Physical and mental health management for the older adult using XGBoost algorithm supported by new media technology
Developing personalized health intervention plans using healthcare data from the CLHLS database
Bibliographic Data
| ID | 22068403 |
|---|---|
| Authors | Yutong Wang (0009-0005-5570-8158, Wuhan University), Xin Guan (0000-0002-1088-2639, Anhui Xinhua University, corresponding author), Shiyuan Qu (0009-0008-3563-2995, University of Leicester), Jiarong Liao (Guangzhou University), Xin Ming (0000-0002-0289-8438, Guangzhou University), Enhui Li (0000-0002-0571-5983, Guangzhou University), Zixi Wang (0000-0002-1176-1177, Guangzhou University) |
| Year | 2025 |
| Volume | 13 |
| Pages | 1535056-1535056 |
| Publication date | 2025-05-30 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Frontiers in Public Health (JOURNAL) |
| Journal identifiers | ISSN: 2296-2565 • E-ISSN: 2296-2565 |
| Publisher | Frontiers Media SA (PUBLISHER • CH) |
| DOI | 10.3389/fpubh.2025.1535056 |
| PMID | 40520309 |
| OpenAlex | W4410905548 |
| Language | EN |
| Citations received | 1 |
| References cited | 20 |
Introduction: With the increasing aging population, there is a growing need for precise and intelligent health management solutions tailored to older adult individuals. This study proposes a comprehensive digital health management platform that integrates new media technologies to support physical and mental well-being among the older adult. Methods: A personalized health management system was designed by integrating multi-source health data and employing artificial intelligence and blockchain technologies to ensure personalized and secure services. Latent Dirichlet Allocation (LDA) was used to extract topic keywords related to older adult health needs, particularly chronic disease understanding. These text features were then combined with image features extracted via ResNet50 to form a multi-modal feature representation. Finally, an XGBoost-based health risk assessment model was constructed and trained using data from the China Longitudinal Healthy Longevity Survey (CLHLS). Results: The LDA+ResNet50 model achieved an average F1 score of 0.926 in classifying five key health-related topic categories, with the highest performance (F1 = 0.97) in the "psychology" domain. The XGBoost model demonstrated excellent classification performance with an accuracy of 0.95, effectively distinguishing between positive and negative health outcomes and capturing complex data patterns. Discussion: This study demonstrates the feasibility and effectiveness of combining topic modeling, deep learning, and machine learning for older adult health risk assessment. The proposed scheme enhances the accuracy and intelligence of health management services, aiding in chronic disease prevention and improving the overall quality of life for older adult individuals
Algorithm · Data mining · Data science · Database · Health care · Computer Science · Digital Mental Health Interventions · Machine Learning in Healthcare · Medicine · Mental Health via Writing · Nursing
Home garden use during Covid-19
The Mental Health Consequences of Covid-19 and Physical Distancing
Barriers and facilitators to the use of e-health by older adults
Mental Health Effects of Covid-19 Pandemia
Designing and scaling up integrated youth mental health care
Construction and Simulation Analysis of Epidemic Propagation Model Based on Covid-19 Characteristics
Applying LDA Topic Modeling in Communication Research
| Unique citing works | 1 |
|---|---|
| Citations per year | 1 |
| Citation span | 2026 - 2026 (1) |
| Citation velocity | current |
| Highly cited | No |
| Citation types | Neutral: 1 |