BACKGROUND: Deep learning algorithms of cerebral blood flow were used to classify cognitive impairment and frailty in people living with HIV (PLWH). Feature extraction techniques identified brain regions that were the strongest predictors. SETTING: Virologically suppressed (<50 copies/mL) PLWH (n = 125) on combination antiretroviral therapy were enrolled. Participants averaged 51.4 (11.4) years of age and 13.7 (2.8) years of education. Participants were administered a neuropsychological battery, assessed for frailty, and completed structural neuroimaging. METHODS: Deep neural network (DNN) models were trained to classify PLWH as cognitively unimpaired or impaired based on neuropsychological tests (Hopkins Verbal Learning Test-Revised and Brief Visuospatial Memory Test-Revised, Trail making, Letter-Number Sequencing, Verbal Fluency, and Color Word Interference), as well as frail, prefrail, or nonfrail based on the Fried phenotype criteria (at least 3 of the following 5: weight loss, physical inactivity, exhaustion, grip strength, walking time). RESULTS: DNNs classified individuals with cognitive impairment in the learning, memory, and executive domains with 82%-86% accuracy (0.81-0.87 AUC). Our model classified nonfrail, prefrail, and frail PLWH with 75% accuracy. The strongest predictors of cognitive impairment were cortical (parietal, occipital, and temporal) and subcortical (amygdala, caudate, and hippocampus) regions, whereas the strongest predictors of frailty were subcortical (amygdala, caudate, hippocampus, thalamus, pallidum, and cerebellum). CONCLUSIONS: DNN models achieved high accuracy in classifying cognitive impairment and frailty status in PLWH. Feature selection algorithms identified predictive regions in each domain and identified overlapping regions between cognitive impairment and frailty. Our results suggest frailty in HIV is primarily subcortical, whereas cognitive impairment in HIV involves subcortical and cortical brain regions.
BACKGROUND:Deep learning algorithms of cerebral blood flow were used to classify cognitive impairment and frailty in people living with HIV (PLWH). Feature extraction techniques identified brain regions that were the strongest predictors. SETTING: Virologically suppressed (<50 copies/mL) PLWH (n = 125) on combination antiretroviral therapy were enrolled. Participants averaged 51.4 (11.4) years of age and 13.7 (2.8) years of education. Participants were administered a neuropsychological battery, assessed for frailty, and completed structural neuroimaging. METHODS: Deep neural network (DNN) models were trained to classify PLWH as cognitively unimpaired or impaired based on neuropsychological tests (Hopkins Verbal Learning Test-Revised and Brief Visuospatial Memory Test-Revised, Trail making, Letter-Number Sequencing, Verbal Fluency, and Color Word Interference), as well as frail, prefrail, or nonfrail based on the Fried phenotype criteria (at least 3 of the following 5: weight loss, physical inactivity, exhaustion, grip strength, walking time). RESULTS: DNNs classified individuals with cognitive impairment in the learning, memory, and executive domains with 82%-86% accuracy (0.81-0.87 AUC). Our model classified nonfrail, prefrail, and frail PLWH with 75% accuracy. The strongest predictors of cognitive impairment were cortical (parietal, occipital, and temporal) and subcortical (amygdala, caudate, and hippocampus) regions, whereas the strongest predictors of frailty were subcortical (amygdala, caudate, hippocampus, thalamus, pallidum, and cerebellum). CONCLUSIONS: DNN models achieved high accuracy in classifying cognitive impairment and frailty status in PLWH. Feature selection algorithms identified predictive regions in each domain and identified overlapping regions between cognitive impairment and frailty. Our results suggest frailty in HIV is primarily subcortical, whereas cognitive impairment in HIV involves subcortical and cortical brain regions.
Authors: Catherine L Carey; Steven Paul Woods; Raul Gonzalez; Emily Conover; Thomas D Marcotte; Igor Grant; Robert K Heaton Journal: J Clin Exp Neuropsychol Date: 2004-05 Impact factor: 2.475
Authors: Sanna Gevers; Matthias J van Osch; Reinoud P H Bokkers; Dennis A Kies; Wouter M Teeuwisse; Charles B Majoie; Jeroen Hendrikse; Aart J Nederveen Journal: J Cereb Blood Flow Metab Date: 2011-02-09 Impact factor: 6.200
Authors: Marc A Norman; David J Moore; Michael Taylor; Donald Franklin; Lucette Cysique; Chris Ake; Deborah Lazarretto; Florin Vaida; Robert K Heaton Journal: J Clin Exp Neuropsychol Date: 2011-06-24 Impact factor: 2.475
Authors: K Robertson; H Jiang; S R Evans; C M Marra; B Berzins; J Hakim; N Sacktor; M Tulius Silva; T B Campbell; A Nair; J Schouten; J Kumwenda; K Supparatpinyo; S Tripathy; N Kumarasamy; A la Rosa; S Montano; A Mwafongo; C Firnhaber; I Sanne; L Naini; F Amod; A Walawander Journal: J Neurovirol Date: 2016-01-05 Impact factor: 2.643
Authors: Loic Desquilbet; Lisa P Jacobson; Linda P Fried; John P Phair; Beth D Jamieson; Marcy Holloway; Joseph B Margolick Journal: J Gerontol A Biol Sci Med Sci Date: 2007-11 Impact factor: 6.053
Authors: Arpi S Terzian; Susan Holman; Niyati Nathwani; Esther Robison; Kathleen Weber; Mary Young; Ruth M Greenblatt; Stephen J Gange Journal: J Womens Health (Larchmt) Date: 2009-12 Impact factor: 2.681
Authors: Robert H Paul; Kyu S Cho; Patrick Luckett; Jeremy F Strain; Andrew C Belden; Jacob D Bolzenius; Jaimie Navid; Paola M Garcia-Egan; Sarah A Cooley; Julie K Wisch; Anna H Boerwinkle; Dimitre Tomov; Abel Obosi; Julie A Mannarino; Beau M Ances Journal: J Acquir Immune Defic Syndr Date: 2020-08-01 Impact factor: 3.731
Authors: Michelle Glans; Sarah A Cooley; Florin Vaida; Anna Boerwinkle; Dimitre Tomov; Kalen J Petersen; Alexander Rosenow; Robert H Paul; Beau M Ances Journal: J Acquir Immune Defic Syndr Date: 2022-05-01 Impact factor: 3.771