1
|
Pu F, Chen W, Li C, Fu J, Gao W, Ma C, Cao X, Zhang L, Hao M, Zhou J, Huang R, Ma Y, Hu K, Liu Z. Heterogeneous associations of multiplexed environmental factors and multidimensional aging metrics. Nat Commun 2024; 15:4921. [PMID: 38858361 PMCID: PMC11164970 DOI: 10.1038/s41467-024-49283-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/24/2023] [Accepted: 05/31/2024] [Indexed: 06/12/2024] Open
Abstract
Complicated associations between multiplexed environmental factors and aging are poorly understood. We manipulated aging using multidimensional metrics such as phenotypic age, brain age, and brain volumes in the UK Biobank. Weighted quantile sum regression was used to examine the relative individual contributions of multiplexed environmental factors to aging, and self-organizing maps (SOMs) were used to examine joint effects. Air pollution presented a relatively large contribution in most cases. We also found fair heterogeneities in which the same environmental factor contributed inconsistently to different aging metrics. Particulate matter contributed the most to variance in aging, while noise and green space showed considerable contribution to brain volumes. SOM identified five subpopulations with distinct environmental exposure patterns and the air pollution subpopulation had the worst aging status. This study reveals the heterogeneous associations of multiplexed environmental factors with multidimensional aging metrics and serves as a proof of concept when analyzing multifactors and multiple outcomes.
Collapse
Affiliation(s)
- Fan Pu
- Center for Clinical Big Data and Analytics of the Second Affiliated Hospital, and Department of Big Data in Health Science School of Public Health, The Key Laboratory of Intelligent Preventive Medicine of Zhejiang Province, Zhejiang University School of Medicine, Hangzhou, 310058, Zhejiang, China
| | - Weiran Chen
- Center for Clinical Big Data and Analytics of the Second Affiliated Hospital, and Department of Big Data in Health Science School of Public Health, The Key Laboratory of Intelligent Preventive Medicine of Zhejiang Province, Zhejiang University School of Medicine, Hangzhou, 310058, Zhejiang, China
| | - Chenxi Li
- Center for Clinical Big Data and Analytics of the Second Affiliated Hospital, and Department of Big Data in Health Science School of Public Health, The Key Laboratory of Intelligent Preventive Medicine of Zhejiang Province, Zhejiang University School of Medicine, Hangzhou, 310058, Zhejiang, China
| | - Jingqiao Fu
- Ocean College, Zhejiang University, Zhoushan, 316021, Zhejiang, China
| | - Weijing Gao
- Center for Clinical Big Data and Analytics of the Second Affiliated Hospital, and Department of Big Data in Health Science School of Public Health, The Key Laboratory of Intelligent Preventive Medicine of Zhejiang Province, Zhejiang University School of Medicine, Hangzhou, 310058, Zhejiang, China
| | - Chao Ma
- School of Economics and Management, Southeast University, Nanjing, 211189, Jiangsu, China
| | - Xingqi Cao
- Center for Clinical Big Data and Analytics of the Second Affiliated Hospital, and Department of Big Data in Health Science School of Public Health, The Key Laboratory of Intelligent Preventive Medicine of Zhejiang Province, Zhejiang University School of Medicine, Hangzhou, 310058, Zhejiang, China
| | - Lingzhi Zhang
- Center for Clinical Big Data and Analytics of the Second Affiliated Hospital, and Department of Big Data in Health Science School of Public Health, The Key Laboratory of Intelligent Preventive Medicine of Zhejiang Province, Zhejiang University School of Medicine, Hangzhou, 310058, Zhejiang, China
| | - Meng Hao
- State Key Laboratory of Genetic Engineering, Collaborative Innovation Center for Genetics and Development, School of Life Sciences and Human Phenome Institute, Fudan University, Shanghai, 200433, China
| | - Jin Zhou
- Key Laboratory of Environmental Stress and Chronic Disease Control & Prevention, Ministry of Education, China Medical University; Department of Biostatistics and Epidemiology, School of Public Health, China Medical University, Shenyang, 110122, Liaoning, China
| | - Rong Huang
- Key Laboratory of Environmental Stress and Chronic Disease Control & Prevention, Ministry of Education, China Medical University; Department of Biostatistics and Epidemiology, School of Public Health, China Medical University, Shenyang, 110122, Liaoning, China
| | - Yanan Ma
- Key Laboratory of Environmental Stress and Chronic Disease Control & Prevention, Ministry of Education, China Medical University; Department of Biostatistics and Epidemiology, School of Public Health, China Medical University, Shenyang, 110122, Liaoning, China.
| | - Kejia Hu
- Department of Big Data in Health Science School of Public Health, Zhejiang University School of Medicine, Hangzhou, 310058, Zhejiang, China.
| | - Zuyun Liu
- Center for Clinical Big Data and Analytics of the Second Affiliated Hospital, and Department of Big Data in Health Science School of Public Health, The Key Laboratory of Intelligent Preventive Medicine of Zhejiang Province, Zhejiang University School of Medicine, Hangzhou, 310058, Zhejiang, China.
| |
Collapse
|
2
|
Zhang H, Hao M, Li Y, Hu Z, Liu Z, Jiang S, Jin L, Wang X. Assessment of Physical Resilience Using Residual Methods and Its Association With Adverse Outcomes in Older Adults. Innov Aging 2023; 7:igad118. [PMID: 38024329 PMCID: PMC10652184 DOI: 10.1093/geroni/igad118] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2023] [Indexed: 12/01/2023] Open
Abstract
Background and Objectives Physical resilience (PR) is recognized as the ability to recover from the adverse effects of a stressor. However, there is a lack of consensus on how to optimally measure PR in older adults in general. We aimed to measure PR using residuals from regression analyses and investigated its association with adverse outcomes in older adults. Research Design and Methods A total of 6 508 older adults were included from the National Health and Aging Trends Study, which was a population-based prospective cohort study. PR was assessed using residual methods from a linear model regressing the short physical performance battery on clinical diseases, age, sex, race/ethnicity, and health condition. Adverse outcomes included all-cause mortality, falls, and overnight hospitalization. Results The mean age was 77.48 (7.84) years. Increased PR was associated with a lower risk of all-cause mortality (hazard ratio [HR] = 0.85, 95% confidence interval [CI]: 0.83-0.87). Compared to participants with reduced PR, those with normal PR had a lower risk for mortality (HR = 0.51, 95% CI: 0.46-0.56). Specifically, restricted cubic spline regression revealed a dose-response relationship between PR and all-cause mortality (p-overall < .0001, p-nonlinear = .011). Additionally, we also found significant associations of increased PR with lower risks of falls (HR = 0.98, 95% CI: 0.96-0.99) and overnight hospitalization (HR = 0.98, 95% CI: 0.97-1.00). Discussion and Implications PR, measured by residual methods, was robustly and independently associated with all-cause mortality, falls, and overnight hospitalization. Our findings provide evidence that this approach may be a simple and feasible strategy to assess PR.
Collapse
Affiliation(s)
- Hui Zhang
- Human Phenome Institute, Zhangjiang Fudan International Innovation Centre, Fudan University, Shanghai, China
| | - Meng Hao
- Human Phenome Institute, Zhangjiang Fudan International Innovation Centre, Fudan University, Shanghai, China
- Fudan Zhangjiang Institute, Shanghai, China
| | - Yi Li
- Human Phenome Institute, Zhangjiang Fudan International Innovation Centre, Fudan University, Shanghai, China
| | - Zixin Hu
- Artificial Intelligence Innovation and Incubation Institute, Fudan University, Shanghai, China
| | - Zuyun Liu
- School of Public Health and the Second Affiliated Hospital, The Key Laboratory of Intelligent Preventive Medicine of Zhejiang Province, Zhejiang University School of Medicine, Hangzhou, Zhejiang, China
| | - Shuai Jiang
- Department of Vascular Surgery, Shanghai Key Laboratory of Vascular Lesion Regulation and Remodeling, Shanghai Pudong Hospital, Fudan University Pudong Medical Center, Shanghai, China
| | - Li Jin
- Human Phenome Institute, Zhangjiang Fudan International Innovation Centre, Fudan University, Shanghai, China
| | - Xiaofeng Wang
- Human Phenome Institute, Zhangjiang Fudan International Innovation Centre, Fudan University, Shanghai, China
- National Clinical Research Centre for Aging and Medicine, Huashan Hospital, Fudan University, Shanghai, China
| |
Collapse
|
3
|
Bernard D, Doumard E, Ader I, Kemoun P, Pagès J, Galinier A, Cussat‐Blanc S, Furger F, Ferrucci L, Aligon J, Delpierre C, Pénicaud L, Monsarrat P, Casteilla L. Explainable machine learning framework to predict personalized physiological aging. Aging Cell 2023; 22:e13872. [PMID: 37300327 PMCID: PMC10410015 DOI: 10.1111/acel.13872] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/22/2022] [Revised: 04/17/2023] [Accepted: 05/03/2023] [Indexed: 06/12/2023] Open
Abstract
Attaining personalized healthy aging requires accurate monitoring of physiological changes and identifying subclinical markers that predict accelerated or delayed aging. Classic biostatistical methods most rely on supervised variables to estimate physiological aging and do not capture the full complexity of inter-parameter interactions. Machine learning (ML) is promising, but its black box nature eludes direct understanding, substantially limiting physician confidence and clinical usage. Using a broad population dataset from the National Health and Nutrition Examination Survey (NHANES) study including routine biological variables and after selection of XGBoost as the most appropriate algorithm, we created an innovative explainable ML framework to determine a Personalized physiological age (PPA). PPA predicted both chronic disease and mortality independently of chronological age. Twenty-six variables were sufficient to predict PPA. Using SHapley Additive exPlanations (SHAP), we implemented a precise quantitative associated metric for each variable explaining physiological (i.e., accelerated or delayed) deviations from age-specific normative data. Among the variables, glycated hemoglobin (HbA1c) displays a major relative weight in the estimation of PPA. Finally, clustering profiles of identical contextualized explanations reveal different aging trajectories opening opportunities to specific clinical follow-up. These data show that PPA is a robust, quantitative and explainable ML-based metric that monitors personalized health status. Our approach also provides a complete framework applicable to different datasets or variables, allowing precision physiological age estimation.
Collapse
Affiliation(s)
- David Bernard
- RESTORE Research CenterUniversité de Toulouse, INSERM 1301, CNRS 5070, EFS, ENVTFrance
- Université Toulouse 1 – Capitole, Institute of Research in Informatics (IRIT) of Toulouse, CNRSToulouseFrance
| | - Emmanuel Doumard
- RESTORE Research CenterUniversité de Toulouse, INSERM 1301, CNRS 5070, EFS, ENVTFrance
| | - Isabelle Ader
- RESTORE Research CenterUniversité de Toulouse, INSERM 1301, CNRS 5070, EFS, ENVTFrance
| | - Philippe Kemoun
- RESTORE Research CenterUniversité de Toulouse, INSERM 1301, CNRS 5070, EFS, ENVTFrance
- Oral Medicine Department and Hospital of ToulouseToulouse Institute of Oral Medicine and Science, CHU de ToulouseToulouseFrance
| | - Jean‐Christophe Pagès
- RESTORE Research CenterUniversité de Toulouse, INSERM 1301, CNRS 5070, EFS, ENVTFrance
- UFR Santé, Département Médecine, Institut Fédératif de Biologie, CHU de ToulouseToulouseFrance
| | - Anne Galinier
- RESTORE Research CenterUniversité de Toulouse, INSERM 1301, CNRS 5070, EFS, ENVTFrance
- UFR Santé, Département Médecine, Institut Fédératif de Biologie, CHU de ToulouseToulouseFrance
| | - Sylvain Cussat‐Blanc
- Université Toulouse 1 – Capitole, Institute of Research in Informatics (IRIT) of Toulouse, CNRSToulouseFrance
- Artificial and Natural Intelligence Toulouse Institute ANITIToulouseFrance
| | - Felix Furger
- RESTORE Research CenterUniversité de Toulouse, INSERM 1301, CNRS 5070, EFS, ENVTFrance
| | - Luigi Ferrucci
- Biomedical Research Centre, National Institute on AgingNIHBaltimoreMarylandUSA
| | - Julien Aligon
- Université Toulouse 1 – Capitole, Institute of Research in Informatics (IRIT) of Toulouse, CNRSToulouseFrance
| | | | - Luc Pénicaud
- RESTORE Research CenterUniversité de Toulouse, INSERM 1301, CNRS 5070, EFS, ENVTFrance
| | - Paul Monsarrat
- RESTORE Research CenterUniversité de Toulouse, INSERM 1301, CNRS 5070, EFS, ENVTFrance
- Oral Medicine Department and Hospital of ToulouseToulouse Institute of Oral Medicine and Science, CHU de ToulouseToulouseFrance
- Artificial and Natural Intelligence Toulouse Institute ANITIToulouseFrance
| | - Louis Casteilla
- RESTORE Research CenterUniversité de Toulouse, INSERM 1301, CNRS 5070, EFS, ENVTFrance
| |
Collapse
|
4
|
Hao M, Zhang H, Hu Z, Jiang X, Song Q, Wang X, Wang J, Liu Z, Wang X, Li Y, Jin L. Phenotype correlations reveal the relationships of physiological systems underlying human ageing. Aging Cell 2021; 20:e13519. [PMID: 34825761 PMCID: PMC8672793 DOI: 10.1111/acel.13519] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2021] [Revised: 10/18/2021] [Accepted: 11/03/2021] [Indexed: 01/02/2023] Open
Abstract
Ageing is characterized by degeneration and loss of function across multiple physiological systems. To study the mechanisms and consequences of ageing, several metrics have been proposed in a hierarchical model, including biological, phenotypic and functional ageing. In particular, phenotypic ageing and interconnected changes in multiple physiological systems occur in all ageing individuals over time. Recently, phenotypic age, a new ageing measure, was proposed to capture morbidity and mortality risk across diverse subpopulations in US cohort studies. Although phenotypic age has been widely used, it may overlook the complex relationships among phenotypic biomarkers. Considering the correlation structure of these phenotypic biomarkers, we proposed a composite phenotype analysis (CPA) strategy to analyse 71 biomarkers from 2074 individuals in the Rugao Longitudinal Ageing Study. CPA grouped these biomarkers into 18 composite phenotypes according to their internal correlation, and these composite phenotypes were mostly consistent with prior findings. In addition, compared with prior findings, this strategy exhibited some different yet important implications. For example, the indicators of kidney and cardiovascular functions were tightly connected, implying internal interactions. The composite phenotypes were further verified through associations with functional metrics of ageing, including disability, depression, cognitive function and frailty. Compared to age alone, these composite phenotypes had better predictive performances for functional metrics of ageing. In summary, CPA could reveal the hidden relationships of physiological systems and identify the links between physiological systems and functional ageing metrics, thereby providing novel insights into potential mechanisms underlying human ageing.
Collapse
Affiliation(s)
- Meng Hao
- State Key Laboratory of Genetic EngineeringCollaborative Innovation Center for Genetics and DevelopmentSchool of Life Sciences and Human Phenome InstituteFudan UniversityShanghaiChina
| | - Hui Zhang
- State Key Laboratory of Genetic EngineeringCollaborative Innovation Center for Genetics and DevelopmentSchool of Life Sciences and Human Phenome InstituteFudan UniversityShanghaiChina
- National Clinical Research Center for Ageing and MedicineHuashan HospitalFudan UniversityShanghaiChina
| | - Zixin Hu
- State Key Laboratory of Genetic EngineeringCollaborative Innovation Center for Genetics and DevelopmentSchool of Life Sciences and Human Phenome InstituteFudan UniversityShanghaiChina
| | - Xiaoyan Jiang
- Key Laboratory of Arrhythmias of the Ministry of Education of ChinaTongji University School of MedicineShanghaiChina
| | - Qi Song
- State Key Laboratory of Genetic EngineeringCollaborative Innovation Center for Genetics and DevelopmentSchool of Life Sciences and Human Phenome InstituteFudan UniversityShanghaiChina
| | - Xi Wang
- State Key Laboratory of Genetic EngineeringCollaborative Innovation Center for Genetics and DevelopmentSchool of Life Sciences and Human Phenome InstituteFudan UniversityShanghaiChina
| | - Jiucun Wang
- State Key Laboratory of Genetic EngineeringCollaborative Innovation Center for Genetics and DevelopmentSchool of Life Sciences and Human Phenome InstituteFudan UniversityShanghaiChina
- Research Unit of Dissecting the Population Genetics and Developing New Technologies for Treatment and Prevention of Skin Phenotypes and Dermatological Diseases (2019RU058)Chinese Academy of Medical SciencesBeijingChina
| | - Zuyun Liu
- Center for Clinical Big Data and AnalyticsSecond Affiliated Hospital and Department of Big Data in Health ScienceSchool of Public HealthZhejiang University School of MedicineHangzhouZhejiangChina
| | - Xiaofeng Wang
- State Key Laboratory of Genetic EngineeringCollaborative Innovation Center for Genetics and DevelopmentSchool of Life Sciences and Human Phenome InstituteFudan UniversityShanghaiChina
- National Clinical Research Center for Ageing and MedicineHuashan HospitalFudan UniversityShanghaiChina
| | - Yi Li
- State Key Laboratory of Genetic EngineeringCollaborative Innovation Center for Genetics and DevelopmentSchool of Life Sciences and Human Phenome InstituteFudan UniversityShanghaiChina
- Research Unit of Dissecting the Population Genetics and Developing New Technologies for Treatment and Prevention of Skin Phenotypes and Dermatological Diseases (2019RU058)Chinese Academy of Medical SciencesBeijingChina
| | - Li Jin
- State Key Laboratory of Genetic EngineeringCollaborative Innovation Center for Genetics and DevelopmentSchool of Life Sciences and Human Phenome InstituteFudan UniversityShanghaiChina
- Research Unit of Dissecting the Population Genetics and Developing New Technologies for Treatment and Prevention of Skin Phenotypes and Dermatological Diseases (2019RU058)Chinese Academy of Medical SciencesBeijingChina
- International Human Phenome InstitutesShanghaiChina
| |
Collapse
|