Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, Germany.
Bonn-Aachen International Center for IT, University of Bonn, Bonn, Germany.
PLoS One. 2023 Feb 24;18(2):e0280609. doi: 10.1371/journal.pone.0280609. eCollection 2023.
Parkinson's disease (PD) is characterized by a long prodromal phase with a multitude of markers indicating an increased PD risk prior to clinical diagnosis based on motor symptoms. Current PD prediction models do not consider interdependencies of single predictors, lack differentiation by subtypes of prodromal PD, and may be limited and potentially biased by confounding factors, unspecific assessment methods and restricted access to comprehensive marker data of prospective cohorts. We used prospective data of 18 established risk and prodromal markers of PD in 1178 healthy, PD-free individuals and 24 incident PD cases collected longitudinally in the Tübingen evaluation of Risk factors for Early detection of NeuroDegeneration (TREND) study at 4 visits over up to 10 years. We employed artificial intelligence (AI) to learn and quantify PD marker interdependencies via a Bayesian network (BN) with probabilistic confidence estimation using bootstrapping. The BN was employed to generate a synthetic cohort and individual marker profiles. Robust interdependencies were observed for BN edges from age to subthreshold parkinsonism and urinary dysfunction, sex to substantia nigra hyperechogenicity, depression, non-smoking and to constipation; depression to symptomatic hypotension and excessive daytime somnolence; solvent exposure to cognitive deficits and to physical inactivity; and non-smoking to physical inactivity. Conversion to PD was interdependent with prior subthreshold parkinsonism, sex and substantia nigra hyperechogenicity. Several additional interdependencies with lower probabilistic confidence were identified. Synthetic subjects generated via the BN based representation of the TREND study were realistic as assessed through multiple comparison approaches of real and synthetic data. Altogether our work demonstrates the potential of modern AI approaches (specifically BNs) both for modelling and understanding interdependencies between PD risk and prodromal markers, which are so far not accounted for in PD prediction models, as well as for generating realistic synthetic data.
帕金森病（PD）的特征是存在较长的前驱期，有许多标志物表明在基于运动症状的临床诊断之前，PD 风险增加。目前的 PD 预测模型没有考虑到单个预测指标的相互依存关系，缺乏对前驱期 PD 亚型的区分，并且可能受到混杂因素、非特异性评估方法以及对前瞻性队列综合标志物数据的限制而存在局限性和潜在偏差。我们使用前瞻性数据，对 1178 名健康、无 PD 的个体和 24 例在图宾根早期神经退行性变危险因素评估研究（TREND）中连续 4 次就诊、长达 10 年的前瞻性队列中收集的 18 种已确立的 PD 风险和前驱标志物进行分析。我们采用人工智能（AI）通过具有使用 bootstrap 进行概率置信估计的贝叶斯网络（BN）来学习和量化 PD 标志物的相互依存关系。该 BN 用于生成合成队列和个体标志物特征。从年龄到亚阈值帕金森病和尿功能障碍、性别到黑质超声高回声、抑郁、不吸烟和便秘；抑郁到症状性低血压和日间过度嗜睡；溶剂暴露到认知障碍和身体活动不足；以及不吸烟到身体活动不足，观察到 BN 边缘存在稳健的相互依存关系。向 PD 的转化与先前的亚阈值帕金森病、性别和黑质超声高回声有关。还确定了其他一些具有较低概率置信度的相互依存关系。通过基于 TREND 研究的 BN 表示生成的合成受试者在通过真实和合成数据的多次比较方法评估时是现实的。总之，我们的工作表明，现代 AI 方法（特别是 BNs）具有建模和理解 PD 风险和前驱标志物之间相互依存关系的潜力，这在 PD 预测模型中尚未得到考虑，同时也具有生成真实合成数据的潜力。
