Artificial neural networks analysis of polysomnographic and clinical features in pediatric acute-onset neuropsychiatric syndrome (Pans): From sleep alteration to “brain fog”

Abstract

Study Objectives: PANS (pediatric acute onset neuropsychiatric syndrome) is thought to be the result of several mechanisms and multiple etiologies, ranging from endocrine/meta-bolic causes to postinfectious autoimmune and neuroinflammatory disorders. Sleep disorders represent one of the most frequent manifestations of PANS, involving around 80% of patients. The present study describes the clinical and polysomnographic features in a group of PANS children identifying the relationships between sleep disorders and other PANS symptoms. Methods: All participants underwent a clinical evaluation including comprehensive sleep history, polysomnography, cognitive assessment and blood chemistry examination. A data mining approach with fourth-generation artificial neural networks has been used in order to discover subtle trends and associations among variables. Results: Polysomnography showed abnormality in 17 out of 23 recruited subjects (73.9%). In particular, 8/17 children (47%) had ineffective sleep, 10/17 (58.8%) fragmented sleep, 8/ 17 (47.1%) periodic limb movement disorder (PLMD) and 11/17 (64.7%) REM-sleep without atonia (RSWA). Most subjects presented more than one sleep disturbances. Notably, among the 19/23 patients diagnosed with Tic/Tourette disorder, 8/19 (42.1%) show PLMD and 10/19 (52.6%) RSWA. Artificial neural network methodology and the auto-contractive map exploited the links among the full spectrum of variables revealing the simultaneous connections among them, facing the complexity of PANS phenotype. Conclusion: Disordered sleep represents, for prevalence and impact on quality of life, a cardinal symptom in patients with PANS. Thus, considering the weight of sleep disturbances on diagnosis and prognosis of PANS, we could consider the possibility of including them among the major diagnostic criteria.