Super learner analysis of real‐time electronically monitored adherence to antiretroviral therapy under constrained optimization and comparison to non‐differentiated care approaches for persons living with HIV in rural Uganda

Abstract

Introduction Real‐time electronic adherence monitoring (EAM) systems could inform on‐going risk assessment for HIV viraemia and be used to personalize viral load testing schedules. We evaluated the potential of real‐time EAM (transferred via cellular signal) and standard EAM (downloaded via USB cable) in rural Uganda to inform individually differentiated viral load testing strategies by applying machine learning approaches. Methods We evaluated an observational cohort of persons living with HIV and treated with antiretroviral therapy (ART) who were monitored longitudinally with standard EAM from 2005 to 2011 and real‐time EAM from 2011 to 2015. Super learner, an ensemble machine learning method, was used to develop a tool for targeting viral load testing to detect viraemia (>1000 copies/ml) based on clinical (CD4 count, ART regimen), viral load and demographic data, together with EAM‐based adherence. Using sample‐splitting (cross‐validation), we evaluated area under the receiver operating characteristic curve (cvAUC), potential for EAM data to selectively defer viral load tests while minimizing delays in viraemia detection, and performance compared to WHO‐recommended testing schedules. Results In total, 443 persons (1801 person‐years) and 485 persons (930 person‐years) contributed to standard and real‐time EAM analyses respectively. In the 2011 to 2015 dataset, addition of real‐time EAM (cvAUC: 0.88; 95% CI: 0.83, 0.93) significantly improved prediction compared to clinical/demographic data alone (cvAUC: 0.78; 95% CI: 0.72, 0.86; p = 0.03). In the 2005 to 2011 dataset, addition of standard EAM (cvAUC: 0.77; 95% CI: 0.72, 0.81) did not significantly improve prediction compared to clinical/demographic data alone (cvAUC: 0.70; 95% CI: 0.64, 0.76; p = 0.08). A hypothetical testing strategy using real‐time EAM to guide deferral of viral load tests would have reduced the number of tests by 32% while detecting 87% of viraemia cases without delay. By comparison, the WHO‐recommended testing schedule would have reduced the number of tests by 69%, but resulted in delayed detection of viraemia a mean of 74 days for 84% of individuals with viraemia. Similar rules derived from standard EAM also resulted in potential testing frequency reductions. Conclusions Our machine learning approach demonstrates potential for combining EAM data with other clinical measures to develop a selective testing rule that reduces number of viral load tests ordered, while still identifying those at highest risk for viraemia.

Data Science Trends Relevant to Nursing Practice: A Rapid Review of the 2020 Literature

“…Most were retrospective cohort studies, 75 76 77 78 79 80 81 82 83 84 85 86 87 while six used prospective cohort studies, 88 89 90 91 92 93 four used a cross-sectional design, 94 95 96 97 and one used a survey for primary data collection. 98 Most studies used the EHR and administrative databases to collect data but three used surveys, 87 96 98 two used public datasets, 78 95 one used mobile phone data, 97 one used images, 90 and one used data from social media. 92 All studies were adult based with the exception of one study examining families.…”

Studying patterns and predictors of HIV viral suppression using A Big Data approach: a research protocol

“…However, these integrated data sources are characterized by high volume and variation, and there are several data analytic challenges in the integrated data structure, including mismatched time scales and multilevel risk predictors. The recent developments in Big Data analytics, such as artificial neural network [ 50 , 51 ], LSTM Neural Network, random forest [ 51 , 52 ], support vector machine [ 51 ], and deep learning approach such as CNN [ 53 ], make it feasible to address these methodological challenges and predict virologic outcomes using data from multiple domains.…”

Predictors of Covid-19 level of concern among older adults from the health and retirement study

“…The proportional odds assumption was evaluated prior to using ordinal and mixed-effects ordinal logistic regression. Finally, we applied ML algorithms to select the best predictive model for Covid-19 level of concern defined as a series of dichotomous variables (‘Low’ vs. ‘Medium’, ‘High’ vs. ‘Low’) 44 – 52 . ML algorithms are more flexible than traditional regression techniques since they can handle a large number of predictors as well as evaluate non-linear relationships and interaction effects, resulting in superior predictive performance.…”

“…Super Learner is an Ensemble ML algorithm that estimates the performance of an initial set of candidate models called “learners” and creates an optimal weighted average of these models known as a convex combination of algorithms or “Ensemble” using specific performance criterion (e.g. cross-validated area under the receiving operating characteristic curve (cv-AUROC)) 44 – 46 , 48 – 54 . The purpose of using Super Learner is to combine the results of multiple parametric and non-parametric models and to evaluate the extent to which socio-demographic, lifestyle and health characteristics are sufficient for predicting Covid-19 level of concern.…”

“…Least Absolute Shrinkage and Selection Operator [LASSO], Random Forests, XGBoost, Support Vector Machines [SVM]) algorithms, a V-fold “inner” cross-validation process, a U-fold “outer” cross-validation process and a loss function to identify the best weighted combination of prediction models from multiple candidates based on calibration, discrimination, and risk classification criteria 44 – 54 . As previously described 44 – 54 , we selected the majority of HRS participants (80%) as a training sample and 20% of HRS participants as a test sample. Two-sided statistical tests were performed while assuming α = 0.05.…”