Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran; Technological Virtual Collaboration (TECVICO Corp.), Vancouver BC, Canada.
Cardiogenetic Research Center, Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran.
Phys Med. 2023 Sep;113:102647. doi: 10.1016/j.ejmp.2023.102647. Epub 2023 Aug 12.
In Parkinson's disease (PD), 5-10% of cases are of genetic origin with mutations identified in several genes such as leucine-rich repeat kinase 2 (LRRK2) and glucocerebrosidase (GBA). We aim to predict these two gene mutations using hybrid machine learning systems (HMLS), via imaging and non-imaging data, with the long-term goal to predict conversion to active disease.
We studied 264 and 129 patients with known LRRK2 and GBA mutations status from PPMI database. Each dataset includes 513 features such as clinical features (CFs), conventional imaging features (CIFs) and radiomic features (RFs) extracted from DAT-SPECT images. Features, normalized by Z-score, were univariately analyzed for statistical significance by the t-test and chi-square test, adjusted by Benjamini-Hochberg correction. Multiple HMLSs, including 11 features extraction (FEA) or 10 features selection algorithms (FSA) linked with 21 classifiers were utilized. We also employed Ensemble Voting (EV) to classify the genes.
For prediction of LRRK2 mutation status, a number of HMLSs resulted in accuracies of 0.98 ± 0.02 and 1.00 in 5-fold cross-validation (80% out of total data points) and external testing (remaining 20%), respectively. For predicting GBA mutation status, multiple HMLSs resulted in high accuracies of 0.90 ± 0.08 and 0.96 in 5-fold cross-validation and external testing, respectively. We additionally showed that SPECT-based RFs added value to the specific prediction of of GBA mutation status.
We demonstrated that combining medical information with SPECT-based imaging features, and optimal utilization of HMLS can produce excellent prediction of the mutations status in PD patients.
在帕金森病（PD）中，有 5-10%的病例是遗传起源的，其突变已在几个基因中被鉴定出来，如富含亮氨酸重复激酶 2（LRRK2）和葡萄糖脑苷脂酶（GBA）。我们旨在使用混合机器学习系统（HMLS），通过影像学和非影像学数据来预测这两种基因突变，长期目标是预测向活跃疾病的转化。
我们研究了 PPMI 数据库中已知 LRRK2 和 GBA 基因突变状态的 264 名和 129 名患者。每个数据集包括 513 个特征，如临床特征（CFs）、常规成像特征（CIFs）和从 DAT-SPECT 图像提取的放射组学特征（RFs）。特征通过 Z 分数进行归一化，然后通过 t 检验和卡方检验进行单变量分析，通过 Benjamini-Hochberg 校正进行调整。利用包括 11 个特征提取（FEA）或 10 个特征选择算法（FSA）与 21 个分类器链接的多个 HMLS。我们还采用了集成投票（EV）来对基因进行分类。
对于 LRRK2 突变状态的预测，一些 HMLS 在 5 折交叉验证（80%的总数据点）和外部测试（剩余 20%）中的准确率分别达到了 0.98±0.02 和 1.00。对于预测 GBA 突变状态，多个 HMLS 在 5 折交叉验证和外部测试中的准确率分别达到了 0.90±0.08 和 0.96。我们还表明，基于 SPECT 的 RFs 为 GBA 突变状态的特定预测增加了价值。
我们证明了将医学信息与基于 SPECT 的成像特征相结合，并优化利用 HMLS，可以对 PD 患者的突变状态进行出色的预测。
