Accuracy in dietary assessment is essential for understanding the role of ingestive behavior in energy balance and chronic disease risk. Traditional and commonly used methods for assessing dietary intake, such as weighed or estimated food records, 24h recalls, and food frequency questionnaires all rely on self-report and are subject to reporting bias, particularly underreporting of energy intake. In this proposal, we describe a novel device for monitoring of food intake behavior, the Automatic Ingestion Monitor (AIM).
The AIM has the potential to provide an accurate tool for monitoring of ingestive behavior by automatically detecting and capturing imagery of food intake.
The AIM does not require any form of self-report from the user, only compliance with wearing the device.
The AIM i s simple to use and unobtrusive to daily activities;it can be worn for multiple days and only needs to be removed when bathing, showering or swimming. To our knowledge, no other monitoring technique has explored such an approach. The validation of the AIM system will be addressed in four specific aims:
Specific Aim 1 : Validate the AIM during ad-libitum food intake.
Specific Aim 2 : Implement semi-automatic energy density estimates from AIM-derived imagery.
Specific Aim 3 : Validate the accuracy of Total Energy Intake (TEI) measurement by the AIM2.0 in a community setting against doubly labeled water.
Specific Aim 4 : Identify the most cost-effective approach to analysis of AIM2.0 sensor and image data to accurately estimate energy intake.

Public Health Relevance

Over two-thirds of the US population is overweight or obese and excess energy intake is recognized as one important contributor to weight gain. Eating is said to be an unconscious, even automatic behavior for many individuals, and the literature is full of examples of dietary behaviors which increase the risk for overeating. In our previous research we developed an Automatic Ingestion Monitor (AIM), a device that that has the advantage that it does not rely on self-report and can automatically and reliably detect food intake, estimate the mass and the energy content of ingested food. The information provided by AIM can be used to improve behavioral weight loss strategies or to develop new kinds of weight loss interventions. In addition, the AIM can also provide an objective method of assessing the effectiveness of pharmacological and behavioral interventions for eating disorders.

Agency
National Institute of Health (NIH)
Institute
National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK)
Type
Research Project (R01)
Project #
1R01DK100796-01A1
Application #
8818917
Study Section
Clinical and Integrative Diabetes and Obesity Study Section (CIDO)
Program Officer
Evans, Mary
Project Start
2014-09-26
Project End
2019-06-30
Budget Start
2014-09-26
Budget End
2015-06-30
Support Year
1
Fiscal Year
2014
Total Cost
$285,393
Indirect Cost
$86,761
Name
University of Alabama in Tuscaloosa
Department
Engineering (All Types)
Type
Schools of Engineering
DUNS #
045632635
City
Tuscaloosa
State
AL
Country
United States
Zip Code
35487
Farooq, Muhammad; Sazonov, Edward (2018) Accelerometer-Based Detection of Food Intake in Free-living Individuals. IEEE Sens J 18:3752-3758
Farooq, Muhammad; McCrory, Megan A; Sazonov, Edward (2017) Reduction of energy intake using just-in-time feedback from a wearable sensor system. Obesity (Silver Spring) 25:676-681
Doulah, Abul; Farooq, Muhammad; Yang, Xin et al. (2017) Meal Microstructure Characterization from Sensor-Based Food Intake Detection. Front Nutr 4:31
Farooq, Muhammad; Sazonov, Edward (2017) Segmentation and Characterization of Chewing Bouts by Monitoring Temporalis Muscle Using Smart Glasses With Piezoelectric Sensor. IEEE J Biomed Health Inform 21:1495-1503
Farooq, Muhammad; Sazonov, Edward (2016) Detection of chewing from piezoelectric film sensor signals using ensemble classifiers. Conf Proc IEEE Eng Med Biol Soc 2016:4929-4932
Farooq, Muhammad; Sazonov, Edward (2016) A Novel Wearable Device for Food Intake and Physical Activity Recognition. Sensors (Basel) 16:
Farooq, Muhammad; Sazonov, Edward (2016) Automatic Measurement of Chew Count and Chewing Rate during Food Intake. Electronics (Basel) 5: