Dataset Information

Social determinants of the association among cerebrovascular disease, hearing loss and cognitive impairment in a middle-aged or older population: Recurrent neural network analysis of the Korean Longitudinal Study of Aging (2014-2016).

ABSTRACT:

Aim

The present study used a deep learning model (recurrent neural network) for testing: (i) whether social determinants are major determinants of the association among cerebrovascular disease, hearing loss and cognitive impairment in a middle-aged or older population (hypothesis?1); and (ii) whether the association among the three diseases is very strong in the middle-aged or older population (hypothesis?2).

Methods

Data came from the Korean Longitudinal Study of Aging (2014-2016), with 6060 participants aged ?53?years. The association among the three diseases was divided into eight categories: one category for having no disease, three categories for having one disease, three categories for having two diseases and one category for having three diseases. Variable importance, the effect of a variable on model performance, was used for evaluating the two hypotheses. Hypothesis 1 was based on whether family support, socioeconomic status and social activity in the year 2014 were the top 10 determinants of the association in the year 2016. Hypothesis 2 was based on whether cerebrovascular disease, hearing loss and cognitive impairment in the year 2014 were the top five determinants of the association in the year 2016.

Results

Based on variable importance from the recurrent neural network, cerebrovascular disease (0.0386), cognitive impairment (0.0151) and hearing loss (0.0092) in 2014 were the top three determinants of the association in 2016. Children alive (0.0072), education (0.0049), income (0.0075), friendship activity (0.0042) and marriage (0.0036) in 2014 were the top 10 determinants of the association in 2016.

Conclusions

The findings of the present study support the two hypotheses, highlighting the importance of preventive measures, family support, socioeconomic status and friendship activity for managing the three diseases. Geriatr Gerontol Int 2019; 19: 711-716.

SUBMITTER: Lee KS

PROVIDER: S-EPMC6851663 | biostudies-literature | 2019 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Social determinants of the association among cerebrovascular disease, hearing loss and cognitive impairment in a middle-aged or older population: Recurrent neural network analysis of the Korean Longitudinal Study of Aging (2014-2016).

Lee Kwang-Sig KS Park Kun Woo KW

Geriatrics & gerontology international 20190630 8

<h4>Aim</h4>The present study used a deep learning model (recurrent neural network) for testing: (i) whether social determinants are major determinants of the association among cerebrovascular disease, hearing loss and cognitive impairment in a middle-aged or older population (hypothesis 1); and (ii) whether the association among the three diseases is very strong in the middle-aged or older population (hypothesis 2).<h4>Methods</h4>Data came from the Korean Longitudinal Study of Aging (2014-2016 ...[more]

PMID: 31257714

Similar Datasets

Project description:Biogas plants (BGPs) produce methane and carbon dioxide through the anaerobic digestion of agricultural waste. Identification of strategies for more stable biogas plant operation and increased biogas yields require better knowledge about the individual degradation steps and the interactions within the microbial communities. The metaprotein profiles of ten agricultural BGPs and one laboratory reactor were investigated using a metaproteomics pipeline. Fractionation of samples using SDS-PAGE was combined with a high resolution Orbitrap mass spectrometer, metagenome sequences specific for BGPs, and the MetaProteomeAnalyzer software. This enabled us to achieve a high coverage of the metaproteome of the BGP microbial communities. The investigation revealed approx. 17,000 protein groups (metaproteins), covering the majority of the expected metabolic networks of the biogas process such as hydrolysis, transport, fermentation processes, amino acid metabolism, methanogenesis and bacterial C1-metabolism. Biological functions could be linked with the taxonomic composition. Two different types of BGPs were classified by the abundance of the acetoclastic methanogenesis and by abundance of enzymes implicating syntrophic acetate oxidation. Linking of the identified metaproteins with the process steps of the Anaerobic Digestion Model 1 proved the main model assumptions but indicated also some improvements such as considering syntrophic acetate oxidation. Beside the syntrophic interactions, the microbial communities in BGPs are also shaped by competition for substrates and host-phage interactions causing cell lysis. In particular, larger amounts of Bacteriophages for the bacterial families Bacillaceae, Enterobacteriaceae and Clostridiaceae, exceeding the cell number of the Bacteria by approximately four-fold. In contrast, less Bacteriophages were found for Archaea, but more CRISPR proteins were detected. On the one hand, the virus induced turnover of biomass might cause slow degradation of complex biomass in BGP. On the other hand, the lysis of bacterial cells allows cycling of essential nutrients.

Project description:BackgroundNewborn hearing screening (NHS) can reduce the economic and social burden of hearing impairment. To track the progress of the goal set by the National Program of Action for Child Development (NPACD) and to estimate the detection rates of hearing impairment, the present study examined NHS coverage in 2008-2010 and 2016 and the detection of hearing impairment across China in 2016.MethodsLicensed medical institutions across China were surveyed in 2012 and 2018 by the National Center for Birth Defects Monitoring of China to collect data for the 2008-2010 period and for 2016 on live births, initial screening rates (total and referral), secondary screening rates (total and referral), and rates of hearing impairment diagnosis among infants who were referred in the secondary screening. To calculate universal newborn hearing screening (UNHS) coverage, the number of newborns who received NHS within 4 weeks after birth was divided by the number of live births. The detection rate of hearing impairment was calculated by combining referral rates on primary and secondary screening with the rate of diagnosis.ResultsNational UNHS coverage increased from 29.9% in 2008 to 86.5% in 2016, with different regions showing different increases. During this period, the number of provinces with UNHS coverage over 90.0% increased from 2 to 17, with UNHS coverage in 2016 being substantially higher in eastern provinces (93.1%) than in western provinces (79.4%). In 2016, the detection rate of hearing impairment across the country was 0.23% (95% CI 0.15-0.25%), and it varied from 0.17% in western provinces to 0.22% in central provinces and 0.28% in eastern provinces. The lowest rate was 0.02% in Heilongjiang Province and the highest rate was 0.63% in Hainan Province.ConclusionsNational UNHS coverage increased substantially from 2008 to 2016, although provinces and regions still showed differences. The detection rate of infant hearing impairment in China is comparable to that in other countries. A national individual-level information system is urgently needed in China to facilitate the integration of screening, diagnosis and treatment of infant hearing impairment, which may also lead to a more accurate estimate of the detection rate.

Dataset Information

Social determinants of the association among cerebrovascular disease, hearing loss and cognitive impairment in a middle-aged or older population: Recurrent neural network analysis of the Korean Longitudinal Study of Aging (2014-2016).

Aim

Methods

Results

Conclusions

Publications

Social determinants of the association among cerebrovascular disease, hearing loss and cognitive impairment in a middle-aged or older population: Recurrent neural network analysis of the Korean Longitudinal Study of Aging (2014-2016).

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets