Abstract
Despite the proven clinical benefits of HAART, mortality may still occur; particularly in those with less than 50 CD4+ cells/mL and, in some cases, with a viral burden below detectable plasma levels of HIV-1 RNA. Multiple factors may predict mortality including initial response to therapy, viral factors and host immune parameters. Due to the complexity of this problem, we developed Artificial Intelligence based tools/Neural Network (NN) to optimally evaluate outcomes of therapy and predict morbidity and mortality. To further validate the accuracy of these tools, we challenged their performance with that of Cox regression modeling (RM). Our study population involved 116 HIV+ individuals who consistently maintained CD4+ count < 50 cells/mL for over 6 months. All patients were treated with antiretrovirals. To assess clinical outcomes, we developed a feedforward back-propagation Neural Network. We then compared the performance of this network to a Cox regression model. The Neural Network outscored the Cox regression model in the ROC curve areas: 0.888 vs 0.760 (HIV+ first Seropositivity to AIDS), 0.901 vs 0.758 (HIV+ first Seropositivity to Last Assessment incl. death) and 0.832 vs 0.799 (AIDS to Last Assessment incl. death), for the NN & Cox, respectively. In patients with a history of AIDS defining events and with severe T-Cell depletion, mortality occurs despite therapy. Although Neural Networks and Cox modeling were successful in predicting mortality, the Neural Network was superior in assessing risk in this population.
Full text
PDF
Selected References
These references are in PubMed. This may not be the complete list of references from this article.
- Effros R. B., Allsopp R., Chiu C. P., Hausner M. A., Hirji K., Wang L., Harley C. B., Villeponteau B., West M. D., Giorgi J. V. Shortened telomeres in the expanded CD28-CD8+ cell subset in HIV disease implicate replicative senescence in HIV pathogenesis. AIDS. 1996 Jul;10(8):F17–F22. doi: 10.1097/00002030-199607000-00001. [DOI] [PubMed] [Google Scholar]
- Galai N., Margolick J. B., Astemborski J., Vlahov D. Existence and failure of T-cell homeostasis prior to AIDS onset in HIV-infected injection drug users. Clin Immunol Immunopathol. 1996 May;79(2):134–141. doi: 10.1006/clin.1996.0060. [DOI] [PubMed] [Google Scholar]
- Giorgi J. V., Hausner M. A., Hultin L. E. Detailed immunophenotype of CD8+ memory cytotoxic T-lymphocytes (CTL) against HIV-1 with respect to expression of CD45RA/RO, CD62L and CD28 antigens. Immunol Lett. 1999 Mar;66(1-3):105–110. doi: 10.1016/s0165-2478(98)00170-9. [DOI] [PubMed] [Google Scholar]
- Hatzakis G., Tsoukas C. Neural networks in the assessment of HIV immunopathology. Proc AMIA Symp. 2001:249–253. [PMC free article] [PubMed] [Google Scholar]
- Margolick J. B., Donnenberg A. D., Chu C., O'Gorman M. R., Giorgi J. V., Muñoz A. Decline in total T cell count is associated with onset of AIDS, independent of CD4(+) lymphocyte count: implications for AIDS pathogenesis. Clin Immunol Immunopathol. 1998 Sep;88(3):256–263. doi: 10.1006/clin.1998.4577. [DOI] [PubMed] [Google Scholar]
- Margolick J. B., Muñoz A., Donnenberg A. D., Park L. P., Galai N., Giorgi J. V., O'Gorman M. R., Ferbas J. Failure of T-cell homeostasis preceding AIDS in HIV-1 infection. The Multicenter AIDS Cohort Study. Nat Med. 1995 Jul;1(7):674–680. doi: 10.1038/nm0795-674. [DOI] [PubMed] [Google Scholar]