Center for Population Health IT, Department of Health Policy and Management, Johns Hopkins Bloomberg School of Public Health, Baltimore, Maryland, United States of America.
PLoS One. 2019 Mar 6;14(3):e0213258. doi: 10.1371/journal.pone.0213258. eCollection 2019.
Payers and providers still primarily use ordinary least squares (OLS) to estimate expected economic and clinical outcomes for risk adjustment purposes. Penalized linear regression represents a practical and incremental step forward that provides transparency and interpretability within the familiar regression framework. This study conducted an in-depth comparison of prediction performance of standard and penalized linear regression in predicting future health care costs in older adults.
This retrospective cohort study included 81,106 Medicare Advantage patients with 5 years of continuous medical and pharmacy insurance from 2009 to 2013. Total health care costs in 2013 were predicted with comorbidity indicators from 2009 to 2012. Using 2012 predictors only, OLS performed poorly (e.g., R2 = 16.3%) compared to penalized linear regression models (R2 ranging from 16.8 to 16.9%); using 2009-2012 predictors, the gap in prediction performance increased (R2:15.0% versus 18.0-18.2%). OLS with a reduced set of predictors selected by lasso showed improved performance (R2 = 16.6% with 2012 predictors, 17.4% with 2009-2012 predictors) relative to OLS without variable selection but still lagged behind the prediction performance of penalized regression. Lasso regression consistently generated prediction ratios closer to 1 across different levels of predicted risk compared to other models.
This study demonstrated the advantages of using transparent and easy-to-interpret penalized linear regression for predicting future health care costs in older adults relative to standard linear regression. Penalized regression showed better performance than OLS in predicting health care costs. Applying penalized regression to longitudinal data increased prediction accuracy. Lasso regression in particular showed superior prediction ratios across low and high levels of predicted risk. Health care insurers, providers and policy makers may benefit from adopting penalized regression such as lasso regression for cost prediction to improve risk adjustment and population health management and thus better address the underlying needs and risk of the populations they serve.
支付者和提供者仍然主要使用普通最小二乘法（OLS）来估计风险调整的预期经济和临床结果。惩罚线性回归代表了朝着实用和增量方向迈出的一步，它在熟悉的回归框架内提供了透明度和可解释性。本研究深入比较了标准和惩罚线性回归在预测老年人未来医疗保健成本方面的预测性能。
这项回顾性队列研究包括 2009 年至 2013 年期间连续 5 年拥有医疗保险和药房保险的 81106 名医疗保险优势患者。使用 2009 年至 2012 年的合并症指标预测 2013 年的总医疗保健费用。仅使用 2012 年的预测因子，OLS 的表现很差（例如，R2=16.3%），与惩罚线性回归模型相比（R2 范围为 16.8%至 16.9%）；使用 2009-2012 年的预测因子，预测性能的差距增加（R2：15.0%与 18.0-18.2%）。使用套索选择的一组减少的预测因子的 OLS 显示出改进的性能（使用 2012 年的预测因子，R2=16.6%；使用 2009-2012 年的预测因子，R2=17.4%），与不进行变量选择的 OLS 相比，但仍落后于惩罚回归的预测性能。与其他模型相比，套索回归在不同预测风险水平下始终生成更接近 1 的预测比率。
与标准线性回归相比，本研究表明在预测老年人未来医疗保健成本方面，使用透明且易于解释的惩罚线性回归具有优势。惩罚回归在预测医疗保健成本方面优于 OLS。将惩罚回归应用于纵向数据可提高预测准确性。特别是，套索回归在低风险和高风险水平下均显示出优越的预测比率。医疗保健保险公司、提供者和政策制定者可能受益于采用惩罚回归（如套索回归）进行成本预测，以改善风险调整和人口健康管理，从而更好地满足其服务人群的基本需求和风险。
