Tetsuya Matoba

Associate Professor

Kyushu University Hospital
Country flagJapan

Research Interests

ApplyKite TwinLearns as you apply

Make your next move.

Prepare your application

Review drafts before you send them.

Explore related searches

Articles (11)

BACKGROUND Accurately predicting left ventricular ejection fraction (LVEF) recovery after percutaneous coronary intervention (PCI) in patients with chronic coronary syndrome (CCS) is crucial for clinical decision-making. OBJECTIVE This study aimed to develop and compare multiple machine learning (ML) models to predict LVEF recovery and identify key contributing features. METHODS We retrospectively analyzed 520 patients with CCS from the Clinical Deep Data Accumulation System database. Patients were categorized into 4 binary classification tasks based on baseline LVEF (≥50% or <50%) and degree of recovery: (1) good recovery, defined as an LVEF increase of >10% compared with ≤0%; and (2) normal recovery, defined as an LVEF increase of 0% to 10% compared with ≤0%. For each task, 3 feature selection strategies (all features, least absolute shrinkage and selection operator [LASSO] regression, and recursive feature elimination [RFE]) were combined with 4 ML algorithms (extreme gradient boosting [XGBoost], categorical boosting, light gradient boosting machine, and random forest), resulting in 48 models. Models were evaluated using 10-fold cross-validation and assessed by the area under the curve (AUC), decision curve analysis, and calibration plots. RESULTS The highest AUCs were achieved by RFE combined with XGBoost (AUC=0.93) for preserved LVEF with good recovery, LASSO combined with XGBoost (AUC=0.79) for preserved LVEF with normal recovery, LASSO combined with XGBoost (AUC=0.88) for reduced LVEF with good recovery, and RFE combined with XGBoost (AUC=0.84) for reduced LVEF with normal recovery. Shapley Additive Explanation analysis identified uric acid, platelets, hematocrit, brain natriuretic peptide, glycated hemoglobin, glucose, creatinine, baseline LVEF, left ventricular end-diastolic internal diameter, heart rate, R wave amplitude in V5, and R wave amplitude in V6 as important predictive factors of LVEF recovery. CONCLUSIONS ML models incorporating feature selection strategies demonstrated strong predictive performance for LVEF recovery after PCI. These interpretable models may support clinical decision-making and can improve the management of patients with CCS after PCI. CLINICALTRIAL

Year:

2025

Background Rhythm control therapy improves the quality of life and prognosis of patients with atrial fibrillation (AF). We assessed the characteristics and clinical outcomes of AF patients with stable coronary artery disease (CAD) undergoing rhythm control therapy. Methods We analyzed 2215 participants from the Atrial Fibrillation and Ischemic Events with Rivaroxaban in Patients with Stable Coronary Artery Disease (AFIRE) trial, including 588 patients who received rhythm control therapy and 1627 who did not. Results At baseline, patients who received rhythm control therapy were generally younger, exhibited a higher prevalence of paroxysmal AF, experienced less heart failure, and had lower CHADS2 scores (CHF, hypertension, age ≥ 75 years, type 2 diabetes, and previous stroke or transient ischemic attack [doubled]) than those who did not. Among the rivaroxaban monotherapy and combination therapy groups, patients with a history of rhythm control therapy showed a lower incidence of the primary efficacy endpoint (a composite of stroke, systemic embolism, myocardial infarction, unstable angina requiring revascularization, or death). However, following multivariate analysis and propensity score matching, no statistically significant difference in the primary efficacy endpoint was observed between patients with and without prior rhythm control therapy (adjusted HR 0.75, 95% CI 0.37–1.51, p = 0.43 in the rivaroxaban group; adjusted HR 0.75, 95% CI 0.43–1.30, p = 0.30 in the combination therapy group). Conclusions The initially observed benefit of rhythm control therapy was not significant after adjusting for baseline characteristics in patients with AF and stable CAD treated with rivaroxaban with or without additional antiplatelet therapy.

Year:

2025

Backgrounds Atrial fibrillation (AF) is a risk factor for adverse cardiovascular outcomes in patients with stable coronary artery disease (CAD). The prognostic relevance of lower systolic blood pressure (SBP) and the optimal antithrombotic strategy in patients with AF and CAD remain to be clarified. Methods This post-hoc analysis of the AFIRE (Atrial Fibrillation and Ischemic Events with Rivaroxaban in Patients with Stable Coronary Artery Disease) trial stratified participants based on median SBP at baseline: >126 mmHg (High SBP group, n=1042) and ≤126 mmHg (Low SBP group, n=1093). The primary efficacy endpoint was a composite of cardiovascular events and all-cause death. The primary safety endpoint was major bleeding. Results The mean SBP was 139 mmHg and 114 mmHg in the High and Low SBP groups, respectively. In the propensity score-matched cohort (n=1684), the Low SBP group had a significantly higher incidence of the primary efficacy endpoint (hazard ratio [HR], 1.38; 95% confidence interval [CI], 1.01–1.88; p=0.039), while the primary safety endpoint was comparable between groups. In the Low SBP group, rivaroxaban monotherapy was associated with lower risks of both the primary efficacy (HR, 0.66; 95% CI, 0.41–0.86; p=0.006) and safety endpoints (HR, 0.40; 95% CI, 0.22–0.74; p=0.003) compared with combination therapy, whereas no significant differences were observed in the High SBP group. Conclusions Lower SBP was associated with increased risk of cardiovascular events and all-cause death. Rivaroxaban monotherapy demonstrated more favorable efficacy and safety outcomes compared with combination therapy, particularly among patients with lower SBP.

Year:

2025

Background Spontaneous coronary artery dissection (SCAD) is characterized by the unexpected formation of an intramural haemorrhage within the wall of an epicardial coronary artery with or without an intimal tear, resulting in an acute coronary syndrome. Haemophilia A and B are inherited X-linked recessive bleeding disorders caused by the absence or dysfunction of clotting factors VIII (FVIII) or IX. Case summary A 50-year-old male patient with a history of haemophilia A, type 2 diabetes and smoking presented to our facility with prolonged chest pain. His laboratory results revealed increased myocardial biomarkers and an elevated activated partial thromboplastin time despite the absence of previous bleeding tendencies or coagulation factor replacement therapy. Non-ST-elevation myocardial infarction was suspected, and coronary angiography detected severe stenosis in the left circumflex artery. Intravascular ultrasound confirmed an intramural haematoma without an intimal tear, resulting in an SCAD diagnosis. The patient, with no bleeding complications, was conservatively treated with medications, including aspirin and bisoprolol. A coronary computed tomographic angiography (CCTA) on day 3 revealed haematoma resolution, and the patient was discharged on day 11. CCTA at 8 months detected the disappearance of the previously seen intramural haematoma. Discussion We revealed two important clinical issues: (i) SCAD in a male patient with haemophilia and (ii) the usefulness of CCTA in observing SCAD lesions.

Year:

2025

Year:

2023

Year:

2022

Year:

2022

Year:

2021

Year:

2021

Year:

2021

Year:

2021

Collaborators (10)

Kazuomi Kario

-

JAPAN
View details

Hideo Fujita

professor

Jichi Medical University Saitama Medical Center

JAPAN
View details

Masato Nakamura

Professor

Toho University

JAPAN
View details

Yoshihiro Miyamoto

Director General

National Cerebral and Cardiovascular Center

JAPAN
View details

Taishi Nakamura

Associate Professor

Kumamoto University Hospital

JAPAN
View details

Masaharu Nakayama

Professor

Tohoku University

JAPAN
View details

Kenichi Tsujita

Professor of Medicine

Kumamoto University

JAPAN
View details

Satoshi Yasuda

Professor and chairmam

Tohoku University graduate school of medicine

JAPAN
View details

Junya Ako

Kitasato University

JAPAN
View details

Jun Takahashi

Associate Professor

Tohoku University Hospital

JAPAN
View details