Andrea Foppiani, Ramona De Amicis, Alessandro Leone, Federica Sileo, Sara Paola Mambrini, Francesca Menichetti, Giorgia Pozzi, Simona Bertoli, Alberto Battezzati
{"title":"预测对糖尿病前期生活方式干预无反应者:一种机器学习方法。","authors":"Andrea Foppiani, Ramona De Amicis, Alessandro Leone, Federica Sileo, Sara Paola Mambrini, Francesca Menichetti, Giorgia Pozzi, Simona Bertoli, Alberto Battezzati","doi":"10.1038/s41430-024-01495-9","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>The clinical care process for people with prediabetes starts with lifestyle intervention, often escalating to more intense treatment due to the low success rate of the first-line intervention. Clinicians lack clear guidelines on which patients would benefit from early treatment with more intensive therapeutic options, so we aimed to develop an algorithm to early identify non-responders to lifestyle intervention for prediabetes.</p><p><strong>Method: </strong>Several statistical and machine learning algorithms were screened with internal cross-validation on the basis of accuracy and discrimination ability to correctly classify patients that would fail to normalize fasting glycemia within one year of being prescribed a lifestyle intervention, solely based on the first examination measurements.</p><p><strong>Result: </strong>Of the many screened algorithm, only a random forest model performed with sufficient accuracy to exceed the historical failure rate of patients within our center, with an accuracy of 0.689 (CI 0.669, 0.710) and an AUROC of 0.687 (CI 0.673, 0.701).</p><p><strong>Conclusions: </strong>This study showcases the ability of machine learning models to provide useful insight in clinical practice leveraging knowledge contained in routinely collected data.</p>","PeriodicalId":11927,"journal":{"name":"European Journal of Clinical Nutrition","volume":" ","pages":""},"PeriodicalIF":3.6000,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Predicting non-responders to lifestyle intervention in prediabetes: a machine learning approach.\",\"authors\":\"Andrea Foppiani, Ramona De Amicis, Alessandro Leone, Federica Sileo, Sara Paola Mambrini, Francesca Menichetti, Giorgia Pozzi, Simona Bertoli, Alberto Battezzati\",\"doi\":\"10.1038/s41430-024-01495-9\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>The clinical care process for people with prediabetes starts with lifestyle intervention, often escalating to more intense treatment due to the low success rate of the first-line intervention. Clinicians lack clear guidelines on which patients would benefit from early treatment with more intensive therapeutic options, so we aimed to develop an algorithm to early identify non-responders to lifestyle intervention for prediabetes.</p><p><strong>Method: </strong>Several statistical and machine learning algorithms were screened with internal cross-validation on the basis of accuracy and discrimination ability to correctly classify patients that would fail to normalize fasting glycemia within one year of being prescribed a lifestyle intervention, solely based on the first examination measurements.</p><p><strong>Result: </strong>Of the many screened algorithm, only a random forest model performed with sufficient accuracy to exceed the historical failure rate of patients within our center, with an accuracy of 0.689 (CI 0.669, 0.710) and an AUROC of 0.687 (CI 0.673, 0.701).</p><p><strong>Conclusions: </strong>This study showcases the ability of machine learning models to provide useful insight in clinical practice leveraging knowledge contained in routinely collected data.</p>\",\"PeriodicalId\":11927,\"journal\":{\"name\":\"European Journal of Clinical Nutrition\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":3.6000,\"publicationDate\":\"2024-10-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"European Journal of Clinical Nutrition\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1038/s41430-024-01495-9\",\"RegionNum\":3,\"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":"European Journal of Clinical Nutrition","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1038/s41430-024-01495-9","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"NUTRITION & DIETETICS","Score":null,"Total":0}
Predicting non-responders to lifestyle intervention in prediabetes: a machine learning approach.
Background: The clinical care process for people with prediabetes starts with lifestyle intervention, often escalating to more intense treatment due to the low success rate of the first-line intervention. Clinicians lack clear guidelines on which patients would benefit from early treatment with more intensive therapeutic options, so we aimed to develop an algorithm to early identify non-responders to lifestyle intervention for prediabetes.
Method: Several statistical and machine learning algorithms were screened with internal cross-validation on the basis of accuracy and discrimination ability to correctly classify patients that would fail to normalize fasting glycemia within one year of being prescribed a lifestyle intervention, solely based on the first examination measurements.
Result: Of the many screened algorithm, only a random forest model performed with sufficient accuracy to exceed the historical failure rate of patients within our center, with an accuracy of 0.689 (CI 0.669, 0.710) and an AUROC of 0.687 (CI 0.673, 0.701).
Conclusions: This study showcases the ability of machine learning models to provide useful insight in clinical practice leveraging knowledge contained in routinely collected data.
期刊介绍:
The European Journal of Clinical Nutrition (EJCN) is an international, peer-reviewed journal covering all aspects of human and clinical nutrition. The journal welcomes original research, reviews, case reports and brief communications based on clinical, metabolic and epidemiological studies that describe methodologies, mechanisms, associations and benefits of nutritional interventions for clinical disease and health promotion.
Topics of interest include but are not limited to:
Nutrition and Health (including climate and ecological aspects)
Metabolism & Metabolomics
Genomics and personalized strategies in nutrition
Nutrition during the early life cycle
Health issues and nutrition in the elderly
Phenotyping in clinical nutrition
Nutrition in acute and chronic diseases
The double burden of ''malnutrition'': Under-nutrition and Obesity
Prevention of Non Communicable Diseases (NCD)