Inferring Destinations and Activity Types of Older Adults From GPS Data: Algorithm Development and Validation

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

Background

Outdoor mobility is an important aspect of older adults’ functional status. GPS has been used to create indicators reflecting the spatiotemporal dimensions of outdoor mobility for applications in health and aging. However, outdoor mobility is a multidimensional construct. There is, as of yet, no classification algorithm that groups and characterizes older adults’ outdoor mobility based on its semantic aspects (ie, mobility intentions and motivations) by integrating geographic and domain knowledge.

Objective

This study assesses the feasibility of using GPS to determine semantic dimensions of older adults’ outdoor mobility, including destinations and activity types.

Methods

A total of 5 healthy individuals, aged 65 years or older, carried a GPS device when traveling outside their homes for 4 weeks. The participants were also given a travel diary to record details of all excursions from their homes, including date, time, and destination information. We first designed and implemented an algorithm to extract destinations and infer activity types (eg, food, shopping, and sport) from the GPS data. We then evaluated the performance of the GPS-derived destination and activity information against the traditional diary method.

Results

Our results detected the stop locations of older adults from their GPS data with an F1 score of 87%. On average, the extracted home locations were within a 40.18-meter (SD 1.18) distance of the actual home locations. For the activity-inference algorithm, our results reached an F1 score of 86% for all participants, suggesting a reasonable accuracy against the travel diary recordings. Our results also suggest that the activity inference’s accuracy measure differed by neighborhood characteristics (ie, Walk Score).

Conclusions

We conclude that GPS technology is accurate for determining semantic dimensions of outdoor mobility. However, further improvements may be needed to develop a robust application of this system that can be adopted in clinical practice.

Related collections

Most cited references 29

Record: found
Abstract: found
Article: not found

Using Measurement-Based Care to Enhance Any Treatment.

Kelli Scott, Cara Lewis (2015)

Measurement-based care (MBC) can be defined as the practice of basing clinical care on client data collected throughout treatment. MBC is considered a core component of numerous evidence-based practices (e.g., Beck & Beck, 2011; Klerman, Weissman, Rounsaville, & Chevron, 1984) and has emerging empirical support as an evidence-based framework that can be added to any treatment (Lambert et al., 2003, Trivedi et al., 2007). The observed benefits of MBC are numerous. MBC provides insight into treatment progress, highlights ongoing treatment targets, reduces symptom deterioration, and improves client outcomes (Lambert et al., 2005). Moreover, as a framework to guide treatment, MBC has transtheoretical and transdiagnostic relevance with broad reach across clinical settings. Although MBC has primarily focused on assessing symptoms (e.g., depression, anxiety), MBC can also be used to assess valuable information about (a) symptoms, (b) functioning and satisfaction with life, (c) putative mechanisms of change (e.g., readiness to change), and (d) the treatment process (e.g., session feedback, working alliance). This paper provides an overview of the benefits and challenges of MBC implementation when conceptualized as a transtheoretical and transdiagnostic framework for evaluating client therapy progress and outcomes across these four domains. The empirical support for MBC use is briefly reviewed, an adult case example is presented to serve as a guide for successful implementation of MBC in clinical practice, and future directions to maximize MBC utility are discussed.

0 comments Cited 113 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

What makes a community age-friendly: A review of international literature.

Jo-Anne Everingham, Jeni Warburton, VIVIAN LUI … (2009)

This paper undertakes a comprehensive review of the growing international literature on age-friendly communities. It examines a range of approaches and identifies the key attributes associated with creating a sustainable environment for seniors. The authors critically evaluate emerging policy trends and models and suggest directions for future research attention. The discussion provides important information and insights for the development of ageing policy and planning in Australia.

0 comments Cited 106 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

Validation of Walk Score for estimating access to walkable amenities.

Shira I. Dunsiger, Bess Marcus, Maria Carr (2011)

Proximity to walkable destinations or amenities is thought to influence physical activity behaviour. Previous efforts attempting to calculate neighbourhood walkability have relied on self-report or time-intensive and costly measures. Walk Score is a novel and publicly available website that estimates neighbourhood walkability based on proximity to 13 amenity categories (eg, grocery stores, coffee shops, restaurants, bars, movie theatres, schools, parks, libraries, book stores, fitness centres, drug stores, hardware stores, clothing/music stores). The purpose of this study is to test the validity and reliability of Walk Score for estimating access to objectively measured walkable amenities. Walk Scores of 379 residential/non-residential addresses in Rhode Island were manually calculated. Geographic information systems (GIS) was used to objectively measure 4194 walkable amenities in the 13 Walk Score categories. GIS data were aggregated from publicly available data sources. Sums of amenities within each category were matched to address data, and Pearson correlations were calculated between the category sums and address Walk Scores. Significant correlations were identified between Walk Score and all categories of aggregated walkable destinations within a 1-mile buffer of the 379 residential and non-residential addresses. Test-retest reliability correlation coefficients for a subsample of 100 addresses were 1.0. These results support Walk Score as a reliable and valid measure of estimating access to walkable amenities. Walk Score may be a convenient and inexpensive option for researchers interested in exploring the relationship between access to walkable amenities and health behaviours such as physical activity.

0 comments Cited 88 times – based on 0 reviews      Review now

Bookmark

All references

Author and article information

Contributors

Sayeh Bayat:

ORCID: https://orcid.org/0000-0003-2554-2140

Institute of Biomaterials and Biomedical EngineeringUniversity of Toronto550 University AvenueToronto, ONCanada1 416 597 3422 ext 7345sayeh.bayat@mail.utoronto.ca

Journal

Journal ID (nlm-ta): JMIR Aging

Journal ID (iso-abbrev): JMIR Aging

Journal ID (publisher-id): JA

Title: JMIR Aging

Publisher: JMIR Publications (Toronto, Canada )

ISSN (Electronic): 2561-7605

Publication date Collection: Jul-Dec 2020

Publication date (Electronic): 28 July 2020

Volume: 3

Issue: 2

Electronic Location Identifier: e18008

Affiliations

[1 ] Institute of Biomaterials and Biomedical Engineering University of Toronto Toronto, ON Canada

[2 ] KITE Research Institute Toronto Rehabilitation Institute University Health Network Toronto, ON Canada

[3 ] Department of Medicine Baycrest Health Sciences Toronto, ON Canada

[4 ] Department of Medicine University of Toronto Toronto, ON Canada

[5 ] Rotman Research Institute Baycrest Health Sciences Toronto, ON Canada

[6 ] Institute of Health Policy, Management and Evaluation University of Toronto Toronto, ON Canada

[7 ] Department of Psychiatry Sunnybrook Health Sciences Centre Toronto, ON Canada

[8 ] Department of Psychiatry University of Toronto Toronto, ON Canada

[9 ] Institute of Medical Science University of Toronto Toronto, ON Canada

[10 ] Laboratoire en Informatique Cognitive et Environnements de Formation Research Institute Department of Science and Technology TELUQ University Montreal, QC Canada

[11 ] Department of Occupational Therapy and Occupational Science University of Toronto Toronto, ON Canada

Author notes

Corresponding Author: Sayeh Bayat sayeh.bayat@ 123456mail.utoronto.ca

Author information

Sayeh Bayat https://orcid.org/0000-0003-2554-2140

Gary Naglie https://orcid.org/0000-0002-6274-0894

Mark J Rapoport https://orcid.org/0000-0003-2670-1975

Elaine Stasiulis https://orcid.org/0000-0003-3572-9371

Belkacem Chikhaoui https://orcid.org/0000-0002-5608-3488

Alex Mihailidis https://orcid.org/0000-0003-2233-0919

Article

Publisher ID: v3i2e18008

DOI: 10.2196/18008

PMC ID: 7420517

PubMed ID: 32720647

SO-VID: 3b58eca5-1478-4dbb-9298-f0c4dfb87193

License:

This is an open-access article distributed under the terms of the Creative Commons Attribution License ( https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR Aging, is properly cited. The complete bibliographic information, a link to the original publication on http://aging.jmir.org, as well as this copyright and license information must be included.

History

Date received : 31 January 2020

Date revision requested : 20 February 2020

Date revision received : 19 March 2020

Date accepted : 1 May 2020

Submit your digital health research with an established publisher
- celebrating 25 years of open access