PMID- 37943581
OWN - NLM
STAT- MEDLINE
DCOM- 20231110
LR  - 20231129
IS  - 1438-8871 (Electronic)
IS  - 1439-4456 (Print)
IS  - 1438-8871 (Linking)
VI  - 25
DP  - 2023 Nov 9
TI  - An AI Dietitian for Type 2 Diabetes Mellitus Management Based on Large Language 
      and Image Recognition Models: Preclinical Concept Validation Study.
PG  - e51300
LID - 10.2196/51300 [doi]
LID - e51300
AB  - BACKGROUND: Nutritional management for patients with diabetes in China is a 
      significant challenge due to the low supply of registered clinical dietitians. To 
      address this, an artificial intelligence (AI)-based nutritionist program that 
      uses advanced language and image recognition models was created. This program can 
      identify ingredients from images of a patient's meal and offer nutritional 
      guidance and dietary recommendations. OBJECTIVE: The primary objective of this 
      study is to evaluate the competence of the models that support this program. 
      METHODS: The potential of an AI nutritionist program for patients with type 2 
      diabetes mellitus (T2DM) was evaluated through a multistep process. First, a 
      survey was conducted among patients with T2DM and endocrinologists to identify 
      knowledge gaps in dietary practices. ChatGPT and GPT 4.0 were then tested through 
      the Chinese Registered Dietitian Examination to assess their proficiency in 
      providing evidence-based dietary advice. ChatGPT's responses to common questions 
      about medical nutrition therapy were compared with expert responses by 
      professional dietitians to evaluate its proficiency. The model's food 
      recommendations were scrutinized for consistency with expert advice. A deep 
      learning-based image recognition model was developed for food identification at 
      the ingredient level, and its performance was compared with existing models. 
      Finally, a user-friendly app was developed, integrating the capabilities of 
      language and image recognition models to potentially improve care for patients 
      with T2DM. RESULTS: Most patients (182/206, 88.4%) demanded more immediate and 
      comprehensive nutritional management and education. Both ChatGPT and GPT 4.0 
      passed the Chinese Registered Dietitian examination. ChatGPT's food 
      recommendations were mainly in line with best practices, except for certain foods 
      like root vegetables and dry beans. Professional dietitians' reviews of ChatGPT's 
      responses to common questions were largely positive, with 162 out of 168 
      providing favorable reviews. The multilabel image recognition model evaluation 
      showed that the Dino V2 model achieved an average F(1) score of 0.825, indicating 
      high accuracy in recognizing ingredients. CONCLUSIONS: The model evaluations were 
      promising. The AI-based nutritionist program is now ready for a supervised pilot 
      study.
CI  - (c)Haonan Sun, Kai Zhang, Wei Lan, Qiufeng Gu, Guangxiang Jiang, Xue Yang, Wanli 
      Qin, Dongran Han. Originally published in the Journal of Medical Internet 
      Research (https://www.jmir.org), 09.11.2023.
FAU - Sun, Haonan
AU  - Sun H
AUID- ORCID: 0000-0003-2352-4758
AD  - School of Life Science, Beijing University of Chinese Medicine, Beijing, China.
FAU - Zhang, Kai
AU  - Zhang K
AUID- ORCID: 0009-0007-8118-3564
AD  - School of Life Science, Beijing University of Chinese Medicine, Beijing, China.
FAU - Lan, Wei
AU  - Lan W
AUID- ORCID: 0009-0006-7937-4743
AD  - Department of Pediatrics, Peking University Shenzhen Hospital, Shenzhen, China.
FAU - Gu, Qiufeng
AU  - Gu Q
AUID- ORCID: 0009-0009-3161-7197
AD  - Department of Pediatrics, Peking University Shenzhen Hospital, Shenzhen, China.
FAU - Jiang, Guangxiang
AU  - Jiang G
AUID- ORCID: 0009-0000-1224-3526
AD  - School of Life Science, Beijing University of Chinese Medicine, Beijing, China.
FAU - Yang, Xue
AU  - Yang X
AUID- ORCID: 0009-0007-7986-5478
AD  - School of Life Science, Beijing University of Chinese Medicine, Beijing, China.
FAU - Qin, Wanli
AU  - Qin W
AUID- ORCID: 0009-0008-5591-1860
AD  - School of Life Science, Beijing University of Chinese Medicine, Beijing, China.
FAU - Han, Dongran
AU  - Han D
AUID- ORCID: 0000-0003-3630-5036
AD  - School of Life Science, Beijing University of Chinese Medicine, Beijing, China.
LA  - eng
PT  - Journal Article
DEP - 20231109
PL  - Canada
TA  - J Med Internet Res
JT  - Journal of medical Internet research
JID - 100959882
SB  - IM
MH  - Humans
MH  - *Nutritionists
MH  - *Diabetes Mellitus, Type 2/therapy
MH  - Artificial Intelligence
MH  - Pilot Projects
MH  - Language
MH  - Meals
PMC - PMC10667983
OTO - NOTNLM
OT  - AI
OT  - ChatGPT
OT  - GPT 4.0
OT  - NLP
OT  - artificial intelligence
OT  - deep learning
OT  - diabetes
OT  - diabetic
OT  - diet
OT  - dietary
OT  - dietician
OT  - digital health
OT  - food
OT  - image recognition
OT  - ingredient recognition
OT  - language model
OT  - machine learning
OT  - meal
OT  - meals
OT  - medical nutrition therapy
OT  - natural language processing
OT  - nutrition
OT  - nutritional
OT  - recommendation
COIS- Conflicts of Interest: None declared.
EDAT- 2023/11/09 12:42
MHDA- 2023/11/10 06:45
PMCR- 2023/11/09
CRDT- 2023/11/09 11:53
PHST- 2023/07/27 00:00 [received]
PHST- 2023/10/06 00:00 [accepted]
PHST- 2023/09/18 00:00 [revised]
PHST- 2023/11/10 06:45 [medline]
PHST- 2023/11/09 12:42 [pubmed]
PHST- 2023/11/09 11:53 [entrez]
PHST- 2023/11/09 00:00 [pmc-release]
AID - v25i1e51300 [pii]
AID - 10.2196/51300 [doi]
PST - epublish
SO  - J Med Internet Res. 2023 Nov 9;25:e51300. doi: 10.2196/51300.