Development of a predictive model for identifying women vulnerable to HIV in Chicago

Using Machine Learning to Identify Patients at Risk of Acquiring HIV in an Urban Health System

BACKGROUND

Effective measures exist to prevent the spread of HIV. However, the identification of patients who are candidates for these measures can be a challenge. A machine learning model to predict risk for HIV may enhance patient selection for proactive outreach.

SETTING

Using data from the electronic health record at Parkland Health, 1 of the largest public healthcare systems in the country, a machine learning model is created to predict incident HIV cases. The study cohort includes any patient aged 16 or older from 2015 to 2019 (n = 458,893).

METHODS

Implementing a 70:30 ratio random split of the data into training and validation sets with an incident rate <0.08% and stratified by incidence of HIV, the model is evaluated using a k-fold cross-validated (k = 5) area under the receiver operating characteristic curve leveraging Light Gradient Boosting Machine Algorithm, an ensemble classifier.

RESULTS

The light gradient boosting machine produces the strongest predictive power to identify good candidates for HIV PrEP. A gradient boosting classifier produced the best result with an AUC of 0.88 (95% confidence interval: 0.86 to 0.89) on the training set and 0.85 (95% confidence interval: 0.81 to 0.89) on the validation set for a sensitivity of 77.8% and specificity of 75.1%.

CONCLUSIONS

A gradient boosting model using electronic health record data can be used to identify patients at risk of acquiring HIV and implemented in the clinical setting to build outreach for preventative interventions.

Predicting the individualized risk of human immunodeficiency virus infection among sexually active women in Ethiopia using a nomogram: prediction model development and validation

Introduction

Women are more vulnerable to HIV infection due to biological and socioeconomic reasons. Developing a predictive model for these vulnerable populations to estimate individualized risk for HIV infection is relevant for targeted preventive interventions. The objective of the study was to develop and validate a risk prediction model that allows easy estimations of HIV infection risk among sexually active women in Ethiopia.

Methods

Data from the 2016 Ethiopian Demographic and Health Survey, which comprised 10,253 representative sexually active women, were used for model development. Variables were selected using the least absolute shrinkage and selection operator (LASSO). Variables selected by LASSO were incorporated into the multivariable mixed-effect logistic regression model. Based on the multivariable model, an easy-to-use nomogram was developed to facilitate its applicability. The performance of the nomogram was evaluated using discrimination and calibration abilities, Brier score, sensitivity, and specificity. Internal validation was carried out using the bootstrapping method.

Results

The model selected seven predictors of HIV infection, namely, age, education, marital status, sex of the household head, age at first sex, multiple sexual partners during their lifetime, and residence. The nomogram had a discriminatory power of 89.7% (95% CI: 88.0, 91.5) and a calibration p-value of 0.536. In addition, the sensitivity and specificity of the nomogram were 74.1% (95% CI: 68.4, 79.2) and 80.9% (95% CI: 80.2, 81.7), respectively. The internally validated model had a discriminatory ability of 89.4% (95% CI: 87.7, 91.1) and a calibration p-value of 0.195. Sensitivity and specificity after validation were 72.9% (95% CI: 67.2, 78.2) and 80.1% (95% CI: 79.3, 80.9), respectively.

Conclusion

A new prediction model that quantifies the individualized risk of HIV infection has been developed in the form of a nomogram and internally validated. It has very good discriminatory power and good calibration ability. This model can facilitate the identification of sexually active women at high risk of HIV infection for targeted preventive measures.

"There hasn't been a push to identify patients in the emergency department"-Staff perspectives on automated identification of candidates for pre-exposure prophylaxis (PrEP): A qualitative study

Automated algorithms for identifying potential pre-exposure prophylaxis (PrEP) candidates are effective among men, yet often fail to detect cisgender women (hereafter referred to as "women") who would most benefit from PrEP. The emergency department (ED) is an opportune setting for implementing automated identification of PrEP candidates, but there are logistical and practical challenges at the individual, provider, and system level. In this study, we aimed to understand existing processes for identifying PrEP candidates and to explore determinants for incorporating automated identification of PrEP candidates within the ED, with specific considerations for ciswomen, through a focus group and individual interviews with ED staff. From May to July 2021, we conducted semi-structured qualitative interviews with 4 physicians and a focus group with 4 patient advocates working in a high-volume ED in Chicago. Transcripts were coded using Dedoose software and analyzed for common themes. In our exploratory study, we found three major themes: 1) Limited PrEP knowledge among ED staff, particularly regarding its use in women; 2) The ED does not have a standardized process for assessing HIV risk; and 3) Perspectives on and barriers/facilitators to utilizing an automated algorithm for identifying ideal PrEP candidates. Overall, ED staff had minimal understanding of the need for PrEP among women. However, participants recognized the utility of an electronic medical record (EMR)-based automated algorithm to identify PrEP candidates in the ED. Facilitators to an automated algorithm included organizational support/staff buy-in, patient trust, and dedicated support staff for follow-up/referral to PrEP care. Barriers reported by participants included time constraints, hesitancy among providers to prescribe PrEP due to follow-up concerns, and potential biases or oversight resulting from missing or inaccurate information within the EMR. Further research is needed to determine the feasibility and acceptability of an EMR-based predictive HIV risk algorithm within the ED setting.