Center for Computational Health, IBM Research, Cambridge, MA, USA.
Department of Neurology, University of Pittsburgh, Pittsburgh, PA, USA.
Lancet Digit Health. 2021 Sep;3(9):e555-e564. doi: 10.1016/S2589-7500(21)00101-1. Epub 2021 Jul 29.
Parkinson's disease is heterogeneous in symptom presentation and progression. Increased understanding of both aspects can enable better patient management and improve clinical trial design. Previous approaches to modelling Parkinson's disease progression assumed static progression trajectories within subgroups and have not adequately accounted for complex medication effects. Our objective was to develop a statistical progression model of Parkinson's disease that accounts for intra-individual and inter-individual variability and medication effects.
In this longitudinal data study, data were collected for up to 7-years on 423 patients with early Parkinson's disease and 196 healthy controls from the Parkinson's Progression Markers Initiative (PPMI) longitudinal observational study. A contrastive latent variable model was applied followed by a novel personalised input-output hidden Markov model to define disease states. Clinical significance of the states was assessed using statistical tests on seven key motor or cognitive outcomes (mild cognitive impairment, dementia, dyskinesia, presence of motor fluctuations, functional impairment from motor fluctuations, Hoehn and Yahr score, and death) not used in the learning phase. The results were validated in an independent sample of 610 patients with Parkinson's disease from the National Institute of Neurological Disorders and Stroke Parkinson's Disease Biomarker Program (PDBP).
PPMI data were download July 25, 2018, medication information was downloaded on Sept 24, 2018, and PDBP data were downloaded between June 15 and June 24, 2020. The model discovered eight disease states, which are primarily differentiated by functional impairment, tremor, bradykinesia, and neuropsychiatric measures. State 8, the terminal state, had the highest prevalence of key clinical outcomes including 18 (95%) of 19 recorded instances of dementia. At study outset 4 (1%) of 333 patients were in state 8 and 138 (41%) of 333 patients reached stage 8 by year 5. However, the ranking of the starting state did not match the ranking of reaching state 8 within 5 years. Overall, patients starting in state 5 had the shortest time to terminal state (median 2·75 [95% CI 1·75-4·25] years).
We developed a statistical progression model of early Parkinson's disease that accounts for intra-individual and inter-individual variability and medication effects. Our predictive model discovered non-sequential, overlapping disease progression trajectories, supporting the use of non-deterministic disease progression models, and suggesting static subtype assignment might be ineffective at capturing the full spectrum of Parkinson's disease progression.
Michael J Fox Foundation.
帕金森病在症状表现和进展方面存在异质性。深入了解这两个方面可以更好地管理患者，并改善临床试验设计。以前用于模拟帕金森病进展的方法假设亚组内存在静态进展轨迹，并且没有充分考虑复杂的药物作用。我们的目标是开发一种能够解释个体内和个体间变异性以及药物作用的帕金森病统计进展模型。
在这项纵向数据研究中，从帕金森病进展标志物倡议（PPMI）的纵向观察研究中收集了 423 名早期帕金森病患者和 196 名健康对照者长达 7 年的数据。应用对比潜在变量模型，然后应用一种新颖的个性化输入-输出隐马尔可夫模型来定义疾病状态。使用七种关键运动或认知结果（轻度认知障碍、痴呆、运动障碍、存在运动波动、运动波动引起的功能障碍、Hoehn 和 Yahr 评分和死亡）上的统计检验来评估状态的临床意义，这些结果未在学习阶段使用。在国立神经病学和中风帕金森病生物标志物计划（PDBP）的 610 名帕金森病患者的独立样本中验证了结果。
PPMI 数据于 2018 年 7 月 25 日下载，药物信息于 2018 年 9 月 24 日下载，PDBP 数据于 2020 年 6 月 15 日至 6 月 24 日下载。该模型发现了八个疾病状态，主要通过功能障碍、震颤、运动迟缓以及神经精神病学指标来区分。状态 8 是终末期，关键临床结局的发生率最高，包括 19 例记录的痴呆症中有 18 例（95%）。在研究开始时，333 名患者中有 4 名（1%）处于状态 8，到第 5 年，333 名患者中有 138 名（41%）达到了第 8 阶段。然而，起始状态的排名与 5 年内达到第 8 阶段的排名并不匹配。总体而言，从状态 5 开始的患者到达终末期的时间最短（中位数 2.75[95%CI 1.75-4.25]年）。
我们开发了一种早期帕金森病的统计进展模型，该模型考虑了个体内和个体间的变异性以及药物作用。我们的预测模型发现了非连续的、重叠的疾病进展轨迹，支持使用非确定性疾病进展模型，并表明静态亚型分配可能无法有效捕捉帕金森病进展的全貌。
迈克尔·J·福克斯基金会。
