Affiliation:
1. School of Public Health, College of Health Sciences, Addis Ababa University, Addis Ababa
2. Adama Hospital Medical College
Abstract
Abstract
Objective
To assess the methodological issues in prediction models developed using electronic medical records (EMR), and their early-stage clinical impact on the HIV care continuum.
Methods
A systematic search of entries in PubMed and Google Scholar was conducted between January 1, 2010, and January 17, 2022, to identify studies developing and deploying EMR-based prediction models. We used the CHARMS (Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies), PROBAST (Prediction Model Risk of Bias Assessment Tool), and TRIPOD (Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis) statement to assess the methodological issues. In addition, we consulted reporting guidelines for early-stage clinical evaluation of decision support systems to assess the clinical impact of the models.
Results
The systematic search yielded 35 eligible articles: 24 (68.6%) aimed at model development and 11 (31.4%) for model deployment. The majority of these studies predicted an individual's risk of carrying HIV (n = 12/35, 34.3%), risk of interrupting HIV care (n = 9/35), and predicted the risk of virological failure (n = 7/35). The methodological assessment for those 24 studies found that they were rated as high risk (n = 6/24), some concerns (n = 14/24), and a low risk of bias (n = 4/24). Several studies didn't report the number of events (n = 14/24), missing data management (n = 12/24), inadequate reporting of statistical performance (n = 18/24), and lack of external validation (n = 21/24) in their model development processes. The early-stage clinical impact assessment for those 9/11 deployed models showed improved care outcomes, such as HIV screening, engagement in care, and viral load suppression.
Conclusions
EMR-based prediction models have been developed, and some are practically deployed as clinical decision support tools in the HIV care continuum. Overall, while early-stage clinical impact is observed with those deployed models, it is important to address methodological concerns and assess their potential clinical impact before widespread implementation.
Systematic review registration
PROSPERO CRD42023454765.
Publisher
Research Square Platform LLC
Reference69 articles.
1. Centers for Disease Control and Prevention (CDC). Understanding the HIV Care Continuum, [Internet]. 2022. Available from: https://www.cdc.gov/hiv/pdf/library/factsheets/cdc-hiv-care-continuum.pdf
2. United Nations Programme on HIV/AIDS (UNAIDS). Global HIV & AIDS statistics — Fact sheet [Internet]. 2023. Available from: https://www.unaids.org/en/resources/fact-sheet
3. Achieving the 95 95 95 targets for all: A pathway to ending AIDS;Frescura L;PLoS ONE,2022
4. Developing a Data-Driven Approach in Order to Improve the Safety and Quality of Patient Care;Cascini F;Front Public Health,2021
5. Predicting High-risk and High-cost Patients for Proactive Intervention;Gao J;Med Care,2022