| Naslov: | Improving personalized meal planning with large language models: identifying and decomposing compound ingredients |
|---|
| Avtorji: | ID Kopitar, Leon (Avtor)
ID Bedrač, Leon (Avtor)
ID Strath, Larissa Jane (Avtor)
ID Bian, Jiang (Avtor)
ID Štiglic, Gregor (Avtor) |
|---|
| Datoteke: |  nutrients-17-01492.pdf (684,70 KB)
MD5: BF0D9BB177BE275EAB7EF59CDC27A42F
 https://www.mdpi.com/2072-6643/17/9/1492
|
|---|
| Jezik: | Angleški jezik |
|---|
| Vrsta gradiva: | Znanstveno delo |
|---|
| Tipologija: | 1.01 - Izvirni znanstveni članek |
|---|
| Organizacija: | FZV - Fakulteta za zdravstvene vede
FERI - Fakulteta za elektrotehniko, računalništvo in informatiko
|
|---|
| Opis: | Background/Objectives: Identifying and decomposing compound ingredients within meal plans presents meal customization and nutritional analysis challenges. It is essential for accurately identifying and replacing problematic ingredients linked to allergies or intolerances and helping nutritional evaluation. Methods: This study explored the effectiveness of three large language models (LLMs)—GPT-4o, Llama-3 (70B), and Mixtral (8x7B), in decomposing compound ingredients into basic ingredients within meal plans. GPT-4o was used to generate 15 structured meal plans, each containing compound ingredients. Each LLM then identified and decomposed these compound items into basic ingredients. The decomposed ingredients were matched to entries in a subset of the USDA FoodData Central repository using API-based search and mapping techniques. Nutritional values were retrieved and aggregated to evaluate accuracy of decomposition. Performance was assessed through manual review by nutritionists and quantified using accuracy and F1-score. Statistical significance was tested using paired t-tests or Wilcoxon signed-rank tests based on normality. Results: Results showed that large models—both Llama-3 (70B) and GPT-4o—outperformed Mixtral (8x7B), achieving average F1-scores of 0.894 (95% CI: 0.84–0.95) and 0.842 (95% CI: 0.79–0.89), respectively, compared to an F1-score of 0.690 (95% CI: 0.62–0.76) from Mixtral (8x7B). Conclusions: The open-source Llama-3 (70B) model achieved the best performance, outperforming the commercial GPT-4o model, showing its superior ability to consistently break down compound ingredients into precise quantities within meal plans and illustrating its potential to enhance meal customization and nutritional analysis. These findings underscore the potential role of advanced LLMs in precision nutrition and their application in promoting healthier dietary practices tailored to individual preferences and needs. |
|---|
| Ključne besede: | artificial intelligence, food analysis, LLM, Ilama, GPT, mixtral, ingredient identification, ingredient decomposition, personalized nutrition, meal customization, nutritional analysis, dietary planning |
|---|
| Status publikacije: | Objavljeno |
|---|
| Verzija publikacije: | Objavljena publikacija |
|---|
| Poslano v recenzijo: | 25.03.2025 |
|---|
| Datum sprejetja članka: | 18.04.2025 |
|---|
| Datum objave: | 29.04.2025 |
|---|
| Založnik: | MDPI |
|---|
| Leto izida: | 2025 |
|---|
| Št. strani: | Str. 1-15 |
|---|
| Številčenje: | Letn. 17, št. 9, št. članka 1492 |
|---|
| PID: | 20.500.12556/DKUM-92722  |
|---|
| UDK: | 004.89:613.2 |
|---|
| COBISS.SI-ID: | 235011587 |
|---|
| DOI: | 10.3390/nu17091492 |
|---|
| ISSN pri članku: | 2072-6643 |
|---|
| Avtorske pravice: | © 2025 by the authors |
|---|
| Datum objave v DKUM: | 08.05.2025 |
|---|
| Število ogledov: | 263 |
|---|
| Število prenosov: | 6 |
|---|
| Metapodatki: |    |
|---|
| Področja: | Ostalo
|
|---|
|
:
|
Kopiraj citat |
|---|
| | | | Skupna ocena: | (0 glasov) |
|---|
| Vaša ocena: | Ocenjevanje je dovoljeno samo prijavljenim uporabnikom. |
|---|
| Objavi na: |  |
|---|
Postavite miškin kazalec na naslov za izpis povzetka. Klik na naslov izpiše
podrobnosti ali sproži prenos. |
