{"title":"可解释的机器学习框架,用于预测与膳食纤维和甘油三酯-葡萄糖指数相关的痛风。","authors":"Shunshun Cao, Yangyang Hu","doi":"10.1186/s12986-024-00802-2","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Gout prediction is essential for the development of individualized prevention and treatment plans. Our objective was to develop an efficient and interpretable machine learning (ML) model using the SHapley Additive exPlanation (SHAP) to link dietary fiber and triglyceride-glucose (TyG) index to predict gout.</p><p><strong>Methods: </strong>Using datasets from the National Health and Nutrition Examination Survey (NHANES) (2005-2018) population to study dietary fiber, the TyG index was used to predict gout. After evaluating the performance of six ML models and selecting the Light Gradient Boosting Machine (LGBM) as the optimal algorithm, we interpret the LGBM model for predicting gout using SHAP and reveal the decision-making process of the model.</p><p><strong>Results: </strong>An initial survey of 70,190 participants was conducted, and after a gradual exclusion process, 12,645 cases were finally included in the study. Selection of the best performing LGBM model for prediction of gout associated with dietary fiber and TyG index (Area under the ROC curve (AUC): 0.823, 95% confidence interval (CI): 0.798-0.848, Accuracy: 95.3%, Brier score: 0.077). The feature importance of SHAP values indicated that age was the most important feature affecting the model output, followed by uric acid (UA). The SHAP values showed that lower dietary fiber values had a more pronounced effect on the positive prediction of the model, while higher values of the TyG index had a more pronounced effect on the positive prediction of the model.</p><p><strong>Conclusion: </strong>The interpretable LGBM model associated with dietary fiber and TyG index showed high accuracy, efficiency, and robustness in predicting gout. Increasing dietary fiber intake and lowering the TyG index are beneficial in reducing the potential risk of gout.</p>","PeriodicalId":19196,"journal":{"name":"Nutrition & Metabolism","volume":"21 1","pages":"25"},"PeriodicalIF":3.9000,"publicationDate":"2024-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11092237/pdf/","citationCount":"0","resultStr":"{\"title\":\"Interpretable machine learning framework to predict gout associated with dietary fiber and triglyceride-glucose index.\",\"authors\":\"Shunshun Cao, Yangyang Hu\",\"doi\":\"10.1186/s12986-024-00802-2\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Gout prediction is essential for the development of individualized prevention and treatment plans. Our objective was to develop an efficient and interpretable machine learning (ML) model using the SHapley Additive exPlanation (SHAP) to link dietary fiber and triglyceride-glucose (TyG) index to predict gout.</p><p><strong>Methods: </strong>Using datasets from the National Health and Nutrition Examination Survey (NHANES) (2005-2018) population to study dietary fiber, the TyG index was used to predict gout. After evaluating the performance of six ML models and selecting the Light Gradient Boosting Machine (LGBM) as the optimal algorithm, we interpret the LGBM model for predicting gout using SHAP and reveal the decision-making process of the model.</p><p><strong>Results: </strong>An initial survey of 70,190 participants was conducted, and after a gradual exclusion process, 12,645 cases were finally included in the study. Selection of the best performing LGBM model for prediction of gout associated with dietary fiber and TyG index (Area under the ROC curve (AUC): 0.823, 95% confidence interval (CI): 0.798-0.848, Accuracy: 95.3%, Brier score: 0.077). The feature importance of SHAP values indicated that age was the most important feature affecting the model output, followed by uric acid (UA). The SHAP values showed that lower dietary fiber values had a more pronounced effect on the positive prediction of the model, while higher values of the TyG index had a more pronounced effect on the positive prediction of the model.</p><p><strong>Conclusion: </strong>The interpretable LGBM model associated with dietary fiber and TyG index showed high accuracy, efficiency, and robustness in predicting gout. Increasing dietary fiber intake and lowering the TyG index are beneficial in reducing the potential risk of gout.</p>\",\"PeriodicalId\":19196,\"journal\":{\"name\":\"Nutrition & Metabolism\",\"volume\":\"21 1\",\"pages\":\"25\"},\"PeriodicalIF\":3.9000,\"publicationDate\":\"2024-05-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11092237/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Nutrition & Metabolism\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1186/s12986-024-00802-2\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"NUTRITION & DIETETICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nutrition & Metabolism","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s12986-024-00802-2","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"NUTRITION & DIETETICS","Score":null,"Total":0}
Interpretable machine learning framework to predict gout associated with dietary fiber and triglyceride-glucose index.
Background: Gout prediction is essential for the development of individualized prevention and treatment plans. Our objective was to develop an efficient and interpretable machine learning (ML) model using the SHapley Additive exPlanation (SHAP) to link dietary fiber and triglyceride-glucose (TyG) index to predict gout.
Methods: Using datasets from the National Health and Nutrition Examination Survey (NHANES) (2005-2018) population to study dietary fiber, the TyG index was used to predict gout. After evaluating the performance of six ML models and selecting the Light Gradient Boosting Machine (LGBM) as the optimal algorithm, we interpret the LGBM model for predicting gout using SHAP and reveal the decision-making process of the model.
Results: An initial survey of 70,190 participants was conducted, and after a gradual exclusion process, 12,645 cases were finally included in the study. Selection of the best performing LGBM model for prediction of gout associated with dietary fiber and TyG index (Area under the ROC curve (AUC): 0.823, 95% confidence interval (CI): 0.798-0.848, Accuracy: 95.3%, Brier score: 0.077). The feature importance of SHAP values indicated that age was the most important feature affecting the model output, followed by uric acid (UA). The SHAP values showed that lower dietary fiber values had a more pronounced effect on the positive prediction of the model, while higher values of the TyG index had a more pronounced effect on the positive prediction of the model.
Conclusion: The interpretable LGBM model associated with dietary fiber and TyG index showed high accuracy, efficiency, and robustness in predicting gout. Increasing dietary fiber intake and lowering the TyG index are beneficial in reducing the potential risk of gout.
期刊介绍:
Nutrition & Metabolism publishes studies with a clear focus on nutrition and metabolism with applications ranging from nutrition needs, exercise physiology, clinical and population studies, as well as the underlying mechanisms in these aspects.
The areas of interest for Nutrition & Metabolism encompass studies in molecular nutrition in the context of obesity, diabetes, lipedemias, metabolic syndrome and exercise physiology. Manuscripts related to molecular, cellular and human metabolism, nutrient sensing and nutrient–gene interactions are also in interest, as are submissions that have employed new and innovative strategies like metabolomics/lipidomics or other omic-based biomarkers to predict nutritional status and metabolic diseases.
Key areas we wish to encourage submissions from include:
-how diet and specific nutrients interact with genes, proteins or metabolites to influence metabolic phenotypes and disease outcomes;
-the role of epigenetic factors and the microbiome in the pathogenesis of metabolic diseases and their influence on metabolic responses to diet and food components;
-how diet and other environmental factors affect epigenetics and microbiota; the extent to which genetic and nongenetic factors modify personal metabolic responses to diet and food compositions and the mechanisms involved;
-how specific biologic networks and nutrient sensing mechanisms attribute to metabolic variability.