Javier Neyra
University of Alabama at Birmingham, AL·Medicine & Clinical Research
Acute kidney injury (AKI) is a sudden loss of kidney function. It strikes up to half of critically ill patients in intensive care units (ICUs) and has few proven treatments.
- Fields
Medicine & Clinical Research
Computer Science
Biomedical Engineering
- Topics
acute kidney injury
continuous renal replacement therapy
dialysis
- Grants
- 3 known grants, through Jun 2028
What they work on
- 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.
- Use the Feasible Solution Algorithm, a method for finding influential combinations of patient features, to identify subgroups of CRRT patients with different risks of dialysis-free survival, to help interpret the models and test their clinical usefulness.
- Provide AKI investigators with curated clinical data, harmonized real-world electronic health record data and stored biospecimens, and build a platform that links patient samples to their health records.
- Develop microfluidic methods for high-resolution mapping of small molecules and peptides in kidney tissue, and kidney-specific PET and MRI imaging to follow injury and treatment response over time in animal models of AKI.
- Build tools for harmonizing EHR data across institutions and a federated multi-task learning platform that evaluates AI-based tools across sites without sharing raw patient data.
More about the research
Doctors also lack reliable ways to predict which patients will survive or recover kidney function. The research described here pairs large-scale patient data and artificial intelligence (AI) with lab-based tools for studying the injured kidney. The goals are to sort patients into meaningful subgroups, predict outcomes, and give other AKI researchers shared data and technologies. The work spans one clinical prediction project and two shared-resource cores within the UAB-UCSD O'Brien Kidney Consortium.
Why it matters
Critically ill patients with acute kidney injury who need continuous dialysis die at high rates, yet doctors have no accurate way to predict who will survive or regain kidney function. Validated AI prediction models could feed into clinical decision-support tools that guide how dialysis is delivered, what the goals of ICU care should be, and what follow-up patients need after discharge. Identifying patient subgroups could also point to more personalized treatments that can be tested in trials. The shared data, biospecimen and imaging resources may speed AKI research more broadly.
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.
Andrew Bishara
University of California-San Francisco, CA·Medicine & Clinical Research·Early-career
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.
Romain Pirracchio
University of California-San Francisco, CA·Medicine & Clinical Research
Train machine learning models on electronic health record data from three health systems to estimate each patient's individual treatment effect from antibiotics, fluid resuscitation and vasopressors in suspected community-onset lung sepsis.
The school
University of Alabama at Birmingham: 45 labs on PI Pages, $866M a year on research, 166 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.