Artificial intelligence-based clinical decision support in modern medical physics: Selection, acceptance, commissioning, and quality assurance.
artificial intelligence
clinical decision support
machine learning
Journal
Medical physics
ISSN: 2473-4209
Titre abrégé: Med Phys
Pays: United States
ID NLM: 0425746
Informations de publication
Date de publication:
Jun 2020
Jun 2020
Historique:
received:
11
03
2019
revised:
27
04
2019
accepted:
27
04
2019
entrez:
18
5
2020
pubmed:
18
5
2020
medline:
2
3
2021
Statut:
ppublish
Résumé
Recent advances in machine and deep learning based on an increased availability of clinical data have fueled renewed interest in computerized clinical decision support systems (CDSSs). CDSSs have shown great potential to improve healthcare, increase patient safety and reduce costs. However, the use of CDSSs is not without pitfalls, as an inadequate or faulty CDSS can potentially deteriorate the quality of healthcare and put patients at risk. In addition, the adoption of a CDSS might fail because its intended users ignore the output of the CDSS due to lack of trust, relevancy or actionability. In this article, we provide guidance based on literature for the different aspects involved in the adoption of a CDSS with a special focus on machine and deep learning based systems: selection, acceptance testing, commissioning, implementation and quality assurance. A rigorous selection process will help identify the CDSS that best fits the preferences and requirements of the local site. Acceptance testing will make sure that the selected CDSS fulfills the defined specifications and satisfies the safety requirements. The commissioning process will prepare the CDSS for safe clinical use at the local site. An effective implementation phase should result in an orderly roll out of the CDSS to the well-trained end-users whose expectations have been managed. And finally, quality assurance will make sure that the performance of the CDSS is maintained and that any issues are promptly identified and solved. We conclude that a systematic approach to the adoption of a CDSS will help avoid pitfalls, improve patient safety and increase the chances of success.
Sections du résumé
BACKGROUND
BACKGROUND
Recent advances in machine and deep learning based on an increased availability of clinical data have fueled renewed interest in computerized clinical decision support systems (CDSSs). CDSSs have shown great potential to improve healthcare, increase patient safety and reduce costs. However, the use of CDSSs is not without pitfalls, as an inadequate or faulty CDSS can potentially deteriorate the quality of healthcare and put patients at risk. In addition, the adoption of a CDSS might fail because its intended users ignore the output of the CDSS due to lack of trust, relevancy or actionability.
AIM
OBJECTIVE
In this article, we provide guidance based on literature for the different aspects involved in the adoption of a CDSS with a special focus on machine and deep learning based systems: selection, acceptance testing, commissioning, implementation and quality assurance.
RESULTS
RESULTS
A rigorous selection process will help identify the CDSS that best fits the preferences and requirements of the local site. Acceptance testing will make sure that the selected CDSS fulfills the defined specifications and satisfies the safety requirements. The commissioning process will prepare the CDSS for safe clinical use at the local site. An effective implementation phase should result in an orderly roll out of the CDSS to the well-trained end-users whose expectations have been managed. And finally, quality assurance will make sure that the performance of the CDSS is maintained and that any issues are promptly identified and solved.
CONCLUSION
CONCLUSIONS
We conclude that a systematic approach to the adoption of a CDSS will help avoid pitfalls, improve patient safety and increase the chances of success.
Identifiants
pubmed: 32418341
doi: 10.1002/mp.13562
pmc: PMC7318221
doi:
Types de publication
Journal Article
Review
Langues
eng
Sous-ensembles de citation
IM
Pagination
e228-e235Subventions
Organisme : Netherlands Organisation for Scientific Research
Informations de copyright
© 2019 The Authors. Medical Physics published by Wiley Periodicals, Inc. on behalf of American Association of Physicists in Medicine.
Références
Implement Sci. 2011 Aug 03;6:92
pubmed: 21824386
BMJ. 2015 Jan 07;350:g7594
pubmed: 25569120
Inform Prim Care. 2012;20(2):115-28
pubmed: 23710776
Implement Sci. 2011 Aug 03;6:87
pubmed: 21824381
Radiother Oncol. 2018 Feb;126(2):312-317
pubmed: 29208513
J Med Eng Technol. 1984 Jan-Feb;8(1):19-23
pubmed: 6716444
JAMA. 2005 Mar 9;293(10):1223-38
pubmed: 15755945
ACP J Club. 1995 Nov-Dec;123(3):A12-3
pubmed: 7582737
J Am Med Inform Assoc. 2012 May-Jun;19(3):346-52
pubmed: 21849334
Mach Learn. 2011 Jul 1;84(1-2):109-136
pubmed: 21799585
Stud Health Technol Inform. 2004;107(Pt 1):145-8
pubmed: 15360792
J Biomed Inform. 2008 Apr;41(2):387-92
pubmed: 18029232
Int J Med Inform. 2008 Oct;77(10):641-9
pubmed: 18353713
J Am Med Inform Assoc. 2018 Jul 1;25(7):862-871
pubmed: 29762678
J Healthc Inf Manag. 2009 Fall;23(4):38-45
pubmed: 19894486
Implement Sci. 2011 Aug 03;6:89
pubmed: 21824383
Proc AMIA Symp. 2002;:265-9
pubmed: 12463828
J Am Med Inform Assoc. 2013 Jul-Aug;20(4):749-57
pubmed: 23564631
Nat Rev Clin Oncol. 2013 Jan;10(1):27-40
pubmed: 23165123
Med Phys. 2018 Nov;45(11):5105-5115
pubmed: 30229951
Br Med J. 1972 Apr 1;2(5804):9-13
pubmed: 4552594
AMIA Annu Symp Proc. 2007 Oct 11;:26-30
pubmed: 18693791
BMC Med Inform Decis Mak. 2012 Feb 14;12:6
pubmed: 22333210
Nat Biomed Eng. 2018 Oct;2(10):719-731
pubmed: 31015651
Ann Intern Med. 2012 Jul 3;157(1):29-43
pubmed: 22751758
Int J Qual Health Care. 2017 Dec 1;29(8):973-980
pubmed: 29177409
BMJ. 2013 Feb 14;346:f657
pubmed: 23412440
Med Care. 2005 May;43(5):461-5
pubmed: 15838410
Yearb Med Inform. 2017 Aug;26(1):125-132
pubmed: 29063552
Proceedings (IEEE Int Conf Bioinformatics Biomed). 2017 Nov;2017:569-572
pubmed: 29302379
BMJ. 2002 Oct 26;325(7370):941
pubmed: 12399345
BMJ. 2005 Apr 2;330(7494):765
pubmed: 15767266
Int J Radiat Oncol Biol Phys. 2019 Feb 1;103(2):460-467
pubmed: 30300689
J AHIMA. 2013 Oct;84(10):42-7; quiz 48
pubmed: 24245088
JAMA. 1998 Oct 21;280(15):1339-46
pubmed: 9794315
J Am Med Inform Assoc. 2005 Jul-Aug;12(4):438-47
pubmed: 15802482
Implement Sci. 2011 Aug 03;6:90
pubmed: 21824384
Nat Med. 2019 Jan;25(1):44-56
pubmed: 30617339
Med Phys. 2017 Sep;44(9):4415-4425
pubmed: 28419482
Phys Med. 2018 Dec;56:90-93
pubmed: 30449653
Nat Med. 2019 Jan;25(1):24-29
pubmed: 30617335
J Am Med Inform Assoc. 2011 May 1;18(3):232-42
pubmed: 21415065
J Am Med Inform Assoc. 2017 May 1;24(3):669-676
pubmed: 28049635
Appl Clin Inform. 2017 Sep 06;8(3):910-923
pubmed: 28880046
AJR Am J Roentgenol. 2014 Nov;203(5):945-51
pubmed: 25341131
Artif Intell Med. 2018 Nov;92:24-33
pubmed: 26706047
Radiother Oncol. 2017 Dec;125(3):392-397
pubmed: 29162279
Implement Sci. 2017 Sep 15;12(1):113
pubmed: 28915822
AMIA Jt Summits Transl Sci Proc. 2016 Jul 20;2016:240-9
pubmed: 27570678
J Am Med Inform Assoc. 2018 May 1;25(5):496-506
pubmed: 29045651
Int J Clin Monit Comput. 1993 Nov;10(4):215-24
pubmed: 8270835