Cognitive and Neuropsychiatric Features of COVID-19 Patients After Hospital Dismission: An Italian Sample.

Background and Aims: Recent studies suggest cognitive, emotional, and behavioral impairments occur in patients after SARS-CoV-2 infection. However, studies are limited to case reports or case series and, to our knowledge, few of them have control groups. This study aims to assess the prevalence of neuropsychological and neuropsychiatric impairment in patients after hospitalization. Methods: We enrolled 29 COVID+ patients (M/F: 17/12; age 58.41 ± 10.00 years; education 11.07 ± 3.77 years, 2 left handers) who needed hospitalization but no IC, about 20 days post-dismission, and 29 COVID- healthy matched controls. Neuropsychological and neuropsychiatric assessments were conducted via teleneuropsychology using the following tests: MMSE, CPM47, RAVLT, CDT, Digit-Span Forward/Backward, Verbal fluencies; BDI-II, STAI. People with previous reported cognitive impairment and neurological or psychiatric conditions were excluded. Clinical and demographics were collected. Comparison between groups was conducted using parametric or non-parametric tests according to data distribution (T-test, Mann Withney-U test; Chi-square goodness of fit). Within COVID+ group, we also evaluated the correlation between the cognitive and behavioral assessment scores and clinical variables collected. Results: Among COVID+, 62% had at least one pathological test (vs. 13% in COVID-; p = 0.000) and significantly worst performances than COVID- in RAVLT learning (42.55 ± 10.44 vs. 47.9 ± 8.29, p = 0.035), RAVLT recall (8.79 ± 3.13 vs. 10.38 ± 2.19, p = 0.03), and recognition (13.69 ± 1.47 vs. 14.52 ± 0.63, p = 0.07). STAI II was higher in COVID- (32.69 ± 7.66 vs. 39.14 ± 7.7, p = 0.002). Chi-square on dichotomous values (normal/pathological) showed a significant difference between groups in Digit backward test (pathological 7/29 COVID+ vs. 0/29 COVID-; p = 0.005). Conclusions: Patients COVID+ assessed by teleneuropsychology showed a vulnerability in some memory and executive functions (working memory, learning, delayed recall, and recognition). Intriguingly, anxiety was higher in the control group. Our findings therefore confirm the impact of COVID-19 on cognition even in patients who did not need IC. Follow-up is needed to evaluate the evolution of COVID-19-related cognitive deficit. Clinical Trial Registration: [ClinicalTrials.gov], identifier [NCT05143320].

Optimization of cognitive assessment in Parkinsonisms by applying artificial intelligence to a comprehensive screening test.

The assessment of cognitive deficits is pivotal for diagnosis and management in patients with parkinsonisms. Low levels of correspondence are observed between evaluations assessed with screening cognitive tests in comparison with those assessed with in-depth neuropsychological batteries. A new tool, we named CoMDA (Cognition in Movement Disorders Assessment), was composed by merging Mini-Mental State Examination (MMSE), Montreal Cognitive Assessment (MoCA), and Frontal Assessment Battery (FAB). In total, 500 patients (400 with Parkinson's disease, 41 with vascular parkinsonism, 31 with progressive supranuclear palsy, and 28 with multiple system atrophy) underwent CoMDA (level 1-L1) and in-depth neuropsychological battery (level 2-L2). Machine learning was developed to classify the CoMDA score and obtain an accurate prediction of the cognitive profile along three different classes: normal cognition (NC), mild cognitive impairment (MCI), and impaired cognition (IC). The classification accuracy of CoMDA, assessed by ROC analysis, was compared with MMSE, MoCA, and FAB. The area under the curve (AUC) of CoMDA was significantly higher than that of MMSE, MoCA and FAB (p < 0.0001, p = 0.028 and p = 0.0007, respectively). Among 15 different algorithmic methods, the Quadratic Discriminant Analysis algorithm (CoMDA-ML) showed higher overall-metrics performance levels in predictive performance. Considering L2 as a 3-level continuous feature, CoMDA-ML produces accurate and generalizable classifications: micro-average ROC curve, AUC = 0.81; and AUC = 0.85 for NC, 0.67 for MCI, and 0.83 for IC. CoMDA and COMDA-ML are reliable and time-sparing tools, accurate in classifying cognitive profile in parkinsonisms.This study has been registered on ClinicalTrials.gov (NCT04858893).