Premium
Cognitive Performance Scores for the Pediatric Automated Neuropsychological Assessment Metrics in Childhood‐Onset Systemic Lupus Erythematosus
Author(s) -
VegaFernandez Patricia,
Vanderburgh White Shana,
Zelko Frank,
Ruth Natasha M.,
Levy Deborah M.,
Muscal Eyal,
KleinGitelman Marisa S.,
Huber Adam M.,
Tucker Lori B.,
RoebuckSpencer Tresa,
Ying Jun,
Brunner Hermine I.
Publication year - 2015
Publication title -
arthritis care and research
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.032
H-Index - 163
eISSN - 2151-4658
pISSN - 2151-464X
DOI - 10.1002/acr.22571
Subject(s) - neurocognitive , cognition , logistic regression , receiver operating characteristic , neuropsychology , effects of sleep deprivation on cognitive performance , medicine , psychology , statistics , artificial intelligence , machine learning , computer science , mathematics , psychiatry
Objective To develop and initially validate a global cognitive performance score (CPS) for the Pediatric Automated Neuropsychological Assessment Metrics (PedANAM) to serve as a screening tool of cognition in childhood lupus. Methods Patients (n = 166) completed the 9 subtests of the PedANAM battery, each of which provides 3 principal performance parameters (accuracy, mean reaction time for correct responses, and throughput). Cognitive ability was measured by formal neurocognitive testing or estimated by the Pediatric Perceived Cognitive Function Questionnaire‐43 to determine the presence or absence of neurocognitive dysfunction (NCD). A subset of the data was used to develop 4 candidate PedANAM‐CPS indices with supervised or unsupervised statistical approaches: PedANAM‐CPS UWA , i.e., unweighted averages of the accuracy scores of all PedANAM subtests; PedANAM‐CPS PCA , i.e., accuracy scores of all PedANAM subtests weighted through principal components analysis; PedANAM‐CPS logit , i.e., algorithm derived from logistic models to estimate NCD status based on the accuracy scores of all of the PedANAM subtests; and PedANAM‐CPS multiscore , i.e., algorithm derived from logistic models to estimate NCD status based on select PedANAM performance parameters. PedANAM‐CPS candidates were validated using the remaining data. Results PedANAM‐CPS indices were moderately correlated with each other (|r| > 0.65). All of the PedANAM‐CPS indices discriminated children by NCD status across data sets ( P < 0.036). The PedANAM‐CPS multiscore had the highest area under the receiver operating characteristic curve (AUC) across all data sets for identifying NCD status (AUC >0.74), followed by the PedANAM‐CPS logit , the PedANAM‐CPS PCA , and the PedANAM‐CPS UWA , respectively. Conclusion Based on preliminary validation and considering ease of use, the PedANAM‐CPS multiscore and the PedANAM‐CPS PCA appear to be best suited as global measures of PedANAM performance.