Poster presentation at:
International AIDS Society Conference (IAS); 17-20 July 2011; Rome, Italy.

Predicting response to antiretroviral therapy without a genotype: a treatment tool for resource-limited settings

Larder BA¹, Revell AD¹, Wang D¹, Ene L², Tempelman H³, Barth RE⁴, Wensing AM⁴, Gazzard B⁵, DeWolf F⁶, Lane HC⁷, Montaner JSS⁸.

¹ RDI, London UK
² “Dr. Victor Babes” Hospital for Infectious and Tropical Diseases, Bucharest, Romania
³ Ndlovu Care Group, Elandsdoorn, South Africa
⁴ UMC Utrecht, Netherlands
⁵ Chelsea and Westminster Hospital, London, UK
⁶ Netherlands HIV Monitoring Foundation, Amsterdam, The Netherlands
⁷ NIAID, Bethesda, USA
⁸ BC Centre for Excellence in HIV/AIDS, Vancouver, Canada

Background
The RDI has pioneered the development of computational models that predict response to antiretroviral therapy from baseline data including genotype, typically with 80% accuracy, which are now available online. Genotyping is not generally affordable in resource-limited settings and here we describe the development of models that do not require a genotype, for use in such settings.

Methods
Treatment change episodes (TCEs) from >15 countries from the RDI database were partitioned at random into a training set of 14,964 and a test set of 800. A committee of 10 random forest models was developed to predict the probability of follow-up viral load ≤400 copies using 10x leave-n out cross-validation (CV).  The input variables were baseline viral load, CD4 count, treatment history, drugs in the new regimen and time to follow-up. Receiver-operator characteristic (ROC) curves were plotted during cross validation, with the 800 test set and with test sets from Romania (n=39) and South Africa (n=56). A subset of 57 TCEs from the 800 test set that had genotypes available were also tested with the RDI’s models that include a genotype.

Results:
The mean area under the curve (AUC) and overall accuracy (OA) were 0.77 and 72% during CV and  0.77 and 71% with the test dataset.  With the Romanian test set the AUC and OA were 0.68 and 67% and with the South African test set 0.69 and 68%.  The RDI genotype models achieved an AUC and OA of 0.77 and 74% with the 57 subset, compared to 0.76 and 68% for the ‘no-genotype’ models.

Conclusions
The RF models’ predictions were only slightly less accurate than models that include the genotype.  They performed well with data from resource-limited clinics not represented in the training dataset suggesting they are generalisable. The models are now available via the RDI’s online treatment selection tool HIV-TRePS.

- Poster from International AIDS Society Conference (IAS); 17-20 July 2011; Rome, Italy.