Do no harm: a roadmap for responsible machine learning for health care

Jenna Wiens^#¹, Suchi Saria^#^{2

3

4}, Mark Sendak⁵, Marzyeh Ghassemi^{6

7

8}, Vincent X Liu⁹, Finale Doshi-Velez¹⁰, Kenneth Jung¹¹, Katherine Heller^{12

13}, David Kale¹⁴, Mohammed Saeed¹⁵, Pilar N Ossorio¹⁶, Sonoo Thadaney-Israni¹⁷, Anna Goldenberg^#^{18

19

20

21}

Affiliations

¹ Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA. wiensj@umich.edu.
² Departments of Computer Science and Statistics, Whiting School of Engineering, Johns Hopkins University, Baltimore, MD, USA.
³ Department of Health Policy and Management, Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD, USA.
⁴ Bayesian Health, New York, NY, USA.
⁵ Duke Institute for Health Innovation, Duke University School of Medicine, Durham, NC, USA.
⁶ Department of Computer Science, University of Toronto, Toronto, Ontario, Canada.
⁷ Department of Medicine, University of Toronto, Toronto, Ontario, Canada.
⁸ Vector Institute, Toronto, Ontario, Canada.
⁹ Kaiser Permanente Division of Research, Oakland, CA, USA.
¹⁰ School of Engineering and Applied Science, Harvard University, Cambridge, MA, USA.
¹¹ Center for Biomedical Informatics Research, Stanford University, Stanford, CA, USA.
¹² Google Inc., Mountain View, CA, USA.
¹³ Department of Statistical Science, Duke University, Durham, NC, USA.
¹⁴ Information Sciences Institute, University of Southern California, Los Angeles, CA, USA.
¹⁵ Department of Internal Medicine, University of Michigan, Ann Arbor, MI, USA.
¹⁶ Law School, University of Wisconsin-Madison, Madison, WI, USA.
¹⁷ Presence and Program in Bedside Medicine, Stanford University School of Medicine, Stanford, CA, USA.
¹⁸ Department of Computer Science, University of Toronto, Toronto, Ontario, Canada. anna.goldenberg@utoronto.ca.
¹⁹ Vector Institute, Toronto, Ontario, Canada. anna.goldenberg@utoronto.ca.
²⁰ SickKids Research Institute, Toronto, Ontario, Canada. anna.goldenberg@utoronto.ca.
²¹ Child and Brain Development Program, CIFAR, Toronto, Ontario, Canada. anna.goldenberg@utoronto.ca.

^# Contributed equally.

PMID: 31427808
DOI: 10.1038/s41591-019-0548-6

Review

Do no harm: a roadmap for responsible machine learning for health care

Jenna Wiens et al. Nat Med. 2019 Sep.

. 2019 Sep;25(9):1337-1340.

doi: 10.1038/s41591-019-0548-6. Epub 2019 Aug 19.

Authors

Affiliations

¹ Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA. wiensj@umich.edu.
² Departments of Computer Science and Statistics, Whiting School of Engineering, Johns Hopkins University, Baltimore, MD, USA.
³ Department of Health Policy and Management, Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD, USA.
⁴ Bayesian Health, New York, NY, USA.
⁵ Duke Institute for Health Innovation, Duke University School of Medicine, Durham, NC, USA.
⁶ Department of Computer Science, University of Toronto, Toronto, Ontario, Canada.
⁷ Department of Medicine, University of Toronto, Toronto, Ontario, Canada.
⁸ Vector Institute, Toronto, Ontario, Canada.
⁹ Kaiser Permanente Division of Research, Oakland, CA, USA.
¹⁰ School of Engineering and Applied Science, Harvard University, Cambridge, MA, USA.
¹¹ Center for Biomedical Informatics Research, Stanford University, Stanford, CA, USA.
¹² Google Inc., Mountain View, CA, USA.
¹³ Department of Statistical Science, Duke University, Durham, NC, USA.
¹⁴ Information Sciences Institute, University of Southern California, Los Angeles, CA, USA.
¹⁵ Department of Internal Medicine, University of Michigan, Ann Arbor, MI, USA.
¹⁶ Law School, University of Wisconsin-Madison, Madison, WI, USA.
¹⁷ Presence and Program in Bedside Medicine, Stanford University School of Medicine, Stanford, CA, USA.
¹⁸ Department of Computer Science, University of Toronto, Toronto, Ontario, Canada. anna.goldenberg@utoronto.ca.
¹⁹ Vector Institute, Toronto, Ontario, Canada. anna.goldenberg@utoronto.ca.
²⁰ SickKids Research Institute, Toronto, Ontario, Canada. anna.goldenberg@utoronto.ca.
²¹ Child and Brain Development Program, CIFAR, Toronto, Ontario, Canada. anna.goldenberg@utoronto.ca.

^# Contributed equally.

PMID: 31427808
DOI: 10.1038/s41591-019-0548-6

Erratum in

Author Correction: 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, Thadaney-Israni S, Goldenberg A. Wiens J, et al. Nat Med. 2019 Oct;25(10):1627. doi: 10.1038/s41591-019-0609-x. Nat Med. 2019. PMID: 31537911

Abstract

Interest in machine-learning applications within medicine has been growing, but few studies have progressed to deployment in patient care. We present a framework, context and ultimately guidelines for accelerating the translation of machine-learning-based interventions in health care. To be successful, translation will require a team of engaged stakeholders and a systematic process from beginning (problem formulation) to end (widespread deployment).

PubMed Disclaimer

References

1. Lazer, D., Kennedy, R., King, G. & Vespignani, A. Big data. The parable of Google Flu: traps in big data analysis. Science 343, 1203–1205 (2014). - DOI
1. Hutson, M. Even artificial intelligence can acquire biases against race and gender. Science https://doi.org/10.1126/science.aal1053 (2017).
1. He, J. et al. The practical implementation of artificial intelligence technologies in medicine. Nat. Med. 25, 30–36 (2019). - DOI
1. Silva, I., Moody, G., Scott, D. J., Celi, L. A. & Mark, R. G. Predicting in-hospital mortality of ICU patients: the Physionet/Computing in Cardiology Challenge 2012. Comput. Cardiol. 39, 245–248 (2012).
1. Luo, Y., Cai, X., Zhang, Y. & Xu, J. Multivariate time series imputation with generative adversarial networks. in Advances in Neural Information Processing Systems 1596–1607 (NeurIPS, 2018).

Publication types

Actions

MeSH terms

Actions
Actions
Actions
Actions
Actions
Actions

LinkOut - more resources

Full Text Sources
- Nature Publishing Group
Medical
- MedlinePlus Health Information

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

Do no harm: a roadmap for responsible machine learning for health care

Affiliations

Do no harm: a roadmap for responsible machine learning for health care

Authors

Affiliations

Erratum in

Abstract

References

Publication types

MeSH terms

LinkOut - more resources

Full Text Sources

Medical