Andrew Bishara
University of California-San Francisco, CA·Medicine & Clinical Research·Early-career
Acute kidney injury, a sudden drop in kidney function, strikes 18–47% of patients after surgery. It is linked to chronic kidney disease, major heart problems, higher costs and death.
- Fields
Medicine & Clinical Research
Computer Science
Biomedical Engineering
- Topics
acute kidney injury
perioperative medicine
surgery outcomes
- Grants
- 1 known grant, through Jul 2028
What they work on
- Implement machine learning models that predict perioperative acute kidney injury in real time during surgery and alert clinicians while kidney-protective treatments can still be given.
- Use the PI's ML visualization technology to improve how clinicians interact with model predictions and recommendations, and to monitor models for sustained accuracy and reliability.
- Test whether the models identify the surgical patients who would benefit most from timely kidney-protective interventions.
- Update the prediction models and use them to describe the landscape of perioperative AKI risk, to inform the design of new treatments.
More about the research
Treatments that protect the kidneys during surgery already exist and work in randomized trials, but they are often not given, because doctors tend to underestimate a patient's risk. Computer models built with machine learning (ML), in which algorithms learn patterns from past patient data, can predict this injury better than clinicians. However, they have rarely been put to use in the operating room because of technical and practical barriers.
Why it matters
Many surgical patients develop kidney injury that might be prevented if clinicians recognized the risk in time. Real-time, interpretable risk alerts during surgery could help anesthesiologists and surgeons start proven kidney-protective treatments for high-risk patients. This could reduce chronic kidney disease, cardiovascular events, healthcare costs and deaths. Mapping the risk landscape may also guide the design of new AKI therapies.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Mei Liu
University of Florida, FL·Medicine & Clinical Research
Develop methods to build the best individualized cohort of similar past patients from EHR data, as the training set for a personalized AKI risk model for each new hospital patient.
Javier Neyra
University of Alabama at Birmingham, AL·Medicine & Clinical Research
Develop and validate deep learning models that predict survival without ongoing dialysis at clinically actionable time points for ICU patients on continuous renal replacement therapy, using EHR and CRRT machine time-series data from 9 institutions.
Matthieu Legrand
University of California-San Francisco, CA·Medicine & Clinical Research
Test whether norepinephrine, which constricts vessels and strengthens the heartbeat, prevents postoperative acute kidney injury better than phenylephrine, a pure vasoconstrictor, in adults undergoing major non-cardiac surgery under general anesthesia.
The school
University of California-San Francisco: 89 labs on PI Pages, $2.1B a year on research, 164 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.