Mobile Application to Deliver Personalized Nutrition for the Prevention of Alzheimer's Disease

Genben Lifesciences（dba GB HealthWatch）是一家数字健康和营养基因组学公司。我们 使命是通过精准营养帮助抗击常见的、与饮食和生活方式相关的慢性疾病， 先进的移动的技术。我们公司开发了HealthWatch 360移动的应用程序， 饮食摄入、体力活动和健康相关症状。这款移动的应用获得了优秀的 iOS和Android平台的评论，拥有超过70，000名注册用户。健康状况- 应用程序中的特定目标提供了基于临床的精细营养建议 预防饮食引起的慢性疾病的指南。阿尔茨海默病（AD）是主要的 在美国痴呆症的原因，第六大死亡原因和国家的主要成本，家庭 和照顾者。第一阶段的建议是开发一个移动的工具， 基于遗传风险的个性化营养和膳食计划，以减轻AD风险。 目标1：制定一个系统的程序，以确定特定的饮食和营养成分 与AD有关。使用1000个基因组第三阶段数据库和营养分析， 与26个人群相对应的传统饮食，我们将分析特定的营养素 与易患AD的遗传变异频率相关。我们假设 当遗传变异被消除时，人群的适应性将得到增强，AD风险将降低。 在给定的人群中选择的食物与富含或耗尽的饮食平衡， 相关营养素。我们将开发统计模型来量化这些关系。 目标2：将营养模式转化为一套预防AD的定量建议。 利用我们从Aim 1中获得的营养数据，结合其他循证营养指南， 对于AD，我们将根据应用程序用户的 基因型、AD家族史和其他健康状况。这些基因型和/或表型- 具体的规则将估计给定营养素的理想范围，并修改传统的"规则"（即， 2015 - 2020年美国膳食指南（Dietary Guidelines for America） 目标3：移动的应用程序，用于提供预防AD的个性化膳食计划。这个移动的 应用程序旨在引导，主动和自我执行的预防AD，并针对那些 高危人群我们建议开发机器学习算法来创建膳食计划， 采用针对给定AD风险基因型的修改的营养范围（来自目标1和2）。用户将能够 修改食物偏好参数（例如，"素食"），同时保持适当的 营养范围。 该项目的一个关键成果将是一个支持全民饮食干预的平台， 将预防性医疗保健与数字时代的日常生活无缝连接。

Genben Lifesciences (dba GB HealthWatch) is a digital health and nutritional genomics company. Our mission is to help fight common, diet- and lifestyle-related chronic diseases with precision nutrition and advanced mobile technologies. Our company developed the HealthWatch 360 mobile app for tracking dietary intake, physical activity and health-related symptoms. This mobile app has received excellent reviews for both the iOS and Android platforms and has over 70,000 registered users. Health condition- specific goals featured in the app provide refined nutritional recommendations based on clinical guidelines for the prevention of diet-induced, chronic diseases. Alzheimer’s disease (AD) is the leading cause of dementia in the U.S., the 6th leading cause of mortality and a major cost to the nation, families and caregivers. This phase I proposal is for the development of a mobile tool that will deliver personalized nutrition and meal plans based on genetic risk in order to mitigate AD risk. Aim 1: Develop a systematic process to identify specific dietary and nutritional components associated with AD. Using the 1000 Genomes Phase 3 database and nutritional analyses of the traditional diets that correspond with the 26 populations, we will analyze whether specific nutrients correlate with the frequency of genetic variants that predispose risk of AD. We hypothesize that a population’s fitness would be enhanced and AD risk would be lower when the genetic variants that are selected for in a given population are in equilibrium with a diet that is enriched or depleted with the correlated nutrient(s). We will develop statistical models that will quantify these relationships. Aim 2: Translate nutritional patterns to a set of quantitative recommendations for AD prevention. With the nutrient data we obtain from Aim 1, combined with other evidence-based nutrition guidelines for AD, we will synthesize a set of qualitative and quantitative nutritional “rules” based on the app user’s genotypes, family history of AD and other health conditions. These genotype- and/or phenotype - specific rules will estimate ideal ranges for a given nutrient and amend the conventional “rules” (i.e. nutritional recommendations) by the 2015-2020 Dietary Guidelines for America. Aim 3: Mobile app for delivery of personalized meal plan for the prevention of AD. This mobile application is designed for guided, proactive and self-executed prevention of AD, and targeted at those who are at elevated risk. We propose developing machine-learning algorithms to create meal plans that employ the modified nutrient ranges (from Aims 1 and 2) for a given AD risk genotype. Users will be able to modify food preference parameters (for example, “vegetarian”) while maintaining the appropriate nutrient ranges. A key outcome of this project will be a platform that supports population-wide dietary intervention by seamlessly connecting preventive healthcare with daily life in the digital age.