Epidemiology Analytics, Janssen Research and Development, Titusville, NJ, USA.
Department of Public Health Sciences, Medical University of South Carolina, Charleston, SC, USA.
Med Decis Making. 2020 Apr;40(3):254-265. doi: 10.1177/0272989X20903267. Epub 2020 Feb 6.
Accurate diagnosis of patients' preferences is central to shared decision making. Missing from clinical practice is an approach that links pretreatment preferences and patient-reported outcomes. . We propose a Bayesian collaborative filtering (CF) algorithm that combines pretreatment preferences and patient-reported outcomes to provide treatment recommendations. We present the methodological details of a Bayesian CF algorithm designed to accomplish 3 tasks: 1) eliciting patient preferences using conjoint analysis surveys, 2) clustering patients into preference phenotypes, and 3) making treatment recommendations based on the posttreatment satisfaction of like-minded patients. We conduct a series of simulation studies to test the algorithm and to compare it to a 2-stage approach. The Bayesian CF algorithm and 2-stage approaches performed similarly when there was extensive overlap between preference phenotypes. When the treatment was moderately associated with satisfaction, both methods made accurate recommendations. The kappa estimates measuring agreement between the true and predicted recommendations were 0.70 (95% confidence interval = 0.052-0.88) and 0.73 (0.56-0.90) under the Bayesian CF and 2-stage approaches, respectively. The 2-stage approach failed to converge in settings in which clusters were well separated, whereas the Bayesian CF algorithm produced acceptable results, with kappas of 0.73 (0.56-0.90) and 0.83 (0.69-0.97) for scenarios with moderate and large treatment effects, respectively. Our approach assumes that the patient population is composed of distinct preference phenotypes, there is association between treatment and outcomes, and treatment effects vary across phenotypes. Findings are also limited to simulated data. . The Bayesian CF algorithm is feasible, provides accurate cluster treatment recommendations, and outperforms 2-stage estimation when clusters are well separated. As such, the approach serves as a roadmap for incorporating predictive analytics into shared decision making.
准确诊断患者的偏好是共同决策的核心。临床实践中缺少一种将治疗前偏好和患者报告的结局联系起来的方法。我们提出了一种贝叶斯协同过滤（CF）算法，该算法结合了治疗前的偏好和患者报告的结局，以提供治疗建议。我们介绍了一种贝叶斯 CF 算法的方法学细节，该算法旨在完成 3 项任务：1）使用联合分析调查来引出患者的偏好，2）将患者聚类为偏好表型，3）根据相似患者的治疗后满意度来做出治疗建议。我们进行了一系列模拟研究来测试算法，并将其与 2 阶段方法进行比较。当偏好表型之间有广泛的重叠时，贝叶斯 CF 算法和 2 阶段方法的表现相似。当治疗与满意度中度相关时，这两种方法都能做出准确的建议。真实和预测建议之间的kappa 估计值分别为 0.70（95%置信区间=0.052-0.88）和 0.73（0.56-0.90），表明这两种方法的一致性都很好。在聚类分离良好的情况下，2 阶段方法无法收敛，而贝叶斯 CF 算法则产生了可接受的结果，其 kappas 值分别为 0.73（0.56-0.90）和 0.83（0.69-0.97），适用于中度和大治疗效果的情况。我们的方法假设患者人群由不同的偏好表型组成，治疗与结局之间存在关联，且治疗效果在表型之间存在差异。研究结果也仅限于模拟数据。贝叶斯 CF 算法是可行的，它提供了准确的聚类治疗建议，并且在聚类分离良好的情况下优于 2 阶段估计。因此，该方法为将预测分析纳入共同决策提供了路线图。
