Study Protocol for the Effects of Artificial Intelligence (AI)-Supported Automated Nutritional Intervention on Glycemic Control in Patients with Type 2 Diabetes Mellitus.
Study Protocol for the Effects of Artificial Intelligence (AI)-Supported Automated Nutritional Intervention on Glycemic Control in Patients with Type 2 Diabetes Mellitus.
复制标题
人工智能 (AI) 支持的自动营养干预对 2 型糖尿病患者血糖控制影响的研究方案。
DOI：
10.1007/s13300-019-0595-5
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Yoneda T
中科院分区：
文献类型：
--
作者：
Oka R;Nomura A;Yasugi A;Kometani M;Gondoh Y;Yoshimura K;Yoneda T
前言营养干预能有效改善2型糖尿病患者的血糖控制，但需要大量人力投入。在人工智能(AI)和远程通信技术的推动下，照片分析技术最近的改进使营养摄入量的自动评估成为可能。人工智能和移动支持的营养干预预计将是传统面对面营养干预的替代方法，但人力资源较少，尽管支持证据尚不完整。本研究的目的是验证人工智能支持的营养干预在改善2型糖尿病患者血糖控制方面与面对面的方法同样有效的假设。方法本研究是一项多中心、非盲法、平行、随机对照研究，比较人工智能支持的自动化营养治疗和传统人类营养治疗在2型糖尿病患者中的疗效。将以饮食控制为主的2型糖尿病患者随机分为AI支持的营养治疗组( 组，n=50)和人类营养治疗组( 组，n=50)。Asken是一款移动应用程序，其营养评估已经通过经典的加权饮食记录方法进行了验证，它已经为这项研究进行了专门的修改，以便遵循日本糖尿病协会的建议(碳水化合物、脂肪和蛋白质的总能量限制分别为50-60、20和20-30%)。计划结果主要结果是糖化血红蛋白水平从基线到12个月的变化，这一结果将在两组之间进行比较。次要结果是空腹血糖、血脂、体重、体重指数、腰围、血压和尿白蛋白排泄的变化。这项随机对照试验的结果将填补营养干预中对人工智能支持的需求与其有效性的科学证据之间的差距。试验登记UMIN000032231。
IntroductionNutritional intervention is effective in improving glycemic control in patients with type 2 diabetes but requires large inputs of manpower. Recent improvements in photo analysis technology facilitated by artificial intelligence (AI) and remote communication technologies have enabled automated evaluations of nutrient intakes. AI- and mobile-supported nutritional intervention is expected to be an alternative approach to conventional in-person nutritional intervention, but with less human resources, although supporting evidence is not yet complete. The aim of this study is to test the hypothesis that AI-supported nutritional intervention is as efficacious as the in-person, face-to-face method in terms of improving glycemic control in patients with type 2 diabetes.MethodsThis is a multicenter, unblinded, parallel, randomized controlled study comparing the efficacy of AI-supported automated nutrition therapy with that of conventional human nutrition therapy in patients with type 2 diabetes. Patients with type 2 diabetes mainly controlled with diet are to be recruited and randomly assigned to AI-supported nutrition therapy (n= 50) and to human nutrition therapy (n= 50). Asken, a mobile application whose nutritional evaluation has been already validated to that by the classical method of weighted dietary records, has been specially modified for this study so that it follows the recommendations of Japan Diabetes Society (total energy restriction with proportion of carbohydrates to fat to protein of 50–60, 20, and 20–30%, respectively).Planned OutcomesThe primary outcome is the change in glycated hemoglobin levels from baseline to 12 months, and this outcome is to be compared between the two groups. The secondary outcomes are changes in fasting plasma glucose, plasma lipid profile, body weight, body mass index, waist circumference, blood pressures, and urinary albumin excretion. The results of this randomized controlled trial will fill the gap between the demand for support of AI in nutritional interventions and the scientific evidence on its efficacy.Trial RegistrationUMIN000032231.