Hideo Fujita

professor

Jichi Medical University Saitama Medical Center
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

About

Professor Hideo Fujita is a faculty member at Jichi Medical University Saitama Medical Center in Japan. His research primarily focuses on cardiovascular medicine, with recent articles examining outcomes related to acute myocardial infarction, left ventricular remodeling, and strategies for coronary artery interventions. He has contributed significantly to understanding clinical outcomes in patients with heart failure and those experiencing ST-elevation myocardial infarction.

Articles (14)

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 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.

Year:

2025

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

Aims Catheter ablation for premature ventricular contractions (PVCs) triggering ventricular fibrillation (VF) after acute myocardial infarction (AMI) has proven effective, with Purkinje potentials often serving as the target. However, the electrophysiological features of Purkinje potentials and their relationship with the conduction system in VF-triggering PVCs remain unclear. Methods This multicentre retrospective study analysed patients who underwent catheter ablation for VF-triggering PVCs during the acute or subacute phase of AMI. Characteristics of Purkinje potentials, including retrograde conduction from the Purkinje network and subsequent anterograde conduction to the right bundle branch (RB), were evaluated for PVC morphology. Results Fifty-three patients (mean age 66±11 years; 13% female) with 67 VF-triggering PVCs were analysed. The mean PVC width was 157 ± 42 ms, with 87% showing RB branch block morphology. Purkinje potentials preceded 72% of PVCs (mean interval 68 ± 42 ms). PVCs with preceding Purkinje potentials had narrower QRS duration (145 ± 26 ms vs. 198 ± 57 ms, P < 0.0001). The coupling interval from the preceding sinus beat was inversely correlated with the interval from Purkinje potential to PVC onset (P < 0.0001). Retrograde Purkinje conduction with subsequent anterograde RB conduction was identified in 9%. In these cases, the coupling interval from the preceding sinus beat was longer (391 ± 12 ms vs. 467 ± 34 ms, P = 0.041). Conclusion Purkinje potentials show distinct properties that influence both QRS duration and PVC timing. The presence of preceding Purkinje potentials together with QRS duration may help guide ablation strategies. In rare cases, Purkinje activity conducts retrogradely from the left bundle and anterogradely through the RB, modifying PVC morphology.

Year:

2025

Background: There are few data verifying the utility of the CHADS-P2A2RC score in comparison with the CHADS2 score for estimating net adverse clinical events (NACE) in real-world settings. Methods: We performed analysis for a total of 3,985 chronic coronary syndrome (CCS) patients without atrial fibrillation (AF) who underwent percutaneous coronary intervention (PCI) between April 2013 and March 2019 for whom information was obtained from the CLIDAS (Clinical Deep Data Accumulation System)-PCI database. The primary endpoint was NACE defined as the composite of 3-point major adverse cardiovascular events (3P-MACE) (cardiovascular death, non-fatal myocardial infarction, and non-fatal stroke) and GUSTO moderate/severe bleeding events. Results: Kaplan-Meier analysis showed that both the CHADS-P2A2RC and CHADS2 scores stratified the risks. The incidences of NACE were stratified well by the very-high-risk category, which was uniquely defined as a CHADS-P2A2RC score of ≥6 (hazard ratio: 2.38, 95% CI=1.91-2.97, p-value <0.001). The area under the curve (AUC) in estimating NACE within 3 years was higher when the CHADS-P2A2RC score was used than when the CHADS2 score was used (0.67 vs. 0.62, p=0.003). This was mainly due to the accuracy in estimating bleeding events (0.66 vs. 0.60, p=0.006). Conclusions: The accuracy in estimating NACE after PCI for CCS patients without AF was higher when the CHADS-P2A2RC score was used than when the CHADS2 score was used, mainly due to the accuracy in predicting bleeding risk. Higher incidences of endpoints were well-stratified by a very-high-risk category defined as a CHADS-P2A2RC score of ≥6.

Year:

2025

Year:

2022

Year:

2021

Year:

2021

Year:

2021

Year:

2020

Year:

2020

Year:

2020

Year:

2020

Year:

2020

Year:

2020

Collaborators (18)

Naotaka Hashiguchi

Takamatsu Red Cross Hospital

JAPAN
View details

Kazuomi Kario

-

JAPAN
View details

Ritsushi Kato

-

JAPAN
View details

Atsuhiko Yagishita

Tokai University

JAPAN
View details

Yoshihiro Miyamoto

Director General

National Cerebral and Cardiovascular Center

JAPAN
View details

Tetsuya Matoba

Associate Professor

Kyushu University Hospital

JAPAN
View details

Taishi Nakamura

Associate Professor

Kumamoto University Hospital

JAPAN
View details

Yuki Komatsu

Lecturer

University of Tsukuba

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

Kenichiro Otsuka

Associate Professor

Osaka University Graduate School of Medicine

JAPAN
View details

Kentaro Minami

Associate Professor

Dokkyo Medical University

JAPAN
View details

Atsushi Shibata

Osaka University

JAPAN
View details

Daiju Fukuda

-

JAPAN
View details

Asahiro Ito

Osaka University Graduate School of Medicine

JAPAN
View details

Tetsuo Sasano

-

JAPAN
View details

Jun Takahashi

Associate Professor

Tohoku University Hospital

JAPAN
View details