• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文学位 >Utilizing patient visit rate predictions to optimize physician panels for timely access and continuity of care at a multi-physician primary care practice
【24h】

Utilizing patient visit rate predictions to optimize physician panels for timely access and continuity of care at a multi-physician primary care practice

机译：利用患者就诊率预测来优化医师小组，以便在多医师初级保健实践中及时获得护理并保持连续性

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Providing timely access and continuity of care is one of the most essential foundations of high-performing primary care practices. However, as the population grows and life expectancy increases, the rising demand is becoming increasingly more difficult to be met by the limited primary care physician resources available today. Understanding the future demand for care and aligning it to physician capacity is crucial to ensuring access and continuity for patients. The primary objective of this study was to design physician panels that optimize access and continuity of care for patients by minimizing the discrepancy between the panel demand and physician capacity. This study utilized data mining techniques to predict future visit rates of a patient population at an academic primary care practice. These techniques include linear regression, support vector regression, LASSO regression, ridge regression, regression trees, boosted regression trees, and random forest regression trees. Primary predictors of future visit rate included patient demographic, clinical, and administrative variables. The predicted visit rates were used in the Panel Redesign Formulation in order to allocate patients and design panels that resulted in minimum probability that demand exceeds a physician's slot capacity (minimum overflow frequency). Minimum overflow frequency was used as a proxy for access and continuity in this study. The highest performing prediction model for future visit rates was the LASSO regression model (RMSE = 2.134, MAE = 1.546, and R2= 0.51). The maximum overflow frequency for panels designed using the standard expected visit count for primary care of 3 per year, the patient-specific visit count from the previous year, and the visit rate predicted by the LASSO model was 16% , 7%, 4%, and respectively. This study can help primary care practices to: (1) accurately predict the expected demand from patient populations and strategically plan for required resources; and (2) design physician panels that result in minimum overflow frequency in order to optimize access and continuity for patients.
机译：提供及时的护理和连续性是高性能初级护理实践的最重要基础之一。然而，随着人口的增长和预期寿命的增加，日益增长的需求变得越来越难以通过当今可用的有限初级保健医师资源来满足。了解未来的护理需求并使其与医师能力保持一致，对于确保患者的出入和连续性至关重要。这项研究的主要目的是设计医师小组，以通过最小化小组需求和医师能力之间的差异来优化患者的就诊和连续性。这项研究利用数据挖掘技术来预测学术初级保健实践中患者群体的未来就诊率。这些技术包括线性回归，支持向量回归，LASSO回归，岭回归，回归树，增强回归树和随机森林回归树。未来访视率的主要预测指标包括患者的人口统计学，临床和管理变量。在小组重新设计配方中使用了预测的就诊率，以便分配患者和设计小组，从而使需求超过医师的治疗能力（最小溢出频率）的可能性最小。在本研究中，最小溢出频率被用作访问和连续性的代理。未来访问率最高的预测模型是LASSO回归模型（RMSE = 2.134，MAE = 1.546和R2 = 0.51）。使用标准初级保健的预期访问次数（每年3次），上一年的特定患者访问次数以及LASSO模型预测的访问率设计的面板的最大溢出频率为16％，7％，4％和。这项研究可以帮助初级保健实践：（1）准确预测患者人群的预期需求，并战略性地规划所需资源； （2）设计医师面板，以最小化溢出频率，以优化患者的出入和连续性。

著录项

  • 作者

    Kweon, So Youn.;

  • 作者单位

    State University of New York at Binghamton.;

  • 授予单位 State University of New York at Binghamton.;
  • 学科 Computer engineering.;Systems science.
  • 学位 M.S.
  • 年度 2016
  • 页码 108 p.
  • 总页数 108
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 水产、渔业;
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号