Shriberg Lawrence D, Lewis Barbara A, Tomblin J Bruce, McSweeny Jane L, Karlsson Heather B, Scheer Alison R
Phonology Project, Waisman Center, University of Wisconsin-Madison, WI 53705, USA.
J Speech Lang Hear Res. 2005 Aug;48(4):834-52. doi: 10.1044/1092-4388(2005/058).
Converging evidence supports the hypothesis that the most common subtype of childhood speech sound disorder (SSD) of currently unknown origin is genetically transmitted. We report the first findings toward a set of diagnostic markers to differentiate this proposed etiological subtype (provisionally termed speech delay-genetic) from other proposed subtypes of SSD of unknown origin. Conversational speech samples from 72 preschool children with speech delay of unknown origin from 3 research centers were selected from an audio archive. Participants differed on the number of biological, nuclear family members (0 or 2+) classified as positive for current and/or prior speech-language disorder. Although participants in the 2 groups were found to have similar speech competence, as indexed by their Percentage of Consonants Correct scores, their speech error patterns differed significantly in 3 ways. Compared with children who may have reduced genetic load for speech delay (no affected nuclear family members), children with possibly higher genetic load (2+ affected members) had (a) a significantly higher proportion of relative omission errors on the Late-8 consonants; (b) a significantly lower proportion of relative distortion errors on these consonants, particularly on the sibilant fricatives /s/, /z/, and //; and (c) a significantly lower proportion of backed /s/ distortions, as assessed by both perceptual and acoustic methods. Machine learning routines identified a 3-part classification rule that included differential weightings of these variables. The classification rule had diagnostic accuracy value of 0.83 (95% confidence limits = 0.74-0.92), with positive and negative likelihood ratios of 9.6 (95% confidence limits = 3.1-29.9) and 0.40 (95% confidence limits = 0.24-0.68), respectively. The diagnostic accuracy findings are viewed as promising. The error pattern for this proposed subtype of SSD is viewed as consistent with the cognitive-linguistic processing deficits that have been reported for genetically transmitted verbal disorders.
越来越多的证据支持这样一种假设,即目前病因不明的儿童语音障碍(SSD)最常见的亚型是由基因传递的。我们报告了关于一组诊断标志物的首批研究结果,以将这种提出的病因亚型(暂称为言语延迟 - 遗传型)与其他病因不明的SSD亚型区分开来。从一个音频档案中选取了来自3个研究中心的72名病因不明的学龄前言语延迟儿童的对话语音样本。参与者在被归类为当前和/或既往存在言语 - 语言障碍阳性的生物学核心家庭成员数量(0或2个以上)上存在差异。尽管发现两组参与者的言语能力相似,以其正确辅音百分比得分作为指标,但他们的语音错误模式在三个方面存在显著差异。与可能言语延迟遗传负荷较低的儿童(无受影响的核心家庭成员)相比,遗传负荷可能较高的儿童(2个以上受影响成员)在(a)晚期8个辅音上的相对省略错误比例显著更高;(b)这些辅音上的相对扭曲错误比例显著更低,特别是在擦音/s/、/z/和/ʃ/上;以及(c)通过感知和声学方法评估,/s/后缩扭曲的比例显著更低。机器学习程序确定了一个包含这些变量不同权重的三部分分类规则。该分类规则的诊断准确性值为0.83(95%置信区间 = 0.74 - 0.92),阳性和阴性似然比分别为9.6(95%置信区间 = 3.1 - 29.9)和0.40(95%置信区间 = 0.24 - 0.68)。诊断准确性研究结果被认为很有前景。这种提出的SSD亚型的错误模式被认为与遗传性言语障碍所报道的认知 - 语言加工缺陷一致。