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

Jenna Wiens; Suchi Saria; Mark Sendak; Marzyeh Ghassemi; Vincent X. Liu; Finale Doshi-Velez; Kenneth Jung; Katherine Heller; David Kale; Mohammed Saeed; Pilar N. Ossorio; Sonoo Thadaney-Israni; Anna Goldenberg

doi:10.1038/s41591-019-0548-6

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

Jenna Wiens
, Suchi Saria
, Mark Sendak
, Marzyeh Ghassemi
, Vincent X. Liu
, Finale Doshi-Velez
, Kenneth Jung
, Katherine Heller
, David Kale
, Mohammed Saeed
, Pilar N. Ossorio
, Sonoo Thadaney-Israni
, Anna Goldenberg

Whiting School of Engineering

Research output: Contribution to journal › Article › peer-review

87 Scopus citations

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).

Original language	English (US)
Pages (from-to)	1337-1340
Number of pages	4
Journal	Nature medicine
Volume	25
Issue number	9
DOIs	https://doi.org/10.1038/s41591-019-0548-6
State	Published - Sep 1 2019

ASJC Scopus subject areas

General Biochemistry, Genetics and Molecular Biology

Access to Document

10.1038/s41591-019-0548-6

Cite this

@article{598fddf8e1144e5589563f2bfcbe907f,

title = "Do no harm: a roadmap for responsible machine learning for health care",

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).",

author = "Jenna Wiens and Suchi Saria and Mark Sendak and Marzyeh Ghassemi and Liu, \{Vincent X.\} and Finale Doshi-Velez and Kenneth Jung and Katherine Heller and David Kale and Mohammed Saeed and Ossorio, \{Pilar N.\} and Sonoo Thadaney-Israni and Anna Goldenberg",

note = "Publisher Copyright: {\textcopyright} 2019, Springer Nature America, Inc.",

year = "2019",

month = sep,

day = "1",

doi = "10.1038/s41591-019-0548-6",

language = "English (US)",

volume = "25",

pages = "1337--1340",

journal = "Nature medicine",

issn = "1078-8956",

publisher = "Nature Research",

number = "9",

}

TY - JOUR

T1 - Do no harm

T2 - a roadmap for responsible machine learning for health care

AU - Wiens, Jenna

AU - Saria, Suchi

AU - Sendak, Mark

AU - Ghassemi, Marzyeh

AU - Liu, Vincent X.

AU - Doshi-Velez, Finale

AU - Jung, Kenneth

AU - Heller, Katherine

AU - Kale, David

AU - Saeed, Mohammed

AU - Ossorio, Pilar N.

AU - Thadaney-Israni, Sonoo

AU - Goldenberg, Anna

PY - 2019/9/1

Y1 - 2019/9/1

N2 - 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).

AB - 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).

UR - https://www.scopus.com/pages/publications/85071331458

UR - https://www.scopus.com/pages/publications/85071331458#tab=citedBy

U2 - 10.1038/s41591-019-0548-6

DO - 10.1038/s41591-019-0548-6

M3 - Article

C2 - 31427808

AN - SCOPUS:85071331458

SN - 1078-8956

VL - 25

SP - 1337

EP - 1340

JO - Nature medicine

JF - Nature medicine

IS - 9

ER -

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

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this