Using the NANA toolkit at home to predict older adults' future depression

J A Andrews, R F Harrison, L J E Brown, L M MacLean, F Hwang, T Smith, Elizabeth A Williams, C Timon, T Adlam, H Khadra, A J Astell

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

BACKGROUND: Depression is currently underdiagnosed among older adults. As part of the Novel Assessment of Nutrition and Aging (NANA) validation study, 40 older adults self-reported their mood using a touchscreen computer over three, one-week periods. Here, we demonstrate the potential of these data to predict future depression status.

METHODS: We analysed data from the NANA validation study using a machine learning approach. We applied the least absolute shrinkage and selection operator with a logistic model to averages of six measures of mood, with depression status according to the Geriatric Depression Scale 10 weeks later as the outcome variable. We tested multiple values of the selection parameter in order to produce a model with low deviance. We used a cross-validation framework to avoid overspecialisation, and receiver operating characteristic (ROC) curve analysis to determine the quality of the fitted model.

RESULTS: The model we report contained coefficients for two variables: sadness and tiredness, as well as a constant. The cross-validated area under the ROC curve for this model was 0.88 (CI: 0.69-0.97).

LIMITATIONS: While results are based on a small sample, the methodology for the selection of variables appears suitable for the problem at hand, suggesting promise for a wider study and ultimate deployment with older adults at increased risk of depression.

CONCLUSIONS: We have identified self-reported scales of sadness and tiredness as sensitive measures which have the potential to predict future depression status in older adults, partially addressing the problem of underdiagnosis.

Original languageEnglish
Pages (from-to)187-190
Number of pages4
JournalJournal of Affective Disorders
Volume213
Early online date14 Feb 2017
DOIs
Publication statusPublished - 15 Apr 2017

Fingerprint

Nutrition Assessment
Depression
Validation Studies
ROC Curve
Geriatrics
Hand
Logistic Models

Keywords

  • Journal Article
  • mental health
  • technology
  • depression
  • nutrition
  • cognition

Cite this

Andrews, J. A., Harrison, R. F., Brown, L. J. E., MacLean, L. M., Hwang, F., Smith, T., ... Astell, A. J. (2017). Using the NANA toolkit at home to predict older adults' future depression. Journal of Affective Disorders, 213, 187-190. https://doi.org/10.1016/j.jad.2017.02.019

Using the NANA toolkit at home to predict older adults' future depression. / Andrews, J A; Harrison, R F; Brown, L J E; MacLean, L M; Hwang, F; Smith, T; Williams, Elizabeth A; Timon, C; Adlam, T; Khadra, H; Astell, A J.

In: Journal of Affective Disorders, Vol. 213, 15.04.2017, p. 187-190.

Research output: Contribution to journalArticle

Andrews, JA, Harrison, RF, Brown, LJE, MacLean, LM, Hwang, F, Smith, T, Williams, EA, Timon, C, Adlam, T, Khadra, H & Astell, AJ 2017, 'Using the NANA toolkit at home to predict older adults' future depression', Journal of Affective Disorders, vol. 213, pp. 187-190. https://doi.org/10.1016/j.jad.2017.02.019
Andrews, J A ; Harrison, R F ; Brown, L J E ; MacLean, L M ; Hwang, F ; Smith, T ; Williams, Elizabeth A ; Timon, C ; Adlam, T ; Khadra, H ; Astell, A J. / Using the NANA toolkit at home to predict older adults' future depression. In: Journal of Affective Disorders. 2017 ; Vol. 213. pp. 187-190.
@article{d6c6e088db2b4d30a0543a84cd3e0877,
title = "Using the NANA toolkit at home to predict older adults' future depression",
abstract = "BACKGROUND: Depression is currently underdiagnosed among older adults. As part of the Novel Assessment of Nutrition and Aging (NANA) validation study, 40 older adults self-reported their mood using a touchscreen computer over three, one-week periods. Here, we demonstrate the potential of these data to predict future depression status.METHODS: We analysed data from the NANA validation study using a machine learning approach. We applied the least absolute shrinkage and selection operator with a logistic model to averages of six measures of mood, with depression status according to the Geriatric Depression Scale 10 weeks later as the outcome variable. We tested multiple values of the selection parameter in order to produce a model with low deviance. We used a cross-validation framework to avoid overspecialisation, and receiver operating characteristic (ROC) curve analysis to determine the quality of the fitted model.RESULTS: The model we report contained coefficients for two variables: sadness and tiredness, as well as a constant. The cross-validated area under the ROC curve for this model was 0.88 (CI: 0.69-0.97).LIMITATIONS: While results are based on a small sample, the methodology for the selection of variables appears suitable for the problem at hand, suggesting promise for a wider study and ultimate deployment with older adults at increased risk of depression.CONCLUSIONS: We have identified self-reported scales of sadness and tiredness as sensitive measures which have the potential to predict future depression status in older adults, partially addressing the problem of underdiagnosis.",
keywords = "Journal Article, mental health, technology, depression, nutrition, cognition",
author = "Andrews, {J A} and Harrison, {R F} and Brown, {L J E} and MacLean, {L M} and F Hwang and T Smith and Williams, {Elizabeth A} and C Timon and T Adlam and H Khadra and Astell, {A J}",
note = "Copyright {\circledC} 2017 The Authors. Published by Elsevier B.V. All rights reserved.",
year = "2017",
month = "4",
day = "15",
doi = "10.1016/j.jad.2017.02.019",
language = "English",
volume = "213",
pages = "187--190",
journal = "Journal of Affective Disorders",
issn = "0165-0327",
publisher = "Elsevier",

}

TY - JOUR

T1 - Using the NANA toolkit at home to predict older adults' future depression

AU - Andrews, J A

AU - Harrison, R F

AU - Brown, L J E

AU - MacLean, L M

AU - Hwang, F

AU - Smith, T

AU - Williams, Elizabeth A

AU - Timon, C

AU - Adlam, T

AU - Khadra, H

AU - Astell, A J

N1 - Copyright © 2017 The Authors. Published by Elsevier B.V. All rights reserved.

PY - 2017/4/15

Y1 - 2017/4/15

N2 - BACKGROUND: Depression is currently underdiagnosed among older adults. As part of the Novel Assessment of Nutrition and Aging (NANA) validation study, 40 older adults self-reported their mood using a touchscreen computer over three, one-week periods. Here, we demonstrate the potential of these data to predict future depression status.METHODS: We analysed data from the NANA validation study using a machine learning approach. We applied the least absolute shrinkage and selection operator with a logistic model to averages of six measures of mood, with depression status according to the Geriatric Depression Scale 10 weeks later as the outcome variable. We tested multiple values of the selection parameter in order to produce a model with low deviance. We used a cross-validation framework to avoid overspecialisation, and receiver operating characteristic (ROC) curve analysis to determine the quality of the fitted model.RESULTS: The model we report contained coefficients for two variables: sadness and tiredness, as well as a constant. The cross-validated area under the ROC curve for this model was 0.88 (CI: 0.69-0.97).LIMITATIONS: While results are based on a small sample, the methodology for the selection of variables appears suitable for the problem at hand, suggesting promise for a wider study and ultimate deployment with older adults at increased risk of depression.CONCLUSIONS: We have identified self-reported scales of sadness and tiredness as sensitive measures which have the potential to predict future depression status in older adults, partially addressing the problem of underdiagnosis.

AB - BACKGROUND: Depression is currently underdiagnosed among older adults. As part of the Novel Assessment of Nutrition and Aging (NANA) validation study, 40 older adults self-reported their mood using a touchscreen computer over three, one-week periods. Here, we demonstrate the potential of these data to predict future depression status.METHODS: We analysed data from the NANA validation study using a machine learning approach. We applied the least absolute shrinkage and selection operator with a logistic model to averages of six measures of mood, with depression status according to the Geriatric Depression Scale 10 weeks later as the outcome variable. We tested multiple values of the selection parameter in order to produce a model with low deviance. We used a cross-validation framework to avoid overspecialisation, and receiver operating characteristic (ROC) curve analysis to determine the quality of the fitted model.RESULTS: The model we report contained coefficients for two variables: sadness and tiredness, as well as a constant. The cross-validated area under the ROC curve for this model was 0.88 (CI: 0.69-0.97).LIMITATIONS: While results are based on a small sample, the methodology for the selection of variables appears suitable for the problem at hand, suggesting promise for a wider study and ultimate deployment with older adults at increased risk of depression.CONCLUSIONS: We have identified self-reported scales of sadness and tiredness as sensitive measures which have the potential to predict future depression status in older adults, partially addressing the problem of underdiagnosis.

KW - Journal Article

KW - mental health

KW - technology

KW - depression

KW - nutrition

KW - cognition

UR - https://doi.org/10.1016/j.jad.2017.02.019

UR - https://doi.org/10.1016/j.jad.2017.02.019

U2 - 10.1016/j.jad.2017.02.019

DO - 10.1016/j.jad.2017.02.019

M3 - Article

VL - 213

SP - 187

EP - 190

JO - Journal of Affective Disorders

JF - Journal of Affective Disorders

SN - 0165-0327

ER -