1
|
Liu Y, Ge P, Zhang X, Wu Y, Sun Z, Bai Q, Jing S, Zuo H, Wang P, Cong J, Li X, Liu K, Wu Y, Wei B. Intrarelationships between suboptimal health status and anxiety symptoms: A network analysis. J Affect Disord 2024; 354:679-687. [PMID: 38527530 DOI: 10.1016/j.jad.2024.03.104] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/02/2024] [Revised: 03/20/2024] [Accepted: 03/22/2024] [Indexed: 03/27/2024]
Abstract
BACKGROUND Suboptimal health status is a global public health concern of worldwide academic interest, which is an intermediate health status between health and illness. The purpose of the survey is to investigate the relationship between anxiety statuses and suboptimal health status and to identify the central symptoms and bridge symptoms. METHODS This study recruited 26,010 participants aged <60 from a cross-sectional study in China in 2022. General Anxiety Disorder-7 (GAD-7) and suboptimal health status short form (SHSQ-9) were used to quantify the levels of anxiety and suboptimal health symptoms, respectively. The network analysis method by the R program was used to judge the central and bridge symptoms. The Network Comparison Test (NCT) was used to investigate the network differences by gender, place of residence, and age in the population. RESULTS In this survey, the prevalence of anxiety symptoms, SHS, and comorbidities was 50.7 %, 54.8 %, and 38.5 %, respectively. "Decreased responsiveness", "Shortness of breath", "Uncontrollable worry" were the nodes with the highest expected influence. "Irritable", "Exhausted" were the two symptom nodes with the highest expected bridge influence in the network. There were significant differences in network structure among different subgroup networks. LIMITATIONS Unable to study the causal relationship and dynamic changes among variables. Anxiety and sub-health were self-rated and may be limited by memory bias. CONCLUSIONS Interventions targeting central symptoms and bridge nodes may be expected to improve suboptimal health status and anxiety in Chinese residents. Researchers can build symptom networks for different populations to capture symptom relationships.
Collapse
Affiliation(s)
- Yangyu Liu
- Center for Medical Artificial Intelligence, Shandong University of Traditional Chinese Medicine, Qingdao 266112, China; Qingdao Academy of Chinese Medical Sciences, Shandong University of Traditional Chinese Medicine, Qingdao 266112, China; Qingdao Key Laboratory of Artificial Intelligence Technology in Traditional Chinese Medicine, Qingdao 266112, China
| | - Pu Ge
- School of Traditional Chinese Medicine, Beijing University of Chinese Medicine, Beijing 100105, China
| | - Xiaoming Zhang
- Department of Cardiovascular Surgery, The Affiliated Hospital of Qingdao University, Qingdao 266000, China
| | - Yunchou Wu
- School of Psychology, Southwest University, Chongqing 400715, China
| | - Zhaocai Sun
- Center for Medical Artificial Intelligence, Shandong University of Traditional Chinese Medicine, Qingdao 266112, China; Qingdao Academy of Chinese Medical Sciences, Shandong University of Traditional Chinese Medicine, Qingdao 266112, China; Qingdao Key Laboratory of Artificial Intelligence Technology in Traditional Chinese Medicine, Qingdao 266112, China
| | - Qian Bai
- School of Management, Beijing University of Chinese Medicine, Beijing 100105, China
| | - Shanshan Jing
- College of Health Sciences, Shandong University of Traditional Chinese Medicine, Jinan, Shandong 250355, China
| | - Huali Zuo
- Warshel Institute for Computational Biology, The Chinese University of Hong Kong, Shenzhen 518172, China
| | - Pingping Wang
- Center for Medical Artificial Intelligence, Shandong University of Traditional Chinese Medicine, Qingdao 266112, China; Qingdao Academy of Chinese Medical Sciences, Shandong University of Traditional Chinese Medicine, Qingdao 266112, China; Qingdao Key Laboratory of Artificial Intelligence Technology in Traditional Chinese Medicine, Qingdao 266112, China
| | - Jinyu Cong
- Center for Medical Artificial Intelligence, Shandong University of Traditional Chinese Medicine, Qingdao 266112, China; Qingdao Academy of Chinese Medical Sciences, Shandong University of Traditional Chinese Medicine, Qingdao 266112, China; Qingdao Key Laboratory of Artificial Intelligence Technology in Traditional Chinese Medicine, Qingdao 266112, China
| | - Xiang Li
- Center for Medical Artificial Intelligence, Shandong University of Traditional Chinese Medicine, Qingdao 266112, China; Qingdao Academy of Chinese Medical Sciences, Shandong University of Traditional Chinese Medicine, Qingdao 266112, China; Qingdao Key Laboratory of Artificial Intelligence Technology in Traditional Chinese Medicine, Qingdao 266112, China
| | - Kunmeng Liu
- Center for Medical Artificial Intelligence, Shandong University of Traditional Chinese Medicine, Qingdao 266112, China; Qingdao Academy of Chinese Medical Sciences, Shandong University of Traditional Chinese Medicine, Qingdao 266112, China; Qingdao Key Laboratory of Artificial Intelligence Technology in Traditional Chinese Medicine, Qingdao 266112, China.
| | - Yibo Wu
- School of Public Health, Peking University, Haidian District, Beijing 100191, China.
| | - Benzheng Wei
- Center for Medical Artificial Intelligence, Shandong University of Traditional Chinese Medicine, Qingdao 266112, China; Qingdao Academy of Chinese Medical Sciences, Shandong University of Traditional Chinese Medicine, Qingdao 266112, China; Qingdao Key Laboratory of Artificial Intelligence Technology in Traditional Chinese Medicine, Qingdao 266112, China.
| |
Collapse
|
2
|
Chen MS, Liu TC, Jhou MJ, Yang CT, Lu CJ. Analyzing Longitudinal Health Screening Data with Feature Ensemble and Machine Learning Techniques: Investigating Diagnostic Risk Factors of Metabolic Syndrome for Chronic Kidney Disease Stages 3a to 3b. Diagnostics (Basel) 2024; 14:825. [PMID: 38667472 PMCID: PMC11048899 DOI: 10.3390/diagnostics14080825] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2024] [Revised: 04/12/2024] [Accepted: 04/13/2024] [Indexed: 04/28/2024] Open
Abstract
Longitudinal data, while often limited, contain valuable insights into features impacting clinical outcomes. To predict the progression of chronic kidney disease (CKD) in patients with metabolic syndrome, particularly those transitioning from stage 3a to 3b, where data are scarce, utilizing feature ensemble techniques can be advantageous. It can effectively identify crucial risk factors, influencing CKD progression, thereby enhancing model performance. Machine learning (ML) methods have gained popularity due to their ability to perform feature selection and handle complex feature interactions more effectively than traditional approaches. However, different ML methods yield varying feature importance information. This study proposes a multiphase hybrid risk factor evaluation scheme to consider the diverse feature information generated by ML methods. The scheme incorporates variable ensemble rules (VERs) to combine feature importance information, thereby aiding in the identification of important features influencing CKD progression and supporting clinical decision making. In the proposed scheme, we employ six ML models-Lasso, RF, MARS, LightGBM, XGBoost, and CatBoost-each renowned for its distinct feature selection mechanisms and widespread usage in clinical studies. By implementing our proposed scheme, thirteen features affecting CKD progression are identified, and a promising AUC score of 0.883 can be achieved when constructing a model with them.
Collapse
Affiliation(s)
- Ming-Shu Chen
- Department of Healthcare Administration, College of Healthcare & Management, Asia Eastern University of Science and Technology, New Taipei City 220, Taiwan
| | - Tzu-Chi Liu
- Graduate Institute of Business Administration, Fu Jen Catholic University, New Taipei City 242, Taiwan
| | - Mao-Jhen Jhou
- Graduate Institute of Business Administration, Fu Jen Catholic University, New Taipei City 242, Taiwan
| | - Chih-Te Yang
- Department of Business Administration, Tamkang University, New Taipei City 251, Taiwan
| | - Chi-Jie Lu
- Graduate Institute of Business Administration, Fu Jen Catholic University, New Taipei City 242, Taiwan
- Artificial Intelligence Development Center, Fu Jen Catholic University, New Taipei City 242, Taiwan
- Department of Information Management, Fu Jen Catholic University, New Taipei City 242, Taiwan
| |
Collapse
|
3
|
Alzain MA, Asweto CO, Hassan SUN, Saeed ME, Kassar A, Ali KEM, Ghorbel M, Zrieq R, Alsaif B, Wang W. Assessing suboptimal health status in the Saudi population: Translation and validation of the SHSQ-25 questionnaire. J Glob Health 2024; 14:04030. [PMID: 38305242 PMCID: PMC10836270 DOI: 10.7189/jogh.14.04030] [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 Suboptimal Health Status (SHS) is realised as a vital feature for improving global health. However, the Arabian world does not have a validated instrument for screening SHS in their population. Therefore, the study aimed to evaluate the psychometric properties of Arabic-translated SHS (ASHSQ-25) in the Saudi Arabian population. Methods We conducted a cross-sectional study among the conveniently sampled 1590 participants from the Saudi population (with a 97.4% response rate). The data was gathered through an online survey and then exported into SPSS and AMOS version 26.0 for analysis. Mann-Whitney and Kruskal-Wallis tests were used to identify the median difference between demographic groups. The one-tailed 90% upper limit of SHS scores was chosen as the cut-off criteria for SHS. Reliability and confirmatory analysis were performed for the psychometric evaluation of ASHSQ-25 in the Saudi Arabian context. Results This study demonstrates that the ASHSQ-25 has good internal consistency, interclass correlation coefficient (ICC) = 0.92; 95% confidence interval (CI) = 0.91-0.93) and reliability (Cronbach's α = 0.92). The confirmatory factor analysis (CFA) results indicated a good fit of the databased on the CMIN/degrees of freedom (df) = 4.461, comparative fit index (CFI) = 0.94, Tucker Lewis index (TLI) = 0.93, and Root Mean Square Error of Approximation (RMSEA) = 0.05. The result factor loadings for each item were high (≥ 0.55), except for one item from the immune system subscale. The SHS cut-off point for ASHSQ-25 was 33, leading to a 23.7% prevalence of SHS. Conclusions This study reveals that ASHSQ-25 has appropriate internal consistency and structural validity to assess SHS in an Arabic-speaking population; therefore, it is recommended.
Collapse
Affiliation(s)
- Mohamed Ali Alzain
- Department of Public Health, College of Public Health and Health Informatics, University of Ha'il, Ha'il City, Saudi Arabia
- Department of Community Medicine, Faculty of Medicine and Health Sciences, University of Dongola, Dongola, Sudan
| | | | - Sehar-Un-Nisa Hassan
- Department of Public Health, College of Public Health and Health Informatics, University of Ha'il, Ha'il City, Saudi Arabia
| | - Mohammed Elshiekh Saeed
- Faculty of Medicine, National University-Sudan, Khartoum, Sudan
- Department of Physiology, Faculty of Medicine, University of Dongola, Dongola, Sudan
| | - Ahmed Kassar
- Department of Public Health, College of Public Health and Health Informatics, University of Ha'il, Ha'il City, Saudi Arabia
| | - Kamal Elbssir Mohammed Ali
- Department of Community Health, Occupation Health and Safety Program, Northern Boarder University, Arar, Saudi Arabia
| | - Mouna Ghorbel
- Department of Biology, College of Sciences, University of Hail, P.O., Ha'il City, Saudi Arabia
| | - Rafat Zrieq
- Department of Public Health, College of Public Health and Health Informatics, University of Ha'il, Ha'il City, Saudi Arabia
- Applied Science Research Centre, Applied Science Private University, Amman, Jordan
| | - Bandar Alsaif
- Department of Public Health, College of Public Health and Health Informatics, University of Ha'il, Ha'il City, Saudi Arabia
| | - Wei Wang
- Clinical Research Center, First Affiliated Hospital, Shantou University Medical College, Shantou, China
- Centre for Precision Health, Edith Cowan University, Joondalup, Western Australia, Australia
- On behalf of Global Health Epidemiology Research Group (GHERG) & Global Suboptimal Health Consortium (GSHC)
| |
Collapse
|