*Department of Veterans Affairs, Office of Productivity, Efficiency and Staffing, Albany, NY †Department of Veterans Affairs, Office of Productivity, Efficiency and Staffing, West Haven, CT ‡Department of Veterans Affairs, Operational Analytics and Reporting, Office of Informatics and Analytics §Department of Veterans Affairs, Office of Secretary ∥Department of Veterans Affairs, Center of Innovation ¶University of Missouri-Kansas City School of Medicine, Kansas City, MO.
Med Care. 2014 Feb;52(2):164-71. doi: 10.1097/MLR.0000000000000041.
Hospitalizations due to ambulatory care sensitive conditions (ACSCs) are widely accepted as an indicator of primary care access and effectiveness. However, broad early intervention to all patients in a health care system may be deemed infeasible due to limited resources.
To develop a predictive model to identify high-risk patients for early intervention to reduce ACSC hospitalizations, and to explore the predictive power of different variables.
The study population included all patients treated for ACSCs in the VA system in fiscal years (FY) 2011 and 2012 (n=2,987,052). With all predictors from FY2011, we developed a statistical model using hierarchical logistic regression with a random intercept to predict the risk of ACSC hospitalizations in the first 90 days and the full year of FY2012. In addition, we configured separate models to assess the predictive power of different variables. We used a random split-sample method to prevent overfitting.
For hospitalizations within the first 90 days of FY2012, the full model reached c-statistics of 0.856 (95% CI, 0.853-0.860) and 0.856 (95% CI, 0.852-0.860) for the development and validation samples, respectively. For predictive power of the variables, the model with only a random intercept yielded c-statistics of 0.587 (95% CI, 0.582-0.593) and 0.578 (95% CI, 0.573-0.583), respectively; with patient demographic and socioeconomic variables added, the c-statistics improved to 0.725 (95% CI, 0.720-0.729) and 0.721 (95% CI, 0.717-0.726), respectively; adding prior year utilization and cost raised the c-statistics to 0.826 (95% CI, 0.822-0.830) and 0.826 (95% CI,0.822-0.830), respectively; the full model was reached with HCCs added. For the 1-year hospitalizations, only the full model was fitted, which yielded c-statistics of 0.835 (95% CI, 0.831-0.837) and 0.833 (95% CI, 0.830-0.837), respectively, for development and validation samples.
Our analyses demonstrate that administrative data can be effective in predicting ACSC hospitalizations. With high predictive ability, the model can assist primary care providers to identify high-risk patients for early intervention to reduce ACSC hospitalizations.
门诊医疗敏感条件（ACSCs）导致的住院治疗被广泛认为是初级保健服务获取和效果的一个指标。然而，由于资源有限，对医疗系统中的所有患者进行广泛的早期干预可能被认为是不可行的。
开发一种预测模型，以识别高危患者，进行早期干预，以减少 ACSC 住院治疗，并探讨不同变量的预测能力。
研究人群包括在 2011 财年和 2012 财年（n=2987052）在退伍军人事务部系统中接受 ACSC 治疗的所有患者。使用 2011 财年的所有预测因子，我们使用分层逻辑回归和随机截距建立了一个统计模型，以预测 2012 财年的前 90 天和全年 ACSC 住院治疗的风险。此外，我们还配置了单独的模型来评估不同变量的预测能力。我们使用随机分割样本方法来防止过度拟合。
对于 2012 财年的前 90 天内的住院治疗，全模型在发展和验证样本中的 C 统计量分别达到 0.856（95%CI，0.853-0.860）和 0.856（95%CI，0.852-0.860）。对于变量的预测能力，仅具有随机截距的模型的 C 统计量分别为 0.587（95%CI，0.582-0.593）和 0.578（95%CI，0.573-0.583）；加入患者人口统计学和社会经济变量后，C 统计量分别提高到 0.725（95%CI，0.720-0.729）和 0.721（95%CI，0.717-0.726）；加入前一年的使用和成本后，C 统计量提高到 0.826（95%CI，0.822-0.830）和 0.826（95%CI，0.822-0.830）；加入 HCC 后达到全模型。对于 1 年的住院治疗，仅拟合了全模型，在发展和验证样本中，C 统计量分别为 0.835（95%CI，0.831-0.837）和 0.833（95%CI，0.830-0.837）。
我们的分析表明，行政数据可以有效地预测 ACSC 住院治疗。该模型具有较高的预测能力，可帮助初级保健提供者识别高危患者，进行早期干预，以减少 ACSC 住院治疗。
