Crowdsourced validation of a machine-learning classification system for autism and ADHD.

Crowdsourced validation of a machine-learning classification system for autism and ADHD.
复制标题

DOI:
10.1038/tp.2017.86
复制
发表时间:
2017-05-16
影响因子:
6.8
通讯作者:
Wall DP
Wall DP
中科院分区:
医学1区
文献类型:
--
作者:
Duda M;Haber N;Daniels J;Wall DP

文献摘要

参考文献

被引文献

相似文献

自闭症谱系障碍(ASD)和注意缺陷多动障碍(ADHD)共同影响美国超过10%的儿童,但这两种疾病之间相当大的行为重叠往往会使鉴别诊断复杂化。目前,还没有旨在区分这两种疾病的筛查测试,并且从最初怀疑到诊断的等待时间超过一年,迫切需要快速准确评估这些和其他发育障碍风险的方法。在之前的一项研究中,我们发现四种机器学习算法能够准确地(曲线下面积(AUC)>0.96)区分ASD和ADHD,只使用社会反应量表(SRS)中的一小部分项目。在这里,我们扩展了我们以前的工作,包括一个新的众包数据集,对我们预先定义的来自ASD(n=248)或ADHD(n=174)儿童父母的前15个SRS衍生问题的响应,以提高我们模型推广到新的“真实世界”数据的能力。通过将这些新的调查数据与我们的初始存档样本(n=3417)混合,并使用二次抽样进行重复交叉验证,我们创建了一个分类算法,该算法仅使用15个问题即可实现AUC=0.89±0.01。
Autism spectrum disorder (ASD) and attention deficit hyperactivity disorder (ADHD) together affect >10% of the children in the United States, but considerable behavioral overlaps between the two disorders can often complicate differential diagnosis. Currently, there is no screening test designed to differentiate between the two disorders, and with waiting times from initial suspicion to diagnosis upwards of a year, methods to quickly and accurately assess risk for these and other developmental disorders are desperately needed. In a previous study, we found that four machine-learning algorithms were able to accurately (area under the curve (AUC)>0.96) distinguish ASD from ADHD using only a small subset of items from the Social Responsiveness Scale (SRS). Here, we expand upon our prior work by including a novel crowdsourced data set of responses to our predefined top 15 SRS-derived questions from parents of children with ASD (n=248) or ADHD (n=174) to improve our model’s capability to generalize to new, ‘real-world’ data. By mixing these novel survey data with our initial archival sample (n=3417) and performing repeated cross-validation with subsampling, we created a classification algorithm that performs with AUC=0.89±0.01 using only 15 questions.
自闭症诊断观察表: 提高诊断有效性的修订算法
DOI: 10.1007/s10803-006-0280-1
发表时间: 2007-04-01
影响因子: 3.9
作者:
Gotham, Katherine;Risi, Susan;Lord, Catherine
通讯作者: Lord, Catherine
DOI: 10.1038/tp.2012.10
发表时间: 2012-04-10
影响因子: 6.8
作者:
Wall DP;Kosmicki J;Deluca TF;Harstad E;Fusaro VA
通讯作者: Fusaro VA
DOI: 10.1023/a:1025014929212
发表时间: 2003-08-01
影响因子: 3.9
作者:
Constantino, JN;Davis, SA;Reich, W
通讯作者: Reich, W
DOI: 10.1007/s10803-007-0427-8
发表时间: 2008-04-01
影响因子: 3.9
作者:
Kleinman, Jamie M.;Ventola, Pamela E.;Fein, Deborah
通讯作者: Fein, Deborah
DOI: 10.3109/17518423.2010.539193
发表时间: 2011-01-01
影响因子: 1.3
作者:
Kozlowski, Alison M.;Matson, Johnny L.;Neal, Daniene
通讯作者: Neal, Daniene