| dc.contributor | 資管系 | |
| dc.creator (作者) | 簡士鎰 | |
| dc.creator (作者) | Chien, Shih-Yi | |
| dc.creator (作者) | Chao, Shiau-Fang;Kang, Yihuang;Hsu, Chan;Yu, Meng-Hsuan;Ku, Chan-Tung | |
| dc.date (日期) | 2022-09 | |
| dc.date.accessioned | 20-十月-2022 16:06:59 (UTC+8) | - |
| dc.date.available | 20-十月-2022 16:06:59 (UTC+8) | - |
| dc.date.issued (上傳時間) | 20-十月-2022 16:06:59 (UTC+8) | - |
| dc.identifier.uri (URI) | http://nccur.lib.nccu.edu.tw/handle/140.119/142457 | - |
| dc.description.abstract (摘要) | Dementia in the older population has become a major issue in health research. Given the prevalence of dementia worldwide, various approaches have been applied to examine the causes of dementia incidence and a wide range of factors are captured from many different perspectives. Despite multifaceted data collected from representative samples, most of the findings are merely based on a small set of certain aspects without utilizing a holistic approach to support a comprehensive overview. The present study introduces advanced machine learning algorithms to examine the longitudinal dataset and to the detection of the important predictive factors associated with dementia changes for older adults. The results are consistent with previous research findings, confirming the importance of subject characteristics (age, gender, and education), and further suggest both physiological (physical ability) and psychosocial (social support) factors to be the critical predictors for dementia status. Instead of evaluating the general relationships among possible causes and dementia incidence, our findings also signify the importance of data stratification to distinguish the distinctive requirements and expectations from different older cohorts. These observations indicate physical performance should be regularly evaluated and psychosocial indicators need to be incorporated into the assessment processes for early detection of dementia, where different interactive schemes (interventions or treatments) should be offered to particular older cohorts. The research findings provide critical dementia predictors that can serve as basic research guidelines to improve dementia care, develop timely interventions, and optimize the effectiveness in promoting the cognitive performance of older persons. | |
| dc.format.extent | 107 bytes | - |
| dc.format.mimetype | text/html | - |
| dc.relation (關聯) | International Journal of Human-Computer Studies, Vol.165, 102834 | |
| dc.subject (關鍵詞) | Mild Cognitive Impairment; Dementia; Machine Learning; Longitudinal Study; Health Prediction; Elderly Care | |
| dc.title (題名) | Understanding Predictive Factors of Dementia for Older Adults: A Machine Learning Approach for Modeling the Dementia Influencers | |
| dc.type (資料類型) | article | |
| dc.identifier.doi (DOI) | 10.1016/j.ijhcs.2022.102834 | |
| dc.doi.uri (DOI) | https://doi.org/10.1016/j.ijhcs.2022.102834 | |
