Computational models as predictors of HIV treatment outcomes for the Phidisa cohort in South Africa

Abstract

BackgroundSelecting the optimal combination of HIV drugs for an individual in resource-limited settings is challenging because of the limited availability of drugs and genotyping.ObjectiveThe evaluation as a potential treatment support tool of computational models that predict response to therapy without a genotype, using cases from the Phidisa cohort in South Africa.MethodsCases from Phidisa of treatment change following failure were identified that had the following data available: baseline CD4 count and viral load, details of failing and previous antiretroviral drugs, drugs in new regimen and time to follow-up. The HIV Resistance Response Database Initiative’s (RDI’s) models used these data to predict the probability of a viral load < 50 copies/mL at follow-up. The models were also used to identify effective alternative combinations of three locally available drugs.ResultsThe models achieved accuracy (area under the receiver–operator characteristic curve) of 0.72 when predicting response to therapy, which is less accurate than for an independent global test set (0.80) but at least comparable to that of genotyping with rules-based interpretation. The models were able to identify alternative locally available three-drug regimens that were predicted to be effective in 69% of all cases and 62% of those whose new treatment failed in the clinic.ConclusionThe predictive accuracy of the models for these South African patients together with the results of previous studies suggest that the RDI’s models have the potential to optimise treatment selection and reduce virological failure in different patient populations, without the use of a genotype.

Predicting CD4 count changes among patients on antiretroviral treatment: Application of data mining techniques

“…revealed a committee of 10 Random Forest algorithms used to predict virologic response to therapy showed an overall accuracy of 63% 31 .…”

“…Using other evaluation metrics such as precision, true positivity rate, false positivity rate and kappa also demonstrated the supreme performance of the Random Forest over J48 and the Artificial Neural Network prediction algorithms. Comparable level of AUC was reported from a recent study by Revell and colleagues31 . Hence, Random Forest can be used to develop cost effective web-based prediction models to help providers forecast patients' future likelihood of immunologic reconstitution without conducting expensive CD4…”

A Computational Approach for the Prediction of Treatment History and the Effectiveness or Failure of Antiretroviral Therapy

“…Experimental tests allow for the evaluation of HIV-1 resistance against RT and PR inhibitors [7,8]. Several machine learning approaches predict the resistance and/or exposure of a particular HIV-1 variant to a drug on the basis of the nucleotide or amino acid sequences of the HIV-1 PR and RT [9][10][11][12][13][14][15][16][17]. Earlier, we reported computational approaches for predicting HIV-1 resistance to RT and PR inhibitors [10,18,19] based on sequences of HIV-1 variants collected from around the world, available from the Stanford HIV Resistance Database (STDB) [20].…”

A comparative study of logistic regression based machine learning techniques for prediction of early virological suppression in antiretroviral initiating HIV patients

“…Many of these models heavily rely on viralogical resistance genotype data which may not be available in resource limited settings [ 21 – 23 ]. Those that avoide genotype data make use of relatively complex classifiers such as random forests(RF) or artificial neural networks (ANN) as the backbone of on-line prediction tools [ 20 , 24 – 27 ]. Such tools and methods are not easily interpretable by medical providers and are inaccessible in resource limited settings where computing facilities may not be available.…”