697    

Background:  The HIV Resistance Response Database Initiative (RDI) has trained Artificial Neural Network (ANN) models using clinical data, which, when tested with independent data from the same clinical setting, have demonstrated accuracy in predicting virological response to antiretroviral therapy from genotype. Here we examine the performance of ANN models developed using datasets of increasing size pooled from several clinical settings.

Methods:  From 153 patients in the NIAID cohort, 228 “treatment change episodes” were obtained:  episodes with a genotype £12 weeks and a viral load £8 before treatment change and follow-up viral load within 4 to 40 weeks. Four ANN models were developed; each trained using 171 treatment change episodes and tested with the remaining 57. Results were compared with those obtained with 13 ANN models using the NIAID data plus data from a second cohort (BC), yielding 747 treatment change episodes. The data were finally added to data from multiple sources in the RDI database, yielding 1581 treatment change episodes and 10 ANN models trained, and tested. All the training and testing sub-datasets were independent, randomly partitioned and normalised.

Results:  Correlation between the predicted and actual viral load change for the 4 ANN models developed from the NIAID cohort gave a mean r² value of 0.71 and mean correct trajectory prediction rate of 76%. The 13 ANN models from the combined NIAID and BC cohorts gave a mean r² value of 0.65 and mean correct trajectory prediction rate of 78%. The 10 models developed from the largest composite dataset gave a mean r² of 0.55 and a mean correct trajectory prediction rate of 74%. The r² value for the composite dataset was significantly lower than for the other 2 datasets.

Conclusions:  These results indicate that ANN models trained using limited data from one clinical setting can be surprisingly accurate in predicting responses to treatment from genotype for other patients from the same cohort. Models developed using considerably more data from a variety of settings are not automatically more accurate, when tested with data from multiple settings. Preliminary analysis suggests that the accuracy of ANN models may depend on the training and test data being similarly diverse, although this does not necessarily imply similarity in terms of specific mutations or drugs. These results confirm the potential of ANN models as an aid to treatment decision-making but underline the need to collect sufficient diversity of data to develop models that are able to predict treatment response for disparate test cases.

Keywords: Resistance; Virologic response; Database