1. |
- Berner, Jessica, et al.
(author)
-
Technology anxiety and technology enthusiasm versus digital ageism
- 2022
-
In: Gerontechnology. - : International Society for Gerontechnology (ISG). - 1569-1101 .- 1569-111X. ; 21:1
-
Journal article (peer-reviewed)abstract
- Background: Europe has called attention to the importance of the e-inclusion of older adults. Society is indicating that the developers, websites, and devices are causing age bias in technology. This affects living independently, the values of ethical principles associated with an older person, and digital ageism: which is an age-related bias in artificial intelligence systems. Objective: This research attempts to investigate the instrument technology anxiety and enthusiasm, and assistive technology devices during the period 2019- 2021. This instrument may be a way to redress misconceptions about digital ageism. The assistive technology device that we will investigate in this study is the adoption of a service that is designed for online health consultations. Method: The participants are part of the longitudinal Swedish National Study on Aging and Care. Technology anxiety and technology enthusiasm are two factors, which aim to measure technophilia (vs technophobia) in older adults. The age range is 63 -99 years of age in 2019 T1 and 66 -101 in 2021 T2. Wilcoxon rank test was conducted to investigate technology enthusiasm, technology anxiety, and how they changed with time. An Edwards Nunnally index was then calculated for both variables to observe a significant change in score from T1 to T2. Mann Whitney U test was used to investigate the variables sex and health status with technology anxiety & technology enthusiasm in T1 & T2. Age, Cognitive function MMSE, and digital social participation were investigated through a Kruskall-Wallis test. A logistic regression was conducted with the significant variable. Results: Between 2019-2021, change in technology enthusiasm was based on less digital social participation (OR: 0.608; CI 95%: 0.476- 0.792). Technology anxiety was significantly higher due to age (OR: 1.086, CI 95%: 1.035-1.139) and less digital social participation (OR: 0.684; CI 95%: 0.522- 0.895). The want for online healthcare consultations was popular but usage was low. Conclusion: Staying active on- line and participating digitally may be a way to reduce digital ageism. However, digital ageism is a complex phenomenon, which requires different solutions in order to include older people and reduce an inaccurate categorisation of this group in the digital society.
|
|
2. |
- Ghazi, Sarah Nauman, 1989-, et al.
(author)
-
Psychological Health and Digital Social Participation of the Older Adults during the COVID-19 Pandemic in Blekinge, Sweden—An Exploratory Study
- 2022
-
In: International Journal of Environmental Research and Public Health. - : MDPI. - 1661-7827 .- 1660-4601. ; 19:6
-
Journal article (peer-reviewed)abstract
- COVID-19 has affected the psychological health of older adults directly and indirectly through recommendations of social distancing and isolation. Using the internet or digital tools to participate in society, one might mitigate the effects of COVID-19 on psychological health. This study explores the social participation of older adults through internet use as a social platform during COVID-19 and its relationship with various psychological health aspects. In this study, we used the survey as a research method, and we collected data through telephonic interviews; and online and paper-based questionnaires. The results showed an association of digital social participation with age and feeling lack of company. Furthermore, in addition, to the increase in internet use in older adults in Sweden during COVID-19, we conclude that digital social participation is essential to maintain psychological health in older adults.
|
|
3. |
- Javeed, Ashir, 1989-, et al.
(author)
-
An Intelligent Learning System for Unbiased Prediction of Dementia Based on Autoencoder and Adaboost Ensemble Learning
- 2022
-
In: Life. - : MDPI. - 2075-1729. ; 12:7, s. 1-18
-
Journal article (peer-reviewed)abstract
- Dementia is a neurological condition that primarily affects older adults and there is stillno cure or therapy available to cure it. The symptoms of dementia can appear as early as 10 yearsbefore the beginning of actual diagnosed dementia. Hence, machine learning (ML) researchershave presented several methods for early detection of dementia based on symptoms. However,these techniques suffer from two major flaws. The first issue is the bias of ML models caused byimbalanced classes in the dataset. Past research did not address this issue well and did not takepreventative precautions. Different ML models were developed to illustrate this bias. To alleviate theproblem of bias, we deployed a synthetic minority oversampling technique (SMOTE) to balance thetraining process of the proposed ML model. The second issue is the poor classification accuracy ofML models, which leads to a limited clinical significance. To improve dementia prediction accuracy,we proposed an intelligent learning system that is a hybrid of an autoencoder and adaptive boostmodel. The autoencoder is used to extract relevant features from the feature space and the Adaboostmodel is deployed for the classification of dementia by using an extracted subset of features. Thehyperparameters of the Adaboost model are fine-tuned using a grid search algorithm. Experimentalfindings reveal that the suggested learning system outperforms eleven similar systems which wereproposed in the literature. Furthermore, it was also observed that the proposed learning systemimproves the strength of the conventional Adaboost model by 9.8% and reduces its time complexity.Lastly, the proposed learning system achieved classification accuracy of 90.23%, sensitivity of 98.00%and specificity of 96.65%.
|
|