I am an EWSC Postdoctoral Fellow at the Broad Institute of MIT and Harvard. I earned my PhD in Computer Science from the University of Toronto. My research lies at the intersection of machine learning and healthcare, with a focus on developing innovative methods to extract actionable clinical insights from complex and multimodal health data.
My work spans areas such as self-supervised representation learning, multimodal learning, and explainability. During my PhD, I received the Apple Scholars in AI/ML Fellowship and the Health System Impact Fellowship from the Canadian Institutes of Health Research (CIHR).

You can find my CV Here




Education

  • Ph.D. in Computer Science, 2023
  • B.Sc in Computer Engineering, University of Toronto, 2018

Awards


Selected Research Papers

  • An Information Criterion for Controlled Disentanglement of Multimodal Data
    Wang, Chenyu;, Gupta, Sharut; Zhang, Xinyi; Tonekaboni, Sana; Jegelka, Stephanie; Jaakkola, Tommi; Uhler, Caroline;
    International Conference on Learning Representations (ICLR), 2025.

  • Learning under Temporal Label Noise
    Nagaraj, Sujay; Gerych, Walter; Tonekaboni, Sana; Goldenberg, Anna; Ustun, Berk; Hartvigsen, Thomas;
    International Conference on Learning Representations (ICLR), 2025.

  • Dynamic Interpretable Change Point Detection for Physiological Data Analysis
    Yu, Jennifer; Behrouzi, Tina; Garg, Kopal; Goldenberg, Anna; Tonekaboni, Sana;
    Machine Learning for Health (ML4H), 2023.

  • Modeling Personalized Heart Rate Response to Exercise and Environmental Factors with Wearables Data
    Nazaret, Achille; Tonekaboni, Sana; Darnell, Gregory; Ren, Shirley You; Sapiro, Guillermo; Miller, Andrew C.;
    npj Digital Medicine, 2023.

  • Decoupling Local and Global Representations of Time Series
    Tonekaboni, Sana; Li, Chun-Liang; Arik, Sercan O.; Goldenberg, Anna; Pfister, Tomas;
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.

  • How to validate Machine Learning Models Prior to Deployment: Silent trial protocol for evaluation of real-time models at the ICU
    Tonekaboni, Sana; Morgenshtern, Gabriela; Assadi, Azadeh; Pokhrel, Aslesha; Huang, Xi; Jayarajan, Anand; Greer, Robert; Pekhimenko, Gennady; McCradden, Melissa; Chevalier, Fanny; Mazwi, Mjaye; Goldenberg, Anna;
    Conference on Health, Inference, and Learning (CHIL), 2022.

  • Learning Unsupervised Representations for ICU Timeseries
    Weatherhead, Addison; Greer, Robert; Moga, Michael-Alice; Mazwi, Mjaye; Eytan, Danny; Goldenberg, Anna; Tonekaboni, Sana;
    Conference on Health, Inference, and Learning (CHIL), 2022.

  • Unsupervised Representation Learning for TimeSeries with Temporal Neighborhood Coding
    Tonekaboni, Sana; Eytan, Danny; Goldenberg, Anna;
    International Conference on Learning Representations (ICLR), 2020.

  • What went wrong and when? Instance-wise feature importance for time-series models
    Tonekaboni, Sana*; Joshi, Shalmali*; Campbell, Kieran; Duvenaud, David; Goldenberg, Anna;
    Neural Information Processing Systems (NeurIPS), 2020.

  • What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use
    Tonekaboni, Sana*; Joshi, Shalmali*; McCradden, Melissa; Goldenberg, Anna;
    Conference on Machine Learning for Healthcare (MLHC), 2019.

  • Prediction of Cardiac Arrest from Physiological Signals in the Pediatric ICU
    Tonekaboni, Sana; Mazwi, Mjaye; Laussen, Peter; Eytan, Danny; Greer, Robert; Goodfellow, Sebastian D.; Goodwin, Andrew; Brudno, Michael; Goldenberg, Anna;
    Conference on Machine Learning for Healthcare (MLHC), 2018.

  • Closed-Loop Neurostimulators: A Survey and A Seizure-Predicting Design Example for Intractable Epilepsy Treatment
    Kassiri, Hossein; Tonekaboni, Sana; Salam, M. Tariqus; Soltani, Nima; Abdelhalim, Karim; Perez Velazquez, Jose Luis; Genov, Roman;
    IEEE Transactions on Biomedical Circuits and Systems 11, 2017.