Personalized antibiograms for machine learning driven antibiotic selection.
Antibiotics
Bacterial infection
Disease prevention
Epidemiology
Journal
Communications medicine
ISSN: 2730-664X
Titre abrégé: Commun Med (Lond)
Pays: England
ID NLM: 9918250414506676
Informations de publication
Date de publication:
2022
2022
Historique:
received:
01
08
2021
accepted:
25
02
2022
entrez:
23
5
2022
pubmed:
24
5
2022
medline:
24
5
2022
Statut:
epublish
Résumé
The Centers for Disease Control and Prevention identify antibiotic prescribing stewardship as the most important action to combat increasing antibiotic resistance. Clinicians balance broad empiric antibiotic coverage vs. precision coverage targeting only the most likely pathogens. We investigate the utility of machine learning-based clinical decision support for antibiotic prescribing stewardship. In this retrospective multi-site study, we developed machine learning models that predict antibiotic susceptibility patterns (personalized antibiograms) using electronic health record data of 8342 infections from Stanford emergency departments and 15,806 uncomplicated urinary tract infections from Massachusetts General Hospital and Brigham & Women's Hospital in Boston. We assessed the trade-off between broad-spectrum and precise antibiotic prescribing using linear programming. We find in Stanford data that personalized antibiograms reallocate clinician antibiotic selections with a coverage rate (fraction of infections covered by treatment) of 85.9%; similar to clinician performance (84.3% Precision empiric antibiotic prescribing with personalized antibiograms could improve patient safety and antibiotic stewardship by reducing unnecessary use of broad-spectrum antibiotics that breed a growing tide of resistant organisms.
Sections du résumé
Background
UNASSIGNED
The Centers for Disease Control and Prevention identify antibiotic prescribing stewardship as the most important action to combat increasing antibiotic resistance. Clinicians balance broad empiric antibiotic coverage vs. precision coverage targeting only the most likely pathogens. We investigate the utility of machine learning-based clinical decision support for antibiotic prescribing stewardship.
Methods
UNASSIGNED
In this retrospective multi-site study, we developed machine learning models that predict antibiotic susceptibility patterns (personalized antibiograms) using electronic health record data of 8342 infections from Stanford emergency departments and 15,806 uncomplicated urinary tract infections from Massachusetts General Hospital and Brigham & Women's Hospital in Boston. We assessed the trade-off between broad-spectrum and precise antibiotic prescribing using linear programming.
Results
UNASSIGNED
We find in Stanford data that personalized antibiograms reallocate clinician antibiotic selections with a coverage rate (fraction of infections covered by treatment) of 85.9%; similar to clinician performance (84.3%
Conclusions
UNASSIGNED
Precision empiric antibiotic prescribing with personalized antibiograms could improve patient safety and antibiotic stewardship by reducing unnecessary use of broad-spectrum antibiotics that breed a growing tide of resistant organisms.
Identifiants
pubmed: 35603264
doi: 10.1038/s43856-022-00094-8
pii: 94
pmc: PMC9053259
doi:
Types de publication
Journal Article
Langues
eng
Pagination
38Subventions
Organisme : NIAID NIH HHS
ID : R25 AI147369
Pays : United States
Informations de copyright
© The Author(s) 2022.
Déclaration de conflit d'intérêts
Competing interestsThe authors declare the following competing interests. C.K.C. receives consultation payment from Fountain Therapeutics, Inc. C.K.C. was an intern at Verily Life Sciences while drafting the paper. J.H.C. co-founded of Reaction Explorer LLC that develops and licenses organic chemistry education software and receives consultation payment from the National Institute of Drug Abuse Clinical Trials Network, Tuolc Inc., Roche Inc., and Younker Hyde MacFarlane PLLC. M.N. receives consultation payment from Vida Health. All other authors declare no competing interests.
Références
J Antimicrob Chemother. 2020 Sep 1;75(9):2677-2680
pubmed: 32542387
Proc Annu Symp Comput Appl Med Care. 1995;:651-5
pubmed: 8563367
J Clin Microbiol. 2018 Nov 27;56(12):
pubmed: 30135230
AMIA Jt Summits Transl Sci Proc. 2020 May 30;2020:108-115
pubmed: 32477629
Future Healthc J. 2019 Jun;6(2):94-98
pubmed: 31363513
Yonsei Med J. 2018 Jan;59(1):4-12
pubmed: 29214770
Int J Qual Health Care. 2011 Apr;23(2):142-50
pubmed: 21131383
J Clin Microbiol. 2018 Mar 26;56(4):
pubmed: 29367292
Chest. 2000 Jul;118(1):146-55
pubmed: 10893372
Clin Infect Dis. 2006 Jan 1;42 Suppl 1:S5-12
pubmed: 16323120
Antimicrob Agents Chemother. 2017 Jan 24;61(2):
pubmed: 27895019
Nat Med. 2019 Jul;25(7):1143-1152
pubmed: 31273328
Arch Intern Med. 2001 Aug 13-27;161(15):1897-902
pubmed: 11493132
JAMA. 2019 Oct 8;322(14):1351-1352
pubmed: 31393527
Lancet. 2004 Nov 20-26;364(9448):1865-71
pubmed: 15555666
Clin J Am Soc Nephrol. 2016 Dec 7;11(12):2132-2140
pubmed: 27895134
Antimicrob Agents Chemother. 2020 Jun 23;64(7):
pubmed: 32312778
Sci Transl Med. 2020 Nov 4;12(568):
pubmed: 33148625
Arch Surg. 2006 Nov;141(11):1109-13; discussion 1114
pubmed: 17116804
Proceedings VLDB Endowment. 2018 Sep;11(13):2263-2276
pubmed: 31179156
Can Vet J. 1997 Jul;38(7):429-37
pubmed: 9220132
Clin Infect Dis. 2008 Jul 1;47(1):117-22
pubmed: 18491969
Circulation. 2000 Jun 13;101(23):E215-20
pubmed: 10851218
Indian J Med Microbiol. 2010 Oct-Dec;28(4):277-80
pubmed: 20966554
Clin Infect Dis. 2018 Jun 18;67(1):134-136
pubmed: 29373664
J Antimicrob Chemother. 2011 Sep;66(9):2168-74
pubmed: 21676904
J Hosp Med. 2012 Feb;7(2):85-90
pubmed: 22095750
Infect Control Hosp Epidemiol. 2017 May;38(5):534-541
pubmed: 28260538
BMC Med Inform Decis Mak. 2017 Dec 08;17(1):168
pubmed: 29216923
J Biomed Inform. 2015 Dec;58:168-174
pubmed: 26483171
J Surg Oncol. 2012 Apr 1;105(5):502-10
pubmed: 22441903
Stat Methods Med Res. 2019 Jan;28(1):309-320
pubmed: 28812439
Clin Infect Dis. 2007 Dec 15;45(12):1543-9
pubmed: 18190314
J Antimicrob Chemother. 2019 Apr 1;74(4):1108-1115
pubmed: 30590545
Lancet Infect Dis. 2015 Dec;15(12):1429-37
pubmed: 26482597
J Antimicrob Chemother. 2008 Sep;62(3):608-16
pubmed: 18550680
Int J Antimicrob Agents. 2010 Apr;35(4):375-81
pubmed: 20122817
Am J Med. 2003 Nov;115(7):529-35
pubmed: 14599631
NPJ Digit Med. 2018 May 8;1:18
pubmed: 31304302
Pediatr Infect Dis J. 2002 Oct;21(10):935-40
pubmed: 12394816
Rev Infect Dis. 1983 Mar-Apr;5(2):279-313
pubmed: 6405475
Comput Biomed Res. 1975 Aug;8(4):303-20
pubmed: 1157471
JAMA Surg. 2013 Jul;148(7):649-57
pubmed: 23552769