Conference paper · 2021 · Open access

Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings

Vinith M. Suriyakumar, Nicolas Papernot, Anna Goldenberg, Marzyeh Ghassemi

ACM Conference on Fairness, Accountability, and Transparency (FAccT), 723–734 · Published 1 March 2021 · DOI 10.1145/3442188.3445934

Open PDFView at the publisherCite this paper

In brief

“Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings” is a 2021 conference paper by Vinith M. Suriyakumar and 3 co-authors, published in ACM Conference on Fairness, Accountability, and Transparency (FAccT). OpenAlex counts 93 citations as of 19 November 2026, which puts it in the top 2% of works published in 2021 by citations. It is open access under a CC BY licence: the full text is free to read at ACM Conference on Fairness, Accountability, and Transparency (FAccT).

Citations
93
Most cited in
2023 (21)
Field-weighted impact
4.23
References
114
Authors
4

Abstract

Machine learning models in health care are often deployed in settings where it is important to protect patient privacy. In such settings, methods for differentially private (DP) learning provide a general-purpose approach to learn models with privacy guarantees. Modern methods for DP learning ensure privacy through the addition of calibrated noise. The resulting privacy-preserving models are unable to learn too much information about the tails of a data distribution, resulting in a loss of accuracy that can disproportionately affect small groups. In this paper, we study the effects of DP learning in health care. We use state-of-the-art methods for DP learning to train privacy-preserving models in clinical prediction tasks, including x-ray classification of images and mortality prediction in time series data. We use these models to perform a comprehensive empirical investigation of the tradeoffs between privacy, utility, robustness to dataset shift and fairness. Our results highlight lesser-known limitations of methods for DP learning in health care, models that exhibit steep tradeoffs between privacy and utility, and models whose predictions are disproportionately influenced by large demographic groups in the training data. We discuss the costs and benefits of differentially private learning in health care with open directions for differential privacy, machine learning and health care.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Suriyakumar, V. M., Papernot, N., Goldenberg, A., & Ghassemi, M. (2021). Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings. ACM Conference on Fairness, Accountability, and Transparency (FAccT), 723–734. https://doi.org/10.1145/3442188.3445934

MLA 9

Suriyakumar, Vinith M., et al. “Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings.” ACM Conference on Fairness, Accountability, and Transparency (FAccT), 2021, pp. 723–734. https://doi.org/10.1145/3442188.3445934.

Chicago

Suriyakumar, Vinith M., Nicolas Papernot, Anna Goldenberg, and Marzyeh Ghassemi. 2021. “Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings.” ACM Conference on Fairness, Accountability, and Transparency (FAccT): 723–734. https://doi.org/10.1145/3442188.3445934.

Harvard

Suriyakumar, V. M. et al. (2021) ‘Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings’, ACM Conference on Fairness, Accountability, and Transparency (FAccT), pp. 723–734. doi:10.1145/3442188.3445934.

IEEE

V. M. Suriyakumar, N. Papernot, A. Goldenberg, and M. Ghassemi, “Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings,” ACM Conference on Fairness, Accountability, and Transparency (FAccT), pp. 723–734, 2021, doi: 10.1145/3442188.3445934.

BibTeX

@inproceedings{suriyakumar2021chasing,
  title     = {{Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings}},
  author    = {Suriyakumar, Vinith M. and Papernot, Nicolas and Goldenberg, Anna and Ghassemi, Marzyeh},
  booktitle = {ACM Conference on Fairness, Accountability, and Transparency (FAccT)},
  year      = {2021},
  pages     = {723--734},
  doi       = {10.1145/3442188.3445934},
  url       = {https://doi.org/10.1145/3442188.3445934}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
20211010
20221515
20232121
20241717
20251717
20261313

Its field-weighted citation impact is 4.23: it has been cited 4.23 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data

  • differential privacy
  • privacy-preserving machine learning
  • health care
  • clinical prediction
  • mortality prediction
  • X-ray classification
  • privacy-utility trade-off
  • fairness

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Suriyakumar, V. M., Papernot, N., Goldenberg, A., & Ghassemi, M. (2021). Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings. ACM Conference on Fairness, Accountability, and Transparency (FAccT), 723–734. https://doi.org/10.1145/3442188.3445934

How many times has this paper been cited?

93 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at ACM Conference on Fairness, Accountability, and Transparency (FAccT): sign in and open the PDF from this page.

Who wrote this paper?

Vinith M. Suriyakumar, Nicolas Papernot, Anna Goldenberg, Marzyeh Ghassemi.

What is the DOI of this paper?

10.1145/3442188.3445934, permanently at https://doi.org/10.1145/3442188.3445934. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.