HealthCare | Data | Publicly available biomedical data

Longitudinal Aging Study in India (LASI)

by

The Longitudinal Aging Study in India (LASI) aims to supply the data needed to understand the situation of India’s elderly population. The evidence base contributes to cross-national studies of aging and informs the design of policies that can protect and support the growing elderly community. The LASI contains various types of data, including demographic data, health data, lifestyle data, social data, economic data, cognitive data, biomarker data, medical history data, and environment data. The pilot portion of the LASI project is supported by an R21 exploratory grant from the National Institute on Aging (NIA). The LASI pilot survey targeted 1,600 individuals aged 45 and older and their spouses. The instruments of LASI pilot include Computer-Assisted Personal Interview (CAPI) and collection of biomarkers

The study is conducted by the International Institute for Population Sciences (IIPS), in collaboration with several academic institutions, including Harvard School of Public Health, University of Southern California, and the University of Southern Denmark, and is funded by NIA/NIH, United Nations Population Fund (UNFPA) India, Ministry of Health and Family Welfare in India, and other academic institutions. 

View Resource
Internal | Machine Learning | Training Resources | All Resources

Machine Learning Essentials for Biomedical Data Science

by

An educational playlist (including 11 videos) covering the key essentials for using machine learning as part of a data science analysis pipeline. While topics are primarily framed around applications in biomedicine, this content is broadly applicable to other domains. This series was prepared at the Cedars Sinai Medical Center in Los Angeles by Dr. Ryan Urbanowicz of the Department of Computational Biomedicine.

View Resource
HealthCare | Publicly available biomedical data | Data

Mexican Health and Aging Study (MHAS)

by

The Mexican Health and Aging Study (MHAS) is a national longitudinal study of adults aged 50 or older in Mexico. The baseline survey, with national and urban/rural representation of adults born in 1951 or earlier, was conducted in 2001 with follow-up interviews in 2003, 2012, 2015, 2018 and 2021. MHAS is partly sponsored by the National Institutes of Health/National Institute on Aging (grant number NIH R01AG018016) in the United States and the Instituto Nacional de Estadística y Geografía (INEGI) in Mexico.

 

View Resource
HealthCare | Data | Publicly available biomedical data

Midlife in the United States (MIDUS)

by

Midlife in the United States (MIDUS) is a longitudinal research project that aims to examine the physical, psychological, and social factors that contribute to health and well-being in midlife and beyond. This study is conducted by a multidisciplinary team led by University of Wisconsin-Madison and is funded by various sources including NIA, NSF, NIMH, and multiple academic institutions. MIDUS has been conducted in three stages: MIDUS I, MIDUS II, AND MIDUS III. 

 

MIDUS I was conducted between 1995 and 1996 and involved data collection from over 7,000 adults aged 25 to 74. This original data collection focused on physical health, mental health, social relationship, and life experiences. 

 

MIDUS II was conducted between 2004 and 2006 and collected data from more than 4900 of the MIDUS I participants. This second phase included additional measures for mental and physical health and also new information on cognitive function, genetics, and biomarkers. 

 

MIDUS III was conducted between 2013 and 2014 and collected data of more than 4500 participants from MIDUS I. This latest phase focused on aging and included information on physical and cognitive function, health care utilization, and social support.

View Resource
HealthCare | Data | Publicly available biomedical data

Minority Aging Research Study (MARS)

by

The Minority Aging Research Study is a unique study designed for older African Americans. The goal is to learn how to prevent common problems associated with aging, including poor memory, slowed walking and weakness. This study aims to understand why we lose certain abilities as we get older, figure out how to improve these abilities, and discover ways to prevent aging-related problems from affecting our children and grandchildren. 

 

View Resource
Software | Feature learning | Technology: Tools, Hardware, and Software | All Resources

Multifactor Dimensionality Reduction (scikit-MDR)

by

A scikit-learn-compatible Python implementation of Multifactor Dimensionality Reduction (MDR) for feature construction. This project is still under active development and we encourage you to check back on this repository regularly for updates. MDR is an effective feature construction algorithm that is capable of modeling higher-order interactions and capturing complex patterns in data sets. MDR currently only works with categorical features and supports both binary classification and regression problems. We are working on expanding the algorithm to cover more problem types and provide more convenience features.

 

View Resource
HealthCare | Data | Publicly available biomedical data

National Archive of Computerized Data on Aging (NACDA)

by

The National Archive of Computerized Data on Aging (NACDA) is a data archive concerned with the process of aging, health-related subjects, and the attitudes and behavior of the aged population. It consists of over sixteen hundred datasets relevant to gerontological research. NACDA operates under the auspices of the Inter-university Consortium for Political and Social Research (ICPSR) at the University of Michigan and is sponsored by the National Institute of Aging. The mission of NACDA is to advance research on aging by helping researchers to profit from the under-exploited potential of a broad range of datasets. 

 

View Resource