Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA.
Department of Medicine, Vanderbilt University Medical Center, Nashville, Tennessee, USA.
AMIA Annu Symp Proc. 2022 Feb 21;2021:591-600. eCollection 2021.
Learning health systems have the ability to systematically evaluate treatments and treatment pathways. Characterization of treatment pathways can enhance a health system's ability to perform systematic evaluation to improve care quality. In this study we use a Long-Short Term Memory (LSTM) autoencoder model to systematically characterize treatment pathways in a prevalent phenotype-Major Depressive Disorder (MDD). LSTM autoencoder models generate representations of medication treatment pathways that account for temporality and complex interactions. Patients with similar pathways are grouped with K-means clustering. Clusters are characterized by analysis of medication utilization sequences and trends, as well as clinical features, such as demographics, outcomes and comorbidities. Cluster characterization identifies endotypes of MDD including acute MDD, moderate-chronic MDD and severe-chronic, but managed MDD.
学习型医疗体系有能力系统地评估治疗方法和治疗途径。治疗途径的特征描述可以增强医疗体系进行系统评估以改善护理质量的能力。在本研究中，我们使用长短时记忆 (LSTM) 自动编码器模型对常见表型-重度抑郁症 (MDD) 中的治疗途径进行系统特征描述。LSTM 自动编码器模型生成药物治疗途径的表示形式，这些表示形式考虑了时间性和复杂的相互作用。具有相似途径的患者通过 K-均值聚类进行分组。聚类通过分析药物使用序列和趋势以及临床特征（如人口统计学、结局和合并症）来进行特征描述。聚类特征描述确定了 MDD 的内表型，包括急性 MDD、中重度慢性 MDD 和重度慢性 MDD，但可以进行管理的 MDD。
