本頁只刊出中文翻譯與中文說明；英文原文請見下方原文連結。
原文連結
論文資訊
- 類型：已發表論文
- 日期：2020-06-17
摘要
Chronic medical conditions show substantial heterogeneity in their clinical features and progression. We develop the novel data-driven, 網絡-based Trajectory Profile Clustering (TPC) algorithm for 1) identification of 疾病 subtypes and 2) early prediction of subtype/疾病 progression patterns. TPC is an easily generalizable method that identifies subtypes by clustering patients with similar 疾病 trajectory profiles, based not only on Parkinson's 疾病 (PD) variable severity, but also on their complex patterns of 演化. TPC is derived from bipartite 網絡s that connect patients to 疾病 variables. Applying our TPC algorithm to a PD clinical dataset, we identify 3 distinct subtypes/patient clusters, each with a characteristic progression profile. We show that TPC predicts the patient's 疾病 subtype 4 years in adva
※ 此為已發表論文，全文需透過期刊付費取得