Mei Liu

Mei Liu,

Associate Professor

Department: MD-HOBI-GENERAL
Business Phone: (352) 627-9143
Business Email: mei.liu@ufl.edu

About Mei Liu

Dr. Liu is an Associate Professor with Tenure in the College of Medicine, Department of Health Outcomes & Biomedical Informatics (HOBI) at the University of Florida. She also serves as the Director of Predictive Analytics and Associate Director of Graduate Education in HOBI.

Dr. Liu received her PhD in Computer Science from the University of Kansas and completed her National Library of Medicine (NLM) postdoctoral fellowship in biomedical informatics at Vanderbilt University. Her research interest in bioinformatics began during her doctoral study with the development of novel machine learning algorithms to improve prediction of protein-protein interactions and protein functions. Her research interest expanded to medical informatics while at Vanderbilt with the development of machine learning models to detect and predict adverse drug reactions using electronic health records (EHRs). Her other research interests include the secondary use of EHR data to model patient risks and disease trajectory and discover underlying risk factors.

Dr. Liu’s current research focus is on the development of novel machine learning and artificial intelligence techniques to accelerate risk factor identification and discovery in medicine using EHR data. Clinical applications of her research include adverse drug reaction, diabetic kidney disease, acute kidney injury (AKI), and sepsis predictions. She is the Principal Investigator for a NIDDK R01 project and an NSF Smart and Connected Health project that focus on the identification of personalized risk factors of AKI with personalized modeling and causal learning and building a secure and robust AKI prediction model with privacy-preserving federated transfer learning using EHR data from 11 PCORnet sites across 9 states.

Additional Positions:
Director of Predictive Analytics
2022 – Current · Department of Health Outcomes and Biomedical Informatics
Associate Director of Graduate Education
2022 – Current · Department of Health Outcomes and Biomedical Informatics

Accomplishments

Distinguished Paper
2017 · American Medical Informatics Association (AMIA) Annual Symposium
Finalist for the AMIA Clinical Research Informatics Award
2017 · American Medical Informatics Association (AMIA) Joint Summit on Translational Science
Distinguished Paper
2013 · American Medical Informatics Association (AMIA) Annual Symposium
Distinguished Paper
2012 · American Medical Informatics Association (AMIA) Joint Summit on Translational Science

Teaching Profile

Courses Taught
2023-2024
GMS7887 Health Outcomes & Policy PhD Research Seminar
2024
GMS6805 Information Modeling in Biomedicine

Research Profile

Open Researcher and Contributor ID (ORCID)

0000-0002-8036-2110

Areas of Interest
  • Artificial Intelligence
  • Biomedical informatics
  • Machine Learning
  • machine learning for predictive analytics

Publications

2023
An open natural language processing (NLP) framework for EHR-based clinical research: a case demonstration using the National COVID Cohort Collaborative (N3C)
Journal of the American Medical Informatics Association. 30(12):2036-2040 [DOI] 10.1093/jamia/ocad134. [PMID] 37555837.
2023
Contrastive Learning of Temporal Distinctiveness for Survival Analysis in Electronic Health Records
Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. 29:1897-1906 [DOI] 10.1145/3583780.3614824.
2023
Digital health and acute kidney injury: consensus report of the 27th Acute Disease Quality Initiative workgroup.
Nature reviews. Nephrology. 19(12):807-818 [DOI] 10.1038/s41581-023-00744-7. [PMID] 37580570.
2023
Leveraging Natural Language Processing to Extract Features of Colorectal Polyps From Pathology Reports for Epidemiologic Study
JCO Clinical Cancer Informatics. (7) [DOI] 10.1200/cci.22.00131.
2023
Long-term kidney function recovery and mortality after COVID-19-associated acute kidney injury: An international multi-centre observational cohort study
eClinicalMedicine. 55 [DOI] 10.1016/j.eclinm.2022.101724.
2023
Protein–ligand binding affinity prediction with edge awareness and supervised attention
iScience. 26(1) [DOI] 10.1016/j.isci.2022.105892. [PMID] 36691617.
2022
A hybrid adaptive approach for instance transfer learning with dynamic and imbalanced data
International Journal of Intelligent Systems. [DOI] 10.1002/int.23055.
2022
A Transfer Learning Approach to Correct the Temporal Performance Drift of Clinical Prediction Models: Retrospective Cohort Study
JMIR Medical Informatics. 10(11) [DOI] 10.2196/38053. [PMID] 36350705.
2022
Antibiotic Timing and Progression to Septic Shock Among Patients in the ED With Suspected Infection.
Chest. 161(1):112-120 [DOI] 10.1016/j.chest.2021.06.029. [PMID] 34186038.
2022
Characterizing the temporal changes in association between modifiable risk factors and acute kidney injury with multi-view analysis.
International journal of medical informatics. 163 [DOI] 10.1016/j.ijmedinf.2022.104785. [PMID] 35504130.
2022
Development and Validation of a Personalized Model With Transfer Learning for Acute Kidney Injury Risk Estimation Using Electronic Health Records.
JAMA network open. 5(7) [DOI] 10.1001/jamanetworkopen.2022.19776. [PMID] 35796212.
2022
Enhancing PCORnet Clinical Research Network data completeness by integrating multistate insurance claims with electronic health records in a cloud environment aligned with CMS security and privacy requirements
Journal of the American Medical Informatics Association. 29(4):660-670 [DOI] 10.1093/jamia/ocab269. [PMID] 34897506.
2022
Temporal dynamics of clinical risk predictors for hospital-acquired acute kidney injury under different forecast time windows
Knowledge-Based Systems. 245 [DOI] 10.1016/j.knosys.2022.108655.
2021
COVID-19 SignSym: a fast adaptation of a general clinical NLP tool to identify and normalize COVID-19 signs and symptoms to OMOP common data model
Journal of the American Medical Informatics Association. 28(6):1275-1283 [DOI] 10.1093/jamia/ocab015. [PMID] 33674830.
2020
Changing relative risk of clinical factors for hospital-acquired acute kidney injury across age groups: a retrospective cohort study
BMC Nephrology. 21(1) [DOI] 10.1186/s12882-020-01980-w. [PMID] 32741377.
2020
COVID-19 SignSym: A fast adaptation of general clinical NLP tools to identify and normalize COVID-19 signs and symptoms to OMOP common data model.
ArXiv. [PMID] 32908948.
2020
Cross-site transportability of an explainable artificial intelligence model for acute kidney injury prediction.
Nature communications. 11(1) [DOI] 10.1038/s41467-020-19551-w. [PMID] 33168827.
2020
Longitudinal Risk Prediction of Chronic Kidney Disease in Diabetic Patients using Temporal-Enhanced Gradient Boosting Machine: Retrospective Cohort Study
JMIR Medical Informatics. 8(1) [DOI] 10.2196/15510. [PMID] 32012067.
2019
Robust clinical marker identification for diabetic kidney disease with ensemble feature selection.
Journal of the American Medical Informatics Association : JAMIA. 26(3):242-253 [DOI] 10.1093/jamia/ocy165. [PMID] 30602020.

Grants

Apr 2024 ACTIVE
Personalized Machine Learning for Acute Kidney Injury Prediction and Prognosis
Role: Principal Investigator
Funding: NATL INST OF HLTH NIDDK
Apr 2024 ACTIVE
All of Us Center for Linkage and Acquisition of Data (CLAD)
Role: Co-Investigator
Funding: UNIV OF NORTH CAROLINA CHAPEL HILL via NATL INST OF HLTH
Dec 2023 ACTIVE
Identifying Personalized Risk of Acute Kidney Injury with Machine Learning
Role: Principal Investigator
Funding: NATL INST OF HLTH NIDDK
Oct 2023 ACTIVE
SCH: INT: Collaborative Research: Privacy-Preserving Federated Transfer Learning for Early Acute Kidney Injury Risk Prediction
Role: Principal Investigator
Funding: NATL SCIENCE FOU
Jan 2022 ACTIVE
OneFlorida+ Phase 3 Clinical Research Network
Role: Principal Investigator
Funding: PATIENT-CENTERED OUTCOMES RES INST
Nov 2021 ACTIVE
RESEARCHING COVID TO ENHANCE RECOVERY (RECOVER) INITIATIVE
Role: Principal Investigator
Funding: CORNELL UNIV via NATL INST OF HLTH NHLBI
Jul 2021 – Jun 2024
Comparative Effectiveness Research for Neuroendocrine Tumors (CER-NET)
Role: Principal Investigator
Funding: UNIV OF IOWA via PATIENT-CENTERED OUTCOMES RES INST

Education

Ph.D. in Computer Science
2009 · University of Kansas
M.S. in Computer Science
2004 · University of Kansas
B.S. in Computer Science
2002 · University of Kansas

Contact Details

Phones:
Business:
(352) 627-9143
Emails:
Business:
mei.liu@ufl.edu
Addresses:
Business Mailing:
PO Box 100147
Gainesville FL 32610
Business Street:
1889 MUSEUM RD STE 7000 FL 7
GAINESVILLE FL 32611