DietNerd: A Nutrition Question-Answering System That Summarizes and Evaluates Peer-Reviewed Scientific Articles

Shela Wu; Zubair Yacub; Dennis Shasha

doi:10.3390/app14199021

DietNerd: A Nutrition Question-Answering System That Summarizes and Evaluates Peer-Reviewed Scientific Articles

Shela Wu, Zubair Yacub, Dennis Shasha

Research output: Contribution to journal › Article › peer-review

Abstract

DietNerd is a large language model-based system designed to enhance public health education in diet and nutrition. The system responds to user questions with concise, evidence-based summaries and assesses the quality and potential biases of cited research. This paper describes the system’s workflow, back-end implementation, and the prompts used. Accuracy and quality-of-response results are presented based on an automated comparison against systematic surveys and against the responses of similar state-of-the-art systems through human feedback from registered dietitians. DietNerd is among the highest-evaluated of these systems and is unique in combining safety features with sophisticated source analysis. Thus, DietNerd could be a tool to bridge the gap between complex scientific literature and public understanding.

Original language	English (US)
Article number	9021
Journal	Applied Sciences (Switzerland)
Volume	14
Issue number	19
DOIs	https://doi.org/10.3390/app14199021
State	Published - Oct 2024

Keywords

PubMed
diet
generative AI
large language models
nutrition
question-answering

ASJC Scopus subject areas

General Materials Science
Instrumentation
General Engineering
Process Chemistry and Technology
Computer Science Applications
Fluid Flow and Transfer Processes

Access to Document

10.3390/app14199021

Cite this

@article{f211269849574129b383bd653d872492,

title = "DietNerd: A Nutrition Question-Answering System That Summarizes and Evaluates Peer-Reviewed Scientific Articles",

abstract = "DietNerd is a large language model-based system designed to enhance public health education in diet and nutrition. The system responds to user questions with concise, evidence-based summaries and assesses the quality and potential biases of cited research. This paper describes the system{\textquoteright}s workflow, back-end implementation, and the prompts used. Accuracy and quality-of-response results are presented based on an automated comparison against systematic surveys and against the responses of similar state-of-the-art systems through human feedback from registered dietitians. DietNerd is among the highest-evaluated of these systems and is unique in combining safety features with sophisticated source analysis. Thus, DietNerd could be a tool to bridge the gap between complex scientific literature and public understanding.",

keywords = "PubMed, diet, generative AI, large language models, nutrition, question-answering",

author = "Shela Wu and Zubair Yacub and Dennis Shasha",

note = "Publisher Copyright: {\textcopyright} 2024 by the authors.",

year = "2024",

month = oct,

doi = "10.3390/app14199021",

language = "English (US)",

volume = "14",

journal = "Applied Sciences (Switzerland)",

issn = "2076-3417",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "19",

}

TY - JOUR

T1 - DietNerd

T2 - A Nutrition Question-Answering System That Summarizes and Evaluates Peer-Reviewed Scientific Articles

AU - Wu, Shela

AU - Yacub, Zubair

AU - Shasha, Dennis

PY - 2024/10

Y1 - 2024/10

N2 - DietNerd is a large language model-based system designed to enhance public health education in diet and nutrition. The system responds to user questions with concise, evidence-based summaries and assesses the quality and potential biases of cited research. This paper describes the system’s workflow, back-end implementation, and the prompts used. Accuracy and quality-of-response results are presented based on an automated comparison against systematic surveys and against the responses of similar state-of-the-art systems through human feedback from registered dietitians. DietNerd is among the highest-evaluated of these systems and is unique in combining safety features with sophisticated source analysis. Thus, DietNerd could be a tool to bridge the gap between complex scientific literature and public understanding.

AB - DietNerd is a large language model-based system designed to enhance public health education in diet and nutrition. The system responds to user questions with concise, evidence-based summaries and assesses the quality and potential biases of cited research. This paper describes the system’s workflow, back-end implementation, and the prompts used. Accuracy and quality-of-response results are presented based on an automated comparison against systematic surveys and against the responses of similar state-of-the-art systems through human feedback from registered dietitians. DietNerd is among the highest-evaluated of these systems and is unique in combining safety features with sophisticated source analysis. Thus, DietNerd could be a tool to bridge the gap between complex scientific literature and public understanding.

KW - PubMed

KW - diet

KW - generative AI

KW - large language models

KW - nutrition

KW - question-answering

UR - http://www.scopus.com/inward/record.url?scp=85206592874&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85206592874&partnerID=8YFLogxK

U2 - 10.3390/app14199021

DO - 10.3390/app14199021

M3 - Article

AN - SCOPUS:85206592874

SN - 2076-3417

VL - 14

JO - Applied Sciences (Switzerland)

JF - Applied Sciences (Switzerland)

IS - 19

M1 - 9021

ER -

DietNerd: A Nutrition Question-Answering System That Summarizes and Evaluates Peer-Reviewed Scientific Articles

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this