Segmenting High-Need, High-Cost Veterans into Potentially Actionable Subgroups

将高需求、高成本的退伍军人细分为潜在可行的亚组

• 批准号: 10176376
• 负责人: Amol S Navathe
• 金额: --
• 依托单位: PHILADELPHIA VA MEDICAL CENTER
• 依托单位国家: 美国
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-10-01 至 2020-03-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10176376
• 关键词: Acute; Algorithms; Care given by nurses; Caring; Case Manager; Cessation of life; Characteristics; Chronic; Classification; Clinical; Clinical Data; Code; Collaborations; Data; Databases; Dementia; Development; Diagnosis; Disease; Disseminated Malignant Neoplasm; Elements; Emergency department visit; Evaluation; Event; Expert Opinion; Foundations; Future; Health; Health Care Costs; Healthcare; Heterogeneity; Hospitalization; Informatics; Infrastructure; Intervention; Laboratories; Life; Link; Machine Learning; Measures; Medical; Methods; Minority; Modeling; Natural Language Processing; Needs Assessment; Outcome; Patient Care; Patient-Focused Outcomes; Patients; Pattern; Pharmacy facility; Primary Health Care; Program Appropriateness; Research; Research Personnel; Resources; Risk; Services; Severities; Social Characteristics; Subgroup; System; Systems Development; Techniques; Testing; Time; Veterans; advanced disease; adverse outcome; base; clinical care; clinically actionable; complex chronic conditions; cost; data infrastructure; data warehouse; density; disability; disadvantaged population; economic impact; experience; frailty; health service use; high risk; hospital readmission; improved; improved outcome; interest; machine learning algorithm; mortality risk; programs; psychosocial; readmission rates; social factors; social health determinants; socioeconomic disadvantage; statistical and machine learning; success

SUMMARY ABSTRACT Background One compelling strategy for improving patient outcomes while reducing healthcare costs is to focus on veterans that account for the vast majority of poor outcomes, health utilization, and VA spending (i.e., HNHC veterans). However, successfully managing HNHC veterans is challenging because these patients are heterogeneous, each requiring a different management strategy. Veterans who intensely use services are of particular interest, especially those with chronic conditions since 20% of them will experience a hospitalization and readmission within 30 days after discharge. Hospitalization, emergency room visits, and re-hospitalization rates are even higher for socioeconomically disadvantaged populations, minorities, and veterans with disability. However, much of this utilization is preventable and could be averted with better longitudinal care. The VA has increased its efforts in identifying HNHC veterans through development of the Care Assessment Needs (CAN) score and care management programs, but without greater detail enabling tailoring of clinical programs HNHC veteran subgroups, linking these scores to strategies to improve care is difficult. Objectives The objectives of this study are to: (1) apply statistical and machine learning clustering methods to classify HNHC veterans into clinically actionable subgroups based on detailed clinical information extending beyond diagnosis codes, (2) compare the HNHC subgroups to veterans with similar diagnoses who were not HNHC, and (3) describe the characteristics of the HNHC subgroups (i.e., CAN Scores) and changes over time. Methods To achieve these objectives, we will analyze patient-level data from the National Patient Care Database (2013- 2015) using the VA Informatics and Computing Infrastructure (VINCI) platform to develop models that cluster HNHC veterans into subgroups based on demographic, clinical, and social characteristics. We will utilize a combination of statistical (latent class analysis) and machine learning clustering (e.g. k-means clustering) algorithms. Our definition of a HNHC veteran will comprise the highest quartiles of predicted risk of death or acute hospitalization (i.e., CAN score > 75). Subgroups and characteristics to compare HNHC and non-HNHC veterans will be constructed using 3 approaches: 1) cluster veterans who are HNHC in 2014, 2) cluster veterans who are HNHC in 2014 and 2015 (persistently HNHC), and 3) cluster all non-HNHC veterans into subgroups. Anticipated Impacts on Veterans Health Care This project aims to identify clinically actionable subgroups of high-need, high-cost (HNHC) veterans using data-driven techniques rather than expert opinion. We hypothesize that distinct clinical characteristics will define subgroups of HNHC veterans and that these subgroups of veterans likely require different management strategies. Thus, the categorization of HNHC veterans into discrete types of patients will support nurse care managers and primary care clinicians in their selection and delivery of appropriate programs to HNHC veterans and more broadly to help the VA to better identify gaps in its clinical and care management programs

摘要 摘要 背景 改善患者治疗结果同时降低医疗成本的一项引人注目的策略是关注 退伍军人造成了绝大多数不良结果、健康利用率和 VA 支出（即 HNHC 退伍军人）。然而，成功管理 HNHC 退伍军人具有挑战性，因为这些患者 异构，每种都需要不同的管理策略。频繁使用服务的退伍军人是 特别感兴趣，尤其是那些患有慢性病的人，因为其中 20% 的人会住院治疗 出院后 30 天内再次入院。住院、急诊室就诊和再住院 对于社会经济弱势群体、少数民族和残疾退伍军人来说，这一比例甚至更高。 然而，这种利用大部分是可以预防的，并且可以通过更好的纵向护理来避免。弗吉尼亚州有 通过制定护理评估需求 (CAN) 加大力度识别 HNHC 退伍军人 评分和护理管理计划，但没有更详细的信息，以便能够定制临床计划 HNHC 对于退伍军人亚群体来说，将这些分数与改善护理的策略联系起来是很困难的。 目标 本研究的目标是：（1）应用统计和机器学习聚类方法进行分类 根据超出范围的详细临床信息，将 HNHC 退伍军人分为临床可操作的亚组 诊断代码，(2) 将 HNHC 亚组与非 HNHC 的具有类似诊断的退伍军人进行比较， (3) 描述 HNHC 亚组的特征（即 CAN 评分）以及随时间的变化。 方法 为了实现这些目标，我们将分析来自国家患者护理数据库（2013- 2015）使用 VA 信息学和计算基础设施 (VINCI) 平台来开发集群模型 根据人口统计、临床和社会特征将 HNHC 退伍军人分为亚组。我们将利用一个 统计（潜在类分析）和机器学习聚类（例如 k-means 聚类）的组合 算法。我们对 HNHC 退伍军人的定义将包括预测死亡风险的最高四分位数或 急性住院（即 CAN 评分 > 75）。用于比较 HNHC 和非 HNHC 的亚组和特征 退伍军人将使用 3 种方法构建：1) 2014 年成为 HNHC 的退伍军人集群，2) 集群 2014 年和 2015 年属于 HNHC 的退伍军人（持续为 HNHC），以及 3) 将所有非 HNHC 退伍军人归入 亚组。 对退伍军人医疗保健的预期影响 该项目旨在通过使用 数据驱动的技术而不是专家意见。我们假设不同的临床特征将 定义 HNHC 退伍军人亚组，这些退伍军人亚组可能需要不同的管理 策略。因此，将 HNHC 退伍军人分类为不同类型的患者将支持护士护理 管理人员和初级保健临床医生为 HNHC 退伍军人选择和提供适当的计划 更广泛地帮助退伍军人管理局更好地识别其临床和护理管理计划中的差距

项目成果

A machine learning approach to identify distinct subgroups of veterans at risk for hospitalization or death using administrative and electronic health record data.

• DOI: 10.1371/journal.pone.0247203
• 发表时间: 2021
• 期刊: PloS one
• 影响因子: 3.7
• 作者: Parikh RB;Linn KA;Yan J;Maciejewski ML;Rosland AM;Volpp KG;Groeneveld PW;Navathe AS
• 通讯作者: Navathe AS