• Using unsupervised machine lea...

*Result*: Using unsupervised machine learning methods to cluster cardio-metabolic profile of the middle-aged and elderly Chinese with general and central obesity.

Title:
Using unsupervised machine learning methods to cluster cardio-metabolic profile of the middle-aged and elderly Chinese with general and central obesity.
Authors:
Xue Y; State Key Laboratory of Mechanism and Quality Research in Chinese Medicine, Institute of Chinese Medical Sciences, University of Macau, Macao, China., Song M; State Key Laboratory of Mechanism and Quality Research in Chinese Medicine, Institute of Chinese Medical Sciences, University of Macau, Macao, China.; Centre for Pharmaceutical Regulatory Sciences, University of Macau, Macao, China., Ung COL; State Key Laboratory of Mechanism and Quality Research in Chinese Medicine, Institute of Chinese Medical Sciences, University of Macau, Macao, China.; Centre for Pharmaceutical Regulatory Sciences, University of Macau, Macao, China.; Department of Public Health and Medicinal Administration, Faculty of Health Sciences, University of Macau, Macao, China., Hu H; State Key Laboratory of Mechanism and Quality Research in Chinese Medicine, Institute of Chinese Medical Sciences, University of Macau, Macao, China. haohu@um.edu.mo.; Centre for Pharmaceutical Regulatory Sciences, University of Macau, Macao, China. haohu@um.edu.mo.; Department of Public Health and Medicinal Administration, Faculty of Health Sciences, University of Macau, Macao, China. haohu@um.edu.mo.
Source:
BMC cardiovascular disorders [BMC Cardiovasc Disord] 2025 Oct 27; Vol. 25 (1), pp. 772. Date of Electronic Publication: 2025 Oct 27.
Publication Type:
Journal Article; Comparative Study
Language:
English
Journal Info:
Publisher: BioMed Central Country of Publication: England NLM ID: 100968539 Publication Model: Electronic Cited Medium: Internet ISSN: 1471-2261 (Electronic) Linking ISSN: 14712261 NLM ISO Abbreviation: BMC Cardiovasc Disord Subsets: MEDLINE
Imprint Name(s):
Original Publication: London : BioMed Central, [2001-
MeSH Terms:
Obesity, Abdominal*/diagnosis , Obesity, Abdominal*/epidemiology , Obesity, Abdominal*/physiopathology , Obesity, Abdominal*/blood , Obesity*/diagnosis , Obesity*/epidemiology , Obesity*/physiopathology , Obesity*/blood , Cardiovascular Diseases*/diagnosis , Cardiovascular Diseases*/epidemiology , Adiposity* , Unsupervised Machine Learning* , Metabolomics*, China/epidemiology ; Biomarkers/blood ; Humans ; Male ; Middle Aged ; Female ; Aged ; Risk Assessment ; Age Factors ; Comorbidity ; Longitudinal Studies ; Cardiometabolic Risk Factors ; Cluster Analysis ; Predictive Value of Tests ; East Asian People
References:
Obes Sci Pract. 2022 Dec 23;9(3):285-295. (PMID: 37287524)
Lipids Health Dis. 2024 May 21;23(1):150. (PMID: 38773587)
Lipids Health Dis. 2018 Dec 20;17(1):289. (PMID: 30572889)
Int J Environ Res Public Health. 2022 Apr 21;19(9):. (PMID: 35564455)
Obes Res Clin Pract. 2021 Nov-Dec;15(6):564-569. (PMID: 34782258)
Metabolism. 2019 Mar;92:51-60. (PMID: 30458177)
Cardiovasc Diabetol. 2022 May 6;21(1):68. (PMID: 35524263)
Obesity (Silver Spring). 2025 Mar;33(3):612-620. (PMID: 39904719)
BMC Public Health. 2024 Apr 1;24(1):929. (PMID: 38556859)
Front Endocrinol (Lausanne). 2021 Jul 14;12:713592. (PMID: 34335479)
Nat Med. 2024 Sep;30(9):2395-2399. (PMID: 38969880)
EClinicalMedicine. 2023 Feb 16;57:101850. (PMID: 36864983)
Lancet Diabetes Endocrinol. 2021 Jun;9(6):373-392. (PMID: 34022156)
J Hepatol. 2024 Apr;80(4):e143-e145. (PMID: 38101754)
Lancet. 2024 Sep 7;404(10456):972-987. (PMID: 39159652)
Lancet Healthy Longev. 2023 Jan;4(1):e23-e33. (PMID: 36521498)
Eur Heart J. 2021 Sep 7;42(34):3388-3403. (PMID: 34333589)
Clin Epidemiol. 2018 Jul 25;10:853-862. (PMID: 30100759)
CMAJ. 2020 Aug 4;192(31):E875-E891. (PMID: 32753461)
Curr Obes Rep. 2024 Sep;13(3):584-595. (PMID: 38958869)
Lancet. 2024 Aug 31;404(10455):824-825. (PMID: 39216958)
Diabetes Metab Syndr. 2019 Mar - Apr;13(2):1099-1103. (PMID: 31336451)
Lancet. 2024 Mar 16;403(10431):1027-1050. (PMID: 38432237)
Lancet Diabetes Endocrinol. 2018 Mar;6(3):164-166. (PMID: 28919063)
Front Genet. 2022 Jan 03;12:783845. (PMID: 35047011)
J Am Med Inform Assoc. 2014 Mar-Apr;21(2):221-30. (PMID: 24201027)
BMC Med. 2021 Dec 15;19(1):320. (PMID: 34906131)
J Biomed Inform. 2020 Feb;102:103364. (PMID: 31891765)
Lancet. 2021 Jul 3;398(10294):53-63. (PMID: 34217401)
Diabetes Obes Metab. 2025 Feb;27(2):501-510. (PMID: 39497471)
Am J Respir Crit Care Med. 2013 Apr 1;187(7):728-35. (PMID: 23392440)
Cardiovasc Diabetol. 2024 Dec 19;23(1):448. (PMID: 39702291)
IEEE J Biomed Health Inform. 2016 Jan;20(1):39-46. (PMID: 25675467)
BMC Public Health. 2023 Oct 5;23(1):1927. (PMID: 37798694)
Curr Heart Fail Rep. 2021 Oct;18(5):253-263. (PMID: 34427881)
BMJ Open. 2022 Nov 23;12(11):e067203. (PMID: 36418130)
Respir Med. 2020 Sep;171:106093. (PMID: 32745966)
Diabetes Obes Metab. 2023 Sep;25(9):2669-2679. (PMID: 37283064)
Lancet. 2016 Aug 20;388(10046):776-86. (PMID: 27423262)
Rev Endocr Metab Disord. 2023 Oct;24(5):825-838. (PMID: 37581871)
Diabetes Metab Syndr Obes. 2020 Mar 30;13:943-962. (PMID: 32280253)
Annu Rev Biomed Data Sci. 2018 Jul;1:53-68. (PMID: 31218278)
Sci Rep. 2024 May 3;14(1):10220. (PMID: 38702424)
J Biomed Inform. 2015 Dec;58:156-165. (PMID: 26464024)
Front Public Health. 2023 Feb 28;11:1122995. (PMID: 36935671)
Curr Epidemiol Rep. 2018 Dec;5(4):331-342. (PMID: 30555773)
Am J Hypertens. 2024 Jul 15;37(8):588-596. (PMID: 38597145)
Int J Med Inform. 2017 Jan;97:120-127. (PMID: 27919371)
Rev Endocr Metab Disord. 2023 Oct;24(5):901-919. (PMID: 37358728)
Obes Sci Pract. 2024 Oct 22;10(5):e70019. (PMID: 39439442)
Obes Rev. 2017 Jul;18(7):715-723. (PMID: 28489290)
J Pers Med. 2025 May 20;15(5):. (PMID: 40423076)
Rev Endocr Metab Disord. 2023 Oct;24(5):809-823. (PMID: 36928809)
J Am Med Inform Assoc. 2023 Jan 18;30(2):367-381. (PMID: 36413056)
BMC Cardiovasc Disord. 2022 Mar 14;22(1):106. (PMID: 35287586)
J Diabetes Res. 2021 May 14;2021:8812431. (PMID: 34056007)
Diabetes Metab Res Rev. 2022 Mar;38(3):e3507. (PMID: 34679251)
Int J Epidemiol. 2014 Feb;43(1):61-8. (PMID: 23243115)
Contributed Indexing:
Keywords: Adiposity; Co-morbidities; Obesity; Unsupervised machine learning
Substance Nomenclature:
0 (Biomarkers)
Entry Date(s):
Date Created: 20251028 Date Completed: 20251028 Latest Revision: 20251118
Update Code:
20260130
PubMed Central ID:
PMC12557893
DOI:
10.1186/s12872-025-05157-x
PMID:
41146029
Database:
MEDLINE

*Further Information*

*Background: Obesity is a disease with high heterogeneity. Both overall obesity and central obesity are associated with increased risks of having cardio-metabolic co-morbidities. This study is aimed to examine the cardio-metabolic characteristics and comorbidity profile of the middle-aged and elderly Chinese with general and central obesity by clustering them into different subgroups, which would lead to a deepened understanding of their distinct medical needs.
Methods: Adopting an unsupervised machine learning approach, we conducted a clustering analysis of the adiposity and cardio-metabolic profiles of the middle-aged and elderly Chinese with general obesity and central obesity. The data was obtained from the China Health and Retirement Longitudinal Study (CHARLS). The subgroup features were examined. The risks of having obesity-related co-morbidities (i.e. hypertension, dyslipidemia, diabetes, heart problem, stroke) in each cluster were then compared.
Results: Among the 7,970 subjects selected from the baseline cohort, 41.88% (n = 3,338) had general obesity, while 71.29% (n = 5,682) had central obesity. These individuals with either general obesity or central obesity were clustered into four groups, respectively: (1) obesity with relatively healthier metabolites; (2) hyperuricemia subtype; (3) hyperglycemia-insulin resistance subtype; and (4) the average subtype. The results indicated among people with either general obesity or central obesity, those with high levels in HbA1c level and TyG index concurrently demonstrated more severe adiposity issues and unhealthier cardio-metabolic profile.
Conclusions: This data-driven study identified a novel classification strategy to identify subtypes of the middle-aged and elderly Chinese with general obesity and central obesity and classify their adiposity and cardio-metabolic profiles. With clinically accessible metrics, this approach could inform precise risk stratification by revealing subtype-specific heterogeneity during initial assessments.
(© 2025. The Author(s).)*

*Declarations. Ethics approval and consent to participate: The CHARLS was approved by the Institutional Review Board of Peking University (IRB00001052-11015 and IRB00001052-11014). The study followed the guidelines of the Declaration of Helsinki. Consent for publication: Not applicable. Competing interests: The authors declare no competing interests.*