Phat Ky Nguyen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Phat Ky Nguyen has a total of 44 co-authors. Here are the top co-authors by number of shared publications:
- Nguyen Quoc Khanh Le
Taipei Medical University
6 shared publications - Le Huu Nhat Minh
Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, USA
5 shared publications - Han Hong Huynh
International Master Program for Translational Science, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan
4 shared publications - Dang Nguyen
Harvard T.H. Chan School of Public Health, Harvard University, Boston, USA
3 shared publications - Huu-Hoai Le
Cardiovascular Research Laboratories, Interventional Cardiology Department, Methodist Hospital, Merrillville, USA
3 shared publications - Le Huu Hanh Nhi
Cardiovascular Research Laboratories, Interventional Cardiology Department, Methodist Hospital, Merrillville, USA
3 shared publications
Latest Publications
- Open Access
- 12 May 2026
- Published by Springer Nature in BMC Infectious Diseases
- Vol. 26 (1)
Valve involvement in infective endocarditis among intravenous drug users: a systematic review and meta-analysis
Background: Intravenous drug use (IVDU) is a major risk factor for infective endocarditis (IE), with right-sided infective endocarditis (RSIE) most frequently observed. However, precise estimates of valve involvement and the relative risk (RR) of RSIE within the IVDU population remain unclear. This systematic review and meta-analysis aimed to quantify the prevalence of RSIE, left-sided IE (LSIE), both-sided IE, and valve-specific involvement in IVDUs while assessing the relative risk of right-sided versus left-sided IE within the IVDU population. Methods: A systematic search was conducted in PubMed, Embase, and Web of Science to identify studies reporting IE in IVDUs. Inclusion criteria followed the PICO framework, ensuring clear definitions of IVDU status and valve involvement. A random-effects model was used to calculate pooled prevalence estimates and RR ratios with 95% confidence intervals (CIs). Heterogeneity was assessed using the I² statistic, and sensitivity analyses were performed. Results: A total of 14 studies involving 1,783 patients met the inclusion criteria. The pooled prevalence of right-sided infective endocarditis (RSIE) was 59% (95% CI: 54%–65%), left-sided infective endocarditis (LSIE) was 39% (95% CI: 33%–46%), and both-sided infective endocarditis was 8% (95% CI: 6%–12%). Among individual valves, the tricuspid valve was most commonly affected (59% (95% CI: 53%–64%)), followed by the mitral valve (21% (95% CI: 18%–26%)) and the aortic valve (16% (95% CI: 12%–20%)). Pulmonic valve involvement was rare (1% (95% CI: 0%–3%)). Overall, individuals who inject drugs (IVDUs) had a 1.49-fold increased risk of developing right-sided IE compared to left-sided IE (RR = 1.49 (95% CI: 1.15–1.95), p = 0.008). Conclusion: This SRMA confirms the predominance of right-sided IE, particularly tricuspid valve involvement, in IVDUs, with a significantly higher risk compared to left-sided IE. The findings underscore the need for targeted screening, early intervention, and IVDU-specific management strategies in IE care. Future research should focus on regional variations, microbiological patterns, and long-term outcomes in this high-risk population. Clinical trial number: Not applicable.
- 12 May 2026
- Published by Springer Nature in BMC Infectious Diseases
- Vol. 26 (1)
Open AccessValve involvement in infective endocarditis among intravenous drug users: a systematic review and meta-analysis
Background: Intravenous drug use (IVDU) is a major risk factor for infective endocarditis (IE), with right-sided infective endocarditis (RSIE) most frequently observed. However, precise estimates of valve involvement and the relative risk (RR) of RSIE within the IVDU population remain unclear. This systematic review and meta-analysis aimed to quantify the prevalence of RSIE, left-sided IE (LSIE), both-sided IE, and valve-specific involvement in IVDUs while assessing the relative risk of right-sided versus left-sided IE within the IVDU population. Methods: A systematic search was conducted in PubMed, Embase, and Web of Science to identify studies reporting IE in IVDUs. Inclusion criteria followed the PICO framework, ensuring clear definitions of IVDU status and valve involvement. A random-effects model was used to calculate pooled prevalence estimates and RR ratios with 95% confidence intervals (CIs). Heterogeneity was assessed using the I² statistic, and sensitivity analyses were performed. Results: A total of 14 studies involving 1,783 patients met the inclusion criteria. The pooled prevalence of right-sided infective endocarditis (RSIE) was 59% (95% CI: 54%–65%), left-sided infective endocarditis (LSIE) was 39% (95% CI: 33%–46%), and both-sided infective endocarditis was 8% (95% CI: 6%–12%). Among individual valves, the tricuspid valve was most commonly affected (59% (95% CI: 53%–64%)), followed by the mitral valve (21% (95% CI: 18%–26%)) and the aortic valve (16% (95% CI: 12%–20%)). Pulmonic valve involvement was rare (1% (95% CI: 0%–3%)). Overall, individuals who inject drugs (IVDUs) had a 1.49-fold increased risk of developing right-sided IE compared to left-sided IE (RR = 1.49 (95% CI: 1.15–1.95), p = 0.008). Conclusion: This SRMA confirms the predominance of right-sided IE, particularly tricuspid valve involvement, in IVDUs, with a significantly higher risk compared to left-sided IE. The findings underscore the need for targeted screening, early intervention, and IVDU-specific management strategies in IE care. Future research should focus on regional variations, microbiological patterns, and long-term outcomes in this high-risk population. Clinical trial number: Not applicable.
- Open Access
- 11 March 2026
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 71 (5) , 055012
A CT radiomics signature enables risk stratification and survival prediction in colorectal liver metastases
Objective. Colorectal liver metastases (CRLM) represent a major clinical challenge because outcomes after hepatic resection vary widely between patients. Preoperative risk stratification remains limited, and radiomics may provide non invasive imaging biomarkers to support prognosis. This study aimed to develop a CT based radiomics signature capable of generating risk scores for predicting overall survival (OS) in patients undergoing CRLM resection. Approach. Preoperative CT scans from 197 CRLM patients were retrospectively obtained from The Cancer Imaging Archive. A total of 851 radiomics features were extracted using 3D Slicer, along with 256 deep features from a 3D convolutional neural network. Data were randomly divided into training (70%) and testing (30%) sets. Feature selection included correlation-based filtering, univariate Cox regression, and multivariate Cox regression with least absolute shrinkage and selection operator (LASSO) regularization. A radiomics-based risk score (Rad score) was calculated to stratify patients into high- and low- risk groups using the median value. Model performance was compared with clinical variables using time-dependent receiver operating characteristic analysis. Main results. The eight feature signature was prognostic in both internal splits. In multivariable Cox models, the Rad score remained an independent predictor of OS in the training cohort (HR = 2.671, 95% CI 2.023–3.527, P -value < 0.001; Harrell C index = 0.738, 95% CI 0.678–0.793) and the testing cohort (HR = 3.036, 95% CI 1.421–6.486, P -value = 0.004; Harrell C index = 0.663, 95% CI 0.558–0.752). Kaplan Meier analysis showed shorter survival in the high risk group than the low risk group in training (median OS 56.5 versus 76.00 months; log rank P -value = 0.0000) and testing (61.45 versus 74.25 months; log rank P -value = 0.0103). In an external cohort of 105 patients, the Rad score also separated risk (Harrell C index = 0.614, 95% CI 0.534–0.697; median OS 15.7 versus 29.87 months; log rank P -value = 0.0015). Significance. A compact CT radiomics signature derived from preoperative imaging provided independent prognostic information for OS and enabled risk stratification in internal testing and external validation. Further validation in independent CRLM cohorts is required before clinical deployment.
- 11 March 2026
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 71 (5) , 055012
Open AccessA CT radiomics signature enables risk stratification and survival prediction in colorectal liver metastases
Objective. Colorectal liver metastases (CRLM) represent a major clinical challenge because outcomes after hepatic resection vary widely between patients. Preoperative risk stratification remains limited, and radiomics may provide non invasive imaging biomarkers to support prognosis. This study aimed to develop a CT based radiomics signature capable of generating risk scores for predicting overall survival (OS) in patients undergoing CRLM resection. Approach. Preoperative CT scans from 197 CRLM patients were retrospectively obtained from The Cancer Imaging Archive. A total of 851 radiomics features were extracted using 3D Slicer, along with 256 deep features from a 3D convolutional neural network. Data were randomly divided into training (70%) and testing (30%) sets. Feature selection included correlation-based filtering, univariate Cox regression, and multivariate Cox regression with least absolute shrinkage and selection operator (LASSO) regularization. A radiomics-based risk score (Rad score) was calculated to stratify patients into high- and low- risk groups using the median value. Model performance was compared with clinical variables using time-dependent receiver operating characteristic analysis. Main results. The eight feature signature was prognostic in both internal splits. In multivariable Cox models, the Rad score remained an independent predictor of OS in the training cohort (HR = 2.671, 95% CI 2.023–3.527, P -value < 0.001; Harrell C index = 0.738, 95% CI 0.678–0.793) and the testing cohort (HR = 3.036, 95% CI 1.421–6.486, P -value = 0.004; Harrell C index = 0.663, 95% CI 0.558–0.752). Kaplan Meier analysis showed shorter survival in the high risk group than the low risk group in training (median OS 56.5 versus 76.00 months; log rank P -value = 0.0000) and testing (61.45 versus 74.25 months; log rank P -value = 0.0103). In an external cohort of 105 patients, the Rad score also separated risk (Harrell C index = 0.614, 95% CI 0.534–0.697; median OS 15.7 versus 29.87 months; log rank P -value = 0.0015). Significance. A compact CT radiomics signature derived from preoperative imaging provided independent prognostic information for OS and enabled risk stratification in internal testing and external validation. Further validation in independent CRLM cohorts is required before clinical deployment.
- 27 November 2025
- Published by Elsevier in Public Health
- Vol. 250, 106050
Protective predictors of cardiovascular disease: an explainable AI approach
- 27 November 2025
- Published by Elsevier in Public Health
- Vol. 250, 106050
Protective predictors of cardiovascular disease: an explainable AI approach
- Open Access
- 7 August 2025
- Published by IOS Press
- Vol. 329, 563-567
AI-Driven Deep Learning Approach for Pan-Cancer Immune Profiling
The tumor immune microenvironment (TME) influences cancer progression and treatment. RNA-Seq has identified six immune subtypes: Wound Healing (WH, C1), IFN- Dominant (IFNG, C2), Inflammatory (INF, C3), Lymphocyte Depleted (LD, C4), Immunologically Quiet (IQ, C5), and TGF-β Dominant (TGFb, C6). This study uses a Convolutional Neural Network (CNN) to classify these subtypes from RNA-Seq data. The model, with ReLU activation and dropout, achieved a 10-fold F1-score of 0.9483 and AUC of 0.9969. Results show CNN’s effectiveness in handling class imbalance and modeling complex gene interactions, outperforming XGBoost, Random Forest, and TabNet. Future work will validate results on independent datasets and incorporate multi-omics data to improve accuracy.
- 7 August 2025
- Published by IOS Press
- Vol. 329, 563-567
Open AccessAI-Driven Deep Learning Approach for Pan-Cancer Immune Profiling
The tumor immune microenvironment (TME) influences cancer progression and treatment. RNA-Seq has identified six immune subtypes: Wound Healing (WH, C1), IFN- Dominant (IFNG, C2), Inflammatory (INF, C3), Lymphocyte Depleted (LD, C4), Immunologically Quiet (IQ, C5), and TGF-β Dominant (TGFb, C6). This study uses a Convolutional Neural Network (CNN) to classify these subtypes from RNA-Seq data. The model, with ReLU activation and dropout, achieved a 10-fold F1-score of 0.9483 and AUC of 0.9969. Results show CNN’s effectiveness in handling class imbalance and modeling complex gene interactions, outperforming XGBoost, Random Forest, and TabNet. Future work will validate results on independent datasets and incorporate multi-omics data to improve accuracy.
- 19 January 2025
- Published by Elsevier in Biochimica et Biophysica Acta (BBA) - Molecular Basis of Disease
- Vol. 1871 (3) , 167680
An in-depth review of AI-powered advancements in cancer drug discovery
- 19 January 2025
- Published by Elsevier in Biochimica et Biophysica Acta (BBA) - Molecular Basis of Disease
- Vol. 1871 (3) , 167680
An in-depth review of AI-powered advancements in cancer drug discovery