decorative bird

Hi , I am
J Yan .

Computational Social Scientist

Understanding health inequalities with AI

about me

Computational social scientist dedicated to understanding health inequalities with advanced AI algorithms.

I specialise in the study of health disparities leveraging machine learning, deep learning, and explainable AI. My research focuses on social determinants of health and their influence on mortality and morbidity outcomes. Currently a DPhil student at Oxford, supervised by Prof. Charles Rahal and Prof. Ridhi Kashyap.

Research Interests: Explainable AI · Health Inequalities · Social Determinants · Computational Demography · Model Evaluation

location

Oxford, UK

email

jiani.yan@wolfson.ox.ac.uk

education

2014 - 2018

BSc
Computer Science

Southwestern University of Finance Economics

Chengdu, China

2018 - 2019

MSc
Financial Economics

University of Birmingham

Birmingham, United Kingdom

2020 - 2022

MPhil
Sociology & Demography

University of Oxford

Oxford, United Kingdom

2022 - Now

DPhil
Computational Social Science

university of oxford

oxford, united kingdom

research projects

Featured work in computational social science and health inequalities

Social Determinants of Health

Examining how social factors influence health outcomes using explainable AI and machine learning approaches.

Prediction Limits

Exploring unknowable limits to prediction in computational social science published in Nature Computational Science.

RobustiPy

Python package for multiversal analysis with model selection, averaging, and resampling capabilities.

Digital Gender Gaps

Mapping subnational gender gaps in internet and mobile adoption using social media advertising data.

UK Biobank Analysis

Advanced clustering and IRT approaches to model chronic disease profiles and multimorbidity trajectories.

GWAS Diversity Monitor

Monitoring diversity in genome-wide association studies and improving representation in genetic research.

publications

Peer-reviewed publications and scientific software

Journal Articles & Software

  1. Valdenegro, D., Yan, J., Dai, D., & Rahal, C. (2026). Introducing RobustiPy: An efficient next generation multiversal library with model selection, averaging, resampling. Patterns (Conditionally Accepted). arXiv
  2. Yan, J., & Rahal, C. (2025). On the unknowable limits to prediction. Nature Computational Science, 5, 188–190. DOI
  3. Yan, J. (2025). Revisiting the social determinants of health with explainable AI: a cross-country perspective. American Journal of Epidemiology, 195(3), 681-688. DOI
  4. Breen, C. F., Fatehkia, M., Yan, J., Zhao, X., Leasure, D. R., Weber, I., & Kashyap, R. (2025). Mapping subnational gender gaps in internet and mobile adoption using social media data. Proceedings of the National Academy of Sciences, 122(42), e2416624122. DOI
  5. Leasure, D.R., Kashyap, R., Rampazzo, F., Dooley, C.A., Elbers, B., Bondarenko, M., Verhagen, M., Frey, A., Yan, J., Akimova, E.T., Fatehkia, M., Trigwell, R., Tatem, A.J., Weber, I., & Mills, M.C. (2023). Nowcasting Daily Population Displacement in Ukraine through Social Media Advertising Data. Population and Development Review. DOI
  6. Leasure, D.R., Yan, J., Bondarenko, M., Kerr, D., Fatehkia, M., Weber, I., & Kashyap, R. (2023). Digital Gender Gaps Web Application, v1.0.0. Zenodo, GitHub. Zenodo | GitHub
  7. Mills, M., Rahal, C., Brazel, D., Yan, J., & Gieysztor, S. (2020). COVID-19 Vaccine Deployment: Behaviour, ethics, misinformation and policy strategies. London: The Royal Society & The British Academy.

Working Papers

  1. Rahal, C., Yan, J., & Verhagen, M. (2026). From a Single Seed Grows a Forest of Uncertainty. In progress.
  2. Yan, J. (2026). Discovering Prevalent Chronic Disease Profiles with Advanced Clustering Methods in UK Biobank. In progress.
  3. Yan, J. (2026). An Item Response Theory Approach to Model Multimorbidity Complexity Trajectory and the Role of Social Determinants in UK Biobank. In progress.
  4. Yan, J., Li, J., Breen, C.F., & Kashyap, R. (2026). Nowcasting global digital gender gaps using social media data. In progress.