Search

Mild cognitive impairment in Parkinson's disease (PD-MCI) includes deficits in different cognitive domains, and one domain to explore for neurocognitive impairment following the DSM-V is social cognition. However, this domain is not included in current criteria for PD-MCI diagnosis. Moreover, tests vary across studies. It is, therefore, crucial to optimize cognitive assessment in PD-MCI. We aimed to do so by using Machine Learning. 275 PD patients were included. Four cognitive batteries were created: two Standard ones (Levels I and II), applying current criteria and "traditional" tests; two Alternative ones (Levels I and II), which incorporated a test of social cognition. These batteries were included in the Random Forest (RF) classifier. To assess RF performance, the AUC was considered, and the Variable Importance Index was estimated to understand the contribution of each test in PD-MCI classification. Standard Level I and II showed an AUC of 0.852 and 0.892, while Alternative Level I and II showed an AUC of 0.898 and of 0.906. Variable Importance Index revealed that TMT B-A, Ekman test, RAVLT-IR, MoCA, and Action Naming were tests that most contributed to PD-MCI classification. The Alternative level I assessment demonstrated a similar classification capacity to the Standard level II assessment. This finding suggests that in the cognitive assessment of PD patients, it is crucial to consider the most affected cognitive domains in this clinical population, including social cognition. Taken together, these results suggest to revise current criteria for the diagnosis of PD-MCI. • The first study that employs Machine Learning (ML) for classifying PD-MCI patients. • The social cognition test is among the tests that best classify PD-MCI patients. • The results highlights the importance of including social cognition into the assessment of PD patients. [ABSTRACT FROM AUTHOR]

Introduction: Patients with obstructive sleep apnea (OSA) suffer from several neurocognitive deficits. We investigated the cognitive and socio-cognitive profiles of patients with severe OSA, controlling for potentially relevant mediating variables (i.e. age, body-mass index, cognitive reserve and depression). Moreover, we studied the neuropsychological profile of a high-risk OSA phenotype characterized by severe OSA and severe nocturnal hypoxemia. Method: We assessed 29 previously untreated severe OSA patients with a mean age of 55.6 (± 9.9 years) and a mean apnea-hypopnea index (AHI) of 53.1 (± 17.4). A control group of 34 healthy participants was also enrolled. Participants completed an extensive neuropsychological battery that included social cognition, a relatively new investigation area among OSA patients. Data analysis: Data were analyzed with a Bayesian approach. Specifically, Bayesian ANCOVA was used to investigate whether the grouping variable could predict test performance. Age, body-mass index, cognitive reserve and state of depression were added as covariates to the null model to weight the effects of these potential confounding factors. Three groups were analyzed: healthy controls (H), OSA with severe apnea and severe nocturnal oxygen desaturation (D+), and OSA with severe apnea non-desaturators (D−). Performances on the various neuropsychological tests were treated as the dependent variables. Results: The results indicate that non-verbal reasoning, the theory of mind skills, and mental shifting ability were impaired in OSA patients. Patients with severe nocturnal hypoxemia underperformed compared to patients with the same severity of apnea but non-desaturators. Additionally, we observed a trend toward a worse performance among OSA desaturator patients in the following abilities: constructional ability, short term verbal memory, phonological fluency, and the ability to inhibit automatic and dominant responses. Conclusion: The data suggest a key role of hypoxemia in affecting cognitive functioning in OSA patients. Executive functions and the concomitant involvement of social cognition are particularly affected. [ABSTRACT FROM AUTHOR]