancona, Italy
| | - Francesco Fedele
- Department of Cardiovascular, Respiratory, Nephrology, Anesthesiology and Geriatric Sciences, Sapienza University of Rome, Rome, Italy
| | | | - Giuseppe De Luca
- Division of Cardiology, Policlinico AOU G. Martino, and Department of Clinical and Experimental Medicine, Cardiology Unit, University of Messina, Messina, Italy
| | - Isabella Tritto
- Division of Cardiology, University of Perugia, School of Medicine, Perugia, Italy
| | - Tommaso Piva
- Cardiology and Coronary Care Unit, Marche University Hospital, Ancona, Italy
| | - Gianfranco Sinagra
- Cardiovascular Department, Azienda Sanitaria Universitaria Integrata, University of Trieste, Italy
| | - Giuseppe Ambrosio
- Division of Cardiology, University of Perugia, School of Medicine, Perugia, Italy
| | - Juan Carlos Kaski
- Molecular and Clinical Sciences, St George's, University of London, London, UK
| | | |
Collapse
|