Artificial Intelligence and the detection of pediatric concussion using epigenomic analysis
Artificial Intelligence and the detection of pediatric concussion using epigenomic analysis
复制标题
DOI：
10.1016/j.brainres.2019.146510
复制
发表时间：
2020-01-01
期刊：
影响因子：
2.9
通讯作者：
Radhakrishna, Uppala
中科院分区：
文献类型：
--
作者：
Bahado-Singh, Ray O.;Vishweswaraiah, Sangeetha;Radhakrishna, Uppala
脑震荡，也称为轻度创伤性脑损伤（mTBI），是最常见的创伤性脑损伤类型。目前脑震荡是一个强烈的科学兴趣，以更好地了解生物学机制和生物标志物的发展领域。我们使用Illumina Infinium甲基化EPIC测定法评估了17例小儿脑震荡孤立病例和18例未受影响对照的全基因组血液DNA胞嘧啶（“CpG”）甲基化。使用免疫途径分析进行途径分析，以帮助阐明疾病的表观遗传和分子机制。基于CpG甲基化水平计算mTBI检测的受试者工作特征（AUC）曲线下面积和FOR p值。多个人工智能（AI）平台，包括深度学习（DL），最新形式的AI，被用来预测脑震荡的基础上i）CpG甲基化标记物单独，ii）结合表观遗传，临床和人口统计学预测。我们发现了449个CpG位点（473个基因），与对照组相比，mTBI中的甲基化具有统计学意义。有4个CpG具有极好的个体准确性（AUC >= 0.90-1.00），而119个CpG显示出预测mTBI的良好准确性（AUC >= 0.80-0.89）。脑震荡后许多CpG位点发生了10%以上的甲基化改变，提示脑震荡后CpG甲基化改变具有生物学意义。通路分析确定了几种生物学上重要的神经通路，包括与以下相关的通路：脑功能受损、认知、记忆、神经传递、智力残疾和行为改变以及相关疾病。表观基因组学和临床预测因子的组合对于使用AI技术检测consusion是高度准确的。使用DL/AI，表观基因组和临床标志物的组合对于预测mTBI具有>= 95%的灵敏度和特异性。在这项新的研究中，我们确定了多个基因在mTBI反应中的显着甲基化变化。表观遗传失调的基因通路包括几个已知参与神经功能的基因通路，从而为我们的发现提供了生物学上的合理性。
Concussion, also referred to as mild traumatic brain injury (mTBI) is the most common type of traumatic brain injury. Currently concussion is an area of intense scientific interest to better understand the biological mechanisms and for biomarker development. We evaluated whole genome-wide blood DNA cytosine ('CpG') methylation in 17 pediatric concussion isolated cases and 18 unaffected controls using Illumina Infinium Methylation EPIC assay. Pathway analysis was performed using Ingenuity Pathway Analysis to help elucidate the epigenetic and molecular mechanisms of the disorder. Area under the receiver operating characteristics (AUC) curves and FOR p-values were calculated for mTBI detection based on CpG methylation levels. Multiple Artificial Intelligence (AI) platforms including Deep Learning (DL), the newest form of AI, were used to predict concussion based on i) CpG methylation markers alone, and ii) combined epigenetic, clinical and demographic predictors. We found 449 CpG sites (473 genes), those were statistically significantly methylated in mTBI compared to controls. There were four CpGs with excellent individual accuracy (AUC >= 0.90-1.00) while 119 displayed good accuracy (AUC >= 0.80-0.89) for the prediction of mTBI. The CpG methylation changes a 10% were observed in many CpG loci after concussion suggesting biological significance. Pathway analysis identified several biologically important neurological pathways that were perturbed including those associated with: impaired brain function, cognition, memory, neurotransmission, intellectual disability and behavioral change and associated disorders. The combination of epigenomic and clinical predictors were highly accurate for the detection of concusion using Al techniques. Using DL/AI, a combination of epigenomic and clinical markers had sensitivity and specificity >= 95% for prediction of mTBI. In this novel study, we identified significant methylation changes in multiple genes in response to mTBI. Gene pathways that were epigenetically dysregulated included several known to be involved in neurological function, thus giving biological plausibility to our findings.