A decision algorithm to promote outpatient antimicrobial stewardship for uncomplicated urinary tract infection

被引:50
作者
Kanjilal, Sanjat [1 ,2 ,3 ]
Oberst, Michael [4 ]
Boominathan, Sooraj [4 ]
Zhou, Helen [5 ]
Hooper, David C. [6 ]
Sontag, David [4 ]
机构
[1] Harvard Med Sch, Dept Populat Med, Boston, MA 02215 USA
[2] Harvard Pilgrim Healthcare Inst, Boston, MA 02215 USA
[3] Brigham & Womens Hosp, Div Infect Dis, Boston, MA 02115 USA
[4] MIT, Inst Med Engn & Sci, 77 Massachusetts Ave, Cambridge, MA 02139 USA
[5] Carnegie Mellon Univ, Machine Learning Dept, Pittsburgh, PA 15213 USA
[6] Massachusetts Gen Hosp, Div Infect Dis, Boston, MA 02114 USA
基金
美国国家科学基金会;
关键词
ANTIBIOTIC-RESISTANCE; FLUOROQUINOLONE USE; CARE; GUIDELINES; DISEASES; AMERICA; SOCIETY; RISK;
D O I
10.1126/scitranslmed.aay5067
中图分类号
Q2 [细胞生物学];
学科分类号
071009 ; 090102 ;
摘要
Antibiotic resistance is a major cause of treatment failure and leads to increased use of broad-spectrum agents, which begets further resistance. This vicious cycle is epitomized by uncomplicated urinary tract infection (UTI), which affects one in two women during their life and is associated with increasing antibiotic resistance and high rates of prescription for broad-spectrum second-line agents. To address this, we developed machine learning models to predict antibiotic susceptibility using electronic health record data and built a decision algorithm for recommending the narrowest possible antibiotic to which a specimen is susceptible. When applied to a test cohort of 3629 patients presenting between 2014 and 2016, the algorithm achieved a 67% reduction in the use of second-line antibiotics relative to clinicians. At the same time, it reduced inappropriate antibiotic therapy, defined as the choice of a treatment to which a specimen is resistant, by 18% relative to clinicians. For specimens where clinicians chose a second-line drug but the algorithm chose a first-line drug, 92% (1066 of 1157) of decisions ended up being susceptible to the first-line drug. When clinicians chose an inappropriate first-line drug, the algorithm chose an appropriate first-line drug 47% (183 of 392) of the time. Our machine learning decision algorithm provides antibiotic stewardship for a common infectious syndrome by maximizing reductions in broad-spectrum antibiotic use while maintaining optimal treatment outcomes. Further work is necessary to improve generalizability by training models in more diverse populations.
引用
收藏
页数:10
相关论文
共 50 条
  • [21] The Appropriateness of Empirical Antimicrobial Treatment of Uncomplicated Urinary Tract Infection in Adult Female Patients in Jazan Region, Saudi Arabia
    Darraj, Majid A.
    CLINICS AND PRACTICE, 2023, 13 (04) : 743 - 752
  • [22] Use of Machine Learning to Assess the Management of Uncomplicated Urinary Tract Infection
    Jones, Noah
    Shih, Ming-Chieh
    Healey, Elizabeth
    Zhai, Chen Wen
    Advani, Sonali
    Smith-McLallen, Aaron
    Sontag, David
    Kanjilal, Sanjat
    JAMA NETWORK OPEN, 2025, 8 (01)
  • [23] Antimicrobial resistance patterns of uncomplicated urinary tract infection among inpatients at the Mousavi education & treatment center, Zanjan, Iran
    Atigh, Mohammadreza Afkari
    Islambulchilar, Mina
    Pourmirza, Nadia
    REVIEWS AND RESEARCH IN MEDICAL MICROBIOLOGY, 2024, 35 (02): : 97 - 106
  • [24] Reducing risk of Clostridium difficile infection and overall use of antibiotic in the outpatient treatment of urinary tract infection
    Ge, Ivy Y.
    Fevrier, Helene B.
    Conell, Carol
    Kheraj, Malika N.
    Flint, Alexander C.
    Smith, Darvin S.
    Herrinton, Lisa J.
    THERAPEUTIC ADVANCES IN UROLOGY, 2018, 10 (10) : 283 - 293
  • [25] Determinants of Quinolone versus Trimethoprim-Sulfamethoxazole Use for Outpatient Urinary Tract Infection
    Stuck, Anna K.
    Taeuber, Martin G.
    Schabel, Maria
    Lehmann, Thomas
    Suter, Herbert
    Muehlemann, Kathrin
    ANTIMICROBIAL AGENTS AND CHEMOTHERAPY, 2012, 56 (03) : 1359 - 1363
  • [26] Latin American consensus on uncomplicated recurrent urinary tract infection-2018
    Haddad, Jorge Milhem
    Ubertazzi, Enrique
    Storme Cabrera, Oscar
    Medina, Martha
    Garcia, Jorge
    Rodriguez-Colorado, Silvia
    Toruno, Efrain
    Matsuoka, Priscila Katsumi
    Castillo-Pino, Edgardo
    INTERNATIONAL UROGYNECOLOGY JOURNAL, 2020, 31 (01) : 35 - 44
  • [27] Cranberry Extract for Symptoms of Acute, Uncomplicated Urinary Tract Infection: A Systematic Review
    Gbinigie, Oghenekome A.
    Spencer, Elizabeth A.
    Heneghan, Carl J.
    Lee, Joseph J.
    Butler, Christopher C.
    ANTIBIOTICS-BASEL, 2021, 10 (01): : 1 - 14
  • [28] In vitro Antimicrobial Susceptibility of Urinary Tract Infection Pathogens in Children
    Taner, Sevgin
    Aydemir, Sabire Sohret
    Ozgur, Su
    Aksoy, Ezgi
    Keskinoglu, Ahmet
    Tunger, Alper
    Kabasakal, Caner
    Bulut, Ipek Kaplan
    JOURNAL OF PEDIATRIC RESEARCH, 2023, 10 (03) : 210 - 215
  • [29] AI driven decision support reduces antibiotic mismatches and inappropriate use in outpatient urinary tract infections
    Ben David, Shirley Shapiro
    Romano, Roni
    Rahamim-Cohen, Daniella
    Azuri, Joseph
    Greenfeld, Shira
    Gedassi, Ben
    Lerner, Uri
    NPJ DIGITAL MEDICINE, 2025, 8 (01):
  • [30] Sex, drugs, bugs, and age: rational selection of empirical therapy for outpatient urinary tract infection in an era of extensive antimicrobial resistance
    Rocha, Jaime L.
    Tuon, Felipe Francisco
    Johnson, James R.
    BRAZILIAN JOURNAL OF INFECTIOUS DISEASES, 2012, 16 (02) : 115 - 121