From reflection to action: Combining machine learning with expert knowledge for nutrition goal recommendations

Elliot G. Mitchell; Elizabeth M. Heitkemper; Marissa Burgermaster; Matthew E. Levine; Yishen Miao; Maria L. Hwang; Pooja M. Desai; Andrea Cassells; Jonathan N. Tobin; Esteban G. Tabak; David J. Albers; Arlene M. Smaldone; Lena Mamykina

doi:10.1145/3411764.3445555

From reflection to action: Combining machine learning with expert knowledge for nutrition goal recommendations

Elliot G. Mitchell, Elizabeth M. Heitkemper, Marissa Burgermaster, Matthew E. Levine, Yishen Miao, Maria L. Hwang, Pooja M. Desai, Andrea Cassells, Jonathan N. Tobin, Esteban G. Tabak, David J. Albers, Arlene M. Smaldone, Lena Mamykina

Mathematics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Self-tracking can help personalize self-management interventions for chronic conditions like type 2 diabetes (T2D), but reflecting on personal data requires motivation and literacy. Machine learning (ML) methods can identify patterns, but a key challenge is making actionable suggestions based on personal health data. We introduce GlucoGoalie, which combines ML with an expert system to translate ML output into personalized nutrition goal suggestions for individuals with T2D. In a controlled experiment, participants with T2D found that goal suggestions were understandable and actionable. A 4-week in-the-wild deployment study showed that receiving goal suggestions augmented participants' self-discovery, choosing goals highlighted the multifaceted nature of personal preferences, and the experience of following goals demonstrated the importance of feedback and context. However, we identified tensions between abstract goals and concrete eating experiences and found static text too ambiguous for complex concepts. We discuss implications for ML-based interventions and the need for systems that offer more interactivity, feedback, and negotiation.

Original language	English (US)
Title of host publication	CHI 2021 - Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems
Subtitle of host publication	Making Waves, Combining Strengths
Publisher	Association for Computing Machinery
Volume	2021
ISBN (Electronic)	9781450380966
DOIs	https://doi.org/10.1145/3411764.3445555
State	Published - May 6 2021
Event	2021 CHI Conference on Human Factors in Computing Systems: Making Waves, Combining Strengths, CHI 2021 - Virtual, Online, Japan Duration: May 8 2021 → May 13 2021

Publication series

Name	Proceedings of the SIGCHI conference on human factors in computing systems. CHI Conference

Conference

Conference	2021 CHI Conference on Human Factors in Computing Systems: Making Waves, Combining Strengths, CHI 2021
Country/Territory	Japan
City	Virtual, Online
Period	5/8/21 → 5/13/21

Keywords

Diabetes self- management
Goal setting
Machine learning
Personal Informatics

ASJC Scopus subject areas

Software
Human-Computer Interaction
Computer Graphics and Computer-Aided Design

Access to Document

10.1145/3411764.3445555

Cite this

Mitchell, E. G., Heitkemper, E. M., Burgermaster, M., Levine, M. E., Miao, Y., Hwang, M. L., Desai, P. M., Cassells, A., Tobin, J. N., Tabak, E. G., Albers, D. J., Smaldone, A. M., & Mamykina, L. (2021). From reflection to action: Combining machine learning with expert knowledge for nutrition goal recommendations. In CHI 2021 - Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems: Making Waves, Combining Strengths (Vol. 2021). (Proceedings of the SIGCHI conference on human factors in computing systems. CHI Conference). Association for Computing Machinery. https://doi.org/10.1145/3411764.3445555

From reflection to action: Combining machine learning with expert knowledge for nutrition goal recommendations. / Mitchell, Elliot G.; Heitkemper, Elizabeth M.; Burgermaster, Marissa et al.
CHI 2021 - Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems: Making Waves, Combining Strengths. Vol. 2021 Association for Computing Machinery, 2021. (Proceedings of the SIGCHI conference on human factors in computing systems. CHI Conference).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Mitchell, EG, Heitkemper, EM, Burgermaster, M, Levine, ME, Miao, Y, Hwang, ML, Desai, PM, Cassells, A, Tobin, JN, Tabak, EG, Albers, DJ, Smaldone, AM & Mamykina, L 2021, From reflection to action: Combining machine learning with expert knowledge for nutrition goal recommendations. in CHI 2021 - Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems: Making Waves, Combining Strengths. vol. 2021, Proceedings of the SIGCHI conference on human factors in computing systems. CHI Conference, Association for Computing Machinery, 2021 CHI Conference on Human Factors in Computing Systems: Making Waves, Combining Strengths, CHI 2021, Virtual, Online, Japan, 5/8/21. https://doi.org/10.1145/3411764.3445555

Mitchell EG, Heitkemper EM, Burgermaster M, Levine ME, Miao Y, Hwang ML et al. From reflection to action: Combining machine learning with expert knowledge for nutrition goal recommendations. In CHI 2021 - Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems: Making Waves, Combining Strengths. Vol. 2021. Association for Computing Machinery. 2021. (Proceedings of the SIGCHI conference on human factors in computing systems. CHI Conference). doi: 10.1145/3411764.3445555

Mitchell, Elliot G. ; Heitkemper, Elizabeth M. ; Burgermaster, Marissa et al. / From reflection to action : Combining machine learning with expert knowledge for nutrition goal recommendations. CHI 2021 - Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems: Making Waves, Combining Strengths. Vol. 2021 Association for Computing Machinery, 2021. (Proceedings of the SIGCHI conference on human factors in computing systems. CHI Conference).

@inproceedings{3268484afd514d0a811d59e2e2105129,

title = "From reflection to action: Combining machine learning with expert knowledge for nutrition goal recommendations",

abstract = "Self-tracking can help personalize self-management interventions for chronic conditions like type 2 diabetes (T2D), but reflecting on personal data requires motivation and literacy. Machine learning (ML) methods can identify patterns, but a key challenge is making actionable suggestions based on personal health data. We introduce GlucoGoalie, which combines ML with an expert system to translate ML output into personalized nutrition goal suggestions for individuals with T2D. In a controlled experiment, participants with T2D found that goal suggestions were understandable and actionable. A 4-week in-the-wild deployment study showed that receiving goal suggestions augmented participants' self-discovery, choosing goals highlighted the multifaceted nature of personal preferences, and the experience of following goals demonstrated the importance of feedback and context. However, we identified tensions between abstract goals and concrete eating experiences and found static text too ambiguous for complex concepts. We discuss implications for ML-based interventions and the need for systems that offer more interactivity, feedback, and negotiation.",

keywords = "Diabetes self- management, Goal setting, Machine learning, Personal Informatics",

author = "Mitchell, {Elliot G.} and Heitkemper, {Elizabeth M.} and Marissa Burgermaster and Levine, {Matthew E.} and Yishen Miao and Hwang, {Maria L.} and Desai, {Pooja M.} and Andrea Cassells and Tobin, {Jonathan N.} and Tabak, {Esteban G.} and Albers, {David J.} and Smaldone, {Arlene M.} and Lena Mamykina",

note = "Publisher Copyright: {\textcopyright} 2021 ACM.; 2021 CHI Conference on Human Factors in Computing Systems: Making Waves, Combining Strengths, CHI 2021 ; Conference date: 08-05-2021 Through 13-05-2021",

year = "2021",

month = may,

day = "6",

doi = "10.1145/3411764.3445555",

language = "English (US)",

volume = "2021",

series = "Proceedings of the SIGCHI conference on human factors in computing systems. CHI Conference",

publisher = "Association for Computing Machinery",

booktitle = "CHI 2021 - Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems",

}

TY - GEN

T1 - From reflection to action

T2 - 2021 CHI Conference on Human Factors in Computing Systems: Making Waves, Combining Strengths, CHI 2021

AU - Mitchell, Elliot G.

AU - Heitkemper, Elizabeth M.

AU - Burgermaster, Marissa

AU - Levine, Matthew E.

AU - Miao, Yishen

AU - Hwang, Maria L.

AU - Desai, Pooja M.

AU - Cassells, Andrea

AU - Tobin, Jonathan N.

AU - Tabak, Esteban G.

AU - Albers, David J.

AU - Smaldone, Arlene M.

AU - Mamykina, Lena

PY - 2021/5/6

Y1 - 2021/5/6

N2 - Self-tracking can help personalize self-management interventions for chronic conditions like type 2 diabetes (T2D), but reflecting on personal data requires motivation and literacy. Machine learning (ML) methods can identify patterns, but a key challenge is making actionable suggestions based on personal health data. We introduce GlucoGoalie, which combines ML with an expert system to translate ML output into personalized nutrition goal suggestions for individuals with T2D. In a controlled experiment, participants with T2D found that goal suggestions were understandable and actionable. A 4-week in-the-wild deployment study showed that receiving goal suggestions augmented participants' self-discovery, choosing goals highlighted the multifaceted nature of personal preferences, and the experience of following goals demonstrated the importance of feedback and context. However, we identified tensions between abstract goals and concrete eating experiences and found static text too ambiguous for complex concepts. We discuss implications for ML-based interventions and the need for systems that offer more interactivity, feedback, and negotiation.

AB - Self-tracking can help personalize self-management interventions for chronic conditions like type 2 diabetes (T2D), but reflecting on personal data requires motivation and literacy. Machine learning (ML) methods can identify patterns, but a key challenge is making actionable suggestions based on personal health data. We introduce GlucoGoalie, which combines ML with an expert system to translate ML output into personalized nutrition goal suggestions for individuals with T2D. In a controlled experiment, participants with T2D found that goal suggestions were understandable and actionable. A 4-week in-the-wild deployment study showed that receiving goal suggestions augmented participants' self-discovery, choosing goals highlighted the multifaceted nature of personal preferences, and the experience of following goals demonstrated the importance of feedback and context. However, we identified tensions between abstract goals and concrete eating experiences and found static text too ambiguous for complex concepts. We discuss implications for ML-based interventions and the need for systems that offer more interactivity, feedback, and negotiation.

KW - Diabetes self- management

KW - Goal setting

KW - Machine learning

KW - Personal Informatics

UR - http://www.scopus.com/inward/record.url?scp=85119088875&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85119088875&partnerID=8YFLogxK

U2 - 10.1145/3411764.3445555

DO - 10.1145/3411764.3445555

M3 - Conference contribution

C2 - 35514864

AN - SCOPUS:85119088875

VL - 2021

T3 - Proceedings of the SIGCHI conference on human factors in computing systems. CHI Conference

BT - CHI 2021 - Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems

PB - Association for Computing Machinery

Y2 - 8 May 2021 through 13 May 2021

ER -

From reflection to action: Combining machine learning with expert knowledge for nutrition goal recommendations

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this