Department of Applied Statistics, Social Science, and Humanities, New York University, New York, NY, USA.
Division of Rheumatology, Sir Mortimer B, Davis Jewish General Hospital, Montreal, Canada.
Stat Methods Med Res. 2019 Oct-Nov;28(10-11):2992-3011. doi: 10.1177/0962280218795187. Epub 2018 Aug 20.
Patient-reported outcome measures are widely used to assess patient experiences, well-being, and treatment response in clinical trials and cohort-based observational studies. However, patients may be asked to respond to many different measures in order to provide researchers and clinicians with a wide array of information regarding their experiences. Collecting such long and cumbersome patient-reported outcome measures may burden patients, increase research costs, and potentially reduce the quality of the data collected. Nonetheless, little research has been conducted on replicable, and reproducible methods to shorten these instruments that result in shortened forms of minimal length. This manuscript proposes the use of mixed integer programming through Optimal Test Assembly as a method to shorten patient-reported outcome measures. This method is compared to the existing standard in the field, which is selecting items based on having high discrimination parameters from an item response theory model. The method is then illustrated in an application to a fatigue scale for patients with Systemic Sclerosis.
患者报告结局测量被广泛用于评估临床试验和基于队列的观察性研究中的患者体验、幸福感和治疗反应。然而，为了向研究人员和临床医生提供有关患者体验的广泛信息，可能会要求患者回答许多不同的测量问题。收集如此冗长而繁琐的患者报告结局测量可能会给患者带来负担，增加研究成本，并可能降低所收集数据的质量。尽管如此，关于可复制和可重复的方法来缩短这些仪器，以得到最短长度的简短形式的研究很少。本文提出使用混合整数规划通过最优测试装配作为缩短患者报告结局测量的方法。该方法与该领域现有的标准进行了比较，后者是根据项目反应理论模型中具有高区分参数来选择项目。然后，该方法在系统性硬化症患者疲劳量表的应用中得到了说明。
