1
|
Azizi M, Jamali AA, Spiteri RJ. Identifying X (Formerly Twitter) Posts Relevant to Dementia and COVID-19: Machine Learning Approach. JMIR Form Res 2024; 8:e49562. [PMID: 38833288 PMCID: PMC11185906 DOI: 10.2196/49562] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/01/2023] [Revised: 12/11/2023] [Accepted: 04/03/2024] [Indexed: 06/06/2024] Open
Abstract
BACKGROUND During the pandemic, patients with dementia were identified as a vulnerable population. X (formerly Twitter) became an important source of information for people seeking updates on COVID-19, and, therefore, identifying posts (formerly tweets) relevant to dementia can be an important support for patients with dementia and their caregivers. However, mining and coding relevant posts can be daunting due to the sheer volume and high percentage of irrelevant posts. OBJECTIVE The objective of this study was to automate the identification of posts relevant to dementia and COVID-19 using natural language processing and machine learning (ML) algorithms. METHODS We used a combination of natural language processing and ML algorithms with manually annotated posts to identify posts relevant to dementia and COVID-19. We used 3 data sets containing more than 100,000 posts and assessed the capability of various algorithms in correctly identifying relevant posts. RESULTS Our results showed that (pretrained) transfer learning algorithms outperformed traditional ML algorithms in identifying posts relevant to dementia and COVID-19. Among the algorithms tested, the transfer learning algorithm A Lite Bidirectional Encoder Representations from Transformers (ALBERT) achieved an accuracy of 82.92% and an area under the curve of 83.53%. ALBERT substantially outperformed the other algorithms tested, further emphasizing the superior performance of transfer learning algorithms in the classification of posts. CONCLUSIONS Transfer learning algorithms such as ALBERT are highly effective in identifying topic-specific posts, even when trained with limited or adjacent data, highlighting their superiority over other ML algorithms and applicability to other studies involving analysis of social media posts. Such an automated approach reduces the workload of manual coding of posts and facilitates their analysis for researchers and policy makers to support patients with dementia and their caregivers and other vulnerable populations.
Collapse
Affiliation(s)
- Mehrnoosh Azizi
- Department of Computer Science, University of Saskatchewan, Saskatoon, SK, Canada
| | - Ali Akbar Jamali
- Department of Computer Science, University of Saskatchewan, Saskatoon, SK, Canada
| | - Raymond J Spiteri
- Department of Computer Science, University of Saskatchewan, Saskatoon, SK, Canada
| |
Collapse
|
2
|
Xian G, Chai Y, Gong Y, He W, Ma C, Zhang X, Zhang J, Ma Y. The relationship between healthy lifestyles and cognitive function in Chinese older adults: the mediating effect of depressive symptoms. BMC Geriatr 2024; 24:299. [PMID: 38549104 PMCID: PMC10979595 DOI: 10.1186/s12877-024-04922-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/29/2023] [Accepted: 03/26/2024] [Indexed: 04/01/2024] Open
Abstract
BACKGROUND Previous studies have proven the positive relationship between healthy lifestyles and cognitive function in older adults. However, the specific impacts and mechanisms require further investigation. Therefore, this study aimed to investigate whether healthy lifestyles and cognitive function were associated with Chinese older adults and whether depressive symptoms mediated their association. METHODS 8272 valid samples were included using the latest data from the Chinese Longitudinal Healthy Longevity Survey (CLHLS). Pearson's test was applied to investigate the relationship between the key variables. Regression models were employed to examine the mediating effects of healthy lifestyles, using Sobel's test and the bootstrap method to confirm path effects. RESULTS There was a significant correlation between healthy lifestyles, depressive symptoms, and cognitive function (p < 0.01). Healthy lifestyles directly impact cognitive function (β = 0.162, p < 0.01). Healthy lifestyles had a significant effect on depressive symptoms (β=-0.301, p < 0.01), while depressive symptoms have a significant impact on cognitive function (β=-0.108, p < 0.01). Depressive symptoms partially mediated the effect of healthy lifestyles on cognitive function (β = 0.032, p < 0.01). The Sobel and bootstrap tests confirmed the robustness of the regression analysis results. CONCLUSION Depressive symptoms mediate the relationship between healthy lifestyles and cognitive function. Our findings suggest that prevention strategies for cognitive impairment in older adults should focus on healthy lifestyles and mental health.
Collapse
Affiliation(s)
- Guowei Xian
- School of Management, Shandong Second Medical University, 261053, Weifang, Shandong, China
| | - Yulin Chai
- School of Management, Shandong Second Medical University, 261053, Weifang, Shandong, China
| | - Yunna Gong
- School of Management, Shandong Second Medical University, 261053, Weifang, Shandong, China
| | - Wenfeng He
- School of Management, Shandong Second Medical University, 261053, Weifang, Shandong, China
| | - Chunxiao Ma
- School of Management, Shandong Second Medical University, 261053, Weifang, Shandong, China
| | - Xiaolin Zhang
- School of Management, Shandong Second Medical University, 261053, Weifang, Shandong, China
| | - Jing Zhang
- School of Management, Shandong Second Medical University, 261053, Weifang, Shandong, China
| | - Yong Ma
- School of Management, Shandong Second Medical University, 261053, Weifang, Shandong, China.
| |
Collapse
|
3
|
Li Y, Tang Y, Lu J, Wu H, Ren L. The dilution effect of healthy lifestyles on the risk of cognitive function attributed to socioeconomic status among Chinese older adults: A national wide prospective cohort study. J Glob Health 2024; 14:04010. [PMID: 38304974 PMCID: PMC10835516 DOI: 10.7189/jogh-14-04010] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/03/2024] Open
Abstract
Background Lower socioeconomic status (SES) is a risk factor for poor cognitive function, while a healthy lifestyle is associated with better cognitive function. We examined the complex relationship between SES and a healthy lifestyle and cognitive function among older Chinese adults. Methods We used a national prospective cohort of the Chinese Longitudinal Healthy Longevity Survey (CLHLS) from 2008-18, aged 65 years and older with normal cognition at baseline. Participants were categorised into the favourable group if they had four to six healthy lifestyle factors and the unfavourable group for zero to three factors. SES was classified as higher and lower by assessing the socioeconomic vulnerability index (SEVI) with six components. Cognitive function was measured using the Mini-Mental State Examination (MMSE) scores and the standardised Z-scores. We applied the linear mixed effects and time-dependent Cox regression models to explore associations and further stratified the analysis by healthy lifestyles. Results A total of 6851 participants were included (the mean age was 80.87, 43.44% had a favourable lifestyle, and 49.29% had higher SES). Over the 10-year follow-up period, SES status and lifestyle profiles significantly affected the decline in the standardised Z-scores (P < 0.05). The higher SES group with favourable lifestyles exhibited a slower cognitive decline than those with lower SES (by 0.031 points per year, P < 0.05). The association was not observed in those in the unfavourable group (0.010 points per year, P > 0.05). During a follow-up, 25.06% of participants developed cognitive impairment (MMSE<18). We also observed a significant interaction between SES and healthy lifestyles (P < 0.05), with the corresponding associations of SES being more pronounced among participants with unfavourable lifestyles (hazard ratio (HR) = 0.821; 95% confidence interval (CI) = 0.701-0.960) than those with favourable lifestyles (HR = 1.006; 95% CI = 0.844-1.200). Conclusions A healthy lifestyle may attenuate the adverse impacts of lower SES on cognitive function among older adults. This study might provide important information for protecting cognitive function, especially in low- and middle-income countries.
Collapse
Affiliation(s)
- Yao Li
- Clinical Centre for Intelligent Rehabilitation Research, Shanghai YangZhi Rehabilitation Hospital, Shanghai Sunshine Rehabilitation Centre, School of Medicine, Tongji University, Shanghai, China
| | - Yuhong Tang
- Clinical Centre for Intelligent Rehabilitation Research, Shanghai YangZhi Rehabilitation Hospital, Shanghai Sunshine Rehabilitation Centre, School of Medicine, Tongji University, Shanghai, China
| | - Jiaping Lu
- Department of Endocrinology, Qingpu Branch of Zhongshan Hospital, Fudan University, Shanghai, China
| | - Hengjing Wu
- Clinical Centre for Intelligent Rehabilitation Research, Shanghai YangZhi Rehabilitation Hospital, Shanghai Sunshine Rehabilitation Centre, School of Medicine, Tongji University, Shanghai, China
| | - Longbing Ren
- China Centre for Health Developments, Peking University, Beijing, China
| |
Collapse
|
4
|
Montero-Sandiego E, Ruiz-Robledillo N, Ferrer-Cascales R, Clement-Carbonell V, Alcocer-Bruno C, Albaladejo-Blázquez N. Spanish validation of the simple lifestyle indicator questionnaire: validity and reliability analysis. Front Public Health 2024; 11:1146010. [PMID: 38264245 PMCID: PMC10803412 DOI: 10.3389/fpubh.2023.1146010] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/17/2023] [Accepted: 12/19/2023] [Indexed: 01/25/2024] Open
Abstract
Introduction It has been shown that lifestyle is a highly modifiable determinant having a direct effect on the health status. Therefore, short and simple questionnaires assessing the lifestyle of the general and clinical population are needed to create interventions on behavioral aspects that can improve the health status. The Simple Lifestyle Indicator Questionnaire (SLIQ) is a validated health scale in English that combines five lifestyle factors: diet, exercise, alcohol consumption, tobacco use, and stress level. The objective of this study was to validate the SLIQ questionnaire in Spanish by analyzing the scale's validity and reliability. Its discriminatory power of the scale was also examined by evaluating the differences in health outcomes according to the levels of adherence to a healthy lifestyle. Methods The sample consisted of 745 participants with an average age of 39.94 (SD: 16.99). A transcultural adaptation process was carried out to validate the SLIQ questionnaire in the Spanish context, to determinate the structural equivalence of the Spanish version as compared to the English version, and to assess the psychometric properties of the scale. PREDIMED and IPAQ scales were used to analyze the convergent validity of the Spanish version of the SLIQ regarding to diet and exercise, and the questionnaires SF-12 and DASS-21 questionnaires were used to assess the capacity of the Spanish version of the SLIQ to discriminate health status related to different levels of reported lifestyles. Results Regarding validity, the results indicate significant correlations between the different dimensions of the SLIQ questionnaire and those used as a reference. As for reliability, the test-retest analyses reveal a high temporal consistency for the scores obtained on the questionnaire. Finally, the differences found in anxiety, depression, and quality of life, with regard to the different levels of adherence in the SLIQ questionnaire, suggest that the questionnaire's Spanish version has adequate discriminatory power. Discussion The obtained correlation coefficients between the SLIQ and the other standardized measures pointed out the adequate convergent validity of the instrument. Moreover, the test-retest results demonstrated the stability of the results obtained through this questionnaire. Finally, the lifestyle categories derived from the SLIQ showed a high ability to discriminate between participants' health profiles. Hence, it can be concluded that the Spanish version of the SLIQ questionnaire is a valid and reliable tool for the quick and effective assessment of lifestyle.
Collapse
Affiliation(s)
| | - Nicolás Ruiz-Robledillo
- Department of Health Psychology, Faculty of Health Science, University of Alicante, Alicante, Spain
| | | | | | | | | |
Collapse
|
5
|
Cheung MC, Sze SL, Chan AS. Chanwuyi Lifestyle Medicine Program Improves Memory and Executive Functions of Older Adults With Mild Cognitive Impairment. Am J Alzheimers Dis Other Demen 2024; 39:15333175241255744. [PMID: 38764310 PMCID: PMC11104026 DOI: 10.1177/15333175241255744] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/21/2024]
Abstract
The Chanwuyi Lifestyle Medicine Program (CLMP) was found to enhance the memory and executive functions of older adults with or without subjective memory complaints. The present study investigated whether similar beneficial effects can be extended to mild cognitive impairment (MCI). Twenty-four older adults with MCI were randomly assigned to receive the CLMP (the experimental group) or strategic memory training (SMT; the active control group) for 10 weeks. They were assessed by neuropsychological tests at baseline and post-intervention. Older adults showed similar visual and verbal memory improvements after receiving the CLMP and SMT. Yet, only those who received the CLMP showed distinct improvements in planning/organization, working memory, and attention in terms of accuracy, with greater cognitive gains associated with older age and lower levels of education and baseline cognitive functions. This study provides preliminary evidence for the effects of the CLMP on improving memory, attention, and executive functions in MCI.
Collapse
Affiliation(s)
- Mei-Chun Cheung
- Department of Social Work, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong SAR, China
- Research Center for Neuropsychological Well-Being, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong SAR, China
| | - Sophia L. Sze
- Research Center for Neuropsychological Well-Being, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong SAR, China
- Neuropsychology Laboratory, Department of Psychology, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong SAR, China
| | - Agnes S. Chan
- Research Center for Neuropsychological Well-Being, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong SAR, China
- Neuropsychology Laboratory, Department of Psychology, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong SAR, China
| |
Collapse
|
6
|
O'Shea DM, Camacho S, Ezzeddine R, Besser L, Tolea MI, Wang L, Galvin C, Gibbs G, Galvin JE. The Mediating Role of Cortical Atrophy on the Relationship between the Resilience Index and Cognitive Function: Findings from the Healthy Brain Initiative. J Alzheimers Dis 2024; 98:1017-1027. [PMID: 38489189 DOI: 10.3233/jad-231346] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/17/2024]
Abstract
Background Lifestyle factors are linked to differences in brain aging and risk for Alzheimer's disease, underscored by concepts like 'cognitive reserve' and 'brain maintenance'. The Resilience Index (RI), a composite of 6 factors (cognitive reserve, physical and cognitive activities, social engagement, diet, and mindfulness) provides such a holistic measure. Objective This study aims to examine the association of RI scores with cognitive function and assess the mediating role of cortical atrophy. Methods Baseline data from 113 participants (aged 45+, 68% female) from the Healthy Brain Initiative were included. Life course resilience was estimated with the RI, cognitive performance with Cognivue®, and brain health using a machine learning derived Cortical Atrophy Score (CAS). Mediation analysis probed the relationship between RI, cognitive outcomes, and cortical atrophy. Results In age and sex adjusted models, the RI was significantly associated with CAS (β= -0.25, p = 0.006) and Cognivue® scores (β= 0.32, p < 0.001). The RI-Cognivue® association was partially mediated by CAS (β= 0.07; 95% CI [0.02, 0.14]). Conclusions Findings revealed that the collective effect of early and late-life lifestyle resilience factors on cognition are partially explained by their association with less brain atrophy. These findings underscore the value of comprehensive lifestyle assessments in understanding the risk and progression of cognitive decline and Alzheimer's disease in an aging population.
Collapse
Affiliation(s)
- Deirdre M O'Shea
- Department of Neurology, Comprehensive Center for Brain Health, University of Miami Miller School of Medicine, Boca Raton, FL, USA
| | - Simone Camacho
- Department of Neurology, Comprehensive Center for Brain Health, University of Miami Miller School of Medicine, Boca Raton, FL, USA
| | - Reem Ezzeddine
- Department of Neurology, Comprehensive Center for Brain Health, University of Miami Miller School of Medicine, Boca Raton, FL, USA
| | - Lilah Besser
- Department of Neurology, Comprehensive Center for Brain Health, University of Miami Miller School of Medicine, Boca Raton, FL, USA
| | - Magdalena I Tolea
- Department of Neurology, Comprehensive Center for Brain Health, University of Miami Miller School of Medicine, Boca Raton, FL, USA
| | - Lily Wang
- Department of Public Health Science, University of Miami Miller School of Medicine, Miami, FL, USA
| | - Conor Galvin
- Department of Neurology, Comprehensive Center for Brain Health, University of Miami Miller School of Medicine, Boca Raton, FL, USA
| | - Gregory Gibbs
- Department of Neurology, Comprehensive Center for Brain Health, University of Miami Miller School of Medicine, Boca Raton, FL, USA
| | - James E Galvin
- Department of Neurology, Comprehensive Center for Brain Health, University of Miami Miller School of Medicine, Boca Raton, FL, USA
| |
Collapse
|