Depression and Suicide Risk in Mild Cognitive Impairment: The Role of Alzheimer's Disease Biomarkers.

BACKGROUND: Patients with depression and mild cognitive impairment (MCI) are at greater risk of developing dementia. Depression involves a higher risk of suicidal ideation (SI) and suicide attempts (SA). Biomarkers of Alzheimer's Disease (AD) could help to clarify the role of depression and SI in AD. METHOD: Fifty-nine participants aged > 50 with criteria of MCI positive (MCI-AD) (n=22) and negative (MCI-Non AD) (n=24) AD and healthy controls (HC) (n=13) were evaluated. We used the Geriatric Depression Scale (GDS-30) and the GDS-SI factor to measure depression and indirect risk for suicide, respectively. Additionally, AD biomarkers such as amyloid-ß (Aß), hyperphosphorilated tau (P-tau), and total tau (T-tau) in cerebrospinal fluid (CSF) were analyzed. RESULTS: No significant differences between the groups were found in depression. However, in the MCI-AD group, lower P-tau and T-tau levels were related to higher GDS-SI scores, suggesting that MCI-AD patients with lower AD pathology are at a higher risk of suicide. CONCLUSIONS: The result highlights the importance of considering SI in the initial phases of AD, and the potential role of AD biomarkers in early detection of symptoms.

Obstructive sleep apnea and Alzheimer's disease-related cerebrospinal fluid biomarkers in mild cognitive impairment.

Previous studies have demonstrated that sleep-breathing disorders, and especially obstructive sleep apnea (OSA), can be observed in patients with a higher risk of progression to Alzheimer's disease (AD). Recent evidence indicates that cerebrospinal fluid (CSF) AD-biomarkers are associated with OSA. In this study, we investigated these associations in a sample of patients with mild cognitive impairment (MCI), a condition that is considered the first clinical phase of AD, when patients showed biomarkers consistent with AD pathology. A total of 57 patients (mean age = 66.19; SD = 7.13) with MCI were included in the study. An overnight polysomnography recording was used to assess objective sleep parameters (i.e. apnea/hypopnea index [AHI], total sleep time, sleep efficiency, sleep latency, arousal index, awakening, stage 1, 2, and slow-wave sleep and rapid eye movement sleep, periodic limb movement index, O2 saturation during sleep, and percentage of time O2 saturation <90%). Phosphorylated-tau (P-tau), total-tau (T-tau), and amyloid-beta 42 (Aß42) were measured in CSF. Unadjusted correlation analyses showed that a higher AHI (reflecting higher OSA severity) was related to higher P-tau and T-tau (both results remained significant after Bonferroni correction, p = 0.001). Importantly, these associations were observed even after adjusting for potential confounders (i.e. age, sex, body mass index, sleep medication, smoking, hypertension, and heart disease). Although more research is needed to establish a causal link, our findings provide evidence that OSA could be related to the pathophysiological mechanisms involved in neurodegeneration in MCI patients.

Probabilistic Distance for Mixtures of Independent Component Analyzers.

Independent component analysis (ICA) is a blind source separation technique where data are modeled as linear combinations of several independent non-Gaussian sources. The independence and linear restrictions are relaxed using several ICA mixture models (ICAMMs) obtaining a two-layer artificial neural network structure. This allows for dependence between sources of different classes, and thus, a myriad of multidimensional probability density functions can be accurate modeled. This paper proposes a new probabilistic distance (PDI) between the parameters learned for two ICAMMs. The PDI is computed explicitly, unlike the popular Kullback-Leibler divergence (KLD) and other similar metrics, removing the need for numerical integration. Furthermore, the PDI is symmetric and bounded within 0 and 1, which enables its use as a posterior probability in fusion approaches. In this paper, the PDI is employed for change detection by measuring the distance between two ICAMMs learned in consecutive time windows. The changes might be associated with relevant states from a process under analysis that are explicitly reflected in the learned ICAMM parameters. The proposed distance was tested in two challenging applications using simulated and real data: 1) detecting flaws in materials using ultrasounds and 2) detecting changes in electroencephalography signals from humans performing neuropsychological tests. The results demonstrate that the PDI outperforms the KLD in change-detection capabilities.