Introduction: When used in combination, antiretroviral drugs are highly effective for suppressing HIV replication. Nevertheless, treatment failure commonly occurs and is generally associated with viral drug resistance. The choice of an alternative regimen may be guided by a drug-resistance test. However, interpretation of resistance from genotypic data poses a major challenge. Methods: As an alternative to current interpretation systems, we have developed artificial neural network (ANN) models to predict virological response to combination therapy from HIV genotype and other clinical information. Results: ANN models trained with genotype, baseline viral load and time to follow-up viral load (1,154 treatment change episodes from multiple clinics), produced predictions of virological response that were highly significantly correlated with actual responses (r2=0.53; P<0.00001) using independent test data from clinics that contributed training data. Augmented models, trained with the additional variables of baseline CD4+ T-cell count and four treatment history variables, were more accurate, explaining 69% of the variance in virological response. Models trained with the full input dataset, but only those data involving highly active antiretroviral therapy (three or more full-dose antiretroviral drugs in combination), performed at an intermediate level, explaining 61% of the variance. The augmented models performed less well when tested with data from unfamiliar clinics that had not contributed data to the training dataset, explaining 46% of the variance in response. Conclusion: These data indicate that ANN models can be quite accurate predictors of virological response to HIV therapy even for patients from unfamiliar clinics. ANN models therefore warrant further development as a potential tool to aid treatment selection.

The development of artificial neural networks to predict virological response to combination HIV therapy.

TORTI, Carlo;
2007-01-01

Abstract

Introduction: When used in combination, antiretroviral drugs are highly effective for suppressing HIV replication. Nevertheless, treatment failure commonly occurs and is generally associated with viral drug resistance. The choice of an alternative regimen may be guided by a drug-resistance test. However, interpretation of resistance from genotypic data poses a major challenge. Methods: As an alternative to current interpretation systems, we have developed artificial neural network (ANN) models to predict virological response to combination therapy from HIV genotype and other clinical information. Results: ANN models trained with genotype, baseline viral load and time to follow-up viral load (1,154 treatment change episodes from multiple clinics), produced predictions of virological response that were highly significantly correlated with actual responses (r2=0.53; P<0.00001) using independent test data from clinics that contributed training data. Augmented models, trained with the additional variables of baseline CD4+ T-cell count and four treatment history variables, were more accurate, explaining 69% of the variance in virological response. Models trained with the full input dataset, but only those data involving highly active antiretroviral therapy (three or more full-dose antiretroviral drugs in combination), performed at an intermediate level, explaining 61% of the variance. The augmented models performed less well when tested with data from unfamiliar clinics that had not contributed data to the training dataset, explaining 46% of the variance in response. Conclusion: These data indicate that ANN models can be quite accurate predictors of virological response to HIV therapy even for patients from unfamiliar clinics. ANN models therefore warrant further development as a potential tool to aid treatment selection.
File in questo prodotto:
File Dimensione Formato  
Larder B; et al.pdf

gestori archivio

Tipologia: Full Text
Licenza: DRM non definito
Dimensione 612.36 kB
Formato Adobe PDF
612.36 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11379/26112
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact