Validation of Mobile Artificial Intelligence Technology–Assisted Dietary Assessment Tool Against Weighed Records and 24-Hour Recall in Adolescent Females in Ghana

Background Important gaps exist on dietary intake of adolescents in low- and middle-income countries (LMICs), partly due to expensive assessment methods and inaccuracy in portion size estimation. Dietary assessment tools leveraging mobile technologies exist but few have been validated in LMICs. Obj...

Descripción completa

Detalles Bibliográficos
Autores principales: Folson, Gloria, Bannerman, Boateng, Atadze, Vicentia, Ador, Gabriel, Kolt, Bastien, McCloske, Peter, Gangupantulu, Rohit, Arrieta, Alejandra, Braga, Bianca C., Arsenault, Joanne, Kehs, Annalyse, Doyle, Frank, Tran, Lan Mai, Hoang, Nga Thu, Hughes, David, Nguyen, Phuong Hong, Gelli, Aulo
Formato: Journal Article
Lenguaje:Inglés
Publicado: Elsevier 2023
Materias:
Acceso en línea:https://hdl.handle.net/10568/130688
_version_ 1855527017984819200
author Folson, Gloria
Bannerman, Boateng
Atadze, Vicentia
Ador, Gabriel
Kolt, Bastien
McCloske, Peter
Gangupantulu, Rohit
Arrieta, Alejandra
Braga, Bianca C.
Arsenault, Joanne
Kehs, Annalyse
Doyle, Frank
Tran, Lan Mai
Hoang, Nga Thu
Hughes, David
Nguyen, Phuong Hong
Gelli, Aulo
author_browse Ador, Gabriel
Arrieta, Alejandra
Arsenault, Joanne
Atadze, Vicentia
Bannerman, Boateng
Braga, Bianca C.
Doyle, Frank
Folson, Gloria
Gangupantulu, Rohit
Gelli, Aulo
Hoang, Nga Thu
Hughes, David
Kehs, Annalyse
Kolt, Bastien
McCloske, Peter
Nguyen, Phuong Hong
Tran, Lan Mai
author_facet Folson, Gloria
Bannerman, Boateng
Atadze, Vicentia
Ador, Gabriel
Kolt, Bastien
McCloske, Peter
Gangupantulu, Rohit
Arrieta, Alejandra
Braga, Bianca C.
Arsenault, Joanne
Kehs, Annalyse
Doyle, Frank
Tran, Lan Mai
Hoang, Nga Thu
Hughes, David
Nguyen, Phuong Hong
Gelli, Aulo
author_sort Folson, Gloria
collection Repository of Agricultural Research Outputs (CGSpace)
description Background Important gaps exist on dietary intake of adolescents in low- and middle-income countries (LMICs), partly due to expensive assessment methods and inaccuracy in portion size estimation. Dietary assessment tools leveraging mobile technologies exist but few have been validated in LMICs. Objective We validated FRANI (Food Recognition Assistance and Nudging Insights), a mobile Artificial Intelligence (AI) dietary assessment application in adolescent females aged 12–18y (n = 36) in Ghana, against weighed records (WR), and multi-pass 24-hour recalls (24HR). Methods Dietary intake was assessed during three non-consecutive days using FRANI, WRs and 24HRs. Equivalence of nutrient intake was tested using mixed effect models adjusted for repeated measures, by comparing ratios (FRANI/WR and 24HR/WR) with equivalence margins at 10%, 15% and 20% error bounds. Agreement between methods was assessed using the concordance correlation coefficient (CCC). Results Equivalence for FRANI and WR was determined at the 10% bound for energy intake, 15% for five nutrients (iron, zinc, folate, niacin, and vitamin B6), and 20% for protein, calcium, riboflavin, and thiamine intakes. Comparisons between 24HR and WR estimated equivalence at the 20% bound for energy, carbohydrate, fibre, calcium, thiamine and vitamin A intakes. The CCCs by nutrient between FRANI and WR ranged between 0.30 and 0.68, which was similar for CCC between 24HR and WR (ranging between 0.38 and 0.67). Comparisons of food consumption episodes from FRANI and WR found 31% omission and 16% intrusion errors. Omission and intrusion errors were lower when comparing 24HR to WR (21% and 13% respectively). Conclusions FRANI AI-assisted dietary assessment could accurately estimate nutrient intake in adolescent females compared to WR in urban Ghana. FRANI estimates were at least as accurate as those provided through 24HR. Further improvements in food-recognition and portion estimation in FRANI could reduce errors and improve overall nutrient intake estimations.
format Journal Article
id CGSpace130688
institution CGIAR Consortium
language Inglés
publishDate 2023
publishDateRange 2023
publishDateSort 2023
publisher Elsevier
publisherStr Elsevier
record_format dspace
spelling CGSpace1306882025-04-03T21:29:27Z Validation of Mobile Artificial Intelligence Technology–Assisted Dietary Assessment Tool Against Weighed Records and 24-Hour Recall in Adolescent Females in Ghana Folson, Gloria Bannerman, Boateng Atadze, Vicentia Ador, Gabriel Kolt, Bastien McCloske, Peter Gangupantulu, Rohit Arrieta, Alejandra Braga, Bianca C. Arsenault, Joanne Kehs, Annalyse Doyle, Frank Tran, Lan Mai Hoang, Nga Thu Hughes, David Nguyen, Phuong Hong Gelli, Aulo adolescence (human) artificial intelligence diet nutrient intake women Background Important gaps exist on dietary intake of adolescents in low- and middle-income countries (LMICs), partly due to expensive assessment methods and inaccuracy in portion size estimation. Dietary assessment tools leveraging mobile technologies exist but few have been validated in LMICs. Objective We validated FRANI (Food Recognition Assistance and Nudging Insights), a mobile Artificial Intelligence (AI) dietary assessment application in adolescent females aged 12–18y (n = 36) in Ghana, against weighed records (WR), and multi-pass 24-hour recalls (24HR). Methods Dietary intake was assessed during three non-consecutive days using FRANI, WRs and 24HRs. Equivalence of nutrient intake was tested using mixed effect models adjusted for repeated measures, by comparing ratios (FRANI/WR and 24HR/WR) with equivalence margins at 10%, 15% and 20% error bounds. Agreement between methods was assessed using the concordance correlation coefficient (CCC). Results Equivalence for FRANI and WR was determined at the 10% bound for energy intake, 15% for five nutrients (iron, zinc, folate, niacin, and vitamin B6), and 20% for protein, calcium, riboflavin, and thiamine intakes. Comparisons between 24HR and WR estimated equivalence at the 20% bound for energy, carbohydrate, fibre, calcium, thiamine and vitamin A intakes. The CCCs by nutrient between FRANI and WR ranged between 0.30 and 0.68, which was similar for CCC between 24HR and WR (ranging between 0.38 and 0.67). Comparisons of food consumption episodes from FRANI and WR found 31% omission and 16% intrusion errors. Omission and intrusion errors were lower when comparing 24HR to WR (21% and 13% respectively). Conclusions FRANI AI-assisted dietary assessment could accurately estimate nutrient intake in adolescent females compared to WR in urban Ghana. FRANI estimates were at least as accurate as those provided through 24HR. Further improvements in food-recognition and portion estimation in FRANI could reduce errors and improve overall nutrient intake estimations. 2023-08 2023-06-08T18:49:35Z 2023-06-08T18:49:35Z Journal Article https://hdl.handle.net/10568/130688 en Open Access Elsevier Folson, Gloria; Kolt, Bastien; Arrieta, Alejandra; Nguyen, Phuong Hong; Gelli, Aulo; et al. 2023. Validation of Mobile Artificial Intelligence Technology–Assisted Dietary Assessment Tool Against Weighed Records and 24-Hour Recall in Adolescent Females in Ghana. Journal of Nutrition 153(8): 2328-2338. https://doi.org/10.1016/j.tjnut.2023.06.001
spellingShingle adolescence (human)
artificial intelligence
diet
nutrient intake
women
Folson, Gloria
Bannerman, Boateng
Atadze, Vicentia
Ador, Gabriel
Kolt, Bastien
McCloske, Peter
Gangupantulu, Rohit
Arrieta, Alejandra
Braga, Bianca C.
Arsenault, Joanne
Kehs, Annalyse
Doyle, Frank
Tran, Lan Mai
Hoang, Nga Thu
Hughes, David
Nguyen, Phuong Hong
Gelli, Aulo
Validation of Mobile Artificial Intelligence Technology–Assisted Dietary Assessment Tool Against Weighed Records and 24-Hour Recall in Adolescent Females in Ghana
title Validation of Mobile Artificial Intelligence Technology–Assisted Dietary Assessment Tool Against Weighed Records and 24-Hour Recall in Adolescent Females in Ghana
title_full Validation of Mobile Artificial Intelligence Technology–Assisted Dietary Assessment Tool Against Weighed Records and 24-Hour Recall in Adolescent Females in Ghana
title_fullStr Validation of Mobile Artificial Intelligence Technology–Assisted Dietary Assessment Tool Against Weighed Records and 24-Hour Recall in Adolescent Females in Ghana
title_full_unstemmed Validation of Mobile Artificial Intelligence Technology–Assisted Dietary Assessment Tool Against Weighed Records and 24-Hour Recall in Adolescent Females in Ghana
title_short Validation of Mobile Artificial Intelligence Technology–Assisted Dietary Assessment Tool Against Weighed Records and 24-Hour Recall in Adolescent Females in Ghana
title_sort validation of mobile artificial intelligence technology assisted dietary assessment tool against weighed records and 24 hour recall in adolescent females in ghana
topic adolescence (human)
artificial intelligence
diet
nutrient intake
women
url https://hdl.handle.net/10568/130688
work_keys_str_mv AT folsongloria validationofmobileartificialintelligencetechnologyassisteddietaryassessmenttoolagainstweighedrecordsand24hourrecallinadolescentfemalesinghana
AT bannermanboateng validationofmobileartificialintelligencetechnologyassisteddietaryassessmenttoolagainstweighedrecordsand24hourrecallinadolescentfemalesinghana
AT atadzevicentia validationofmobileartificialintelligencetechnologyassisteddietaryassessmenttoolagainstweighedrecordsand24hourrecallinadolescentfemalesinghana
AT adorgabriel validationofmobileartificialintelligencetechnologyassisteddietaryassessmenttoolagainstweighedrecordsand24hourrecallinadolescentfemalesinghana
AT koltbastien validationofmobileartificialintelligencetechnologyassisteddietaryassessmenttoolagainstweighedrecordsand24hourrecallinadolescentfemalesinghana
AT mccloskepeter validationofmobileartificialintelligencetechnologyassisteddietaryassessmenttoolagainstweighedrecordsand24hourrecallinadolescentfemalesinghana
AT gangupantulurohit validationofmobileartificialintelligencetechnologyassisteddietaryassessmenttoolagainstweighedrecordsand24hourrecallinadolescentfemalesinghana
AT arrietaalejandra validationofmobileartificialintelligencetechnologyassisteddietaryassessmenttoolagainstweighedrecordsand24hourrecallinadolescentfemalesinghana
AT bragabiancac validationofmobileartificialintelligencetechnologyassisteddietaryassessmenttoolagainstweighedrecordsand24hourrecallinadolescentfemalesinghana
AT arsenaultjoanne validationofmobileartificialintelligencetechnologyassisteddietaryassessmenttoolagainstweighedrecordsand24hourrecallinadolescentfemalesinghana
AT kehsannalyse validationofmobileartificialintelligencetechnologyassisteddietaryassessmenttoolagainstweighedrecordsand24hourrecallinadolescentfemalesinghana
AT doylefrank validationofmobileartificialintelligencetechnologyassisteddietaryassessmenttoolagainstweighedrecordsand24hourrecallinadolescentfemalesinghana
AT tranlanmai validationofmobileartificialintelligencetechnologyassisteddietaryassessmenttoolagainstweighedrecordsand24hourrecallinadolescentfemalesinghana
AT hoangngathu validationofmobileartificialintelligencetechnologyassisteddietaryassessmenttoolagainstweighedrecordsand24hourrecallinadolescentfemalesinghana
AT hughesdavid validationofmobileartificialintelligencetechnologyassisteddietaryassessmenttoolagainstweighedrecordsand24hourrecallinadolescentfemalesinghana
AT nguyenphuonghong validationofmobileartificialintelligencetechnologyassisteddietaryassessmenttoolagainstweighedrecordsand24hourrecallinadolescentfemalesinghana
AT gelliaulo validationofmobileartificialintelligencetechnologyassisteddietaryassessmenttoolagainstweighedrecordsand24hourrecallinadolescentfemalesinghana