Chinese Traditional and Herbal Drugs
|
2025, 56(12): 4345-4352
Screening and prediction of nutritional characteristics of sweet taste diet based on Tibetan medicine property theory and machine learning
Full
REN Zengjia1, DUOJIE Caidan1, WAN Macuo1, NIANGJIA Ben1, ZHOU Zejia1, LENG Benzhaxi2, QIEYANG Rangzhong1, NIMA Cairang3
Affiliations
1 Tibetan Medicine Health Preservation and Public Health Research Office, College of Tibetan Medicine, Qinghai University, Xining 810016, China;
2 National Key Laboratory of Tibetan Language Intelligent Processing, Qinghai Normal University, Xining 810008, China;
3 Jin Zhen Piter Ma Department, Qinghai Tibetan Medicine Hospital, Xining 810099, China
doi: 10.7501/j.issn.0253-2670.2025.12.018
Outline
Objective This study aims to combine traditional Tibetan medicine property theory with modern machine learning methods to construct a Tibetan dietary sweet taste prediction model based on nutritional characteristics, providing scientific evidence for the scientific modernization of Tibetan medicine property theory. Methods A Tibetan dietary database containing 786 foods was constructed by systematically reviewing classic Tibetan medicine literature and modern food nutrition data. Key nutritional feature variables were screened through recursive feature elimination and five-fold cross-validation (RFECV), and sweet taste prediction models were constructed based on seven machine learning algorithms. The feature importance and model prediction mechanism were analyzed using the CatBoost optimal model combined with the SHAP interpretation framework to verify the interpretability and individualized prediction capability of the model. Results Eight core features were ultimately selected from 29 nutrients, with mineral elements (iron, calcium, sodium, phosphorus, potassium) accounting for 62.5%, indicating that minerals play an important role in the classification of sweet-tasting foods. The CatBoost model performed best on multiple performance metrics, with an area under curve (AUC) value of 0.78, accuracy of 0.83, and recall of 1.00 on the test set. SHAP analysis showed that calcium and iron were the most critical factors affecting sweet taste classification, and revealed synergistic and antagonistic effects between mineral features. Decision path analysis indicated that the model has good feature hierarchical recognition and individualized prediction capabilities. Conclusion This study systematically analyzed the nutritional characteristics of Tibetan sweet-tasting foods through machine learning methods for the first time, verifying the key role of mineral elements in the “earth and water produce sweetness” theory, providing modern scientific evidence for the Tibetan dietary “flavor-nature transforms flavor” theory. The constructed sweet taste prediction model has good generalization performance and interpretability, providing a theoretical foundation and technical support for dietary optimization in plateau regions and the design of functional foods with the same source of medicine and food in Tibetan medicine. Future research will combine multimodal data and clinical experiments to further enhance the practicality and precision intervention capabilities of the model.
Tibetan medicine property theory
/
sweet taste prediction
/
machine learning
/
SHAP interpretation
/
nutritional characteristic
仁增加, 多杰才旦, 万玛措, 娘加本, 周则加, 冷本扎西, 切羊让忠, 尼玛才让.
基于藏医药性理论与机器学习的甘味饮食营养素特征筛选与预测研究.
中草药,
2025
, 56
(12)
: 4345
-4352
.
DOI: 10.7501/j.issn.0253-2670.2025.12.018
REN Zengjia, DUOJIE Caidan, WAN Macuo, NIANGJIA Ben, ZHOU Zejia, LENG Benzhaxi, QIEYANG Rangzhong, NIMA Cairang.
Screening and prediction of nutritional characteristics of sweet taste diet based on Tibetan medicine property theory and machine learning[J].
Chinese Traditional and Herbal Drugs,
2025
, 56
(12)
: 4345
-4352
.
DOI: 10.7501/j.issn.0253-2670.2025.12.018
Year 2025 volume 56 Issue 12
41
7
Cite this Article
BibTeX
Article Info
doi: 10.7501/j.issn.0253-2670.2025.12.018
- Receive Date:2025-03-19
- Online Date:2026-11-13