Yale Chang

Here is my email:

Research Interests

• Disease risk prediction and risk factor identification for acute care
• Patient similarity and disease subtyping for personalized healthcare
• Treatment optimization with causal inference and reinforcement learning

• Uncertainty quantification of predictive models
• Domain adaptation, out-of-distribution detection
• Bayesian neural network and deep generative models
• Reinforcement learning
• Causal inference
• Sequence models

Selected Publications

1. Y. Chang, C. Antonescu, S. Ravindranath, J. Dong, M. Lu, F. Vicario, L. Wondrely, P. Thompson, and D. Swearingen
   Early prediction of cardiogenic shock using machine learning
   Frontiers in Cardiovascular Medicine, p.1868, 2022. [Link]


2. Y. Chang, C. Antonescu, S. Ravindranath, J. Dong, M. Lu, F. Vicario, L. Wondrely, P. Thompson, and D. Swearingen
   Machine learning for early prediction of cardiogenic shock
   Journal of the American College of Cardiology, 79(9_Supplement):278–278, 2022. [Link]


3. A. Rahman, Y. Chang, J. Dong, B. Conroy, A. Natarajan, T. Kinoshita, F. Vicario, J. Frassica, and M. Xu-Wilson
   Early prediction of hemodynamic interventions in the intensive care unit using machine learning
   Critical Care, 25(1):1-9,2021. [Link]


4. A. Natarajan, G. Boverman, Y. Chang, C. Antonescu, and J. Rubin.
   Convolution-free waveform transformers for multi-lead ecg classification
   In 2021 Computing in Cardiology (CinC), Volume 48, pages 1-4, IEEE, 2021. [Link]


5. E. Schwager, K. Jansson, A. Rahman, S. Schiffer, Y. Chang, G. Boverman, B. Gross, M. Xu-Wilson, P. Boehme, H. Truebel, and others.
   Utilizing machine learning to improve clinical trial design for acute respiratory distress syndrome
   NPJ digital madicine, 4(1):1-9, 2021. [Link]


6. A. Natarajan, Y. Chang, S. Mariani, A. Rahman, G. Boverman, S. Vij, and J. Rubin.
   A wide and deep transformer neural network for 12-lead ecg classification.
   In 2020 Computing in Cardiology, pages 1-4, IEEE, 2020. [Link]
   (Using the approach proposed in this paper, we won 1st place in PhysioNet Challenge 2020)
   


7. S. Parvaneh^* and Y. Chang^*
   Shapelet discovery for atrial fibrillation detection
   In 2020 Computing in Cardiology Conference (CinC). IEEE, 2020. [Link]


8. A. Rahman, Y. Chang, B. Conroy, and M. Xu-Wilson.
   Phenotyping with prior knowledge using patient similarity.
   In Machine Learning for Healthcare Conference , 2020. [Link]


9. Y. Chang^*, J. Rubin^*, G. Boverman, S. Vij, A. Rahman, A. Natarajan, and S. Parvaneh.
   A multi-task imputation and classification neural architecture for early prediction of sepsis from multivariate clinical time series.
   In 2019 Computing in Cardiology Conference (CinC), volume 46. IEEE, 2019. [Link]
   (Using the approach proposed in this paper, we won 2nd place in the hackathon of PhysioNet Challenge 2019)
   


10. C. Wu, J. Miller, Y. Chang, M. Sznaier, and J. Dy.
    Solving interpretable kernel dimension reduction.
    In Advances in neural information processing systems, 2019. [Link]


11. J. Chen, Y. Chang, P. Castaldi, M. Cho, B. Hobbs, and J. Dy.
    Crowdclustering with partition labels
    InInternational Conference on Artificial Intelligence and Statistics, pages 1127-1136, 2018. [Link]


12. A. Boueiz, Y. Chang, M. H. Cho, G. R. Washko, R. S. J. Estépar, R. P. Bowler, J. D. Crapo, D. L. DeMeo, J. G. Dy, E. K. Silverman, and others.
    Lobar emphysema distribution is associated with 5-year radiological disease progression.
    Chest, 153(1):65-76, 2018. [Link]


13. A. Boueiz, Y. Chang, M. Cho, D. DeMeo, J. Dy, E. Silverman, and P. Castaldi.
    Machine learn- ing prediction of 5-year progression of fev1 in the copdgene study.
    In D101. Mechanistic and translational studies in COPD,pages A7430–A7430. American Thoracic Society, 2018. [Link]


14. Y. Chang, J. Chen, M. H. Cho, P. J. Castaldi, E. K. Silverman, and J. G. Dy.
    Multiple clustering views from multiple uncertain experts.
    In International Conference on Machine Learning, pages 674-683, 2017. [Link]


15. Y. Chang, J. Chen, M. Cho, P. Castaldi, E. Silverman, and J. Dy.
    Clustering from multiple uncertain experts
    In Artificial Intelligence and Statistics, pages 28–36, 2017. [Link]


16. Y. Chang, J. Chen, M. H. Cho, P. J. Castaidi, E. K. Silverman, and J. G. Dy.
    Clustering with domain-specific usefulness scores
    In Proceedings of the 2017 SIAM International Conference on Data Mining, pages 207–215. SIAM, 2017. [Link]


17. Y. Chang and J. G. Dy.
    Informative subspace learning for counterfactual inference
    In The 31st AAAI Conference on Artificial Intelligence, 2017. [Link]


18. A. A. Ding, J. G. Dy, Y. Li, and Y. Chang.
    A robust-equitable measure for feature ranking and selection.
    The Journal of Machine Learning Research, 18(1):2394–2439, 2017. [Link]


19. J. C. Ross, P. J. Castaldi, M. H. Cho, J. Chen, Y. Chang, J. G. Dy, E. K. Silverman, G. R. Washko, and R. S. J. Estépar.
    A bayesian nonparametric model for disease subtyping: application to emphysema phenotypes.
    IEEE transactions on medical imaging, 36(1):343–354, 2017. [Link]


20. Y. Chang, Y. Li, A. Ding, and J. Dy.
    A robust-equitable copula dependence measure for feature selection.
    In Artificial Intelligence and Statistics, pages 84–92, 2016. [Link]


21. Y. Chang, K. Glass, Y.-Y. Liu, E. K. Silverman, J. D. Crapo, R. Tal-Singer, R. Bowler, J. Dy, M. Cho, and P. Castaldi.
    COPD subtypes identified by network-based clustering of blood gene expression.
    Genomics, 107(2):51–58, 2016. [Link]


22. J. Chen, Y. Chang, B. Hobbs, P. Castaldi, M. Cho, E. Silverman, and J. Dy.
    Interpretable clustering via discriminative rectangle mixture model.
    In Data Mining (ICDM), 2016 IEEE 16th International Conference, pages 823-828. IEEE, 2016. [Link]


23. Y. Li, Y. Chang, T. Vandal, D. Das, A. Ding, A. Ganguly, and J. Dy.
    Copula based covariate selection in climate for statistical downscaling.
    The 2015 International Workshop on Climate Informatics, Boulder, Colorado. [Link]


24. P. J. Castaldi, J. Dy, J. Ross, Y. Chang, G. R. Washko, D. Curran-Everett, A. Williams, D. A. Lynch, B. J. Make, J. D. Crapo, and others.
    Cluster analysis in the copdgene study identifies subtypes of smokers with distinct patterns of airway disease and emphysema.
    Thorax, 2014. [Link]

Professional Service

Workflow chair of ICML (2018)

Program committee of ICML (2017, 2019 - 2021), NeurIPS (2017 - 2019, 2021), ICLR (2018 - 2021), AAAI (2019 - 2021), AISTATS (2019 - 2021), JMLR (2018 - 2019), PAMI (2018), IJCAI (2019-2020)

External reviewer of: NeurIPS (2013 - 2015), ICML (2015), AISTATS (2016), JMLR (2015 - 2016), AAAI (2014), UAI (2015)