Jacqueline Stocking
University of California-Davis, CA·Medicine & Clinical Research·Early-career
After planned surgery, some adults cannot breathe well enough on their own. They may stay on a ventilator for a long time or fail to get enough oxygen.
- Fields
Medicine & Clinical Research
Public Health & Epidemiology
Computer Science
- Topics
postoperative respiratory failure
elective surgery
mechanical ventilation
- Grants
- 1 known grant, through Jul 2028
What they work on
- Optimize and validate an automated, EHR-based model predicting postoperative respiratory failure, using surgical patient data from 2014 to 2021 and pre- and intra-operative risk factors.
- Identify distinct postoperative respiratory failure phenotypes from routine clinical and blood markers such as mean arterial pressure and creatinine, and test whether they predict failure within 48 hours.
- Develop and deploy a proof-of-concept PRF probability score and dashboard embedded in the electronic health record, tested in a pre-production environment.
- Test whether mapping hospital data into the OMOP Common Data Model loses information and lowers prediction accuracy compared with the native site-specific model.
More about the research
This complication, postoperative respiratory failure (PRF), affects up to 7.5% of patients. It is linked to about $53,000 in added hospital charges, nine extra days in the hospital and a 22% rise in in-hospital deaths. Because it may be preventable, spotting high-risk patients early matters.
Why it matters
Adults having elective surgery could benefit if clinicians can see their real-time risk of postoperative respiratory failure. Such a warning could allow earlier preventive or personalized treatment. A validated EHR-embedded score could help hospitals reduce a complication that adds days of hospitalization, tens of thousands of dollars in charges, and higher in-hospital mortality.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Michael Rosenberg
University of Colorado Denver/Anschutz Medical Campus, CO·Medicine & Clinical Research
Develop and test a cloud-based deep-learning model that predicts risk of drug-induced long QT syndrome from electronic health record data on hospitalized and outpatient patients, without requiring a prior electrocardiogram.
Shamim Nemati
University of California-San Diego, CA·Biomedical Engineering
Compare a large language model–supported differential diagnosis system against the binary sepsis model COMPOSER for accuracy, with expert clinician review of the diagnosis lists, using retrospective hospital data.
Li-Wei H Lehman
Massachusetts Institute of Technology, MA·Medicine & Clinical Research
Estimate what would happen under different treatment strategies for neuromuscular blockade and steroids in ARDS by emulating target trials in intensive care records, using g-methods that correct for the fact that sicker patients receive more aggressive care.
The school
University of California-Davis: 49 labs on PI Pages, $1.0B a year on research, 647 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.