Antiretroviral therapy optimisation without genotype resistance testing : a perspective on treatment history based models

Although genotypic resistance testing (GRT) is recommended to guide combination antiretroviral therapy (cART), funding and/or facilities to perform GRT may not be available in low to middle income countries. Since treatment history (TH) impacts response to subsequent therapy, we investigated a set o...

Full description

Saved in:
Bibliographic Details
Main Authors: Prosperi, Mattia C. F., Sloot, Peter M. A., van de Vijver, David A. M. C., Rosen-Zvi, Michal, Altmann, André, Zazzi, Maurizio, Schülter, Eugen, Struck, Daniel, Di Giambenedetto, Simona, Kaiser, Rolf, Vandamme, Anne-Mieke, Sönnerborg, Anders
Other Authors: School of Computer Engineering
Format: Article
Language:English
Published: 2013
Subjects:
Online Access:https://hdl.handle.net/10356/96297
http://hdl.handle.net/10220/9870
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-96297
record_format dspace
spelling sg-ntu-dr.10356-962972022-02-16T16:29:58Z Antiretroviral therapy optimisation without genotype resistance testing : a perspective on treatment history based models Prosperi, Mattia C. F. Sloot, Peter M. A. van de Vijver, David A. M. C. Rosen-Zvi, Michal Altmann, André Zazzi, Maurizio Schülter, Eugen Struck, Daniel Di Giambenedetto, Simona Kaiser, Rolf Vandamme, Anne-Mieke Sönnerborg, Anders School of Computer Engineering DRNTU::Engineering::Computer science and engineering::Computer applications::Life and medical sciences Although genotypic resistance testing (GRT) is recommended to guide combination antiretroviral therapy (cART), funding and/or facilities to perform GRT may not be available in low to middle income countries. Since treatment history (TH) impacts response to subsequent therapy, we investigated a set of statistical learning models to optimise cART in the absence of GRT information. Methods and Findings The EuResist database was used to extract 8-week and 24-week treatment change episodes (TCE) with GRT and additional clinical, demographic and TH information. Random Forest (RF) classification was used to predict 8- and 24-week success, defined as undetectable HIV-1 RNA, comparing nested models including (i) GRT+TH and (ii) TH without GRT, using multiple cross-validation and area under the receiver operating characteristic curve (AUC). Virological success was achieved in 68.2% and 68.0% of TCE at 8- and 24-weeks (n = 2,831 and 2,579), respectively. RF (i) and (ii) showed comparable performances, with an average (st.dev.) AUC 0.77 (0.031) vs. 0.757 (0.035) at 8-weeks, 0.834 (0.027) vs. 0.821 (0.025) at 24-weeks. Sensitivity analyses, carried out on a data subset that included antiretroviral regimens commonly used in low to middle income countries, confirmed our findings. Training on subtype B and validation on non-B isolates resulted in a decline of performance for models (i) and (ii). Conclusions Treatment history-based RF prediction models are comparable to GRT-based for classification of virological outcome. These results may be relevant for therapy optimisation in areas where availability of GRT is limited. Further investigations are required in order to account for different demographics, subtypes and different therapy switching strategies Published version 2013-04-29T07:03:42Z 2019-12-06T19:28:22Z 2013-04-29T07:03:42Z 2019-12-06T19:28:22Z 2010 2010 Journal Article Prosperi, M. C. F., Rosen-Zvi, M., Altmann, A., Zazzi, M., Di Giambenedetto, S., Kaiser, R., et al. (2010). Antiretroviral Therapy Optimisation without Genotype Resistance Testing: A Perspective on Treatment History Based Models. PLoS ONE, 5(10), e13753. 1932-6203 https://hdl.handle.net/10356/96297 http://hdl.handle.net/10220/9870 10.1371/journal.pone.0013753 21060792 en PLoS ONE © 2010 Prosperi et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering::Computer applications::Life and medical sciences
spellingShingle DRNTU::Engineering::Computer science and engineering::Computer applications::Life and medical sciences
Prosperi, Mattia C. F.
Sloot, Peter M. A.
van de Vijver, David A. M. C.
Rosen-Zvi, Michal
Altmann, André
Zazzi, Maurizio
Schülter, Eugen
Struck, Daniel
Di Giambenedetto, Simona
Kaiser, Rolf
Vandamme, Anne-Mieke
Sönnerborg, Anders
Antiretroviral therapy optimisation without genotype resistance testing : a perspective on treatment history based models
description Although genotypic resistance testing (GRT) is recommended to guide combination antiretroviral therapy (cART), funding and/or facilities to perform GRT may not be available in low to middle income countries. Since treatment history (TH) impacts response to subsequent therapy, we investigated a set of statistical learning models to optimise cART in the absence of GRT information. Methods and Findings The EuResist database was used to extract 8-week and 24-week treatment change episodes (TCE) with GRT and additional clinical, demographic and TH information. Random Forest (RF) classification was used to predict 8- and 24-week success, defined as undetectable HIV-1 RNA, comparing nested models including (i) GRT+TH and (ii) TH without GRT, using multiple cross-validation and area under the receiver operating characteristic curve (AUC). Virological success was achieved in 68.2% and 68.0% of TCE at 8- and 24-weeks (n = 2,831 and 2,579), respectively. RF (i) and (ii) showed comparable performances, with an average (st.dev.) AUC 0.77 (0.031) vs. 0.757 (0.035) at 8-weeks, 0.834 (0.027) vs. 0.821 (0.025) at 24-weeks. Sensitivity analyses, carried out on a data subset that included antiretroviral regimens commonly used in low to middle income countries, confirmed our findings. Training on subtype B and validation on non-B isolates resulted in a decline of performance for models (i) and (ii). Conclusions Treatment history-based RF prediction models are comparable to GRT-based for classification of virological outcome. These results may be relevant for therapy optimisation in areas where availability of GRT is limited. Further investigations are required in order to account for different demographics, subtypes and different therapy switching strategies
author2 School of Computer Engineering
author_facet School of Computer Engineering
Prosperi, Mattia C. F.
Sloot, Peter M. A.
van de Vijver, David A. M. C.
Rosen-Zvi, Michal
Altmann, André
Zazzi, Maurizio
Schülter, Eugen
Struck, Daniel
Di Giambenedetto, Simona
Kaiser, Rolf
Vandamme, Anne-Mieke
Sönnerborg, Anders
format Article
author Prosperi, Mattia C. F.
Sloot, Peter M. A.
van de Vijver, David A. M. C.
Rosen-Zvi, Michal
Altmann, André
Zazzi, Maurizio
Schülter, Eugen
Struck, Daniel
Di Giambenedetto, Simona
Kaiser, Rolf
Vandamme, Anne-Mieke
Sönnerborg, Anders
author_sort Prosperi, Mattia C. F.
title Antiretroviral therapy optimisation without genotype resistance testing : a perspective on treatment history based models
title_short Antiretroviral therapy optimisation without genotype resistance testing : a perspective on treatment history based models
title_full Antiretroviral therapy optimisation without genotype resistance testing : a perspective on treatment history based models
title_fullStr Antiretroviral therapy optimisation without genotype resistance testing : a perspective on treatment history based models
title_full_unstemmed Antiretroviral therapy optimisation without genotype resistance testing : a perspective on treatment history based models
title_sort antiretroviral therapy optimisation without genotype resistance testing : a perspective on treatment history based models
publishDate 2013
url https://hdl.handle.net/10356/96297
http://hdl.handle.net/10220/9870
_version_ 1725985803901861888