Time to reality check the promises of machine learning-powered precision medicine

Jack Wilkinson; Kellyn F Arnold; Eleanor J Murray; Maarten van Smeden; Kareem Carr; Rachel Sippy; Marc de Kamps; Andrew Beam; Stefan Konigorski; Christoph Lippert; Mark S Gilthorpe; Peter W G Tennant

doi:10.1016/S2589-7500(20)30200-4

Time to reality check the promises of machine learning-powered precision medicine

Jack Wilkinson, Kellyn F Arnold, Eleanor J Murray, Maarten van Smeden, Kareem Carr, Rachel Sippy, Marc de Kamps, Andrew Beam, Stefan Konigorski, Christoph Lippert, Mark S Gilthorpe, Peter W G Tennant

Statistics

Research output: Contribution to journal › Comment/debate › peer-review

Abstract

Machine learning methods, combined with large electronic health databases, could enable a personalised approach to medicine through improved diagnosis and prediction of individual responses to therapies. If successful, this strategy would represent a revolution in clinical research and practice. However, although the vision of individually tailored medicine is alluring, there is a need to distinguish genuine potential from hype. We argue that the goal of personalised medical care faces serious challenges, many of which cannot be addressed through algorithmic complexity, and call for collaboration between traditional methodologists and experts in medical machine learning to avoid extensive research waste.

Original language	English
Pages (from-to)	e677-e680
Number of pages	4
Journal	The Lancet Digital Health
Volume	2
Issue number	12
Early online date	16 Sept 2020
DOIs	https://doi.org/10.1016/S2589-7500(20)30200-4
Publication status	Published - Dec 2020

Keywords

Delivery of Health Care/methods
Humans
Machine Learning
Precision Medicine/methods

Access to Document

10.1016/S2589-7500(20)30200-4Licence: CC BY

Wilkinson_2020_LancetDH_check-ML-powered-PM_CC
Copyright © 2020 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license.
Final published version, 93.2 KBLicence: CC BY

Cite this

@article{6fb228ebd6d74fd8bcd711fa05e873bc,

title = "Time to reality check the promises of machine learning-powered precision medicine",

abstract = "Machine learning methods, combined with large electronic health databases, could enable a personalised approach to medicine through improved diagnosis and prediction of individual responses to therapies. If successful, this strategy would represent a revolution in clinical research and practice. However, although the vision of individually tailored medicine is alluring, there is a need to distinguish genuine potential from hype. We argue that the goal of personalised medical care faces serious challenges, many of which cannot be addressed through algorithmic complexity, and call for collaboration between traditional methodologists and experts in medical machine learning to avoid extensive research waste.",

keywords = "Delivery of Health Care/methods, Humans, Machine Learning, Precision Medicine/methods",

author = "Jack Wilkinson and Arnold, {Kellyn F} and Murray, {Eleanor J} and {van Smeden}, Maarten and Kareem Carr and Rachel Sippy and {de Kamps}, Marc and Andrew Beam and Stefan Konigorski and Christoph Lippert and Gilthorpe, {Mark S} and Tennant, {Peter W G}",

note = "JW is supported by a Wellcome Institutional Strategic Support Fund award (204796/Z/16/Z). MSG and PWGT are supported by The Alan Turing Institute (EP/N510129/1). CL is supported by the German Federal Ministry of Education and Research in the project KI-LAB-ITSE (project number 01|S19066). ",

year = "2020",

month = dec,

doi = "10.1016/S2589-7500(20)30200-4",

language = "English",

volume = "2",

pages = "e677--e680",

journal = "The Lancet Digital Health",

issn = "2589-7500",

publisher = "Elsevier",

number = "12",

}

TY - JOUR

T1 - Time to reality check the promises of machine learning-powered precision medicine

AU - Wilkinson, Jack

AU - Arnold, Kellyn F

AU - Murray, Eleanor J

AU - van Smeden, Maarten

AU - Carr, Kareem

AU - Sippy, Rachel

AU - de Kamps, Marc

AU - Beam, Andrew

AU - Konigorski, Stefan

AU - Lippert, Christoph

AU - Gilthorpe, Mark S

AU - Tennant, Peter W G

N1 - JW is supported by a Wellcome Institutional Strategic Support Fund award (204796/Z/16/Z). MSG and PWGT are supported by The Alan Turing Institute (EP/N510129/1). CL is supported by the German Federal Ministry of Education and Research in the project KI-LAB-ITSE (project number 01|S19066).

PY - 2020/12

Y1 - 2020/12

N2 - Machine learning methods, combined with large electronic health databases, could enable a personalised approach to medicine through improved diagnosis and prediction of individual responses to therapies. If successful, this strategy would represent a revolution in clinical research and practice. However, although the vision of individually tailored medicine is alluring, there is a need to distinguish genuine potential from hype. We argue that the goal of personalised medical care faces serious challenges, many of which cannot be addressed through algorithmic complexity, and call for collaboration between traditional methodologists and experts in medical machine learning to avoid extensive research waste.

AB - Machine learning methods, combined with large electronic health databases, could enable a personalised approach to medicine through improved diagnosis and prediction of individual responses to therapies. If successful, this strategy would represent a revolution in clinical research and practice. However, although the vision of individually tailored medicine is alluring, there is a need to distinguish genuine potential from hype. We argue that the goal of personalised medical care faces serious challenges, many of which cannot be addressed through algorithmic complexity, and call for collaboration between traditional methodologists and experts in medical machine learning to avoid extensive research waste.

KW - Delivery of Health Care/methods

KW - Humans

KW - Machine Learning

KW - Precision Medicine/methods

U2 - 10.1016/S2589-7500(20)30200-4

DO - 10.1016/S2589-7500(20)30200-4

M3 - Comment/debate

C2 - 33328030

SN - 2589-7500

VL - 2

SP - e677-e680

JO - The Lancet Digital Health

JF - The Lancet Digital Health

IS - 12

ER -

Time to reality check the promises of machine learning-powered precision medicine

Abstract

Keywords

Access to Document

Fingerprint

Cite this