Academic Journal
Identification of cognitive subtypes and risk networks in Chinese older adults: based on latent profile analysis and explainable machine learning.
| Τίτλος: | Identification of cognitive subtypes and risk networks in Chinese older adults: based on latent profile analysis and explainable machine learning. |
|---|---|
| Συγγραφείς: | Lai L; The Institute of Infectious Disease and Vaccine, School of Public Health, Zhejiang Chinese Medical University, 548 Binwen Road, Binjiang District, Hangzhou, Zhejiang, 310053, China.; Center for Vaccine Impact Assessment, Key Laboratory for Quality Monitoring and Evaluation of Vaccines and Biological Products, National Medical Products Administration, 548 Binwen Road, Binjiang District, Hangzhou, Zhejiang, 310053, China., Dong B; The Institute of Infectious Disease and Vaccine, School of Public Health, Zhejiang Chinese Medical University, 548 Binwen Road, Binjiang District, Hangzhou, Zhejiang, 310053, China.; Center for Vaccine Impact Assessment, Key Laboratory for Quality Monitoring and Evaluation of Vaccines and Biological Products, National Medical Products Administration, 548 Binwen Road, Binjiang District, Hangzhou, Zhejiang, 310053, China., Fu C; The Institute of Infectious Disease and Vaccine, School of Public Health, Zhejiang Chinese Medical University, 548 Binwen Road, Binjiang District, Hangzhou, Zhejiang, 310053, China. fuchuanxi@zcmu.edu.cn.; Center for Vaccine Impact Assessment, Key Laboratory for Quality Monitoring and Evaluation of Vaccines and Biological Products, National Medical Products Administration, 548 Binwen Road, Binjiang District, Hangzhou, Zhejiang, 310053, China. fuchuanxi@zcmu.edu.cn. |
| Πηγή: | BMC geriatrics [BMC Geriatr] 2026 Aug 03; Vol. 26 (1). Date of Electronic Publication: 2026 Aug 03. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: BioMed Central Country of Publication: England NLM ID: 100968548 Publication Model: Electronic Cited Medium: Internet ISSN: 1471-2318 (Electronic) Linking ISSN: 14712318 NLM ISO Abbreviation: BMC Geriatr Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: London : BioMed Central, [2001]- |
| Ιατρικοί όροι (MeSH): | Cognitive Dysfunction*/diagnosis , Cognitive Dysfunction*/psychology , Cognitive Dysfunction*/epidemiology , Cognitive Dysfunction*/classification , Cognition*/physiology , Cognition*/classification , Machine Learning*, China/epidemiology ; Humans ; Female ; Aged ; Male ; Longitudinal Studies ; Risk Factors ; Middle Aged ; Random Forest ; Predictive Learning Models ; Aged, 80 and over ; East Asian People |
| Περίληψη: | Background: Traditional cognitive screening often relies on total scores, which can easily mask asynchronous impairment patterns across different cognitive domains. In particular, calculation ability, a sensitive indicator of executive function, is frequently misattributed to normal aging and overlooked clinically. This study aims to utilize data-driven methods to identify specific concealed cognitive phenotypes in the older population and deconstruct their underlying sociodemographic and clinical driving mechanisms. Methods: This study included 7,159 older participants from the China Health and Retirement Longitudinal Study (CHARLS). Latent Profile Analysis (LPA) was employed to identify latent cognitive subtypes based on three dimensions: orientation, calculation, and memory. Prediction models were constructed using Boruta feature selection and the Random Forest algorithm. Furthermore, SHAP (SHapley Additive exPlanations) and Gaussian Graphical Models (GGM) were utilized to quantify the nonlinear contributions and network interactions of risk factors. Results: LPA identified a unique cognitive impairment subtype termed Calculation-Dominant Impairment, accounting for 24.6% of the sample population. Although the majority of respondents were classified as cognitively intact (55.0%), this specific subgroup exhibited a disproportionately severe decline in calculation function (V-shaped deficit), while episodic memory was relatively preserved. The Random Forest model demonstrated superior performance in identifying this subtype (AUC = 0.781), significantly outperforming traditional linear models, and achieved high specificity (specificity = 0.960). Interpretability analysis revealed a pattern dominated by significant social determinants: education level and internet use were the primary predictors, with importance weights significantly exceeding those of somatic comorbidities such as hypertension and diabetes. Network analysis further confirmed that internet use acts as a critical "bridge node" connecting age and education level, exerting a potential cognitive reserve effect in mitigating calculation decline. Conclusion: This study defines a cognitive impairment subtype primarily driven by education poverty and digital exclusion, which is prone to be missed in routine memory-centric screenings. The findings suggest that biomedical interventions alone may be insufficient to prevent such decline; promoting digital inclusion among older adults should be regarded as a critical public health strategy to compensate for early-life educational deficits and prevent the decline of calculation and executive functions. (© 2026. The Author(s).) |
| Competing Interests: | Declarations. Ethics approval and consent to participate: The data used in this study were derived from the China Health and Retirement Longitudinal Study (CHARLS). The original CHARLS survey protocol was approved by the Biomedical Ethics Review Committee of Peking University (Approval No. IRB00001052-11015), and all respondents signed informed consent forms prior to the survey. All methods were carried out in accordance with relevant guidelines and regulations (e.g., Declaration of Helsinki). Consent for publication: Not applicable. Competing interests: The authors declare no competing interests. |
| References: | Bioinformatics. 2001 Jun;17(6):520-5. (PMID: 11395428) Lancet. 2015 Oct 24;386(10004):1698-706. (PMID: 26595643) Psychol Methods. 2018 Dec;23(4):617-634. (PMID: 29595293) Behav Res Methods. 2018 Feb;50(1):195-212. (PMID: 28342071) Neuroimage. 2011 Feb 1;54(3):2382-93. (PMID: 20946958) Am J Epidemiol. 2012 Feb 1;175(3):210-7. (PMID: 22262640) Psychol Aging. 2019 Feb;34(1):17-24. (PMID: 30211596) J Gerontol A Biol Sci Med Sci. 2018 Oct 8;73(11):1519-1524. (PMID: 29211879) Front Public Health. 2025 Feb 18;13:1510418. (PMID: 40041182) J Gerontol B Psychol Sci Soc Sci. 1997 May;52 Spec No:37-48. (PMID: 9215356) Int J Epidemiol. 2014 Apr;43(2):576-85. (PMID: 24671021) Neurology. 2010 Mar 23;74(12):951-5. (PMID: 20308679) Brain. 2015 Sep;138(Pt 9):2732-49. (PMID: 26141491) Biometrics. 1988 Sep;44(3):837-45. (PMID: 3203132) Int J Public Health. 2023 Jan 19;68:1605322. (PMID: 36798738) Int J Epidemiol. 2014 Feb;43(1):61-8. (PMID: 23243115) Lancet. 2024 Aug 10;404(10452):572-628. (PMID: 39096926) Med Decis Making. 2006 Nov-Dec;26(6):565-74. (PMID: 17099194) Int J Geriatr Psychiatry. 2000 Aug;15(8):677-9. (PMID: 10960879) BMJ. 2009 Jun 29;338:b2393. (PMID: 19564179) |
| Contributed Indexing: | Keywords: Calculation-dominant impairment; Cognitive phenotypes; Cognitive reserve; Digital inclusion; Explainable machine learning; Latent Profile Analysis |
| Entry Date(s): | Date Created: 20261009 Date Completed: 20261010 Latest Revision: 20261011 |
| Update Code: | 20261011 |
| DOI: | 10.1186/s12877-026-08079-1 |
| PMID: | 42855675 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 1471-2318 |
|---|---|
| DOI: | 10.1186/s12877-026-08079-1 |