Northern Ontario School of Medicine, Sudbury, Ontario, Canada.
J Eval Clin Pract. 2012 Dec;18(6):1226-34. doi: 10.1111/j.1365-2753.2012.01880.x. Epub 2012 Jul 22.
The Patient Journey Record system (PaJR) is an application of a complex adaptive chronic care model in which early detection of adverse changes in patient biopsychosocial trajectories prompts tailored care, constitute the cornerstone of the model.
To evaluate the PaJR system's impact on care and the experiences of older people with chronic illness, who were at risk of repeat admissions over 12 months.
Community-based cohort study - random assignment into intervention and usual care group, with process and outcome evaluation.
Adult and older patients with multiple morbidity, one or more chronic diseases with one or more overnight hospitalizations, and seven or more general practice visits in the past 6 months. COMPLEX INTERVENTION: PaJR lay care guides/advocates call patients and their caregivers. The care guides summarize their semi-structured conversations about health concerns and well-being. Predictive modelling and rules-based algorithms trigger alerts in relation to online call summaries. Alerts are acted upon according to agreed guidelines.
Descriptive and comparative statistics.
Impact on unplanned emergency ambulatory care sensitive admissions (ACSC) with an overnight stay; sensitivity of alerts and predictions; rates of care guides-supported activities.
Five part-time lay care guides and a care manager monitored 153 intervention patients for 500 person months with 5050 phone calls. The 153 patients in the intervention group were comparable to the 61 controls. The intervention group reported in 50% of calls that their health limited their social activities; and one-third of calls reported immediate health concerns. Predictive analytics were highly sensitive to risk of hospitalization. ACSC admissions were reduced by 50% compared to controls across the sites.
The initial implementation of a complex patient-centred adaptive chronic care model using lay care guides, supported by machine learning, appeared sensitive to risk of hospitalization and capable of stabilizing illness journeys in older patients with multi-morbidity.
Actions based on alerts produced in this study appeared to significantly reduce hospitalizations. This paves the way for further testing of the model.
患者旅程记录系统（PaJR）是复杂适应慢性病管理模型的一种应用，通过早期检测患者生物心理轨迹的不良变化，提示针对性的护理，构成了该模型的基石。
评估 PaJR 系统对护理的影响以及有慢性病风险的老年人的体验，这些老年人在 12 个月内有再次住院的风险。
基于社区的队列研究——随机分配到干预组和常规护理组，进行过程和结果评估。
患有多种疾病的成年和老年患者，有一个或多个慢性病，且在过去 6 个月内有一次或多次住院过夜和七次或更多次全科就诊。
PaJR 初级保健护理指导/倡导员致电患者及其照顾者。护理指导总结他们关于健康问题和幸福感的半结构化对话。预测模型和基于规则的算法会根据在线通话摘要触发警报。根据商定的指南采取行动。
描述性和比较性统计。
对无计划的非住院急诊保健敏感入院（ACSC）的影响，包括过夜；警报和预测的灵敏度；护理指导支持活动的比率。
五名兼职初级保健护理指导和一名护理经理在 500 个人月内监测了 153 名干预患者，进行了 5050 次电话访问。干预组的 153 名患者与对照组的 61 名患者可比。干预组在 50%的电话中报告其健康状况限制了他们的社交活动；三分之一的电话报告了即时的健康问题。预测分析对住院风险高度敏感。与对照组相比，各站点的 ACSC 入院率降低了 50%。
使用初级保健护理指导，辅以机器学习，初步实施复杂的以患者为中心的自适应慢性病管理模型，对住院风险敏感，并能够稳定患有多种疾病的老年患者的疾病进程。
基于该研究中产生的警报采取的行动似乎显著减少了住院次数。这为进一步测试该模型铺平了道路。
