Interpretable, Fair and Reproducible Risk Surveillance for Kidney Health in COVID-19 patients using Artificial Intelligence and Novel Computable Phenotypes
Faculty Mentor’s Name: Dr. Tezcan Ozrazgat Baslanti
Email: tezcan.ozrazgat@medicine.ufl.edu
Phone Number: (352) 273-6668
Project Category: Clinical
International Component or Travel: No
Research Project Description:
There is no systematic assessment of different trajectories of AKI and risk factors for developing persistent kidney disease and renal non-recovery in patients with COVID-19. Our central hypothesis is that, by applying computable kidney health phenotype to data from the multi-center OneFlorida network for patients with COVID-19, we can identify unique characteristics of patients with more malignant phenotypes of persistent kidney injury and renal non-recovery among COVID-19 infection-associated AKI. We will develop deep learning models predicting which patients are at risk of developing these trajectories. Our rationale is that such understanding may facilitate development of treatment protocols that could aid clinicians in medical decision making and improve outcomes for patients with COVID-19. The role of the medical student will be to help prepare results and do literature review and write introduction and discussion parts of the manuscript.
Integration of Intraoperative Data with Preoperative Data for Improved Postoperative Sepsis Risk Prediction
Faculty Mentor’s Name: Dr. Azra Bihorac
Email: abihorac@medicine.ufl.edu
Phone Number: (352) 273-9009
Project Category: Clinical
International Component or Travel: No
Research Project Description:
The project aims at developing prediction models to help study patient risk scores for postoperative sepsis complication given preoperative medical history and intraoperative EMR responses. The role of the medical student will be to review electronic health records to adjudicate sepsis phenotyping as well as help prepare results and do literature review and write introduction and discussion parts of the manuscript.
Clinical Phenotypes for AKI Using Clustering of Time Series
Faculty Mentor’s Name: Dr. Tezcan Ozrazgat Baslanti
Email: tezcan.ozrazgat@medicine.ufl.edu
Phone Number: (352) 273-6668
Project Category: Clinical
International Component or Travel: No
Research Project Description:
The purpose of this study is to use clustering to predict pathophysiologic signatures and clinical trajectory during the early stages of acute kidney injury. We hypothesized that clustering analysis of electronic health record data would reveal distinct, predictable patient phenotypes with unique pathophysiological signatures and clinical trajectories. The role of the medical student will be to help prepare results and do literature review and write introduction and discussion parts of the manuscript.
ALPHA-Artificial intelligence Augmented Acute Illness Phenotypes
Faculty Mentor’s Name: Dr. Azra Bihorac
Email:abihorac@medicine.ufl.edu
Phone Number: (352) 273-9009
Project Category: Clinical
International Component or Travel: No
Research Project Description:
Patients with acute illness in intensive care unit (ICU) have sudden dysfunction of multiple organ systems presenting as a heterogenous syndrome that encompasses a multidimensional array of clinical, socioeconomic and biological features. Different combinations of these features may naturally cluster into previously undescribed subsets or “clinical phenotypes” that may have different clinical trajectories. The digital data captured during routine ICU care can be utilized for understanding and classifying acute illness using unsupervised clustering approaches but the complexity and granularity of ICU data poses a problem for conventional clustering. We propose to utilize deep learning networks to learn non-linear mappings and transform ICU data into clustering-friendly representation.