A Smart-Home System to Unobtrusively and Continuously Assess Loneliness in Older Adults

Johanna Austin, Hiroko Dodge, Thomas Riley, Peter Jacobs, Stephen Thielke, Jeffrey Kaye

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Loneliness is a common condition in older adults and is associated with increased morbidity and mortality, decreased sleep quality, and increased risk of cognitive decline. Assessing loneliness in older adults is challenging due to the negative desirability biases associated with being lonely. Thus, it is necessary to develop more objective techniques to assess loneliness in older adults. In this paper, we describe a system to measure loneliness by assessing in-home behavior using wireless motion and contact sensors, phone monitors, and computer software as well as algorithms developed to assess key behaviors of interest. We then present results showing the accuracy of the system in detecting loneliness in a longitudinal study of 16 older adults who agreed to have the sensor platform installed in their own homes for up to 8 months. We show that loneliness is significantly associated with both time out-of-home (β = -0.88 and p2 for the model was 0.35. We also show the model's ability to predict out-of-sample loneliness, demonstrating that the correlation between true loneliness and predicted out-of-sample loneliness is 0.48. When compared with the University of California at Los Angeles loneliness score, the normalized mean absolute error of the predicted loneliness scores was 0.81 and the normalized root mean squared error was 0.91. These results represent first steps toward an unobtrusive, objective method for the prediction of loneliness among older adults, and mark the first time multiple objective behavioral measures that have been related to this key health outcome.

Original languageEnglish (US)
Article number7488979
JournalIEEE Journal of Translational Engineering in Health and Medicine
Volume4
DOIs
StatePublished - 2016

Fingerprint

Loneliness
Contact sensors
Health
Sensors
Aptitude
Los Angeles
Longitudinal Studies
Sleep
Software

Keywords

  • ambient assessment
  • In-home monitoring
  • loneliness
  • longitudinal models
  • older adults

ASJC Scopus subject areas

  • Biomedical Engineering
  • Medicine(all)

Cite this

A Smart-Home System to Unobtrusively and Continuously Assess Loneliness in Older Adults. / Austin, Johanna; Dodge, Hiroko; Riley, Thomas; Jacobs, Peter; Thielke, Stephen; Kaye, Jeffrey.

In: IEEE Journal of Translational Engineering in Health and Medicine, Vol. 4, 7488979, 2016.

Research output: Contribution to journalArticle

@article{c8c4ad3ed1dc4204b8c601ecd20a193c,
title = "A Smart-Home System to Unobtrusively and Continuously Assess Loneliness in Older Adults",
abstract = "Loneliness is a common condition in older adults and is associated with increased morbidity and mortality, decreased sleep quality, and increased risk of cognitive decline. Assessing loneliness in older adults is challenging due to the negative desirability biases associated with being lonely. Thus, it is necessary to develop more objective techniques to assess loneliness in older adults. In this paper, we describe a system to measure loneliness by assessing in-home behavior using wireless motion and contact sensors, phone monitors, and computer software as well as algorithms developed to assess key behaviors of interest. We then present results showing the accuracy of the system in detecting loneliness in a longitudinal study of 16 older adults who agreed to have the sensor platform installed in their own homes for up to 8 months. We show that loneliness is significantly associated with both time out-of-home (β = -0.88 and p2 for the model was 0.35. We also show the model's ability to predict out-of-sample loneliness, demonstrating that the correlation between true loneliness and predicted out-of-sample loneliness is 0.48. When compared with the University of California at Los Angeles loneliness score, the normalized mean absolute error of the predicted loneliness scores was 0.81 and the normalized root mean squared error was 0.91. These results represent first steps toward an unobtrusive, objective method for the prediction of loneliness among older adults, and mark the first time multiple objective behavioral measures that have been related to this key health outcome.",
keywords = "ambient assessment, In-home monitoring, loneliness, longitudinal models, older adults",
author = "Johanna Austin and Hiroko Dodge and Thomas Riley and Peter Jacobs and Stephen Thielke and Jeffrey Kaye",
year = "2016",
doi = "10.1109/JTEHM.2016.2579638",
language = "English (US)",
volume = "4",
journal = "IEEE Journal of Translational Engineering in Health and Medicine",
issn = "2168-2372",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - A Smart-Home System to Unobtrusively and Continuously Assess Loneliness in Older Adults

AU - Austin, Johanna

AU - Dodge, Hiroko

AU - Riley, Thomas

AU - Jacobs, Peter

AU - Thielke, Stephen

AU - Kaye, Jeffrey

PY - 2016

Y1 - 2016

N2 - Loneliness is a common condition in older adults and is associated with increased morbidity and mortality, decreased sleep quality, and increased risk of cognitive decline. Assessing loneliness in older adults is challenging due to the negative desirability biases associated with being lonely. Thus, it is necessary to develop more objective techniques to assess loneliness in older adults. In this paper, we describe a system to measure loneliness by assessing in-home behavior using wireless motion and contact sensors, phone monitors, and computer software as well as algorithms developed to assess key behaviors of interest. We then present results showing the accuracy of the system in detecting loneliness in a longitudinal study of 16 older adults who agreed to have the sensor platform installed in their own homes for up to 8 months. We show that loneliness is significantly associated with both time out-of-home (β = -0.88 and p2 for the model was 0.35. We also show the model's ability to predict out-of-sample loneliness, demonstrating that the correlation between true loneliness and predicted out-of-sample loneliness is 0.48. When compared with the University of California at Los Angeles loneliness score, the normalized mean absolute error of the predicted loneliness scores was 0.81 and the normalized root mean squared error was 0.91. These results represent first steps toward an unobtrusive, objective method for the prediction of loneliness among older adults, and mark the first time multiple objective behavioral measures that have been related to this key health outcome.

AB - Loneliness is a common condition in older adults and is associated with increased morbidity and mortality, decreased sleep quality, and increased risk of cognitive decline. Assessing loneliness in older adults is challenging due to the negative desirability biases associated with being lonely. Thus, it is necessary to develop more objective techniques to assess loneliness in older adults. In this paper, we describe a system to measure loneliness by assessing in-home behavior using wireless motion and contact sensors, phone monitors, and computer software as well as algorithms developed to assess key behaviors of interest. We then present results showing the accuracy of the system in detecting loneliness in a longitudinal study of 16 older adults who agreed to have the sensor platform installed in their own homes for up to 8 months. We show that loneliness is significantly associated with both time out-of-home (β = -0.88 and p2 for the model was 0.35. We also show the model's ability to predict out-of-sample loneliness, demonstrating that the correlation between true loneliness and predicted out-of-sample loneliness is 0.48. When compared with the University of California at Los Angeles loneliness score, the normalized mean absolute error of the predicted loneliness scores was 0.81 and the normalized root mean squared error was 0.91. These results represent first steps toward an unobtrusive, objective method for the prediction of loneliness among older adults, and mark the first time multiple objective behavioral measures that have been related to this key health outcome.

KW - ambient assessment

KW - In-home monitoring

KW - loneliness

KW - longitudinal models

KW - older adults

UR - http://www.scopus.com/inward/record.url?scp=84976567596&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84976567596&partnerID=8YFLogxK

U2 - 10.1109/JTEHM.2016.2579638

DO - 10.1109/JTEHM.2016.2579638

M3 - Article

AN - SCOPUS:84976567596

VL - 4

JO - IEEE Journal of Translational Engineering in Health and Medicine

JF - IEEE Journal of Translational Engineering in Health and Medicine

SN - 2168-2372

M1 - 7488979

ER -