Full List on Google Scholar.


  • ClinicalVis: An evaluation of open-source visualization to support clinical decision-making in the intensive care unit.
    Marzyeh Ghassemi, Mahima Pushkarna, James Wexler, Jesse Johnson, Paul Varghese
    Download Preprint

Refereed Conference Papers

  • CheXclusion: Fairness gaps in deep chest X-ray classifiers.
    Laleh Seyyed-Kalantari, Guanxiong Liu, Matthew McDermott, Marzyeh Ghassemi
    To appear in PSB 2021
    Download Preprint.
  • SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness
    Nathan Ng, Kyunghyun Cho and Marzyeh Ghassemi
    To appear in EMNLP 2020
  • Hurtful words: quantifying biases in clinical contextual word embeddings.
    Haoran Zhang, Amy X. Lu, Mohamed Abdalla, Matthew McDermott, Marzyeh Ghassemi
    Proccedings of ACM CHIL 2020.
  • MIMIC-Extract: a data extraction, preprocessing, and representation pipeline for MIMIC-III.
    Shirly Wang, Matthew B. A. McDermott, Geeticka Chauhan, Marzyeh Ghassemi, Michael C. Hughes, Tristan Naumann.
    Proccedings of ACM CHIL 2020.
  • A review of challenges and opportunities in machine learning for health.
    Marzyeh Ghassemi, Tristan Naumann, Peter Schulam, Andrew L. Beam, Rajesh Ranganath
    Download Preprint
    In AMIA 2020 Informatics Summit.
  • Treating health disparities with artificial intelligence.
    Chen, I. Y., Joshi, S., and Ghassemi, M.
    Nature Medicine 2020, 26(1):16–17.
    Download Paper.
  • Challenges to the Reproducibility of Machine Learning Models in Health Care. Beam, A. L., Manrai, A. K., and Ghassemi, M.
    JAMA 2020.
    Download Paper.
  • The cells out of sample (coos) dataset and benchmarks for measuring out-of-sample generalization of image classifiers.
    Lu, A., Lu, A., Schormann, W., Ghassemi, M., Andrews, D., and Moses, A. NeurIPS 2019.
    Download Paper.
  • Clinically Accurate Chest X-Ray Report Generation
    Guanxiong Liu, Tzu-Ming Harry Hsu, Matthew McDermott, Willie Boag, Wei-Hung Weng, Peter Szolovits, Marzyeh Ghassemi. In Machine Learning for Healthcare 2019, JMLR WC Track.
    Download Paper.
  • Feature robustness in non-stationary health records: Caveats to deployable model performance in common clinical machine learning tasks.
    Nestor, B., McDermott, M. B., Boag, W., Berner, G., Naumann, T. J., Hughes, M., Goldenberg, A., and Ghassemi, M. In Machine Learning for Healthcare 2019, JMLR WC Track
    Download Paper.
  • Learning from few subjects with large amounts of voice monitoring data
    Ortiz, J. J., Mehta, D., Van Stan, J., Hillman, R., Guttag, J., and Ghassemi, M. In Machine Learning for Healthcare 2019, JMLR WC Track
    Download Paper. Read about it on MIT News.
  • Continuous State-Space Models for Optimal Sepsis Treatment-a Deep Reinforcement Learning Approach
    Aniruddh Raghu, Matthieu Komorowski, Leo Anthony Celi, Peter Szolovits, Marzyeh Ghassemi
    MLHC 2017, Boston, MA. (33% Acceptance Rate)

    Proceedings of the 2nd Machine Learning for Healthcare Conference, 2017; JMLR W&C V68
    Download Preprint
  • Predicting Intervention Onset in the ICU with Switching State Space Models
    Marzyeh Ghassemi*, Mike Wu*, Michael C. Hughes*, Peter Szolovits, and Finale Doshi-Velez
    Proceedings of the AMIA Summit on Clinical Research Informatics (CRI), 2017
    Download Preprint. Nominated for Best Paper.
  • Prediction Using Patient Comparison vs. Modeling: A Case Study for Mortality Prediction
    Mark Hoogendoorn, Ali el Hassouni, Kwongyen Mok, Marzyeh Ghassemi, Peter Szolovits
    EMBC 2016, Orlando, FL
    Download Preprint.
  • A Multivariate Timeseries Modeling Approach to Severity of Illness Assessment
    and Forecasting in ICU with Sparse, Heterogeneous Clinical Data
    Marzyeh Ghassemi*, Marco A.F. Pimentel*, Tristan Naumann, Thomas Brennan, David A. Clifton, Peter Szolovits, Mengling Feng
    AAAI 2015, Austin, TX (27% Acceptance Rate)
    Download Preprint.

Journal Papers

  • Do no harm: a roadmap for responsible machine learning for health care.
    Wiens J, Saria S, Sendak M, Ghassemi M, Liu VX, Doshi-Velez F, Jung K, Heller K, Kale D, Saeed M, Ossorio PN.  Nature medicine. 2019 Aug 19:1-4.
    View Online.
  • Practical guidance on artificial intelligence for health-care data
    Ghassemi M, Naumann T, Schulam P, Beam AL, Chen IY, Ranganath R. Lancet Digital Health, Volume 1, ISSUE 4, Pe157-e159, August 01, 2019
    View Online.
  • The Disparate Impacts of Medical and Mental Health with AI.
    Chen, I., Szolovits, P., and Ghassemi, M.
    AMA J Ethics. 2019;21(2):E167-179.
    Download Preprint.
  • Predicting early psychiatric readmission with natural language processing of narrative discharge summaries
    Anna Rumshisky, Marzyeh Ghassemi, Tristan Naumann, Peter Szolovits, Victor Castro, Thomas McCoy and Roy Perlis
    Translational Psychiatry (2016) 6, e921; doi:10.1038
    View Online; Download Preprint.
  • Understanding vasopressor intervention and weaning: Risk prediction in a public heterogeneous clinical time series database
    Marzyeh Ghassemi*, Mike Wu*, Mengling Feng, Leo A. Celi, Peter Szolovits, Finale Doshi-Velez
    Journal of the American Medical Informatics Association (JAMIA) 2016
    View Online; Download Preprint.
  • Using ambulatory voice monitoring to investigate common voice disorders: Research update
    Daryush Mehta, Jarrad H. Van Stan, Matias Zañartu, Marzyeh Ghassemi, et al.
    Frontiers in Bioengineering and Biotechnology, in press, 2015.
    View Open Access. Download Preprint.
  • State of the art review: the data revolution in critical care 
    Marzyeh Ghassemi, Leo Anthony Celi and David J Stone
    Critical Care 2015, vol 19, no. 118.
    View Open Access. Download PDF.
  • Short-Term Mortality Prediction for Elderly Patients Using Medicare Claims Data
    Maggie Makar, Marzyeh Ghassemi, David M. Cutler, and Ziad Obermeyer
    International Journal of Machine Learning and Computing vol. 5, no. 3, pp. 192-197, 2015.
    Download Preprint.
  • Making Big Data Useful for Health Care: A Summary of the Inaugural MIT Critical Data Conference
    Marzyeh Ghassemi**, et al.
    ** All authors were members of the MIT Critical Data Conference 2014 Organizing Committee, and names were listed alphabetically.
    JMIR Med Inform 2014;2(2):e22; PMID 25600172; PMCID PMC4288071
    Download Preprint.
  • Learning to detect vocal hyperfunction from ambulatory necksurface acceleration features: Initial results for vocal fold nodules
    Marzyeh Ghassemi, Jarrad H. Van Stan, Daryush D. Mehta, Matías Zañartu, Harold A. Cheyne II, Robert E. Hillman, and John V. Guttag
    IEEE Transactions on Biomedical Engineering Volume 61, Issue 6, Page: 1668–1675 as TBME.2013.2297372
    Selected for a TBME Spotlight; Cited 10 times in the following year.
    Download Preprint.

  • Leveraging a critical care database: SSRI use prior to icu admission is associated with increased hospital mortality
    Marzyeh Ghassemi, John Marshall, Nakul Singh, David J. Stone, Leo A. Celi
    CHEST Journal as Chest. 2013/chest.13-1722.
    Download Preprint.

Refereed Workshop Proceedings

  • Reproducibility in Machine Learning for Health
    Matthew B.A. McDermott, Shirly Wang, Nikki Marinsek, Rajesh Ranganath, Marzyeh Ghassemi, Luca Foschini
    Reproducibility in Machine Learning Workshop at ICLR 2019
    May 06, 2019, New Orleans, Louisiana, United States
    Download paper here.
  • Rethinking clinical prediction: Why machine learning must consider year of care and feature aggregation
    Bret Nestor, Matthew B. A. McDermott, Geeticka Chauhan, Tristan Naumann, Michael C. Hughes, Anna Goldenberg, Marzyeh Ghassemi
    Machine Learning for Health (ML4H) Workshop at NeurIPS 2018
    December 08, 2018, Montreal, Canada
    Download paper here.
  • The Effect of Heterogeneous Data for Alzheimer's Disease Detection from Speech
    Aparna Balagopalan, Jekaterina Novikova, Frank Rudzicz, Marzyeh Ghassemi
    Machine Learning for Health (ML4H) Workshop at NeurIPS 2018
    December 08, 2018, Montreal, Canada
    Download paper here.
  • Modeling Mistrust in End-of-Life Care
    Willie Boag, Harini Suresh, Leo Anthony Celi, Peter Szolovits, Marzyeh Ghassemi
    5th Workshop on Fairness, Accountability, and Transparency in Machine Learning (FAT/ML 2018)
    Co-located with 35th International Conference on Machine Learning (ICML 2018)
    15 July 2018, Stockholm, Sweden
  • An Open Benchmark for Causal Inference Using the MIMIC-III Dataset
    Leo A. Celi, Ken Jung, Marzyeh Ghassemi, Carlos Guzman, Uri Shalit, David Sontag
    OHDSI Collaborator Showcase in OHDSI Symposium
    Washington DC, September 23 2016
    Download OHDSI Poster; Download OHDSI Abstract
  • Confirming the themes and interpretive unity of Ghazal poetry using topic models
    Ehsaneddin Asgari, Marzyeh Ghassemi and Mark Finlayson
    NIPS 2013 Workshop on Topic Models: Computation, Application, and Evaluation
    Download NIPS 2013 Workshop Paper
  • Detecting Voice Modes for Vocal Hyperfunction Prevention
    Marzyeh Ghassemi, Eugene Shih, Daryush Mehta, Shengran Feng, Jarrad Van Stan, Robert Hillman, John Guttag
    WiML/NIPS 2012 Workshop
    Download NIPS 2012 Poster
  • Topic Models for Mortality Modeling in Intensive Care Units
    Marzyeh Ghassemi, Tristan Naumann, Rohit Joshi, Anna Rumshisky
    ICML 2012 Machine Learning for Clinical Data Analysis Workshop
    Download ICML 2012 Workshop Paper

Theses & Book Chapters

  • Data Analysis.
    Jesse D. Raffa, Marzyeh Ghassemi, Tristan Naumann, Mengling Feng, and Douglas Hsu. "Data Analysis." In Secondary Analysis of Electronic Health Records, pp. 205-261. Springer International Publishing, 2016.
    Download PDF or View Chapter
  • State of the Art Review: The Data Revolution in Critical Care
    Marzyeh Ghassemi, David J. Stone, Leo A. Celi
    Annual Update in Intensive Care and Emergency Medicine 2015. Springer International Publishing, 2015. 573-586
    Download Preprint
  • Methods and Models for Acute Hypotensive Episode Prediction
    Marzyeh Ghassemi
    Oxford University MSc Thesis
    Download MSc Thesis

Invited Talks & Presentations

  • AMIA Ignite, Chicago, IL
    Nov. 15, 2016
    Ignite Talk on "How Machine Learning Can Change Health"
  • NLM/NIH Informatics Training Conference, Rockville, MD
    June 23-24, 2015
    Open Mic session on "Severity of Illness Assessment and Forecasting in ICU with Sparse, Heterogeneous Clinical Data".

Student Competitions

  • Probabilistically Populated Medical Record Templates:  Reducing Clinical Documentation Time Using Patient Cooperation
    Tristan Naumann, Marzyeh Ghassemi, Andreea Bodnari, Rohit Joshi
    Third Place Prize Winners
    AMIA 2013 Student Design Challenge: Reinventing Clinical Documentation
    Download Proposal

(*) These authors contributed equally, and should be considered co-first authors.