Modeling individual differences: A case study of the application of system identification for personalizing a physical activity intervention

Sayali S. Phatak, Mohammad T. Freigoun, César A. Martín, Daniel Rivera, Elizabeth V. Korinek, Marc Adams, Matthew Buman, Predrag Klasnja, Eric B. Hekler

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Background: Control systems engineering methods, particularly, system identification (system ID), offer an idiographic (i.e., person-specific) approach to develop dynamic models of physical activity (PA) that can be used to personalize interventions in a systematic, scalable way. The purpose of this work is to: (1) apply system ID to develop individual dynamical models of PA (steps/day measured using Fitbit Zip) in the context of a goal setting and positive reinforcement intervention informed by Social Cognitive Theory; and (2) compare insights on potential tailoring variables (i.e., predictors expected to influence steps and thus moderate the suggested step goal and points for goal achievement) selected using the idiographic models to those selected via a nomothetic (i.e., aggregated across individuals) approach. Method: A personalized goal setting and positive reinforcement intervention was deployed for 14 weeks. Baseline PA measured in weeks 1–2 was used to inform personalized daily step goals delivered in weeks 3–14. Goals and expected reward points (granted upon goal achievement) were pseudo-randomly assigned using techniques from system ID, with goals ranging from their baseline median steps/day up to 2.5× baseline median steps/day, and points ranging from 100 to 500 (i.e., $0.20–$1.00). Participants completed a series of daily self-report measures. Auto Regressive with eXogenous Input (ARX) modeling and multilevel modeling (MLM) were used as the idiographic and nomothetic approaches, respectively. Results: Participants (N = 20, mean age = 47.25 ± 6.16 years, 90% female) were insufficiently active, overweight (mean BMI = 33.79 ± 6.82 kg/m2) adults. Results from ARX modeling suggest that individuals differ in the factors (e.g., perceived stress, weekday/weekend) that influence their observed steps/day. In contrast, the nomothetic model from MLM suggested that goals and weekday/weekend were the key variables that were predictive of steps. Assuming the ARX models are more personalized, the obtained nomothetic model would have led to the identification of the same predictors for 5 of the 20 participants, suggesting a mismatch of plausible tailoring variables to use for 75% of the sample. Conclusion: The idiographic approach revealed person-specific predictors beyond traditional MLM analyses and unpacked the inherent complexity of PA; namely that people are different and context matters. System ID provides a feasible approach to develop personalized dynamical models of PA and inform person-specific tailoring variable selection for use in adaptive behavioral interventions.

Original languageEnglish (US)
Pages (from-to)82-97
Number of pages16
JournalJournal of Biomedical Informatics
Volume79
DOIs
StatePublished - Mar 1 2018

Fingerprint

Individuality
Identification (control systems)
Reinforcement
Systems engineering
Identification (Psychology)
Multilevel Analysis
Dynamic models
Reward
Control systems
Self Report

Keywords

  • Adaptive interventions
  • Behavior change
  • Dynamical systems modeling
  • Idiographic modeling
  • Physical activity
  • System identification
  • Wearables

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Cite this

Modeling individual differences : A case study of the application of system identification for personalizing a physical activity intervention. / Phatak, Sayali S.; Freigoun, Mohammad T.; Martín, César A.; Rivera, Daniel; Korinek, Elizabeth V.; Adams, Marc; Buman, Matthew; Klasnja, Predrag; Hekler, Eric B.

In: Journal of Biomedical Informatics, Vol. 79, 01.03.2018, p. 82-97.

Research output: Contribution to journalArticle

Phatak, Sayali S. ; Freigoun, Mohammad T. ; Martín, César A. ; Rivera, Daniel ; Korinek, Elizabeth V. ; Adams, Marc ; Buman, Matthew ; Klasnja, Predrag ; Hekler, Eric B. / Modeling individual differences : A case study of the application of system identification for personalizing a physical activity intervention. In: Journal of Biomedical Informatics. 2018 ; Vol. 79. pp. 82-97.
@article{6ac9d75ed73642ff8e8d7ca52aabfc2f,
title = "Modeling individual differences: A case study of the application of system identification for personalizing a physical activity intervention",
abstract = "Background: Control systems engineering methods, particularly, system identification (system ID), offer an idiographic (i.e., person-specific) approach to develop dynamic models of physical activity (PA) that can be used to personalize interventions in a systematic, scalable way. The purpose of this work is to: (1) apply system ID to develop individual dynamical models of PA (steps/day measured using Fitbit Zip) in the context of a goal setting and positive reinforcement intervention informed by Social Cognitive Theory; and (2) compare insights on potential tailoring variables (i.e., predictors expected to influence steps and thus moderate the suggested step goal and points for goal achievement) selected using the idiographic models to those selected via a nomothetic (i.e., aggregated across individuals) approach. Method: A personalized goal setting and positive reinforcement intervention was deployed for 14 weeks. Baseline PA measured in weeks 1–2 was used to inform personalized daily step goals delivered in weeks 3–14. Goals and expected reward points (granted upon goal achievement) were pseudo-randomly assigned using techniques from system ID, with goals ranging from their baseline median steps/day up to 2.5× baseline median steps/day, and points ranging from 100 to 500 (i.e., $0.20–$1.00). Participants completed a series of daily self-report measures. Auto Regressive with eXogenous Input (ARX) modeling and multilevel modeling (MLM) were used as the idiographic and nomothetic approaches, respectively. Results: Participants (N = 20, mean age = 47.25 ± 6.16 years, 90{\%} female) were insufficiently active, overweight (mean BMI = 33.79 ± 6.82 kg/m2) adults. Results from ARX modeling suggest that individuals differ in the factors (e.g., perceived stress, weekday/weekend) that influence their observed steps/day. In contrast, the nomothetic model from MLM suggested that goals and weekday/weekend were the key variables that were predictive of steps. Assuming the ARX models are more personalized, the obtained nomothetic model would have led to the identification of the same predictors for 5 of the 20 participants, suggesting a mismatch of plausible tailoring variables to use for 75{\%} of the sample. Conclusion: The idiographic approach revealed person-specific predictors beyond traditional MLM analyses and unpacked the inherent complexity of PA; namely that people are different and context matters. System ID provides a feasible approach to develop personalized dynamical models of PA and inform person-specific tailoring variable selection for use in adaptive behavioral interventions.",
keywords = "Adaptive interventions, Behavior change, Dynamical systems modeling, Idiographic modeling, Physical activity, System identification, Wearables",
author = "Phatak, {Sayali S.} and Freigoun, {Mohammad T.} and Mart{\'i}n, {C{\'e}sar A.} and Daniel Rivera and Korinek, {Elizabeth V.} and Marc Adams and Matthew Buman and Predrag Klasnja and Hekler, {Eric B.}",
year = "2018",
month = "3",
day = "1",
doi = "10.1016/j.jbi.2018.01.010",
language = "English (US)",
volume = "79",
pages = "82--97",
journal = "Journal of Biomedical Informatics",
issn = "1532-0464",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Modeling individual differences

T2 - A case study of the application of system identification for personalizing a physical activity intervention

AU - Phatak, Sayali S.

AU - Freigoun, Mohammad T.

AU - Martín, César A.

AU - Rivera, Daniel

AU - Korinek, Elizabeth V.

AU - Adams, Marc

AU - Buman, Matthew

AU - Klasnja, Predrag

AU - Hekler, Eric B.

PY - 2018/3/1

Y1 - 2018/3/1

N2 - Background: Control systems engineering methods, particularly, system identification (system ID), offer an idiographic (i.e., person-specific) approach to develop dynamic models of physical activity (PA) that can be used to personalize interventions in a systematic, scalable way. The purpose of this work is to: (1) apply system ID to develop individual dynamical models of PA (steps/day measured using Fitbit Zip) in the context of a goal setting and positive reinforcement intervention informed by Social Cognitive Theory; and (2) compare insights on potential tailoring variables (i.e., predictors expected to influence steps and thus moderate the suggested step goal and points for goal achievement) selected using the idiographic models to those selected via a nomothetic (i.e., aggregated across individuals) approach. Method: A personalized goal setting and positive reinforcement intervention was deployed for 14 weeks. Baseline PA measured in weeks 1–2 was used to inform personalized daily step goals delivered in weeks 3–14. Goals and expected reward points (granted upon goal achievement) were pseudo-randomly assigned using techniques from system ID, with goals ranging from their baseline median steps/day up to 2.5× baseline median steps/day, and points ranging from 100 to 500 (i.e., $0.20–$1.00). Participants completed a series of daily self-report measures. Auto Regressive with eXogenous Input (ARX) modeling and multilevel modeling (MLM) were used as the idiographic and nomothetic approaches, respectively. Results: Participants (N = 20, mean age = 47.25 ± 6.16 years, 90% female) were insufficiently active, overweight (mean BMI = 33.79 ± 6.82 kg/m2) adults. Results from ARX modeling suggest that individuals differ in the factors (e.g., perceived stress, weekday/weekend) that influence their observed steps/day. In contrast, the nomothetic model from MLM suggested that goals and weekday/weekend were the key variables that were predictive of steps. Assuming the ARX models are more personalized, the obtained nomothetic model would have led to the identification of the same predictors for 5 of the 20 participants, suggesting a mismatch of plausible tailoring variables to use for 75% of the sample. Conclusion: The idiographic approach revealed person-specific predictors beyond traditional MLM analyses and unpacked the inherent complexity of PA; namely that people are different and context matters. System ID provides a feasible approach to develop personalized dynamical models of PA and inform person-specific tailoring variable selection for use in adaptive behavioral interventions.

AB - Background: Control systems engineering methods, particularly, system identification (system ID), offer an idiographic (i.e., person-specific) approach to develop dynamic models of physical activity (PA) that can be used to personalize interventions in a systematic, scalable way. The purpose of this work is to: (1) apply system ID to develop individual dynamical models of PA (steps/day measured using Fitbit Zip) in the context of a goal setting and positive reinforcement intervention informed by Social Cognitive Theory; and (2) compare insights on potential tailoring variables (i.e., predictors expected to influence steps and thus moderate the suggested step goal and points for goal achievement) selected using the idiographic models to those selected via a nomothetic (i.e., aggregated across individuals) approach. Method: A personalized goal setting and positive reinforcement intervention was deployed for 14 weeks. Baseline PA measured in weeks 1–2 was used to inform personalized daily step goals delivered in weeks 3–14. Goals and expected reward points (granted upon goal achievement) were pseudo-randomly assigned using techniques from system ID, with goals ranging from their baseline median steps/day up to 2.5× baseline median steps/day, and points ranging from 100 to 500 (i.e., $0.20–$1.00). Participants completed a series of daily self-report measures. Auto Regressive with eXogenous Input (ARX) modeling and multilevel modeling (MLM) were used as the idiographic and nomothetic approaches, respectively. Results: Participants (N = 20, mean age = 47.25 ± 6.16 years, 90% female) were insufficiently active, overweight (mean BMI = 33.79 ± 6.82 kg/m2) adults. Results from ARX modeling suggest that individuals differ in the factors (e.g., perceived stress, weekday/weekend) that influence their observed steps/day. In contrast, the nomothetic model from MLM suggested that goals and weekday/weekend were the key variables that were predictive of steps. Assuming the ARX models are more personalized, the obtained nomothetic model would have led to the identification of the same predictors for 5 of the 20 participants, suggesting a mismatch of plausible tailoring variables to use for 75% of the sample. Conclusion: The idiographic approach revealed person-specific predictors beyond traditional MLM analyses and unpacked the inherent complexity of PA; namely that people are different and context matters. System ID provides a feasible approach to develop personalized dynamical models of PA and inform person-specific tailoring variable selection for use in adaptive behavioral interventions.

KW - Adaptive interventions

KW - Behavior change

KW - Dynamical systems modeling

KW - Idiographic modeling

KW - Physical activity

KW - System identification

KW - Wearables

UR - http://www.scopus.com/inward/record.url?scp=85042427475&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042427475&partnerID=8YFLogxK

U2 - 10.1016/j.jbi.2018.01.010

DO - 10.1016/j.jbi.2018.01.010

M3 - Article

C2 - 29409750

AN - SCOPUS:85042427475

VL - 79

SP - 82

EP - 97

JO - Journal of Biomedical Informatics

JF - Journal of Biomedical Informatics

SN - 1532-0464

ER -