Phan Thanh Phuc

Mr. Phan Thanh Phuc

University Medical Center, Ho Chi Minh City, Viet Nam
+1
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 September 2023 in Cancer Medicine
Verified
Journal Article
Open access
SCShih‐Min Chen
Shih‐Min Chen
PPPhan Thanh Phuc
Phan Thanh Phuc
PNPhung-Anh Nguyen
Phung-Anh Nguyen
WBWhitney Burton
Whitney Burton
SLShwu‐Jiuan Lin
Shwu‐Jiuan Lin
JHJason C. Hsu
Jason C. Hsu
Introduction: Pancreatic cancer is associated with poor prognosis. Considering the increased global incidence of diabetes cases and that individuals with diabetes are considered a high‐risk subpopulation for pancreatic cancer, it is critical to detect the risk of pancreatic cancer within populations of person living = with diabetes. This study aimed to develop a novel prediction model for pancreatic cancer risk among patients with diabetes, using = a real‐world database containing clinical features and employing numerous artificial intelligent approach algorithms.Methods: This retrospective observational study analyzed data on patients with Type 2 diabetes from a multisite Taiwanese EMR database between 2009 and 2019. Predictors were selected in accordance with the literature review and clinical perspectives. The prediction models were constructed using machine learning algorithms such as logistic regression, linear discriminant analysis, gradient boosting machine, and random forest.Results: The cohort consisted of 66,384 patients. The Linear Discriminant Analysis (LDA) model generated the highest AUROC of 0.9073, followed by the Voting Ensemble and Gradient Boosting machine models. LDA, the best model, exhibited an accuracy of 84.03%, a sensitivity of 0.8611, and a specificity of 0.8403. The most significant predictors identified for pancreatic cancer risk were glucose, glycated hemoglobin, hyperlipidemia comorbidity, antidiabetic drug use, and lipid‐modifying drug use.Conclusion: This study successfully developed a highly accurate 4‐year risk model for pancreatic cancer in patients with diabetes using real‐world clinical data and multiple machine‐learning algorithms. Potentially, our predictors offer an opportunity to identify pancreatic cancer early and thus increase prevention and invention windows to impact survival in diabetic patients.

25 July 2023 in Cancer Science
Verified
Journal Article
Open access
QNQuynh Thi Nhu Nguyen
Quynh Thi Nhu Nguyen
PNPhung-Anh Nguyen
Phung-Anh Nguyen
CWChun‐Jung Wang
Chun‐Jung Wang
PPPhan Thanh Phuc
Phan Thanh Phuc
RLRuo‐Kai Lin
Ruo‐Kai Lin
JHJason C. Hsu
Jason C. Hsu
The study used clinical data to develop a prediction model for breast cancer survival. Breast cancer prognostic factors were explored using machine learning techniques. We conducted a retrospective study using data from the Taipei Medical University Clinical Research Database, which contains electronic medical records from three affiliated hospitals in Taiwan. The study included female patients aged over 20 years who were diagnosed with primary breast cancer and had medical records in hospitals between January 1, 2009 and December 31, 2020. The data were divided into training and external testing datasets. Nine different machine learning algorithms were applied to develop the models. The performances of the algorithms were measured using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1‐score. A total of 3914 patients were included in the study. The highest AUC of 0.95 was observed with the artificial neural network model (accuracy, 0.90; sensitivity, 0.71; specificity, 0.73; PPV, 0.28; NPV, 0.94; and F1‐score, 0.37). Other models showed relatively high AUC, ranging from 0.75 to 0.83. According to the optimal model results, cancer stage, tumor size, diagnosis age, surgery, and body mass index were the most critical factors for predicting breast cancer survival. The study successfully established accurate 5‐year survival predictive models for breast cancer. Furthermore, the study found key factors that could affect breast cancer survival in Taiwanese women. Its results might be used as a reference for the clinical practice of breast cancer treatment.

HDHuy Le Duc
Huy Le Duc
Nhi Thi Hong NguyenNhi Thi Hong Nguyen
Nhi Thi Hong Nguyen
PPPhan Thanh Phuc
Phan Thanh Phuc
CHChung-Chien Huang
Chung-Chien Huang
There is little knowledge about how the influence of non-pharmaceutical interventions (NPIs) reduces the COVID-19 infection rate during the period of vaccine rollout. This study aimed to examine the effectiveness of NPIs on decreasing the epidemic growth of COVID-19 between before and after the vaccine rollout period among Asian countries. Our ecological study included observations from 30 Asian countries over the 20 weeks of the pre- and post-vaccination period. Data were extracted from the Oxford COVID-19 Government Response Tracker and other open databases. Longitudinal analysis was utilized to evaluate the impacts of public health responses and vaccines. The facial covering policy was the most effective intervention in the pre-vaccination period, followed by border control and testing policies. In the post-vaccination period, restrictions on gatherings and public transport closure both play a key role in reducing the epidemic growth rate. Vaccine coverage of 1–5%, 5–10%, 10–30%, and over 30% of the population was linked with an average reduction of 0.12%, 0.32%, 0.31%, and 0.59%, respectively. Our findings support the evidence that besides the vaccine increasingly contributing to pandemic control, the implementation of NPIs also plays a key role.

1 February 2025 in eClinicalMedicine
Verified
Journal Article
Open access
JJJack L. Janetzki
Jack L. Janetzki
JKJung Ho Kim
Jung Ho Kim
EMEvan Minty
Evan Minty
JLJung Ah Lee
Jung Ah Lee
DMDaniel R. Morales
Daniel R. Morales
SYSeng Chan You
Seng Chan You
Fluoroquinolones (FQs) are commonly used to treat urinary tract infections (UTIs), but some studies have suggested they may increase the risk of aortic aneurysm or dissection (AA/AD). However, no large-scale international study has thoroughly assessed this risk. A retrospective cohort study was conducted using a large, distributed network analysis across 14 databases from 5 countries (United States, South Korea, Japan, Taiwan, and Australia). The study included 13,588,837 patients aged 35 or older who initiated systemic fluoroquinolones (FQs) or comparable antibiotics (trimethoprim with or without sulfamethoxazole [TMP] or cephalosporins [CPHs]) for UTI treatment in the outpatient setting between JAN 01, 2010 and DEC 31, 2019. Patients were included if at the index date they had at least 365 days of prior observation and were not hospitalised for any reason on or within 7 days prior to the index date. The primary outcome was AA/AD occurrence within 60 days of exposure, with secondary outcomes examining AA and AD separately. Cox proportional hazards models with 1:1 propensity score (PS) matching were used to estimate the risk, with results calibrated using negative control outcomes. Analyses were subjected to pre-defined study diagnostics, and only those passing all diagnostics were reported. Hazard ratios (HRs) were pooled using Bayesian random-effects meta-analysis. Among analyses that passed diagnostics there were 1,954,798 and 1,195,962 propensity-matched pairs for the FQ versus TMP and FQ versus CPH comparisons respectively. For the 60-day follow-up there was no difference in risk of AA/AD between FQ and TMP (absolute rate difference [ARD], 0.21 per 1000 person-year; calibrated HR, 0.91 [95% CI 0.73–1.10]). There was no significant difference in risk for FQ versus CPH (ARD, 0.11 per 1000 person-year; calibrated HR, 1.01 [95% CI 0.82–1.25]). This large-scale study used a rigorous design with objective diagnostics to address bias and confounding. There was no increased risk of AA/AD associated with FQ compared to TMP or CPH in patients treated for UTI in the outpatient setting. As we only examined FQ used to treat UTIs in the outpatient setting, the results may not be generalisable to other indications with different severity. 10.13039/501100008005 Yonsei University College of Medicine , Government-wide R&D Fund project for infectious disease research (GFID), Republic of Korea, 10.13039/501100000925 National Health and Medical Research Council (NHMRC) 10.13039/100015539 Australian Government . 10.13039/100000738 Department of Veterans Affairs (VA) Informatics and Computing Infrastructure (VINCI), 10.13039/100000738 Department of Veterans Affairs , the United States Government.

11 December 2024 in Journal of Medical Internet Research
Verified
Journal Article
Open access
PPPhan Thanh Phuc
Phan Thanh Phuc
PNPhung-Anh Nguyen
Phung-Anh Nguyen
NNNam Nhat Nguyen
Nam Nhat Nguyen
MHMin-Huei Hsu
Min-Huei Hsu
Nguyen Quoc Khanh LeNguyen Quoc Khanh Le
Nguyen Quoc Khanh Le
JHJason C. Hsu
Jason C. Hsu
Background: The possible association between diabetes mellitus and dementia has raised concerns, given the observed coincidental occurrences. Objective: This study aimed to develop a personalized predictive model, using artificial intelligence, to assess the 5-year and 10-year dementia risk among patients with type 2 diabetes mellitus (T2DM) who are prescribed antidiabetic medications. Methods: This retrospective multicenter study used data from the Taipei Medical University Clinical Research Database, which comprises electronic medical records from 3 hospitals in Taiwan. This study applied 8 machine learning algorithms to develop prediction models, including logistic regression, linear discriminant analysis, gradient boosting machine, light gradient boosting machine, AdaBoost, random forest, extreme gradient boosting, and artificial neural network (ANN). These models incorporated a range of variables, encompassing patient characteristics, comorbidities, medication usage, laboratory results, and examination data. Results: This study involved a cohort of 43,068 patients diagnosed with type 2 diabetes mellitus, which accounted for a total of 1,937,692 visits. For model development and validation, 1,300,829 visits were used, while an additional 636,863 visits were reserved for external testing. The area under the curve of the prediction models range from 0.67 for the logistic regression to 0.98 for the ANNs. Based on the external test results, the model built using the ANN algorithm had the best area under the curve (0.97 for 5-year follow-up period and 0.98 for 10-year follow-up period). Based on the best model (ANN), age, gender, triglyceride, hemoglobin A1c, antidiabetic agents, stroke history, and other long-term medications were the most important predictors. Conclusions: We have successfully developed a novel, computer-aided, dementia risk prediction model that can facilitate the clinical diagnosis and management of patients prescribed with antidiabetic medications. However, further investigation is required to assess the model’s feasibility and external validity.

13 June 2022 in Vaccines
Verified
Journal Article
Open access
PDF file
HDHuy Le Duc
Huy Le Duc
CSChung-Liang Shih
Chung-Liang Shih
YCYao-Mao Chang
Yao-Mao Chang
Nhi Thi Hong NguyenNhi Thi Hong Nguyen
Nhi Thi Hong Nguyen
PPPhan Thanh Phuc
Phan Thanh Phuc
CHChung-Chien Huang
Chung-Chien Huang
Our study aims to compare the pandemic resilience index and explore the associated factors during the Delta and Omicron variant periods. In addition, the study aims to identify the characteristics of countries that had good performances. We analyzed observation data among 29 countries over the first eight weeks during the two periods of Delta and Omicron variant dominance. Data were extracted from open public databases. The Omicron variant caused a lowered mortality rate per 100,000 COVID-19 patients; however, it is still imposing a colossal burden on health care systems. We found the percentage of the population fully vaccinated and high government indices were significantly associated with a better resilience index in both the Delta and Omicron periods. In contrast, the higher death rate of cancers and greater years lived with disability (YLD) caused by low bone density were linked with poor resilience index in the Omicron periods. Over two periods of Delta and Omicron, countries with good performance had a lower death rate from chronic diseases and lower YLD caused by nutrition deficiency and PM2.5. Our findings suggest that governments need to keep enhancing the vaccine coverage rates, developing interventions for populations with chronic diseases and nutrition deficiency to mitigate COVID-19 impacts on these targeted vulnerable cohorts.