Validation of a recommender system for prompting omitted foods in online dietary assessment surveys

Timur Osadchiy, Ivan Poliakov, Patrick Olivier, Maisie Rowland, Emma Foster

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

Recall assistance methods are among the key aspects that improve the accuracy of online dietary assessment surveys. These methods still mainly rely on experience of trained interviewers with nutritional background, but data driven approaches could improve cost-efficiency and scalability of automated dietary assessment. We evaluated the effectiveness of a recommender algorithm developed for an online dietary assessment system called Intake24, that automates the multiple-pass 24-hour recall method. The recommender builds a model of eating behavior from recalls collected in past surveys. Based on foods they have already selected, the model is used to remind respondents of associated foods that they may have omitted to report. The performance of prompts generated by the model was compared to that of prompts hand-coded by nutritionists in two dietary studies. The results of our studies demonstrate that the recommender system is able to capture a higher number of foods omitted by respondents of online dietary surveys than prompts hand-coded by nutritionists. However, the considerably lower precision of generated prompts indicates an opportunity for further improvement of the system.

Original languageEnglish
Title of host publicationPervasiveHealth'19 - Proceedings of the 13th EAI International Conference on Pervasive Computing Technologies for Healthcare
Subtitle of host publication20-23 May 2019, Trento, Italy
EditorsJochen Meyer, Lena Mamykina
Place of PublicationNew York NY USA
PublisherAssociation for Computing Machinery (ACM)
Pages208-215
Number of pages8
ISBN (Electronic)9781450361262
DOIs
Publication statusPublished - 2019
EventEAI International Conference on Pervasive Computing Technologies for Healthcare 2019 - Trento, Italy
Duration: 20 May 201923 May 2019
Conference number: 13th
https://www.fbk.eu/en/event/pervasive-health-2019/

Conference

ConferenceEAI International Conference on Pervasive Computing Technologies for Healthcare 2019
Abbreviated titlePervasiveHealth 2019
CountryItaly
CityTrento
Period20/05/1923/05/19
Internet address

Keywords

  • Dietary assessment
  • Healthcare technology
  • Recommender systems
  • Usability

Cite this

Osadchiy, T., Poliakov, I., Olivier, P., Rowland, M., & Foster, E. (2019). Validation of a recommender system for prompting omitted foods in online dietary assessment surveys. In J. Meyer, & L. Mamykina (Eds.), PervasiveHealth'19 - Proceedings of the 13th EAI International Conference on Pervasive Computing Technologies for Healthcare: 20-23 May 2019, Trento, Italy (pp. 208-215). New York NY USA: Association for Computing Machinery (ACM). https://doi.org/10.1145/3329189.3329191
Osadchiy, Timur ; Poliakov, Ivan ; Olivier, Patrick ; Rowland, Maisie ; Foster, Emma. / Validation of a recommender system for prompting omitted foods in online dietary assessment surveys. PervasiveHealth'19 - Proceedings of the 13th EAI International Conference on Pervasive Computing Technologies for Healthcare: 20-23 May 2019, Trento, Italy . editor / Jochen Meyer ; Lena Mamykina. New York NY USA : Association for Computing Machinery (ACM), 2019. pp. 208-215
@inproceedings{38871bda397d4b5a94e5923322bf9b95,
title = "Validation of a recommender system for prompting omitted foods in online dietary assessment surveys",
abstract = "Recall assistance methods are among the key aspects that improve the accuracy of online dietary assessment surveys. These methods still mainly rely on experience of trained interviewers with nutritional background, but data driven approaches could improve cost-efficiency and scalability of automated dietary assessment. We evaluated the effectiveness of a recommender algorithm developed for an online dietary assessment system called Intake24, that automates the multiple-pass 24-hour recall method. The recommender builds a model of eating behavior from recalls collected in past surveys. Based on foods they have already selected, the model is used to remind respondents of associated foods that they may have omitted to report. The performance of prompts generated by the model was compared to that of prompts hand-coded by nutritionists in two dietary studies. The results of our studies demonstrate that the recommender system is able to capture a higher number of foods omitted by respondents of online dietary surveys than prompts hand-coded by nutritionists. However, the considerably lower precision of generated prompts indicates an opportunity for further improvement of the system.",
keywords = "Dietary assessment, Healthcare technology, Recommender systems, Usability",
author = "Timur Osadchiy and Ivan Poliakov and Patrick Olivier and Maisie Rowland and Emma Foster",
year = "2019",
doi = "10.1145/3329189.3329191",
language = "English",
pages = "208--215",
editor = "Jochen Meyer and Mamykina, {Lena }",
booktitle = "PervasiveHealth'19 - Proceedings of the 13th EAI International Conference on Pervasive Computing Technologies for Healthcare",
publisher = "Association for Computing Machinery (ACM)",
address = "United States of America",

}

Osadchiy, T, Poliakov, I, Olivier, P, Rowland, M & Foster, E 2019, Validation of a recommender system for prompting omitted foods in online dietary assessment surveys. in J Meyer & L Mamykina (eds), PervasiveHealth'19 - Proceedings of the 13th EAI International Conference on Pervasive Computing Technologies for Healthcare: 20-23 May 2019, Trento, Italy . Association for Computing Machinery (ACM), New York NY USA, pp. 208-215, EAI International Conference on Pervasive Computing Technologies for Healthcare 2019, Trento, Italy, 20/05/19. https://doi.org/10.1145/3329189.3329191

Validation of a recommender system for prompting omitted foods in online dietary assessment surveys. / Osadchiy, Timur; Poliakov, Ivan; Olivier, Patrick; Rowland, Maisie; Foster, Emma.

PervasiveHealth'19 - Proceedings of the 13th EAI International Conference on Pervasive Computing Technologies for Healthcare: 20-23 May 2019, Trento, Italy . ed. / Jochen Meyer; Lena Mamykina. New York NY USA : Association for Computing Machinery (ACM), 2019. p. 208-215.

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

TY - GEN

T1 - Validation of a recommender system for prompting omitted foods in online dietary assessment surveys

AU - Osadchiy, Timur

AU - Poliakov, Ivan

AU - Olivier, Patrick

AU - Rowland, Maisie

AU - Foster, Emma

PY - 2019

Y1 - 2019

N2 - Recall assistance methods are among the key aspects that improve the accuracy of online dietary assessment surveys. These methods still mainly rely on experience of trained interviewers with nutritional background, but data driven approaches could improve cost-efficiency and scalability of automated dietary assessment. We evaluated the effectiveness of a recommender algorithm developed for an online dietary assessment system called Intake24, that automates the multiple-pass 24-hour recall method. The recommender builds a model of eating behavior from recalls collected in past surveys. Based on foods they have already selected, the model is used to remind respondents of associated foods that they may have omitted to report. The performance of prompts generated by the model was compared to that of prompts hand-coded by nutritionists in two dietary studies. The results of our studies demonstrate that the recommender system is able to capture a higher number of foods omitted by respondents of online dietary surveys than prompts hand-coded by nutritionists. However, the considerably lower precision of generated prompts indicates an opportunity for further improvement of the system.

AB - Recall assistance methods are among the key aspects that improve the accuracy of online dietary assessment surveys. These methods still mainly rely on experience of trained interviewers with nutritional background, but data driven approaches could improve cost-efficiency and scalability of automated dietary assessment. We evaluated the effectiveness of a recommender algorithm developed for an online dietary assessment system called Intake24, that automates the multiple-pass 24-hour recall method. The recommender builds a model of eating behavior from recalls collected in past surveys. Based on foods they have already selected, the model is used to remind respondents of associated foods that they may have omitted to report. The performance of prompts generated by the model was compared to that of prompts hand-coded by nutritionists in two dietary studies. The results of our studies demonstrate that the recommender system is able to capture a higher number of foods omitted by respondents of online dietary surveys than prompts hand-coded by nutritionists. However, the considerably lower precision of generated prompts indicates an opportunity for further improvement of the system.

KW - Dietary assessment

KW - Healthcare technology

KW - Recommender systems

KW - Usability

UR - http://www.scopus.com/inward/record.url?scp=85067889434&partnerID=8YFLogxK

U2 - 10.1145/3329189.3329191

DO - 10.1145/3329189.3329191

M3 - Conference Paper

AN - SCOPUS:85067889434

SP - 208

EP - 215

BT - PervasiveHealth'19 - Proceedings of the 13th EAI International Conference on Pervasive Computing Technologies for Healthcare

A2 - Meyer, Jochen

A2 - Mamykina, Lena

PB - Association for Computing Machinery (ACM)

CY - New York NY USA

ER -

Osadchiy T, Poliakov I, Olivier P, Rowland M, Foster E. Validation of a recommender system for prompting omitted foods in online dietary assessment surveys. In Meyer J, Mamykina L, editors, PervasiveHealth'19 - Proceedings of the 13th EAI International Conference on Pervasive Computing Technologies for Healthcare: 20-23 May 2019, Trento, Italy . New York NY USA: Association for Computing Machinery (ACM). 2019. p. 208-215 https://doi.org/10.1145/3329189.3329191