Search

Objective A case definition of HIV lipodystrophy has recently been developed from a combination of clinical, metabolic and imaging/body composition variables using logistic regression methods. We aimed to evaluate whether artificial neural networks could improve the diagnostic accuracy.Methods The database of the case-control Lipodystrophy Case Definition Study was split into 504 subjects (265 with and 239 without lipodystrophy) used for training and 284 independent subjects (152 with and 132 without lipodystrophy) used for validation. Back-propagation neural networks with one or two middle layers were trained and validated. Results were compared against logistic regression models using the same information.Results Neural networks using clinical variables only (41 items) achieved consistently superior performance than logistic regression in terms of specificity, overall accuracy and area under the ROC curve. Their average sensitivity and specificity were 72.4 and 71.2%, as compared with 73.0 and 62.9% for logistic regression, respectively (area under the ROC curve, 0.784 vs 0.748). The discriminating performance of the neural networks was largely unaffected when built excluding 13 parameters that patients may not have readily available. The average sensitivity and specificity of the neural networks remained the same when metabolic variables were also considered (total 60 items) without a clear advantage against logistic regression (overall accuracy 71.8%). The performance of networks considering also body composition variables was similar to that of logistic regression (overall accuracy 78.5% for both).Conclusions Neural networks may offer a means to improve the discriminating performance for HIV lipodystrophy, when only clinical data are available and a rapid approximate diagnostic decision is needed. In this context, information on metabolic parameters is apparently not helpful in improving the diagnosis of HIV lipodystrophy, unless imaging and body composition studies are also obtained.

Objectives (1) To document rates and patterns of adherence from enrollment until week 24 of an AIDS clinical trial; (2) to examine the association of adherence to clinical end-points including plasma HIV-1 RNA level and CD4 cell count; and (3) to identify predictors of adherence from clinical, behavioural, psychosocial and demographic factors.Design Sub-study of a multicentre, randomised, open-label, comparison-controlled trial; 21 collaborating units of the Adult AIDS Clinical Trials Group. Observational, prospective analysis.Methods Ninety-three subjects with baseline plasma HIV-1 RNA levels >500 copies/ml, who completed clinical assessment, plasma HIV-1 RNA titres and CD4 cell counts at study entry, weeks 2, 4 and every 4 weeks thereafter until week 24. All patients were antiretroviral-experienced but were naive to non-nucleoside reverse transcriptase inhibitors and protease inhibitors. Self-reported adherence to antiretroviral therapies prescribed as part of the trial was assessed every 4 weeks from trial, week 4 until week 24.Results Average adherence was high, with 63% of subjects reporting >95% adherence across the trial. However, there was a significant decline in adherence over time on trial. After controlling for potential confounding variables, patients who were less than 95% adherent to medications were 3.5-times more likely to have treatment failure (HIV-1 RNA >50 copies/ml) than subjects with adherence rates of 95–100%. The strongest predictor of adherence was adverse clinical events (for example, dermatological, gastrointestinal symptoms): patients with adverse events were 12.8-times less likely to have 95–100% adherence. Other clinical, demographic, psychosocial and behavioural factors were also significant predictors of adherence.Conclusions Adherence influences virological outcome even in AIDS clinical trials where overall adherence rates are high and should therefore be monitored in future trials. Intervention may be warranted to enhance adherence for subjects who have early toxicities, express concern about taking medications as directed, and for women and minorities.