1
|
Barmpas P, Tasoulis S, Vrahatis AG, Georgakopoulos SV, Anagnostou P, Prina M, Ayuso-Mateos JL, Bickenbach J, Bayes I, Bobak M, Caballero FF, Chatterji S, Egea-Cortés L, García-Esquinas E, Leonardi M, Koskinen S, Koupil I, Paja̧k A, Prince M, Sanderson W, Scherbov S, Tamosiunas A, Galas A, Haro JM, Sanchez-Niubo A, Plagianakos VP, Panagiotakos D. A divisive hierarchical clustering methodology for enhancing the ensemble prediction power in large scale population studies: the ATHLOS project. Health Inf Sci Syst 2022; 10:6. [PMID: 35529251 PMCID: PMC9013733 DOI: 10.1007/s13755-022-00171-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/13/2021] [Accepted: 03/30/2022] [Indexed: 01/13/2023] Open
Abstract
The ATHLOS cohort is composed of several harmonized datasets of international groups related to health and aging. As a result, the Healthy Aging index has been constructed based on a selection of variables from 16 individual studies. In this paper, we consider additional variables found in ATHLOS and investigate their utilization for predicting the Healthy Aging index. For this purpose, motivated by the volume and diversity of the dataset, we focus our attention upon data clustering, where unsupervised learning is utilized to enhance prediction power. Thus we show the predictive utility of exploiting hidden data structures. In addition, we demonstrate that imposed computation bottlenecks can be surpassed when using appropriate hierarchical clustering, within a clustering for ensemble classification scheme, while retaining prediction benefits. We propose a complete methodology that is evaluated against baseline methods and the original concept. The results are very encouraging suggesting further developments in this direction along with applications in tasks with similar characteristics. A straightforward open source implementation for the R project is also provided (https://github.com/Petros-Barmpas/HCEP). Supplementary Information The online version contains supplementary material available at 10.1007/s13755-022-00171-1.
Collapse
Affiliation(s)
- Petros Barmpas
- Department of Computer Science and Biomedical Informatics, University of Thessaly, Lamia, Greece
| | - Sotiris Tasoulis
- Department of Computer Science and Biomedical Informatics, University of Thessaly, Lamia, Greece
| | - Aristidis G. Vrahatis
- Department of Computer Science and Biomedical Informatics, University of Thessaly, Lamia, Greece
| | | | - Panagiotis Anagnostou
- Department of Computer Science and Biomedical Informatics, University of Thessaly, Lamia, Greece
| | - Matthew Prina
- Social Epidemiology Research Group. Health Service and Population Research Department, Institute of Psychiatry, Psychology & Neuroscience, King’s College London, London, UK
- Global Health Institute, King’s College London, London, UK
| | - José Luis Ayuso-Mateos
- Centro de Investigación Biomédica en Red de Salud Mental, CIBERSAM, Madrid, Spain
- Department of Psychiatry, Universidad Autónoma de Madrid, Madrid, Spain
- Hospital Universitario de La Princesa, Instituto de Investigación Sanitaria Princesa (IIS Princesa), Madrid, Spain
| | - Jerome Bickenbach
- Swiss Paraplegic Research, Guido A. Zäch Institute (GZI), Nottwil, Switzerland
- Department of Health Sciences & Health Policy, University of Lucerne, Lucerne, Switzerland
| | - Ivet Bayes
- Centro de Investigación Biomédica en Red de Salud Mental, CIBERSAM, Madrid, Spain
- Research, Innovation and Teaching Unit. Parc Sanitari Sant Joan de Déu, Sant Boi de Llobregat, Spain
| | - Martin Bobak
- Department of Epidemiology and Public Health, University College London, London, UK
| | - Francisco Félix Caballero
- Department Preventive Medicine and Public Health, Universidad Autónoma de Madrid, Idipaz, Madrid, Spain
- Centro de Investigación Biomédica en Red de Epidemiología y Salud Pública, CIBERESP, Madrid, Spain
| | - Somnath Chatterji
- Information, Evidence and Research, World Health Organization, Geneva, Switzerland
| | - Laia Egea-Cortés
- Research, Innovation and Teaching Unit. Parc Sanitari Sant Joan de Déu, Sant Boi de Llobregat, Spain
| | - Esther García-Esquinas
- Department Preventive Medicine and Public Health, Universidad Autónoma de Madrid, Idipaz, Madrid, Spain
- Centro de Investigación Biomédica en Red de Epidemiología y Salud Pública, CIBERESP, Madrid, Spain
| | | | - Seppo Koskinen
- National Institute for Health and Welfare (THL), Helsinki, Finland
| | - Ilona Koupil
- Centre for Health Equity Studies, Department of Public Health Sciences, Stockholm University, Stockholm, Sweden
- Department of Public Health Sciences, Karolinska Institutet, Stockholm, Sweden
| | - Andrzej Paja̧k
- Department of Epidemiology and Population Studies, Jagienllonian University, Krakow, Poland
| | - Martin Prince
- Global Health Institute, King’s College London, London, UK
- Centre for Global Mental Health. Health Service and Population Research Department, Institute of Psychiatry, Psychology & Neuroscience, King’s College London, London, UK
| | - Warren Sanderson
- International Institute for Applied Systems Analysis, World Population Program, Wittgenstein Centre for Demography and Global Human Capital, Laxenburg, Austria
- Department of Economics, Stony Brook University, Stony Brook, NY USA
| | - Sergei Scherbov
- International Institute for Applied Systems Analysis, World Population Program, Wittgenstein Centre for Demography and Global Human Capital, Laxenburg, Austria
- Austrian Academy of Science, Vienna Institute of Demography, Vienna, Austria
- Russian Presidential Academy of National Economy and Public Administration (RANEPA), Moscow, Russian Federation
| | | | - Aleksander Galas
- Department of Epidemiology and Preventive Medicine, Jagiellonian University, Krakow, Poland
| | - Josep Maria Haro
- Centro de Investigación Biomédica en Red de Salud Mental, CIBERSAM, Madrid, Spain
- Research, Innovation and Teaching Unit. Parc Sanitari Sant Joan de Déu, Sant Boi de Llobregat, Spain
| | - Albert Sanchez-Niubo
- Centro de Investigación Biomédica en Red de Salud Mental, CIBERSAM, Madrid, Spain
- Research, Innovation and Teaching Unit. Parc Sanitari Sant Joan de Déu, Sant Boi de Llobregat, Spain
| | - Vassilis P. Plagianakos
- Department of Computer Science and Biomedical Informatics, University of Thessaly, Lamia, Greece
| | - Demosthenes Panagiotakos
- Department of Nutrition and Dietetics, School of Health Science and Education, Harokopio University, Athens, Greece
| |
Collapse
|
2
|
Olaya B, Moneta MV, Doménech-Abella J, Miret M, Bayes I, Ayuso-Mateos JL, Haro JM. Mobility Difficulties, Physical Activity, and All-cause Mortality Risk in a Nationally representative Sample of Older Adults. J Gerontol A Biol Sci Med Sci 2019. [PMID: 28633439 DOI: 10.1093/gerona/glx121] [Citation(s) in RCA: 23] [Impact Index Per Article: 4.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022] Open
Abstract
Background This study sought to determine the association between levels of physical activity and mobility difficulties and time to death while accounting for the effect of several confounders. We also examined the possible interaction between them and how various daily-life mobility difficulties could predict all-cause mortality. Methods A nationally representative sample of 2,074 noninstitutionalized adults aged 60 years and older was analyzed. Vital status over a 3-year follow-up period was ascertained through national registers or by asking participants' relatives. Kaplan-Meier survival curves were stratified by levels of physical activity and mobility difficulties. Unadjusted and adjusted Cox proportional hazards regression models (by age, gender, marital status, years of education, multimorbidity, tobacco and alcohol consumption, depression, and memory function) were calculated, and interactions between the predictors and the covariates were explored. Results There was a dose-gradient effect of physical activity on time to death, with high levels associated with a 51% lower risk of dying, compared with moderate physical activity. Each unit increase in mobility functioning was associated with a 2% drop in mortality. Difficulties in standing for long periods, getting where one wants to go or extending arms to reach objects, were also found to be strong predictors of all-cause mortality. Conclusions Our results confirm the importance of older adults practicing moderate-to-vigorous physical activity. The assessment of self-reported difficulties in daily-life mobility activities, such as standing for long periods or not being able to move around, could be used in health settings as a screening for mortality risk.
Collapse
Affiliation(s)
- Beatriz Olaya
- Research, Innovation and Teaching Unit, Institut de Recerca Sant Joan de Déu, Esplugues de Llobregat, Spain.,Parc Sanitari Sant Joan de Déu, Universitat de Barcelona, Fundació Sant Joan de Déu, Sant Boi de Llobregat, Spain.,Instituto de Salud Carlos III, Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Madrid, Spain
| | - Maria Victoria Moneta
- Research, Innovation and Teaching Unit, Institut de Recerca Sant Joan de Déu, Esplugues de Llobregat, Spain.,Parc Sanitari Sant Joan de Déu, Universitat de Barcelona, Fundació Sant Joan de Déu, Sant Boi de Llobregat, Spain.,Instituto de Salud Carlos III, Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Madrid, Spain
| | - Joan Doménech-Abella
- Research, Innovation and Teaching Unit, Institut de Recerca Sant Joan de Déu, Esplugues de Llobregat, Spain.,Parc Sanitari Sant Joan de Déu, Universitat de Barcelona, Fundació Sant Joan de Déu, Sant Boi de Llobregat, Spain
| | - Marta Miret
- Instituto de Salud Carlos III, Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Madrid, Spain.,Department of Psychiatry, Universidad Autónoma de Madrid, Spain.,Department of Psychiatry, Instituto de Investigación Sanitaria Princesa (IP), Hospital Universitario de La Princesa, Madrid, Spain
| | - Ivet Bayes
- Research, Innovation and Teaching Unit, Institut de Recerca Sant Joan de Déu, Esplugues de Llobregat, Spain.,Parc Sanitari Sant Joan de Déu, Universitat de Barcelona, Fundació Sant Joan de Déu, Sant Boi de Llobregat, Spain
| | - José Luis Ayuso-Mateos
- Instituto de Salud Carlos III, Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Madrid, Spain.,Department of Psychiatry, Universidad Autónoma de Madrid, Spain.,Department of Psychiatry, Instituto de Investigación Sanitaria Princesa (IP), Hospital Universitario de La Princesa, Madrid, Spain
| | - Josep Maria Haro
- Research, Innovation and Teaching Unit, Institut de Recerca Sant Joan de Déu, Esplugues de Llobregat, Spain.,Parc Sanitari Sant Joan de Déu, Universitat de Barcelona, Fundació Sant Joan de Déu, Sant Boi de Llobregat, Spain.,Instituto de Salud Carlos III, Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Madrid, Spain
| |
Collapse
|
3
|
Olaya B, Moneta MV, Caballero FF, Tyrovolas S, Bayes I, Ayuso-Mateos JL, Haro JM. Latent class analysis of multimorbidity patterns and associated outcomes in Spanish older adults: a prospective cohort study. BMC Geriatr 2017; 17:186. [PMID: 28821233 PMCID: PMC5563011 DOI: 10.1186/s12877-017-0586-1] [Citation(s) in RCA: 75] [Impact Index Per Article: 10.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2016] [Accepted: 08/10/2017] [Indexed: 01/08/2023] Open
Abstract
Background This study sought to identify multimorbidity patterns and determine the association between these latent classes with several outcomes, including health, functioning, disability, quality of life and use of services, at baseline and after 3 years of follow-up. Methods We analyzed data from a representative Spanish cohort of 3541 non-institutionalized people aged 50 years old and over. Measures were taken at baseline and after 3 years of follow-up. Latent Class Analysis (LCA) was conducted using eleven common chronic conditions. Generalized linear models were conducted to determine the adjusted association of multimorbidity latent classes with several outcomes. Results 63.8% of participants were assigned to the “healthy” class, with minimum disease, 30% were classified under the “metabolic/stroke” class and 6% were assigned to the “cardiorespiratory/mental/arthritis” class. Significant cross-sectional associations were found between membership of both multimorbidity classes and poorer memory, quality of life, greater burden and more use of services. After 3 years of follow-up, the “metabolic/stroke” class was a significant predictor of lower levels of verbal fluency while the two multimorbidity classes predicted poor quality of life, problems in independent living, higher risk of hospitalization and greater use of health services. Conclusions Common chronic conditions in older people cluster together in broad categories. These broad clusters are qualitatively distinct and are important predictors of several health and functioning outcomes. Future studies are needed to understand underlying mechanisms and common risk factors for patterns of multimorbidity and to propose more effective treatments. Electronic supplementary material The online version of this article (doi:10.1186/s12877-017-0586-1) contains supplementary material, which is available to authorized users.
Collapse
Affiliation(s)
- Beatriz Olaya
- Research, Innovation and Teaching Unit, Institut de Recerca Sant Joan de Déu, Carrer Dr. Antoni Pujadas, 42, Esplugues de Llobregat, 08830, Barcelona, Spain. .,Parc Sanitari Sant Joan de Déu, Universitat de Barcelona, Fundació Sant Joan de Déu, Sant Boi de Llobregat, Barcelona, Spain. .,Instituto de Salud Carlos III, Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Madrid, Spain.
| | - Maria Victoria Moneta
- Research, Innovation and Teaching Unit, Institut de Recerca Sant Joan de Déu, Carrer Dr. Antoni Pujadas, 42, Esplugues de Llobregat, 08830, Barcelona, Spain.,Parc Sanitari Sant Joan de Déu, Universitat de Barcelona, Fundació Sant Joan de Déu, Sant Boi de Llobregat, Barcelona, Spain.,Instituto de Salud Carlos III, Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Madrid, Spain
| | - Francisco Félix Caballero
- Instituto de Salud Carlos III, Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Madrid, Spain.,Department of Psychiatry, Universidad Autónoma de Madrid, Madrid, Spain.,Department of Psychiatry, Instituto de Investigación Sanitaria Princesa (IP), Hospital Universitario de La Princesa, Madrid, Spain
| | - Stefanos Tyrovolas
- Research, Innovation and Teaching Unit, Institut de Recerca Sant Joan de Déu, Carrer Dr. Antoni Pujadas, 42, Esplugues de Llobregat, 08830, Barcelona, Spain.,Parc Sanitari Sant Joan de Déu, Universitat de Barcelona, Fundació Sant Joan de Déu, Sant Boi de Llobregat, Barcelona, Spain.,Instituto de Salud Carlos III, Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Madrid, Spain
| | - Ivet Bayes
- Research, Innovation and Teaching Unit, Institut de Recerca Sant Joan de Déu, Carrer Dr. Antoni Pujadas, 42, Esplugues de Llobregat, 08830, Barcelona, Spain.,Parc Sanitari Sant Joan de Déu, Universitat de Barcelona, Fundació Sant Joan de Déu, Sant Boi de Llobregat, Barcelona, Spain
| | - José Luis Ayuso-Mateos
- Instituto de Salud Carlos III, Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Madrid, Spain.,Department of Psychiatry, Universidad Autónoma de Madrid, Madrid, Spain.,Department of Psychiatry, Instituto de Investigación Sanitaria Princesa (IP), Hospital Universitario de La Princesa, Madrid, Spain
| | - Josep Maria Haro
- Research, Innovation and Teaching Unit, Institut de Recerca Sant Joan de Déu, Carrer Dr. Antoni Pujadas, 42, Esplugues de Llobregat, 08830, Barcelona, Spain.,Parc Sanitari Sant Joan de Déu, Universitat de Barcelona, Fundació Sant Joan de Déu, Sant Boi de Llobregat, Barcelona, Spain.,Instituto de Salud Carlos III, Centro de Investigación Biomédica en Red de Salud Mental (CIBERSAM), Madrid, Spain
| |
Collapse
|
4
|
Almoosawi S, Cole D, Nicholson S, Bayes I, Teucher B, Bates B, Mindell J, Tipping S, Deverill C, Stephen AM. Biomarkers of diabetes risk in the National Diet and Nutrition Survey rolling programme (2008-2011). J Epidemiol Community Health 2013; 68:51-6. [PMID: 24052516 PMCID: PMC3888635 DOI: 10.1136/jech-2013-202885] [Citation(s) in RCA: 9] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/27/2022]
Abstract
This study describes the distribution of glycosylated haemoglobin (HbA1c) and glucose concentrations in the combined year 1 (2008–2009), year 2 (2009–2010) and year 3 (2010–2011) of the National Diet and Nutrition Survey (NDNS) rolling programme. The NDNS rolling programme is a nationally representative survey of food consumption, nutrient intakes and nutritional status of people aged 1.5 years and over living in England, Wales, Scotland and Northern Ireland. The study population comprised survey members who completed three or four days of dietary recording and who provided a blood sample. After excluding survey members with self-reported diabetes (n=25), there were 1016 results for HbA1c and 942 for glucose (not the same individuals in each case). Around 5.4% of men and 1.7% of women aged 19–64 years, and 5.1% of men and 5.9% of women aged ≥65 years had impaired fasting glucose (glucose concentrations 6.1–6.9 mmol/L). Over 20% of men aged ≥65 years had fasting glucose concentrations above the clinical cut-off for diabetes (≥7 mmol/L) compared to 2.1% of women of similar age (p=0.007). Similarly, 16.4% of men had HbA1c concentrations ≥6.5%, compared to 1.5% of women (p=0.003). Children and teenagers had fasting glucose and HbA1c values largely within the normal range. To conclude, this is the first study to provide data on the distribution of HbA1c and glucose concentrations in a nationally representative sample of the British population. The high prevalence of men aged ≥65 years with HbA1c and glucose concentrations above the clinical cut-off of diabetes warrants further attention.
Collapse
Affiliation(s)
- S Almoosawi
- MRC Human Nutrition Research, Elsie Widdowson Laboratory, , Cambridge, UK
| | | | | | | | | | | | | | | | | | | |
Collapse
|