Development of a Human Immunodeficiency Virus Risk Prediction Model Using Electronic Health Record Data From an Academic Health System in the Southern United States
Clinical Infectious Diseases · 2023
DOI: 10.1093/cid/ciac775 ↗Kurz gefasst
Fachartikel in der Zeitschrift Clinical Infectious Diseases, 2023. Verfasst von Charles M Burns und 9 weiteren Autor:innen. Beteiligte Einrichtung: Division of Infectious Diseases, Duke University Medical Center, Durham, North Carolina, USA. Hauptthemen laut MEDLINE: Pre-Exposure Prophylaxis, HIV Infections. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NHLBI NIH HHS, NIAID NIH HHS, NIH HHS.
Abstract (Originalsprache)
Background
Human immunodeficiency virus (HIV) pre-exposure prophylaxis (PrEP) is underutilized in the southern United States. Rapid identification of individuals vulnerable to diagnosis of HIV using electronic health record (EHR)-based tools may augment PrEP uptake in the region.
Methods
Using machine learning, we developed EHR-based models to predict incident HIV diagnosis as a surrogate for PrEP candidacy. We included patients from a southern medical system with encounters between October 2014 and August 2016, training the model to predict incident HIV diagnosis between September 2016 and August 2018. We obtained 74 EHR variables as potential predictors. We compared Extreme Gradient Boosting (XGBoost) versus least absolute shrinkage selection operator (LASSO) logistic regression models, and assessed performance, overall and among women, using area under the receiver operating characteristic curve (AUROC) and area under precision recall curve (AUPRC).
Results
Of 998 787 eligible patients, 162 had an incident HIV diagnosis, of whom 49 were women. The XGBoost model outperformed the LASSO model for the total cohort, achieving an AUROC of 0.89 and AUPRC of 0.01. The female-only cohort XGBoost model resulted in an AUROC of 0.78 and AUPRC of 0.00025. The most predictive variables for the overall cohort were race, sex, and male partner. The strongest positive predictors for the female-only cohort were history of pelvic inflammatory disease, drug use, and tobacco use.
Conclusions
Our machine-learning models were able to effectively predict incident HIV diagnoses including among women. This study establishes feasibility of using these models to identify persons most suitable for PrEP in the South.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Division of Infectious Diseases, Duke University Medical Center, Durham, North Carolina, USA.
- School of Medicine, Duke University, Durham, North Carolina, USA.
- Duke Institute for Health Innovation, Durham, North Carolina, USA.
- Division of Infectious Disease, Beth Israel Deaconess Medical Center, Boston, Massachusetts, USA.
- Department of Population Medicine, Harvard Medical School, Boston, Massachusetts, USA.
- Division of Infectious Diseases, Louisiana State University Health Sciences Center, New Orleans, Louisiana, USA.
ORCID-Profile: Charles M Burns, Mark Sendak
Förderung
- NHLBI NIH HHS
- NIAID NIH HHS
- NIH HHS
- NIMH NIH HHS
- Duke University Center for AIDS Research
- National Institutes of Health
- National Institute of Allergy and Infectious Diseases
- National Institute of Mental Health
Zitieren
APA
Burns, C. M., Pung, L., Witt, D., Gao, M., Sendak, M., Balu, S., Krakower, D., Marcus, J. L., Okeke, N. L., & Clement, M. E. (2023). Development of a Human Immunodeficiency Virus Risk Prediction Model Using Electronic Health Record Data From an Academic Health System in the Southern United States. Clinical Infectious Diseases. https://doi.org/10.1093/cid/ciac775
Vancouver
Burns CM, Pung L, Witt D, Gao M, Sendak M, Balu S, et al. Development of a Human Immunodeficiency Virus Risk Prediction Model Using Electronic Health Record Data From an Academic Health System in the Southern United States. Clinical Infectious Diseases. 2023. doi:10.1093/cid/ciac775
BibTeX
@article{Burns2023,
author = {Burns, Charles M and Pung, Leland and Witt, Daniel and Gao, Michael and Sendak, Mark and Balu, Suresh and Krakower, Douglas and Marcus, Julia L and Okeke, Nwora Lance and Clement, Meredith E},
title = {Development of a Human Immunodeficiency Virus Risk Prediction Model Using Electronic Health Record Data From an Academic Health System in the Southern United States},
journal = {Clinical Infectious Diseases},
year = {2023},
doi = {10.1093/cid/ciac775}
}
EUVIMED