Using artificially intelligent text messaging technology to improve American Heart Association's Life's Simple 7 Health Behaviors: LS7 Bot + Backup

项目总结/摘要 我们的目标是通过多层次干预改善心血管疾病风险因素的控制 利用整合在卫生系统中的手机短信， 心脏协会的生活简单7（LS 7）生活方式因素（血糖、胆固醇、血压、身体状况） 活动、体重、饮食和吸烟）。当不受控制时，这些生活方式因素导致共同共存 慢性疾病（例如，高血压、糖尿病）、发病率、保健费用和死亡。的患者 经历健康差异（即，少数族裔人士、英语能力有限的人士及 收入）受心血管疾病的影响不成比例，疾病控制较差， 后遗症 自我管理是个人在管理慢性病中的作用，并有强有力的证据证明其有益。它 包括自我护理，生活方式的改变（例如，增加体力活动），按规定服用药物， 管理慢性疾病的恶化。短信干预改善了健康行为 包括身体活动和药物依从性。将行为“轻推”定义为一个小的 选择架构的变化，“以可预测的方式改变人们的行为”到短信， 进一步扩大其影响。行为轻推更个性化，更能与患者产生共鸣， 改变健康行为。然而，文本消息干预通常没有被传递到大的 样本，侧重于经历健康差异的患者，也没有利用卫生系统电子健康 记录（EHR）数据，以个性化内容并最大限度地扩大消息的规模、覆盖范围和影响。 使用患者级别的随机务实试验，我们将测试3种短信的比较有效性 交付策略：1）通用文本消息; 2）交互式AI聊天机器人文本消息利用证据- 基于沟通策略，关注患者背景和影响自我的社会文化因素， 管理;或3）交互式AI聊天机器人文本消息传递加上主动药剂师管理。我们计划 从3个卫生系统的诊所招募6，000名患者，这些系统负责照顾大量经历健康问题的人群 差异：1）丹佛卫生和医院管理局，2）健康家庭卫生中心和3）STRIDE 社区卫生中心。我们将使用卫生系统EHR数据来识别符合条件的患者， 干预，并评估以患者为中心的结果。研究结果将提供有关 以人口为基础的最佳普及战略，使所有健康状况不均衡的患者参与自我保健， 管理，以改善AHA的LS 7。干预将在真实的世界环境中进行， 常规临床护理和改善获得护理的机会。我们将从一个卫生系统吸取经验教训， 以适应研究中的其他卫生系统。

PROJECT SUMMARY/ABSTRACT Our goal is to improve control of cardiovascular (CV) disease risk factors using a multilevel intervention leveraging cellphone-based text messages integrated within health systems to improve control of American Heart Association’s Life’s Simple 7 (LS7) lifestyle factors (blood glucose, cholesterol, blood pressure, physical activity, weight, diet, and smoking). When uncontrolled, these lifestyle factors lead to common co-existing chronic conditions (e.g., hypertension, diabetes), morbidity, health care costs and death. Patients who experience health disparities (i.e., ethnic minorities, those with limited English proficiency and those with low- income) are disproportionately affected by CV diseases, have worse disease control and suffer greater sequelae. Self-management is an individual’s role in managing chronic disease and has strong evidence of benefit. It includes self-care, lifestyle changes (e.g., increase physical activity), taking medications as prescribed and managing exacerbations of chronic condition(s). Text messaging interventions have improved health behaviors including physical activity and medication adherence. Incorporating behavioral “nudges,” defined as a small change in choice architecture that “alters people’s behavior in a predictable way” into text messages may further augment its impact. Behavioral nudges are more personalized, resonate better with patients, and have changed health behaviors. However, text message interventions have typically not been delivered to large samples, focused on patients experiencing health disparities, nor leveraged health system electronic health record (EHR) data to personalize content and maximize scale, reach and impact of messages. Using a patient-level randomized pragmatic trial, we will test the comparative effectiveness of 3 text messaging delivery strategies: 1) generic text messages; 2) interactive AI chatbot text messaging leveraging evidenced- based communication strategies with attention to patient context and sociocultural factors influencing self- management; or 3) interactive AI chatbot text messaging plus proactive pharmacist management. We plan to enroll 6,000 patients from clinics within 3 health systems that care for large populations experiencing health disparities: 1) Denver Health and Hospital Authority, 2), Salud Family Health Centers and 3) STRIDE Community Health Center. We will use health system EHR data to identify eligible patients, deliver the intervention, and assess patient-centered outcomes. The study findings will provide evidence regarding the best population-based strategy for universal delivery to engage all patients with health disparities in self- management to improve the AHA’s LS7. The intervention will be delivered in real world settings to augment routine clinical care and improve access to care. We will incorporate lessons learned from one health system into adaptations for the other health systems in the study.