Empiric neurocognitive performance profile discovery and interpretation in HIV infection
The measurement and determinants of HIV-associated neurocognitive disorders (HAND) are under intense debate. We used latent profile analysis (LPA) and machine learning to define neurocognitive performance profiles and identify their associated risk factors in HIV patients receiving antiretroviral therapy (ART). Neurocognitive performance was assessed by a multidomain neuropsychological test battery. LPA was used to define individual neurocognitive profiles. Random forest analyses (RFA) identified the most important factors distinguishing each profile. Three profiles emerged from the LPA: profile 1 (P1, n = 159) achieved the highest performance, while profile 2 (P2, n = 163) had lowered executive functions and verbal memory, and profile 3 (P3, n = 59) was globally impaired. RFA achieved good prediction (area under the curve ≥ 0.80) only for global impairment (P3). Non-North American descent was the dominant predictor of P3, followed by factors coinciding with non-North American descent (female sex and toxoplasma seropositivity). Additional predictors included unemployment, current depressive symptoms, lower nadir CD4, and longstanding HIV. Restricting analyses to North Americans pointed to the additional importance of ART achieving high CSF levels and older age in prediction of P3. HAND diagnoses were most common in the globally impaired profile (P3 = 89.8%), followed by the group with reduced higher-order neurocognitive performance (P2 = 16.6%). Thus, implementation of LPA and RFA empirically distinguished three distinct neurocognitive performance profiles in this HIV-infected cohort while also highlighting potential risk factors and their relative importance to neurocognitive impairment. These data-driven analytical methods pointed to discernible demographic, HIV- and treatment-related risk factor constellations in patients born outside and within North America that might influence diagnostic and therapeutic decisions.
KeywordsHIV-associated neurocognitive disorders Neuropsychology Mixture modeling Machine learning Risk factors
The authors would like to thank the patients and the staff at the Southern Alberta Clinic for their participation in the study. The authors further thank Roger A. Dixon, Kirstie McDermott, and Matthew Johnson for their statistical help.
This study was supported by the Canadian Institutes of Health Research (CIHR) Emerging Team Grant (RFN: 125271) (CP, MJG, EF).
Compliance with ethical standards
The study was approved by the University of Calgary, Conjoint Health Research Ethics Board, CHREB13-0615.
Conflict of interest
The authors declare that they have no conflict of interest.
- Antinori A, Arendt G, Becker JT, Brew BJ, Byrd DA, Cherner M, Clifford DB, Cinque P, Epstein LG, Goodkin K, Gisslen M, Grant I, Heaton RK, Joseph J, Marder K, Marra CM, McArthur JC, Nunn M, Price RW, Pulliam L, Robertson KR, Sacktor N, Valcour V, Wojna VE (2007) Updated research nosology for HIV-associated neurocognitive disorders. Neurology 69:1789–1799CrossRefGoogle Scholar
- Berrett AN, Gale SD, Erickson LD, Brown BL, Hedges DW (2017) Toxoplasma gondii moderates the association between multiple folate-cycle factors and cognitive function in U.S. adults. Nutrients 9:E564Google Scholar
- Bharti AR, McCutchan A, Deutsch R, Smith DM, Ellis RJ, Cherner M, Woods SP, Heaton RK, Grant I, Letendre SL (2016) Latent toxoplasma infection and higher Toxoplasma gondii immunoglobulin G levels are associated with worse neurocognitive functioning in HIV-infected adults. Clin Infect Dis 63:1655–1660CrossRefGoogle Scholar
- Brandt J, Benedict RH (2001) Hopkins Verbal Learning Test - Revised. Psychological Assessment Resources, Inc, LutzGoogle Scholar
- Cherner M, Suarez P, Lazzaretto D, Fortuny LA, Mindt MR, Dawes S, Marcotte T, Grant I, Heaton R, Group H (2007) Demographically corrected norms for the Brief Visuospatial Memory Test - Revised and Hopkins Verbal Learning Test - Revised in monolingual Spanish speakers from the U.S.-Mexico border region. Arch Clin Neuropsychol 22:343–353Google Scholar
- Cysique LA, Heaton RK, Kamminga J, Lane T, Gates TM, Moore DM, Hubner E, Carr A, Brew BJ (2014) HIV-associated neurocognitive disorder in Australia: a case of a high-functioning and optimally treated cohort and implications for international neuroHIV research. J Neurovirol 20:258–268CrossRefGoogle Scholar
- Delis DC, Kaplan E, Kramer JH (2001) Delis-Kaplan Executive Function System (D-KEFS). The Psychological Corporation, San AntonioGoogle Scholar
- Hair JF (2006) Multivariate data analysis, 6th edn. Pearson Prentice Hall, Upper Saddle RiverGoogle Scholar
- Jernigan TL, Archibald SL, Fennema-Notestine C, Taylor MJ, Theilmann RJ, Julaton MD, Notestine RJ, Wolfson T, Letendre SL, Ellis RJ, Heaton RK, Gamst AC, Franklin DR Jr, Clifford DB, Collier AC, Gelman BB, Marra C, JC MA, JA MC, Morgello S, Simpson DM, Grant I, Group C (2011) Clinical factors related to brain structure in HIV: the CHARTER study. J Neurovirol 17:248–257CrossRefGoogle Scholar
- Kongs SK, Thompson LL, Iverson GL, Heaton RK (2000) Winsconsin Card Sorting Test-64 card version. Psychological Assessment Resources, OdessaGoogle Scholar
- Letendre S, Marquie-Beck J, Capparelli E, Best B, Clifford D, Collier AC, Gelman BB, JC MA, JA MC, Morgello S, Simpson D, Grant I, Ellis RJ, CHARTER Group (2008) Validation of the CNS penetration-effectiveness rank for quantifying antiretroviral penetration into the central nervous system. Arch Neurol 65:65–70CrossRefGoogle Scholar
- McGuinness B, Barrett SL, McIlvenna J, Passmore AP, Shorter GW (2015) Predicting conversion to dementia in a memory clinic: a standard clinical approach compared with an empirically defined clustering method (latent profile analysis) for mild cognitive impairment subtyping. Alzheimers Dement (Amst) 1:447–454Google Scholar
- Molsberry SA, Cheng Y, Kingsley L, Jacobson L, Levine AJ, Martin E, Miller EN, Munro CA, Ragin A, Sacktor N, Becker JT, Neuropsychology Working Group of the Multicenter ACS (2018) Neuropsychological phenotypes among men with and without HIV disease in the Multicenter AIDS Cohort Study. AIDS 32:1679–1688Google Scholar
- Muthen BO, Muthen LK (1998-2015) Mplus user’s guide, 7th edn. Muthen & Muthen, Los AngelesGoogle Scholar
- Public Health Agency of Canada (2015) HIV and AIDS in Canada: surveillance report to December 31, 2014. Minister of Public Works and Government Services Canada, OttawaGoogle Scholar
- R Core Team (2017) R: a language and environment for statistical computing. R Foundation for Statistical Computing, ViennaGoogle Scholar
- Rubin LH, Sundermann EE, Cook JA, Martin EM, Golub ET, Weber KM, Cohen MH, Crystal H, Cederbaum JA, Anastos K, Young M, Greenblatt RM, Maki PM (2014) Investigation of menopausal stage and symptoms on cognition in human immunodeficiency virus-infected women. Menopause 21:997–1006CrossRefGoogle Scholar
- Rubin LH, Cook JA, Springer G, Weber KM, Cohen MH, Martin EM, Valcour VG, Benning L, Alden C, Milam J, Anastos K, Young MA, Gustafson DR, Sundermann EE, Maki PM (2017) Perceived and post-traumatic stress are associated with decreased learning, memory, and fluency in HIV-infected women. AIDS 31:2393–1401CrossRefGoogle Scholar
- Sacktor N, Skolasky RL, Seaberg E, Munro C, Becker JT, Martin E, Ragin A, Levine A, Miller E (2016) Prevalence of HIV-associated neurocognitive disorders in the Multicenter AIDS Cohort Study. Neurology 86:334–340Google Scholar
- Schretlen D, Testa SM, Pearlson GD (2010) Calibrated Neuropsychological Normative System. Psychological Assessment Resources, LutzGoogle Scholar
- Smith A (1973) Symbol Digit Modalities Test. Western Psychological Services, Los AngelesGoogle Scholar
- Strobl C, Boulesteix AL, Kneib T, Augustin T, Zeileis A (2008) Conditional variable importance for random forests. BMC Bioinf 9:307Google Scholar
- Tripathi A, Jerrell JM, Liese AD, Zhang J, Rizvi AA, Albrecht H, Duffus WA (2013) Association of clinical and therapeutic factors with incident dyslipidemia in a cohort of human immunodeficiency virus-infected and non-infected adults: 1994-2011. Metab Syndr Relat Disord 11:417–426CrossRefGoogle Scholar
- Trites RL (1977) Grooved Pegboard. Royal Ottawa Hospital, OttawaGoogle Scholar
- Wilkinson GS, Robertson GJ (2006) Wide Range Achievement Test (4th ed.). Psychological Assessment Resources, LutzGoogle Scholar
- Woods SP, Rippeth JD, Frol AB, Levy JK, Ryan E, Soukup VM, Hinkin CH, Lazzaretto D, Cherner M, Marcotte TD, Gelman BB, Morgello S, Singer EJ, Grant I, Heaton RK (2004) Interrater reliability of clinical ratings and neurocognitive diagnoses in HIV. J Clin Exp Neuropsychol 26:759–778CrossRefGoogle Scholar
- Wright EJ, Grund B, Cysique LA, Robertson KR, Brew BJ, Collins G, Shlay JC, Winston A, Read TR, Price RW, International Network for Strategic Initiatives in Global HIVTSSG (2015) Factors associated with neurocognitive test performance at baseline: a substudy of the INSIGHT Strategic Timing of Antiretroviral Treatment (START) trial. HIV Med 16(Suppl 1):97–108CrossRefGoogle Scholar