Using Artificial Intelligence to Optimize Delivery of Weight Loss Treatment

使用人工智能优化减肥治疗的实施

• 批准号: 10210830
• 负责人: Evan M Forman
• 金额: $ 63.42万
• 依托单位: DREXEL UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-05-04 至 2026-04-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10210830
• 关键词: Accelerometer; Accountability; Address; Adult; Affect; Algorithms; American; Area; Artificial Intelligence; Automobile Driving; Behavior Therapy; Behavioral; Behavioral Research; Binge Eating; Body Weight decreased; Calories; Caring; Cellular Phone; Characteristics; Cost Savings; Cost-Benefit Analysis; Data; Effectiveness; Expert Systems; Frequencies; Gender; Goals; Gold; Government; Health system; Hour; Individual; Informal Social Control; Insurance; Intake; Internet; Intervention; Learning; Mental Depression; Minority; Mobile Health Application; Modality; Modeling; Monitor; Motivation; Nature; Obesity; Obesity Epidemic; Outcome; Overweight; Pain management; Participant; Persons; Phase; Physical activity; Policies; Population; Professional counselor; Psychological reinforcement; Race; Randomized; Resources; Robotics; Sample Size; Selection for Treatments; System; Telephone; Testing; Text; Text Messaging; Time; Training; Treatment Efficacy; Weight; Wireless Technology; acceptability and feasibility; base; care systems; clinically significant; cost; cost effective treatment; cost-effectiveness evaluation; design; digital; effective therapy; improved; improved outcome; innovation; intelligent algorithm; learning progression; medication compliance; overweight adults; programs; psychologic; recruit; remote delivery; responders and non-responders; response; skills; success; treatment responders; weight loss intervention; weight loss program

Abstract Seventy percent of American adults are overweight or obese, presenting an unprecedented challenge to the nation’s health systems. Effective behavioral programs exist, but these programs are intensive, long-term and require highly-trained clinicians, making them prohibitively expensive and thus limiting disseminability. Approaches to decreasing costs include replacing highly-trained clinicians with paraprofessionals, reducing contact frequency, and/or automating intervention. However, although these alternative interventions result in considerably lower average weight losses, variability of weight loss is high. Specifically, and consistent with a Supportive Accountability Model, a substantial minority of participants in high-intensity interventions receive no benefit, while a subset of those receiving low-intensity interventions achieve clinically significant weight loss. An ideal weight loss treatment system would enhance outcomes and reduce costs by matching each participant to the intervention he/she needs, thus adapting to participants’ needs and conserving resources where they are not needed. Stepped care represents one such system, but has had mixed success and suffers from a number of shortcomings. The innovative artificial intelligence (AI) strategy of reinforcement learning (RL) provides rapidly and repeatedly-varying features of intervention, continuously "learning" which features provide optimal responses for which participants. Our team recently completed a pilot of an AI weight loss system in which overweight adults received a brief in-person weight loss intervention and then were randomly assigned to receive 3 months of non-optimized interventions (i.e., 12-minute phone calls) or an optimized combination of phone calls, text exchanges, and automated messages, selected based on each participants’ response to each intervention as determined by weight and behavioral data. As hypothesized, we achieved equivalent weight losses at a fraction of the time cost. The proposed study would recruit 320 overweight adults, provide 1 month of group-based behavioral weight loss treatment and then randomize participants to either continue to receive group-based behavioral weight loss in a remote format for 11 months (BWL-S) or to reinforcement learning-based treatment (BWL-AI). In line with our Supportive Accountability model, BWL-AI would vary modality, intensity and counselor skill based on continuously-monitored participant digital data. The proposed study--the first of its kind--would expand on our pilot in several ways including sample size, duration, and features of intervention selected by the AI system. Aims of this project are to test the hypotheses that weight loss outcomes in BWL-AI will be equivalent to or better than BWL-S, and that the cost per participant and per kg of lost weight will be less in BWL-AI than in BWL-S. Other include characterizing the AI system (in terms of interventions selected), assessing feasibility and acceptability of the refined AI system, evaluating psychological and demographic predictors of AI intervention selection and investigating differences between responders and non-responders in how the AI system allocates resources.

抽象的 百分之七十的美国成年人超重或肥胖，这给人类健康带来了前所未有的挑战。 国家的卫生系统存在有效的行为计划，但这些计划是密集的、长期的和 需要训练有素的人群，这使得它们的成本过高，从而限制了传播能力。 降低成本的方法包括用辅助专业人员取代训练有素的教练、减少 然而，尽管这些替代干预措施会导致接触频率和/或自动化干预。 平均体重减轻相当低，体重减轻的变异性很高，并且与 支持性问责模型，高强度干预措施中的相当少数参与者没有得到任何支持 受益，而接受低强度干预的一部分人实现了临床上显着的体重减轻。 理想的减肥治疗系统将通过匹配每个减肥治疗系统来增强效果并降低成本 参与者接受他/她需要的干预，从而适应参与者的需求并节省资源 分级护理就是这样一种制度，但成效参差不齐。 强化学习的创新人工智能（AI）策略存在诸多缺点。 （RL）提供快速且反复变化的干预特征，“学习”其特征 我们的团队最近完成了一项人工智能减肥试点。 系统中，超重的成年人接受了简短的面对面减肥干预，然后随机分组 分配接受 3 个月的非优化干预（即 12 分钟电话）或优化干预 电话、短信和自动消息的组合，根据每个’进行选择 根据体重和行为数据确定对每次干预的反应。 拟议的研究将招募 320 名超重成年人， 提供 1 个月的基于小组的行为减肥治疗，然后将参与者随机分配到 继续以远程形式接受基于团体的行为减肥 11 个月 (BWL-S) 或 基于强化学习的治疗 (BWL-AI) 符合我们的支持责任模型 BWL-AI。 将根据持续监控的参与者数字数据改变方式、强度和咨询师技能。 拟议的研究——同类中的第一个——将从几个方面扩展我们的试点，包括样本量、持续时间、 人工智能系统选择的干预措施和特征 该项目的目的是检验以下假设。 BWL-AI 的减肥效果将相当于或优于 BWL-S，并且每个参与者的成本 BWL-AI 中每公斤减轻的重量将小于 BWL-S 中的其他包括表征 AI 系统（在 所选择的干预措施的条款），评估完善的人工智能系统的可行性和可接受性，评估 人工智能干预选择的心理和人口预测因素以及调查之间的差异 AI系统如何分配资源的响应者和非响应者。