Search

Background: In the older general population, neurodegenerative diseases (NDs) are associated with increased disability, decreased physical and cognitive function. Detecting risk factors can help implement prevention measures. Using deep neural networks (DNNs), a machine-learning algorithm could be an alternative to Cox regression in tabular datasets with many predictive features. We aimed to compare the performance of different types of DNNs with regularized Cox proportional hazards models to predict NDs in the older general population. Methods: We performed a longitudinal analysis with participants of the English Longitudinal Study of Ageing. We included men and women with no NDs at baseline, aged 60 years and older, assessed every 2 years from 2004 to 2005 (wave2) to 2016–2017 (wave 8). The features were a set of 91 epidemiological and clinical baseline variables. The outcome was new events of Parkinson's, Alzheimer or dementia. After applying multiple imputations, we trained three DNN algorithms: Feedforward, TabTransformer, and Dense Convolutional (Densenet). In addition, we trained two algorithms based on Cox models: Elastic Net regularization (CoxEn) and selected features (CoxSf). Results: 5433 participants were included in wave 2. During follow-up, 12.7% participants developed NDs. Although the five models predicted NDs events, the discriminative ability was superior using TabTransformer (Uno's C-statistic (coefficient (95% confidence intervals)) 0.757 (0.702, 0.805). TabTransformer showed superior time-dependent balanced accuracy (0.834 (0.779, 0.889)) and specificity (0.855 (0.0.773, 0.909)) than the other models. With the CoxSf (hazard ratio (95% confidence intervals)), age (10.0 (6.9, 14.7)), poor hearing (1.3 (1.1, 1.5)) and weight loss 1.3 (1.1, 1.6)) were associated with a higher DNN risk. In contrast, executive function (0.3 (0.2, 0.6)), memory (0, 0, 0.1)), increased gait speed (0.2, (0.1, 0.4)), vigorous physical activity (0.7, 0.6, 0.9)) and higher BMI (0.4 (0.2, 0.8)) were associated with a lower DNN risk. Conclusion: TabTransformer is promising for prediction of NDs with heterogeneous tabular datasets with numerous features. Moreover, it can handle censored data. However, Cox models perform well and are easier to interpret than DNNs. Therefore, they are still a good choice for NDs. [ABSTRACT FROM AUTHOR]

B Correction: BMC Medical Research Methodology 23, 8 (2023) b B https://doi.org/10.1186/s12874-023-01837-4 b Following publication of the original article [[1]], the author requested to change the funding source section in the article. Reference 1 Aguayo GA, Zhang L, Vaillant M. Machine learning for predicting neurodegenerative diseases in the general older population: a cohort study. [Extracted from the article]

Objectives: This study aimed to assess the prevalence of dementia and cognitive complaints in a cross-sectional sample of Luxembourg seniors, and to discuss the results in the societal context of high cognitive reserve resulting from multilingualism. Methods: A population sample of 1,377 people representative of Luxembourg residents aged over 64 years was initially identified via the national social insurance register. There were three different levels of contribution: full participation in the study, partial participation, and non-participation. We examined the profiles of these three different samples so that we could infer the prevalence estimates in the Luxembourgish senior population as a whole using the prevalence estimates obtained in this study. Results: After careful attention to the potential bias and of the possibility of underestimation, we considered the obtained prevalence estimates of 3.8% for dementia (with corresponding 95% confidence limits (CL) of 2.8% and 4.8%) and 26.1% for cognitive complaints (CL = [17.8–34.3]) as trustworthy. Conclusion: Based on these findings, we postulate that high cognitive reserve may result in surprisingly low prevalence estimates of cognitive complaints and dementia in adults over the age of 64 years, which thereby corroborates the longer disability-free life expectancy observed in the Luxembourg population. To the best of our knowledge, this study is the first to report such Luxembourgish public health data. [ABSTRACT FROM AUTHOR]

Objective: Investigate the protective effect of multilingualism on cognition in seniors. Methods: As part of the MemoVie study conducted on 232 non-demented volunteers aged 65 and more, neurogeriatric and neuropsychological evaluations were performed. Participants were classified as presenting either cognitive impairment without dementia (CIND) or being free of any cognitive impairment (CIND-free). Language practices, socio-demographic data and lifestyle habits were recorded. In this retrospective nested case-control design, we used as proxies of multilingualism: number of languages practiced, age of acquisition and duration of practice, emphasizing the temporal pattern of acquisition, and the resulting practice of several languages sequentially or concomitantly during various periods of life. This special angle on the matter offered to our work a dimension particularly original and innovative. Results: 44 subjects (19%) had CIND, the others were cognitively normal. All practiced from 2 to 7 languages. When compared with bilinguals, participants who practiced more than 2 languages presented a lower risk of CIND, after adjustment for education and age (odds ratio (OR) = 0.30, 95% confidence limits (95%CL) = [0.10–0.92]). Progressing from 2 to 3 languages, instead of staying bilingual, was associated with a 7-fold protection against CIND (OR = 0.14, 95%CL = [0.04–0.45], p = 0.0010). A one year delay to reach multilingualism (3 languages practiced being the threshold) multiplied the risk of CIND by 1.022 (OR = 1.022, 95%CL = [1.01–1.04], p = 0.0044). Also noteworthy, just as for multilingualism, an impact of cognitively stimulating activities on the occurrence of CIND was found as well (OR = 0.979, 95%CL = [0.961–0.998], p = 0.033). Conclusion: The study did not show independence of multilingualism and CIND. Rather it seems to show a strong association toward a protection against CIND. Practicing multilingualism from early life on, and/or learning it at a fast pace is even more efficient. This protection might be related to the enhancement of cognitive reserve and brain plasticity, thereby preserving brain functions from alterations during aging. [ABSTRACT FROM AUTHOR]

Background: Cognitive impairment and Alzheimer's disease (AD) are increasingly considered a major public health problem. The MemoVie cohort study aims to investigate the living conditions or risk factors under which the normal cognitive capacities of the senior population in Luxembourg (≥ 65 year-old) evolve (1) to mild cognitive impairment (MCI)--transitory non-clinical stage--and (2) to AD. Identifying MCI and AD predictors undeniably constitutes a challenge in public health in that it would allow interventions which could protect or delay the occurrence of cognitive disorders in elderly people. In addition, the MemoVie study sets out to generate hitherto unavailable data, and a comprehensive view of the elderly population in the country. Methods/design: The study has been designed with a view to highlighting the prevalence in Luxembourg of MCI and AD in the first step of the survey, conducted among participants selected from a random sample of the general population. A prospective cohort is consequently set up in the second step, and appropriate follow-up of the non-demented participants allows improving the knowledge of the preclinical stage of MCI. Case-control designs are used for cross-sectional or retrospective comparisons between outcomes and biological or clinical factors. To ensure maximal reliability of the information collected, we decided to opt for structured face to face interviews. Besides health status, medical and family history, demographic and socio-cultural information are explored, as well as education, habitat network, social behavior, leisure and physical activities. As multilingualism is expected to challenge the cognitive alterations associated with pathological ageing, it is additionally investigated. Data relative to motor function, including balance, walk, limits of stability, history of falls and accidents are further detailed. Finally, biological examinations, including ApoE genetic polymorphism are carried out. In addition to standard blood parameters, the lipid status of the participants is subsequently determined from the fatty acid profiles in their red blood cells. The study obtained the legal and ethical authorizations. Discussion: By means of the multidisciplinary MemoVie study, new insights into the onset of cognitive impairment during aging should be put forward, much to the benefit of intervention strategies as a whole. [ABSTRACT FROM AUTHOR]

Purpose: The glutathione detoxification pathway includes glutathione S-transferase (GST) and peroxidase (GPX) isoenzymes as well as glutathione reductase (GSSR). Though well established from cultured cancer cell lines, its involvement in resistance is still unclear in the tumours. This study aimed to describe the parameters that influence the glutathione contents and associated activities in breast cancer. Methods: The components of the glutathione pathway were measured in the tumours from 41 women with primary breast cancer in comparison with those in the matched tumour-free samples. Appropriate statistical studies (regression analysis, Wilcoxon signed rank test) explored the influence of clinical and prognostic factors. Results: Reduced and total glutathione contents were largely increased ( P < 0.0001) and all related activities were significantly enhanced in the tumours. Interindividual variations were described, probably due to various parameters (age, menopause, axillary lymph node status, S and G2 + M cell fractions, ER, cathepsin-D and c-ErbB-2 expressions) that influence particular components of the glutathione pathway, especially the glutathione levels. Conclusions: The breast tumours improved their redox status and detoxification capacities depending on various parameters of significance for cell proliferation and aggressiveness, which supports the involvement of the glutathione pathway in malignant cell resistance to oxidative stress and apoptosis. [ABSTRACT FROM AUTHOR]