Jonathan Chen
Stanford University, CA·Medicine & Clinical Research
Doctors usually choose an antibiotic before lab tests confirm which drug will work. Each such guess can either fuel antibiotic resistance, by using a broad-spectrum drug when a narrower one would do, or leave a patient undertreated.
- Fields
Medicine & Clinical Research
Computer Science
Public Health & Epidemiology
- Topics
antibiotic resistance
antimicrobial resistance
antibiotic stewardship
- Grants
- 1 known grant, through Jun 2028
What they work on
- Harmonize and share electronic health record data on suspected urinary tract infections across Stanford, UT Southwestern and Harvard to support multi-site model building.
- Develop and validate Personalized Antibiogram machine learning models that predict a patient's microbial culture and antibiotic susceptibility results before tests return.
- Prospectively validate the antibiogram models by integrating them into the electronic health record in real time, instead of relying only on retrospective evaluation.
- Develop automated electronic phenotyping methods to identify UTIs in health records, along with a validated measure of how appropriate and desirable an antibiotic choice was.
More about the research
Resistant infections already cause more than 2.8 million illnesses a year in the US. Urinary tract infections (UTIs) are the most common bacterial infection and account for 25–50% of antibiotic prescriptions. More than 20% of UTI bacteria already resist common antibiotics.
Why it matters
Patients with urinary tract infections could receive an effective antibiotic sooner, with fewer unnecessary broad-spectrum prescriptions. Hospitals and stewardship programs would gain tools to measure whether prescribing is appropriate. Better prescribing could help slow the spread of resistant bacteria and reduce the up to $42 billion a year in avoidable US costs tied to antibiotic misuse.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Bradford Becken
University of Nebraska Medical Center, NE·Medicine & Clinical Research
Assess the translation potential of an automated dynamic antibiogram through experiential learning and first-hand interviews across the healthcare industry ecosystem.
Eva Raphael
University of California-San Francisco, CA·Public Health & Epidemiology·Early-career
Identify demographic and neighborhood-level risk factors for community-onset UTIs caused by ESBL-producing E. coli in women, using causal inference methods, compared with other resistant and with antibiotic-susceptible UTIs.
Jennie Kwon
Washington University in St Louis, MO·Medicine & Clinical Research
Identify clinical risk factors for community-associated antibiotic-resistant infections, using a database of patients with urinary tract and bloodstream infections from community and healthcare settings.
The school
Stanford University: 87 labs on PI Pages, $1.6B a year on research, 739 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.