A screening algorithm for HIV-associated neurocognitive disorders.

摘要: Background HIV physicians have limited time for cognitive screening. Here we developed an extra-brief, clinically based tool predicting HIV-associated neurocognitive impairment (HAND) in order to determine which HIV-positive individuals require a more comprehensive neurological/neuropsychological (NP) assessment. Methods Ninety-seven with advanced disease recruited HIV out-patient clinic received standard NP testing. A screening algorithm was using support vector machines, optimized prediction procedure classifying into two groups (here NP-impaired and NP-normal) on set of predictors. Results The final utilized age, current CD4 cell count, past central nervous system HIV-related diseases treatment duration required approximately 3 min complete, good overall accuracy 78% (against the gold standard; NP-impairment status derived from testing) specificity 70%. Conclusion This noncognitive-based should prove useful identify HIV-infected patients at high risk HAND who formal assessment. We propose staged guidelines, algorithm, improved therapeutic management. Future larger, international studies are planned test predictive effect nadir hepatitis C virus infection, gender, ethnicity viral clade. recommend use this first version Caucasian men disease.