Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR Aging

Date Submitted: Feb 27, 2022
Date Accepted: Aug 6, 2022

The final, peer-reviewed published version of this preprint can be found here:

Enhancing Food Intake Tracking in Long-term Care With Automated Food Imaging and Nutrient Intake Tracking (AFINI-T) Technology: Validation and Feasibility Assessment

Pfisterer K, Amelard R, Boger J, Keller H, Chung A, Wong A

Enhancing Food Intake Tracking in Long-term Care With Automated Food Imaging and Nutrient Intake Tracking (AFINI-T) Technology: Validation and Feasibility Assessment

JMIR Aging 2022;5(4):e37590

DOI: 10.2196/37590

PMID: 36394940

PMCID: 9716425

Enhancing food intake tracking in long-term care with automated food imaging and nutrient intake tracking (AFINI-T) technology: A preliminary validation and feasibility study

  • Kaylen Pfisterer; 
  • Robert Amelard; 
  • Jennifer Boger; 
  • Heather Keller; 
  • Audrey Chung; 
  • Alexander Wong

ABSTRACT

Background:

Half of long-term care (LTC) residents are malnourished increasing hospitalization, mortality, morbidity, with lower quality of life. Current tracking methods are subjective and time consuming.

Objective:

This paper presents the automated food imaging and nutrient intake tracking (AFINI-T) technology designed for LTC.

Methods:

We propose a novel convolutional autoencoder for food classification, trained on an augmented UNIMIB2016 dataset and tested on our simulated LTC food intake dataset.

Results:

On 12 meal scenarios with up to 15 classes each, the top-1 classification accuracy was 88.9% with a mean intake error of -0.4 mL±36.7 mL. Nutrient intake estimation by volume was strongly linearly correlated with nutrient estimates from mass (r2 0.92 to 0.99) with good agreement between methods (σ= −2.7 to −0.01; zero within each of the limits of agreement).

Conclusions:

The AFINI-T approach is a deep-learning powered computational nutrient sensing system that may provide a novel means for more accurately and objectively tracking LTC resident food intake to support and prevent malnutrition tracking strategies.


 Citation

Please cite as:

Pfisterer K, Amelard R, Boger J, Keller H, Chung A, Wong A

Enhancing Food Intake Tracking in Long-term Care With Automated Food Imaging and Nutrient Intake Tracking (AFINI-T) Technology: Validation and Feasibility Assessment

JMIR Aging 2022;5(4):e37590

DOI: 10.2196/37590

PMID: 36394940

PMCID: 9716425

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.