Trial Outcomes & Findings for Validity of an AI-based Program to Identify Foods and Estimate Food Portion Size (NCT NCT05343585)

Last Updated: 2023-11-18

Results Overview

Agreement surrounding identification of food and beverages provided compared with known identification, at the item level, and across all items where identification is determined by: 1) Nutrition AI without correction (automated), 2) Nutrition AI with user correction (semi-automated) For a food identified through the Nutrition AI to be considered an exact food match, the name of the food identified must match or be a close match to the food served. For example, a fruit cocktail identified as a fruit salad is an acceptable match. Proportions will be used to assess whether the percentage of food items plated that were correctly identified by Nutrition AI is different to the percentage of foods correctly identified by a criterion method (human rater). Descriptive data will also be used to describe the frequency at which food plated was correctly identified for all food items across all participants. In total there was 255 food items tested across all participants.

Recruitment status

COMPLETED

Study phase

Target enrollment

24 participants

Primary outcome timeframe

One study visit of ~2 hours

Results posted on

2023-11-18

Participant Flow

Participant milestones

Participant milestones
Measure	Experimental * Training and use of Openfit * Using the app to estimate food intake from simulated meals in a laboratory at PBRC or LSU (participants will not eat food during the meals) * Rating the usability and satisfaction of the app PortionSize AI: For this pilot study, using a convenience sample, the investigators will recruit up to 25 adults to use the Nutrition AI technology in Openfit to identify and estimate portion size of foods provided and simulated plate waste, and food intake in a laboratory setting at Pennington Biomedical Research Center (PBRC) and/or Louisiana State University (LSU). Laboratory members within the Ingestive Behavioral Laboratory will also test the ability of Nutrition AI to identify foods and to quantify foods provided, plate waste and food intake, in the laboratory. Meals will be simulated, and participants will not consume the foods provided.
Overall Study STARTED	24
Overall Study COMPLETED	24
Overall Study NOT COMPLETED	0

Reasons for withdrawal

Withdrawal data not reported

Baseline Characteristics

Validity of an AI-based Program to Identify Foods and Estimate Food Portion Size

Baseline characteristics by cohort

Baseline characteristics by cohort
Measure	Experimental n=24 Participants * Training and use of Openfit * Using the app to estimate food intake from simulated meals in a laboratory at PBRC or LSU (participants will not eat food during the meals) * Rating the usability and satisfaction of the app PortionSize AI: For this pilot study, using a convenience sample, the investigators will recruit up to 25 adults to use the Nutrition AI technology in Openfit to identify and estimate portion size of foods provided and simulated plate waste, and food intake in a laboratory setting at Pennington Biomedical Research Center (PBRC) and/or Louisiana State University (LSU). Laboratory members within the Ingestive Behavioral Laboratory will also test the ability of Nutrition AI to identify foods and to quantify foods provided, plate waste and food intake, in the laboratory. Meals will be simulated, and participants will not consume the foods provided.
Age, Continuous	35.0 years STANDARD_DEVIATION 9.5 • n=5 Participants
Sex: Female, Male Female	17 Participants n=5 Participants
Sex: Female, Male Male	7 Participants n=5 Participants
Race (NIH/OMB) American Indian or Alaska Native	0 Participants n=5 Participants
Race (NIH/OMB) Asian	3 Participants n=5 Participants
Race (NIH/OMB) Native Hawaiian or Other Pacific Islander	0 Participants n=5 Participants
Race (NIH/OMB) Black or African American	4 Participants n=5 Participants
Race (NIH/OMB) White	17 Participants n=5 Participants
Race (NIH/OMB) More than one race	0 Participants n=5 Participants
Race (NIH/OMB) Unknown or Not Reported	0 Participants n=5 Participants
Region of Enrollment United States	24 participants n=5 Participants
Education Some College or Bachelor's Degree	10 Participants n=5 Participants
Education Postgraduate degree	14 Participants n=5 Participants
Employment Full time	22 Participants n=5 Participants
Employment Part time	2 Participants n=5 Participants
Body Mass Index	24.6 kg/m^2 STANDARD_DEVIATION 4.1 • n=5 Participants

PRIMARY outcome

Timeframe: One study visit of ~2 hours

Outcome measures

Outcome measures
Measure	Experimental n=255 Food items * Training and use of Openfit * Using the app to estimate food intake from simulated meals in a laboratory at PBRC or LSU (participants will not eat food during the meals) * Rating the usability and satisfaction of the app PortionSize AI: For this pilot study, using a convenience sample, the investigators will recruit up to 25 adults to use the Nutrition AI technology in Openfit to identify and estimate portion size of foods provided and simulated plate waste, and food intake in a laboratory setting at Pennington Biomedical Research Center (PBRC) and/or Louisiana State University (LSU). Laboratory members within the Ingestive Behavioral Laboratory will also test the ability of Nutrition AI to identify foods and to quantify foods provided, plate waste and food intake, in the laboratory. Meals will be simulated, and participants will not consume the foods provided.
Identification of Food Plated Using the Openfit Mobile App Food items that were automatically identified as an exact match across all participants.	118 Food items
Identification of Food Plated Using the Openfit Mobile App Food items that were semi-automatically identified as an exact match across all participants.	221 Food items

PRIMARY outcome

Timeframe: One study visit of ~2 hours

Error between mean estimates of food plated (kcal) and known food plated (kcal), determined by: 1) Nutrition AI without user correction (automated), 2) Nutrition AI with user correction (semi-automated) Mean error and Bland-Altman analysis will be performed to determine errors in estimation of food plated from the Nutrition AI compared to estimations from the criterion measure (weighed food).

Outcome measures

Outcome measures
Measure	Experimental n=24 Participants * Training and use of Openfit * Using the app to estimate food intake from simulated meals in a laboratory at PBRC or LSU (participants will not eat food during the meals) * Rating the usability and satisfaction of the app PortionSize AI: For this pilot study, using a convenience sample, the investigators will recruit up to 25 adults to use the Nutrition AI technology in Openfit to identify and estimate portion size of foods provided and simulated plate waste, and food intake in a laboratory setting at Pennington Biomedical Research Center (PBRC) and/or Louisiana State University (LSU). Laboratory members within the Ingestive Behavioral Laboratory will also test the ability of Nutrition AI to identify foods and to quantify foods provided, plate waste and food intake, in the laboratory. Meals will be simulated, and participants will not consume the foods provided.
Portion Size Estimation (kcal) of Food Plated Using the Openfit Mobile App Energy of weighed meals.	577 kcal Standard Deviation 150
Portion Size Estimation (kcal) of Food Plated Using the Openfit Mobile App Energy of automated estimates	826 kcal Standard Deviation 490
Portion Size Estimation (kcal) of Food Plated Using the Openfit Mobile App Energy of semi-automated estimates	769 kcal Standard Deviation 445

PRIMARY outcome

Timeframe: One study visit of ~2 hours

After completing assessment of food plated, participants will complete a user satisfaction survey (USS). The USS was adapted from a previous version used to assess the usability of a mobile application for dietary assessment. The USS includes five quantitative questions and three open response questions. The quantitative questions will each be scored using a 6-point Likert scale, with 1 being the lowest and worst score, and 6 being the highest and best score. Data for each of the five quantitative responses in the USS will be averaged across participants and presented separately as mean (SD). Open responses will be evaluated using qualitative methods to identify common themes.

Outcome measures

Outcome measures
Measure	Experimental n=24 Participants * Training and use of Openfit * Using the app to estimate food intake from simulated meals in a laboratory at PBRC or LSU (participants will not eat food during the meals) * Rating the usability and satisfaction of the app PortionSize AI: For this pilot study, using a convenience sample, the investigators will recruit up to 25 adults to use the Nutrition AI technology in Openfit to identify and estimate portion size of foods provided and simulated plate waste, and food intake in a laboratory setting at Pennington Biomedical Research Center (PBRC) and/or Louisiana State University (LSU). Laboratory members within the Ingestive Behavioral Laboratory will also test the ability of Nutrition AI to identify foods and to quantify foods provided, plate waste and food intake, in the laboratory. Meals will be simulated, and participants will not consume the foods provided.
User Satisfaction of the Openfit Mobile App for Recording Food Plated How satisfied are you with the app for identifying the food provided?	4.1 score on a scale Standard Deviation 1.3
User Satisfaction of the Openfit Mobile App for Recording Food Plated How satisfied are you with the app for estimating the amount of food provided?	4.0 score on a scale Standard Deviation 1.5
User Satisfaction of the Openfit Mobile App for Recording Food Plated How easy was it to use the app to identify the food provided?	4.2 score on a scale Standard Deviation 1.4
User Satisfaction of the Openfit Mobile App for Recording Food Plated How easy was it to use the app for estimating the amount of food provided?	4.0 score on a scale Standard Deviation 1.6
User Satisfaction of the Openfit Mobile App for Recording Food Plated How much did the training help prepare you for using the app?	5.5 score on a scale Standard Deviation 0.7

PRIMARY outcome

Timeframe: One study visit of ~2 hours

Participants will complete the Computer Usability Satisfaction Questionnaire (CSUQ). The CSUQ is frequently used to assess the usability of mobile applications. The CSUQ consists of 19 questions, each scored using a 7-point Likert scale (with 1 being the lowest and best score and 7 being the highest and worst score) and participants will rate satisfaction, usefulness, information quality, and interface quality of the Openfit app. The average of these 19 questions (1 being the best average score and 7 being the worst average score) provides an overall usability score.

Outcome measures

Outcome measures
Measure	Experimental n=24 Participants * Training and use of Openfit * Using the app to estimate food intake from simulated meals in a laboratory at PBRC or LSU (participants will not eat food during the meals) * Rating the usability and satisfaction of the app PortionSize AI: For this pilot study, using a convenience sample, the investigators will recruit up to 25 adults to use the Nutrition AI technology in Openfit to identify and estimate portion size of foods provided and simulated plate waste, and food intake in a laboratory setting at Pennington Biomedical Research Center (PBRC) and/or Louisiana State University (LSU). Laboratory members within the Ingestive Behavioral Laboratory will also test the ability of Nutrition AI to identify foods and to quantify foods provided, plate waste and food intake, in the laboratory. Meals will be simulated, and participants will not consume the foods provided.
Usability of the Openfit Mobile App for Recording Food Plated	2.4 score on a scale Standard Deviation 0.22

Adverse Events

Experimental

Serious events: 0 serious events

Other events: 0 other events

Deaths: 0 deaths

Serious adverse events

Adverse event data not reported

Other adverse events

Adverse event data not reported

Additional Information

Chloe Panizza Lozano

Pennington Biomedical Research Center

Phone: (225) 763-2500

Email: [email protected]

Results disclosure agreements

Principal investigator is a sponsor employee
Publication restrictions are in place