Tho Nguyen

MD · MPH | Junior Researcher

Contact Information

Email: thon@donga.edu.vn | Phone: (+84) 906 432 742
Location: Da Nang, Vietnam | LinkedIn · ORCID iD · GitHub


Research Profile

Junior researcher (MD, MPH) specialising in health data science, with demonstrated experience in applying transformer-based machine learning, causal inference, and biostatistics to clinical and public health datasets.

Publication:

  • Medical AI: 02 Book chapters [1st author], 05 Conference Proceedings [1st author: 3/5]

  • Public health: 01 article Q1 (accepted) [co-author], 04 articles (Vietnam Journals) [1st author/co-author: 2/4]

Experienced in large-scale multi-national observational studies using R and Python, data management, detect unusual respondents, mining & analysis. Learning, experiencing real medical data through applied AI models, advancing causal analysis to prepare a PhD position in health data science program.


Research Interests

  • Machine learning (ML) and foundation models for tabular data

  • Causal inference methods for observational health data: SEM/path, mediation, propensity score

  • Health data science methodology: missing data, detecting unusual respondent, bias analysis


Education

Master of Public Health (MPH) — GPA 3.36 / 4.0 | Hanoi University of Public Health, Vietnam | 2022–2024

Thesis: Maltreatment experiences and association with depression — a cross-sectional study of 2356 secondary school students in Bac Giang Province, 2023

Methods: Logistic regression, SEM, path analysis (R); survey design (KoboToolbox)

Supervisor: Assoc. Prof. Nguyen Thanh Huong

Degree Focus: Epidemiology, biostatistics, public health surveillance.


Medical Doctor (MD) in Preventive Medicine | Hue University of Medicine and Pharmacy, Vietnam | 2014 – 2020


Research Experience

Lead Researcher — (1) FT-Transformer diabetes classification, (2) Fall detection detection

International Research Institute for AI and Data Science, Dong A University | Collaboration: University of Lille (France)
2021 – 2025

(1) FT-Transformer diabetes classification:

  • Compared foundation Transformer architecture with ML enhanced with KNN imputation and Independent Component Analysis (ICA) for classifying high-risk diabetes in women from tabular clinical data.

  • First-author in Springer LNICST (RAIDS 2024) and presented at ISSAT Data Science Conference 2025

  • Implemented full ML pipeline in Python: feature engineering, cross-validation, hyperparameter tuning, model interpretability (SHAP)

(2) Fall detection detection:


Primary Researcher — MPH Thesis Study

Hanoi University of Public Health | 2022 – 2024

  • Designed and executed a cross-sectional epidemiological study of maltreatment experiences and depression in 2300+ adolescents at 8 secondary schools in Bac Giang Province,

  • Led full research cycle: ethics approval, survey instrument design, data collection coordination, statistical analysis, and manuscript preparation,

  • Primary analysis: multivariate logistic regression, SEM, path analysis in R

  • Collaboration with Swiss team funded by Swiss National Science Foundation (NAFOSTED Grant IZVSZ1.203300, CHF ~291,000).


Statistical Research Assistant

Swiss-Vietnamese Collaborative Study on Child Maltreatment | 2022 – 2025

  • Designed and deployed multi-national digital data collection using KoboToolbox (Vietnam) and Unipark (Switzerland)
  • Built reproducible data cleaning, management, and analysis pipelines in R and SPSS
  • Applied regression, SEM, and path analysis to identify predictors of child maltreatment and depression
  • Collaborated with Swiss and Vietnamese post-doctoral teams; co-authored Q1 journal paper & 01 Q4 journal paper, 1st author 01 paper (VJPM), co-author 02 papers (VJPM, JHDS)

Research Intern Supervisor & Conference Coordinator

International Research Institute for AI and Data Science, Dong A University | 2023 – Present

  • Supervised 30+ data science master’s students on research methodology, R/Python programming, and project design in collaboration with the University of Lille (France)
  • Web Chair and Programme Committee Member for 10+ international conferences (RAIDS, ISSAT, SmartLife); hosted special sessions on responsible AI in health

Other Research Roles

Head of International Unit2023 – Present
International Research Institute for AI and Data Science, Dong A University

Research Secretariat2021
Family Hospital, Scientific Research Department, Da Nang


Publications

Peer-Reviewed Journal Articles

Meret, S. W., Ha, T. D., Julia, Q., Huong, N. T., Tho, N., Thi, M. Le., David, C. L., Thomas. G. (2026). Disclosure of Child Physical Abuse: A Comparative Study on Prevalence and Disclosure Patterns in Switzerland and Vietnam. Child and Adolescent Social Work Journal. (Accepted)

[First author] Nguyen T, Bui TP, Nguyen TP, Dinh TH, Vu TTM, Nguyen TQC, Nguyen TH, Le MT. (2024). Physical abuse injuries in children aged 13–15 years: a cross-sectional study in 8 secondary schools. Vietnam Journal of Preventive Medicine, 34(06):159–167. https://doi.org/10.51403/0868-2836/2024/1935

Le MT, Nguyen T, Bui TP, Nguyen TP, Dinh TH, Vu TTM, Nguyen TQC, Nguyen TH. (2024). Overview of risk and protective factors for maltreatment of children 13–15 years old from 2005 to present. Vietnam Journal of Preventive Medicine, 34(06):9–16. https://doi.org/10.51403/0868-2836/2024/1916

Le MT, Nguyen T, Nguyen MA, Dinh TH, Nguyen TQC, Nguyen TP, Bui TP, Vu TTM, Nguyen TH. (2023). How KoboToolbox versus Unipark platform are selected in data survey to detect child maltreatment in Vietnam: A discussion paper. Journal of Health and Development Studies, 7(04):155–162. https://doi.org/10.38148/JHDS.0704SKPT23-062

[1st author] Nguyen T, Tran KV. (2019). The situation of using internet of pregnant women, mothers of children under 2 years old for health information seeking at Huong Long Ward, Hue City. Journal of Community Medicine, 1(48):72–77.


Book Chapters (Springer)

[1st author] Nguyen T, Nguyen QT, Tran KD, Koehl L, Tran KP. Transformer-Based Models for Predicting High-Risk Diabetes in Women Using Tabular Data. In: Responsible Artificial Intelligence and Data Science. RAIDS 2024. LNICST, vol 673. Springer, Cham. https://doi.org/10.1007/978-3-032-14055-5_6

Le TM, Nguyen T, Thu HD, Phuong BT, Nguyen HT. Application of Digital Survey Tools to Screen for Child Maltreatment Among Secondary School Students in Vietnam. In: Responsible Artificial Intelligence and Data Science. RAIDS 2024. LNICST, vol 673. Springer, Cham. https://doi.org/10.1007/978-3-032-14055-5_3

[1st author] Nguyen T, Nguyen DH, Nguyen QT, Tran KD, Tran KP. Human-Centered Edge AI and Wearable Technology for Workplace Health and Safety in Industry 5.0. In: AI for Safety and Reliability Engineering. Springer Nature Switzerland, pp. 171–183. https://doi.org/10.1007/978-3-031-71495-5_8

[1st author] Nguyen T, Tran KD, Raza A, Nguyen QT, Bui HM, Tran KP. Wearable technology for smart manufacturing in Industry 5.0. In: AI for Smart Manufacturing. Springer International Publishing, pp. 225–254. https://doi.org/10.1007/978-3-031-30510-8_11


Conference Proceedings & Presentations

Le HDV, Dao HL, Nguyen T. (2025). Enhanced transparency clinical decision-making via interpretable AI model system. ICASI 2025, IET, vol 2025, pp. 438–440. https://doi.org/10.1049/icp.2025.2588

[1st author] Nguyen T, Mai HX, Nguyen QT, Tran KD, Koehl L, Tran KP. A Comprehensive Approach to Tabular Data Classification: FT-Transformer Enhanced by KNN Imputation and ICA in Diabetes Classification. 3rd ISSAT International Conference on Data Science in Business, Finance and Industry, Da Nang, 6–8 Jan 2025.

[1st author] Nguyen T, Tran KD, Raza A, Nguyen QT, Bui HM, Tran KP. Wearable Technology for Smart Manufacturing in Industry 5.0: Applications, Challenges, and Case Studies. 2nd ISSAT International Conference on Data Science, Da Nang, 8–10 Jan 2023.

Le, L. H., KOEHL, L., Tho, N. (2026). Toward robust and frugal AI Models for capture and analysis of Physiological Signals. Proceedings of Second Responsible Artificial Intelligence and Data Science Conference 2026

Conference Presentations & Posters


Research Funding

Amount Project Period
~USD 291,345 NAFOSTED/SNF — Schools detecting child maltreatment (Code: IZVSZ1.203300). Role: Statistical Research Assistant. 2022 – 2025

Technical Skills

Category Skills
Programming R , Python
Statistics Regression (linear, logistic, Poisson, Ordinal), survival analysis, SEM, path analysis, mediation, moderation, latent class analysis, network analsis
ML / AI FT-Transformer, random forests, gradient boosting, deep learning (CNNs), model explainability (SHAP, LIME)
Epi Methods Cross-sectional, cohort, case-control designs; STROBE/CONSORT reporting; IRB protocol development
Data Tools KoboToolbox, Unipark, SPSS, STATA, R Markdown / Quarto
Languages Vietnamese (native), English (B2 - IELTS)

Academic Service

  • Peer Reviewer: Dong A University Journal of Science
  • Web Chair & Programme Committee Member: RAIDS 2024, 2026, SmartLife, ISSAT, and 7+ other international conferences (2022–present)
  • Session Chair / Host: Special session on Responsible AI in Health, RAIDS Conference 2024

Tho Nguyen · Researcher & Health Data Scientist · thon@donga.edu.vn · Last updated: 08 April 2026