Disentangling the relationship of subjective cognitive decline and depressive symptoms in the development of cognitive decline and dementia.

INTRODUCTION: Subjective cognitive decline (SCD) and depressive symptoms (DS) frequently co-occur prior to dementia. However, the temporal sequence of their emergence and their combined prognostic value for cognitive decline and dementia is unclear. METHODS: Temporal relationships of SCD, DS and memory decline were examined by latent difference score modeling in a high-aged, population-based cohort (N = 3217) and validated using Cox-regression of dementia-conversion. In 334 cognitively unimpaired SCD-patients from memory-clinics, we examined the association of DS with cognitive decline and with cerebrospinal fluid (CSF) Alzheimer's disease (AD) biomarkers. RESULTS: In the population-based cohort, SCD preceded DS. High DS were associated with increased risk of dementia conversion in individuals with SCD. In SCD-patients from memory-clinics, high DS were associated with greater cognitive decline. CSF Aß42 predicted increasing DS. DISCUSSION: SCD typically precedes DS in the evolution to dementia. SCD-patients from memory-clinics with DS may constitute a high-risk group for cognitive decline. HIGHLIGHTS: Subjective cognitive decline (SCD) precedes depressive symptoms (DS) as memory declines. Emerging or persistent DS after SCD reports predict dementia. In SCD patients, more amyloid pathology relates to increasing DS. SCD patients with DS are at high risk for symptomatic progression.

Extending DeepTrio for sensitive detection of complex de novo mutation patterns.

De novo mutations (DNMs), and among them clustered DNMs within 20 bp of each other (cDNMs) are known to be a potential cause of genetic disorders. However, identifying DNM in whole genome sequencing (WGS) data is a process that often suffers from low specificity. We propose a deep learning framework for DNM and cDNM detection in WGS data based on Google's DeepTrio software for variant calling, which considers regions of 110 bp up- and downstream from possible variants to take information from the surrounding region into account. We trained a model each for the DNM and cDNM detection tasks and tested it on data generated on the HiSeq and NovaSeq platforms. In total, the model was trained on 82 WGS trios generated on the NovaSeq and 16 on the HiSeq. For the DNM detection task, our model achieves a sensitivity of 95.7% and a precision of 89.6%. The extended model adds confidence information for cDNMs, in addition to standard variant classes and DNMs. While this causes a slight drop in DNM sensitivity (91.96%) and precision (90.5%), on HG002 cDNMs can be isolated from other variant classes in all cases (5 out of 5) with a precision of 76.9%. Since the model emits confidence probabilities for each variant class, it is possible to fine-tune cutoff thresholds to allow users to select a desired trade-off between sensitivity and specificity. These results show that DeepTrio can be retrained to identify complex mutational signatures with only little modification effort.

A dynamic ensemble model for short-term forecasting in pandemic situations.

During the COVID-19 pandemic, many hospitals reached their capacity limits and could no longer guarantee treatment of all patients. At the same time, governments endeavored to take sensible measures to stop the spread of the virus while at the same time trying to keep the economy afloat. Many models extrapolating confirmed cases and hospitalization rate over short periods of time have been proposed, including several ones coming from the field of machine learning. However, the highly dynamic nature of the pandemic with rapidly introduced interventions and new circulating variants imposed non-trivial challenges for the generalizability of such models. In the context of this paper, we propose the use of ensemble models, which are allowed to change in their composition or weighting of base models over time and could thus better adapt to highly dynamic pandemic or epidemic situations. In that regard, we also explored the use of secondary metadata-Google searches-to inform the ensemble model. We tested our approach using surveillance data from COVID-19, Influenza, and hospital syndromic surveillance of severe acute respiratory infections (SARI). In general, we found ensembles to be more robust than the individual models. Altogether we see our work as a contribution to enhance the preparedness for future pandemic situations.

Minor neuropsychological deficits in patients with subjective cognitive decline.

OBJECTIVE: To determine the nature and extent of minor neuropsychological deficits in patients with subjective cognitive decline (SCD) and their association with CSF biomarkers of Alzheimer disease (AD). METHOD: We analyzed data from n = 449 cognitively normal participants (n = 209 healthy controls, n = 240 patients with SCD) from an interim data release of the German Center for Neurodegenerative Diseases Longitudinal Cognitive Impairment and Dementia Study (DELCODE). An extensive neuropsychological test battery was applied at baseline for which we established a latent, 5 cognitive domain factor structure comprising learning and memory, executive functions, language abilities, working memory, and visuospatial functions. We compared groups in terms of global and domain-specific performance and correlated performance with different CSF markers of AD pathology. RESULTS: We observed worse performance (Cohen d = ≈0.25-0.5, adjusted for age, sex differences with analysis of covariance) in global performance, memory, executive functions, and language abilities for the SCD group compared to healthy controls. In addition, worse performance in these domains was moderately (r = ≈0.3) associated with lower CSF ß-amyloid42/40 and CSF ß-amyloid42/phosphorylated tau181 in the whole sample and specifically in the SCD subgroup. CONCLUSIONS: Within the spectrum of clinically unimpaired (i.e., before mild cognitive impairment) cognitive performance, SCD is associated with minor deficits in memory, executive function, and language abilities. The association of these subtle cognitive deficits with AD CSF biomarkers speaks to their validity and potential use for the early detection of underlying preclinical AD.