An update to the HIV-TRePS system: the development and evaluation of new global and local computational models to predict HIV treatment outcomes, with or without a genotype
<p>Objectives: Optimizing antiretroviral drug combination on an individual basis in resource-limited settings is challenging because of the limited availability of drugs and genotypic resistance testing. Here, we describe our latest computational models to predict treatment responses, with or...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Journal article |
| Published: |
Oxford University Press
2016
|
| _version_ | 1797106245117673472 |
|---|---|
| author | Revell, A Wang, D Wood, R Morrow, C Tempelman, H Hamers, R Reiss, P van Sighem, A Nelson, M Montaner, J Lane, H Larder, B |
| author_facet | Revell, A Wang, D Wood, R Morrow, C Tempelman, H Hamers, R Reiss, P van Sighem, A Nelson, M Montaner, J Lane, H Larder, B |
| author_sort | Revell, A |
| collection | OXFORD |
| description | <p>Objectives: Optimizing antiretroviral drug combination on an individual basis in resource-limited settings is challenging because of the limited availability of drugs and genotypic resistance testing. Here, we describe our latest computational models to predict treatment responses, with or without a genotype, and compare the potential utility of global and local models as a treatment tool for South Africa.</p><p> Methods: Global random forest models were trained to predict the probability of virological response to therapy following virological failure using 29 574 treatment change episodes (TCEs) without a genotype, 3179 of which were from South Africa and were used to develop local models. In addition, 15 130 TCEs including genotypes were used to develop another set of models. The 'no-genotype' models were tested with an independent global test set (n = 1700) plus a subset from South Africa (n = 222). The genotype models were tested with 750 independent cases.</p><p> Results: The global no-genotype models achieved area under the receiver-operating characteristic curve (AUC) values of 0.82 and 0.79 with the global and South African tests sets, respectively, and the South African models achieved AUCs of 0.70 and 0.79. The genotype models achieved an AUC of 0.84. The global no-genotype models identified more alternative, locally available regimens that were predicted to be effective for cases that failed their new regimen in the South African clinics than the local models. Both sets of models were significantly more accurate predictors of outcomes than genotyping with rules-based interpretation. </p><p>Conclusions: These latest global models predict treatment responses accurately even without a genotype, out-performed the local South African models and have the potential to help optimize therapy, particularly in resource-limited settings.</p> |
| first_indexed | 2024-03-07T06:58:58Z |
| format | Journal article |
| id | oxford-uuid:ff15c900-7f19-4a87-8e76-77d122b7e4a2 |
| institution | University of Oxford |
| last_indexed | 2024-03-07T06:58:58Z |
| publishDate | 2016 |
| publisher | Oxford University Press |
| record_format | dspace |
| spelling | oxford-uuid:ff15c900-7f19-4a87-8e76-77d122b7e4a22022-03-27T13:41:54ZAn update to the HIV-TRePS system: the development and evaluation of new global and local computational models to predict HIV treatment outcomes, with or without a genotypeJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:ff15c900-7f19-4a87-8e76-77d122b7e4a2Symplectic Elements at OxfordOxford University Press2016Revell, AWang, DWood, RMorrow, CTempelman, HHamers, RReiss, Pvan Sighem, ANelson, MMontaner, JLane, HLarder, B<p>Objectives: Optimizing antiretroviral drug combination on an individual basis in resource-limited settings is challenging because of the limited availability of drugs and genotypic resistance testing. Here, we describe our latest computational models to predict treatment responses, with or without a genotype, and compare the potential utility of global and local models as a treatment tool for South Africa.</p><p> Methods: Global random forest models were trained to predict the probability of virological response to therapy following virological failure using 29 574 treatment change episodes (TCEs) without a genotype, 3179 of which were from South Africa and were used to develop local models. In addition, 15 130 TCEs including genotypes were used to develop another set of models. The 'no-genotype' models were tested with an independent global test set (n = 1700) plus a subset from South Africa (n = 222). The genotype models were tested with 750 independent cases.</p><p> Results: The global no-genotype models achieved area under the receiver-operating characteristic curve (AUC) values of 0.82 and 0.79 with the global and South African tests sets, respectively, and the South African models achieved AUCs of 0.70 and 0.79. The genotype models achieved an AUC of 0.84. The global no-genotype models identified more alternative, locally available regimens that were predicted to be effective for cases that failed their new regimen in the South African clinics than the local models. Both sets of models were significantly more accurate predictors of outcomes than genotyping with rules-based interpretation. </p><p>Conclusions: These latest global models predict treatment responses accurately even without a genotype, out-performed the local South African models and have the potential to help optimize therapy, particularly in resource-limited settings.</p> |
| spellingShingle | Revell, A Wang, D Wood, R Morrow, C Tempelman, H Hamers, R Reiss, P van Sighem, A Nelson, M Montaner, J Lane, H Larder, B An update to the HIV-TRePS system: the development and evaluation of new global and local computational models to predict HIV treatment outcomes, with or without a genotype |
| title | An update to the HIV-TRePS system: the development and evaluation of new global and local computational models to predict HIV treatment outcomes, with or without a genotype |
| title_full | An update to the HIV-TRePS system: the development and evaluation of new global and local computational models to predict HIV treatment outcomes, with or without a genotype |
| title_fullStr | An update to the HIV-TRePS system: the development and evaluation of new global and local computational models to predict HIV treatment outcomes, with or without a genotype |
| title_full_unstemmed | An update to the HIV-TRePS system: the development and evaluation of new global and local computational models to predict HIV treatment outcomes, with or without a genotype |
| title_short | An update to the HIV-TRePS system: the development and evaluation of new global and local computational models to predict HIV treatment outcomes, with or without a genotype |
| title_sort | update to the hiv treps system the development and evaluation of new global and local computational models to predict hiv treatment outcomes with or without a genotype |
| work_keys_str_mv | AT revella anupdatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT wangd anupdatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT woodr anupdatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT morrowc anupdatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT tempelmanh anupdatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT hamersr anupdatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT reissp anupdatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT vansighema anupdatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT nelsonm anupdatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT montanerj anupdatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT laneh anupdatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT larderb anupdatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT revella updatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT wangd updatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT woodr updatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT morrowc updatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT tempelmanh updatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT hamersr updatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT reissp updatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT vansighema updatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT nelsonm updatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT montanerj updatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT laneh updatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype AT larderb updatetothehivtrepssystemthedevelopmentandevaluationofnewglobalandlocalcomputationalmodelstopredicthivtreatmentoutcomeswithorwithoutagenotype |