Estimating caloric intake in bedridden hospital patients with audio and neck-worn sensors

Shibo Zhang, Dzung Nguyen, Gan Zhang, Runsheng Xu, Nikolaos Maglaveras, Nabil Alshurafa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present an approach for estimating calorie intake given a limited number of foods provided to patients in an in-bed setting. Data collected from a proximity sensor, inertial measurement unit, ambient light, and audio sensor placed around the neck are used to classify food-Type consumed by second using a random forest classifier. A multiple linear regression model is then developed for each food-Type to map second-level features to calories per second. We conducted a user study in a patient simulated lab setting, where 10 participants were asked to eat while sitting on a patient bed. A user-independent analysis demonstrated food-Type detection at 97.2% F1-Score, and an average Absolute Error of 3.0 kCal per food-Type. Our system shows promise in distinguishing food items and predicting calorie intake in a bedridden participant setting given a limited set of food items.

Original languageEnglish (US)
Title of host publicationProceedings - 2018 IEEE/ACM International Conference on Connected Health
Subtitle of host publicationApplications, Systems and Engineering Technologies, CHASE 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-2
Number of pages2
ISBN (Electronic)9781538672068
DOIs
StatePublished - Feb 21 2019
Event3rd IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2018 - Washington, United States
Duration: Sep 26 2018Sep 28 2018

Publication series

NameProceedings - 2018 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2018

Conference

Conference3rd IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2018
CountryUnited States
CityWashington
Period9/26/189/28/18

Fingerprint

Energy Intake
Neck
food
Food
Sensors
Linear Models
Food Analysis
Proximity sensors
Units of measurement
Linear regression
Classifiers
Light
regression

Keywords

  • Calorie intake estimation
  • Eating behavior
  • Food identification
  • Hospital malnutrition
  • Wearable sensor

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Biomedical Engineering
  • Health(social science)
  • Communication
  • Software
  • Computer Science Applications
  • Health Informatics

Cite this

Zhang, S., Nguyen, D., Zhang, G., Xu, R., Maglaveras, N., & Alshurafa, N. (2019). Estimating caloric intake in bedridden hospital patients with audio and neck-worn sensors. In Proceedings - 2018 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2018 (pp. 1-2). (Proceedings - 2018 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1145/3278576.3278577
Zhang, Shibo ; Nguyen, Dzung ; Zhang, Gan ; Xu, Runsheng ; Maglaveras, Nikolaos ; Alshurafa, Nabil. / Estimating caloric intake in bedridden hospital patients with audio and neck-worn sensors. Proceedings - 2018 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2018. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1-2 (Proceedings - 2018 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2018).
@inproceedings{25434721a9d944b08904e2120414ee36,
title = "Estimating caloric intake in bedridden hospital patients with audio and neck-worn sensors",
abstract = "We present an approach for estimating calorie intake given a limited number of foods provided to patients in an in-bed setting. Data collected from a proximity sensor, inertial measurement unit, ambient light, and audio sensor placed around the neck are used to classify food-Type consumed by second using a random forest classifier. A multiple linear regression model is then developed for each food-Type to map second-level features to calories per second. We conducted a user study in a patient simulated lab setting, where 10 participants were asked to eat while sitting on a patient bed. A user-independent analysis demonstrated food-Type detection at 97.2{\%} F1-Score, and an average Absolute Error of 3.0 kCal per food-Type. Our system shows promise in distinguishing food items and predicting calorie intake in a bedridden participant setting given a limited set of food items.",
keywords = "Calorie intake estimation, Eating behavior, Food identification, Hospital malnutrition, Wearable sensor",
author = "Shibo Zhang and Dzung Nguyen and Gan Zhang and Runsheng Xu and Nikolaos Maglaveras and Nabil Alshurafa",
year = "2019",
month = "2",
day = "21",
doi = "10.1145/3278576.3278577",
language = "English (US)",
series = "Proceedings - 2018 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1--2",
booktitle = "Proceedings - 2018 IEEE/ACM International Conference on Connected Health",
address = "United States",

}

Zhang, S, Nguyen, D, Zhang, G, Xu, R, Maglaveras, N & Alshurafa, N 2019, Estimating caloric intake in bedridden hospital patients with audio and neck-worn sensors. in Proceedings - 2018 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2018. Proceedings - 2018 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2018, Institute of Electrical and Electronics Engineers Inc., pp. 1-2, 3rd IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2018, Washington, United States, 9/26/18. https://doi.org/10.1145/3278576.3278577

Estimating caloric intake in bedridden hospital patients with audio and neck-worn sensors. / Zhang, Shibo; Nguyen, Dzung; Zhang, Gan; Xu, Runsheng; Maglaveras, Nikolaos; Alshurafa, Nabil.

Proceedings - 2018 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2018. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1-2 (Proceedings - 2018 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Estimating caloric intake in bedridden hospital patients with audio and neck-worn sensors

AU - Zhang, Shibo

AU - Nguyen, Dzung

AU - Zhang, Gan

AU - Xu, Runsheng

AU - Maglaveras, Nikolaos

AU - Alshurafa, Nabil

PY - 2019/2/21

Y1 - 2019/2/21

N2 - We present an approach for estimating calorie intake given a limited number of foods provided to patients in an in-bed setting. Data collected from a proximity sensor, inertial measurement unit, ambient light, and audio sensor placed around the neck are used to classify food-Type consumed by second using a random forest classifier. A multiple linear regression model is then developed for each food-Type to map second-level features to calories per second. We conducted a user study in a patient simulated lab setting, where 10 participants were asked to eat while sitting on a patient bed. A user-independent analysis demonstrated food-Type detection at 97.2% F1-Score, and an average Absolute Error of 3.0 kCal per food-Type. Our system shows promise in distinguishing food items and predicting calorie intake in a bedridden participant setting given a limited set of food items.

AB - We present an approach for estimating calorie intake given a limited number of foods provided to patients in an in-bed setting. Data collected from a proximity sensor, inertial measurement unit, ambient light, and audio sensor placed around the neck are used to classify food-Type consumed by second using a random forest classifier. A multiple linear regression model is then developed for each food-Type to map second-level features to calories per second. We conducted a user study in a patient simulated lab setting, where 10 participants were asked to eat while sitting on a patient bed. A user-independent analysis demonstrated food-Type detection at 97.2% F1-Score, and an average Absolute Error of 3.0 kCal per food-Type. Our system shows promise in distinguishing food items and predicting calorie intake in a bedridden participant setting given a limited set of food items.

KW - Calorie intake estimation

KW - Eating behavior

KW - Food identification

KW - Hospital malnutrition

KW - Wearable sensor

UR - http://www.scopus.com/inward/record.url?scp=85063253037&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063253037&partnerID=8YFLogxK

U2 - 10.1145/3278576.3278577

DO - 10.1145/3278576.3278577

M3 - Conference contribution

T3 - Proceedings - 2018 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2018

SP - 1

EP - 2

BT - Proceedings - 2018 IEEE/ACM International Conference on Connected Health

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Zhang S, Nguyen D, Zhang G, Xu R, Maglaveras N, Alshurafa N. Estimating caloric intake in bedridden hospital patients with audio and neck-worn sensors. In Proceedings - 2018 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1-2. (Proceedings - 2018 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2018). https://doi.org/10.1145/3278576.3278577