A Cross-Sectional Reproducibility Study of a Standard Camera Sensor Using Artificial Intelligence to Assess Food Items: The FoodIntech Project.
artificial intelligence
machine learning
mobile phone images
portion evaluation
reliability
Journal
Nutrients
ISSN: 2072-6643
Titre abrégé: Nutrients
Pays: Switzerland
ID NLM: 101521595
Informations de publication
Date de publication:
05 Jan 2022
05 Jan 2022
Historique:
received:
23
11
2021
revised:
30
12
2021
accepted:
01
01
2022
entrez:
11
1
2022
pubmed:
12
1
2022
medline:
29
1
2022
Statut:
epublish
Résumé
Having a system to measure food consumption is important to establish whether individual nutritional needs are being met in order to act quickly and to minimize the risk of undernutrition. Here, we tested a smartphone-based food consumption assessment system named FoodIntech. FoodIntech, which is based on AI using deep neural networks (DNN), automatically recognizes food items and dishes and calculates food leftovers using an image-based approach, i.e., it does not require human intervention to assess food consumption. This method uses one-input and one-output images by means of the detection and synchronization of a QRcode located on the meal tray. The DNN are then used to process the images and implement food detection, segmentation and recognition. Overall, 22,544 situations analyzed from 149 dishes were used to test the reliability of this method. The reliability of the AI results, based on the central intra-class correlation coefficient values, appeared to be excellent for 39% of the dishes (
Identifiants
pubmed: 35011096
pii: nu14010221
doi: 10.3390/nu14010221
pmc: PMC8747564
pii:
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Subventions
Organisme : FEDER
ID : 2016-6200FEO003S04417
Références
Nutrients. 2016 Sep 09;8(9):
pubmed: 27618096
J Nutr Health Aging. 2017;21(6):614-621
pubmed: 28537324
Clin Nutr. 2013 Oct;32(5):746-51
pubmed: 23305605
Public Health Nutr. 2019 May;22(7):1168-1179
pubmed: 29576027
JMIR Form Res. 2020 Oct 26;4(10):e18507
pubmed: 33104010
Obesity (Silver Spring). 2012 Apr;20(4):891-9
pubmed: 22134199
JMIR Mhealth Uhealth. 2015 Mar 13;3(1):e30
pubmed: 25775506
J Acad Nutr Diet. 2021 Apr;121(4):749-761.e1
pubmed: 33187931
Nutrients. 2021 Jan 22;13(2):
pubmed: 33499405
Br J Nutr. 2009 Feb;101(3):446-56
pubmed: 18616837
Eur J Clin Nutr. 2018 Jun;72(6):879-887
pubmed: 29563639
Nutrients. 2018 Dec 18;10(12):
pubmed: 30567362
Annu Int Conf IEEE Eng Med Biol Soc. 2019 Jul;2019:5696-5699
pubmed: 31947145
Nutrients. 2015 Jun 17;7(6):4897-910
pubmed: 26091234
Appetite. 2015 Jan;84:11-9
pubmed: 25261733
Clin Nutr. 2015 Aug;34(4):761-6
pubmed: 25234612
Appetite. 2013 Apr;63:31-5
pubmed: 23262297
J Hum Nutr Diet. 2014 Jan;27 Suppl 1:72-81
pubmed: 23848588
JMIR Mhealth Uhealth. 2020 Sep 9;8(9):e16953
pubmed: 32902389
J Chiropr Med. 2016 Jun;15(2):155-63
pubmed: 27330520
J Sch Health. 2008 Aug;78(8):432-7
pubmed: 18651930
Appetite. 2017 Sep 1;116:389-394
pubmed: 28527951
Clin Nutr. 2016 Dec;35(6):1543-1549
pubmed: 27126712
Nutr J. 2020 Sep 18;19(1):104
pubmed: 32948201
Sensors (Basel). 2020 Jul 31;20(15):
pubmed: 32752007
Stat Med. 1998 Jan 15;17(1):101-10
pubmed: 9463853
Nutrients. 2019 Apr 18;11(4):
pubmed: 31003547
Psychol Bull. 1979 Mar;86(2):420-8
pubmed: 18839484
J Am Diet Assoc. 2003 Sep;103(9):1139-45
pubmed: 12963941
Clin Nutr ESPEN. 2018 Feb;23:122-128
pubmed: 29460787
Public Health Nutr. 2014 Aug;17(8):1671-81
pubmed: 24476848
Clin Nutr. 2010 Oct;29(5):552-9
pubmed: 20434820
Proc Nutr Soc. 2017 Aug;76(3):283-294
pubmed: 27938425