Utilizing speech analysis to differentiate progressive supranuclear palsy from Parkinson's disease.
Utilizing speech analysis to differentiate progressive supranuclear palsy from Parkinson's disease.
复制标题
利用言语分析区分进行性核上性麻痹和帕金森病。
DOI：
10.1016/j.parkreldis.2023.105835
复制
发表时间：
2023
影响因子：
4.1
通讯作者：
Pantelyat,Alexander
中科院分区：
文献类型：
--
作者：
Kang,Kyurim;Nunes,AdonayS;Sharma,Mansi;Hall,AJ;Mishra,RamKinker;Casado,Jose;Cole,Rylee;Derhammer,Marc;Barchard,Gregory;Najafi,Bijan;Vaziri,Ashkan;Wills,Anne-Marie;Pantelyat,Alexander
在疾病早期阶段区分帕金森病（PD）和进行性核上性麻痹（PSP）对于临床试验的招募和临床护理/预后非常重要。方法我们招募21名有可靠照顾者的PSP（n= 11）或PD（n= 10）患者。在BioDigit Home平板电脑（BioSensics LLC, Newton, MA USA）上记录标准化段落阅读、计数和持续发声，并使用BioDigit语音平台（BioSensics LLC, Newton, MA USA）分析评估的语音特征。通过独立测试比较PSP和PD参与者的每个语音特征。我们还使用Spearman相关来评估言语测量和临床评分（如PSP评定量表和MoCA）之间的关联。此外，利用Rainbow通道阅读分析对该模型进行PSP和PD分类的性能进行了评价。结果在彩虹段落阅读过程中，PSP参与者的发音速度(2.45（0.49)vs 3.60（0.47）单词/分钟）显著低于PD参与者(2.33(1.08)vs 3.67(1.18))，可理解性动态时间扭曲(DTW, 0.26（0.19) vs 0.53(0.26)）和相似度DTW (0.43（0.27) vs 0.67(0.13)）。PSP参与者在阅读文章时也有更长的停顿时间(17.24（5.47)vs 8.45（3.13）秒）和更长的总信号时间(52.44（6.67)vs 36.67（6.73）秒）。在发声“a”方面，PSP参与者的谱熵、谱质心和谱展显著高于PD参与者，而在发声“e”方面无显著差异。PD参与者的反向数字计数比PSP参与者更准确(14.89（3.86)vs 7.36(4.67)）。PSP评定量表（PSPRS）构音障碍（r= 0.79,p= 0.004）和球项得分（r= 0.803,p= 0.005）与反数计数的发音率呈正相关。正反数计数与蒙特利尔认知评估总分呈正相关（r= 0.703,p= 0.016）。使用段落阅读衍生度量的机器学习模型的AUC为0.93，正确分类PSP和PD参与者的敏感性/特异性分别为0.95和0.90。结论本研究证明了利用数字健康技术平台区分PSP与PD的可行性。需要进一步的多中心研究来扩展和验证我们的初步发现。
IntroductionDistinguishing Parkinson's disease (PD) from Progressive supranuclear palsy (PSP) at early disease stages is important for clinical trial enrollment and clinical care/prognostication.MethodsWe recruited 21 participants with PSP(n= 11) or PD(n= 10) with reliable caregivers. Standardized passage reading, counting, and sustained phonation were recorded on the BioDigit Home tablet (BioSensics LLC, Newton, MA USA), and speech features from the assessments were analyzed using the BioDigit Speech platform (BioSensics LLC, Newton, MA USA). An independentt-test was performed to compare each speech feature between PSP and PD participants. We also performed Spearman's correlations to evaluate associations between speech measures and clinical scores (e.g., PSP rating scales and MoCA). In addition, the model's performance in classifying PSP and PD was evaluated using Rainbow passage reading analysis.ResultsDuring Rainbow passage reading, PSP participants had a significantly slower articulation rate (2.45(0.49) vs 3.60(0.47) words/minute), lower speech-to-pause ratio (2.33(1.08) vs 3.67(1.18)), intelligibility dynamic time warping (DTW, 0.26(0.19) vs 0.53(0.26)), and similarity DTW (0.43(0.27) vs 0.67(0.13)) compared to PD participants. PSP participants also had longer pause times (17.24(5.47) vs 8.45(3.13) sec) and longer total signal times (52.44(6.67) vs (36.67(6.73) sec) when reading the passage. In terms of the phonation ‘a’, PSP participants showed a significant higher spectral entropy, spectral centroid, and spectral spread compared to PD participants and no differences were found for phonation ‘e’. PD participants had more accurate reverse number counts than PSP participants (14.89(3.86) vs 7.36(4.67)). PSP Rating Scale (PSPRS) dysarthria (r= 0.79,p= 0.004) and bulbar item scores (r= 0.803,p= 0.005) were positively correlated with articulation rate in reverse number counts. Correct reverse number counts were positively correlated with total Montreal Cognitive Assessment scores (r= 0.703,p= 0.016). Machine learning models using passage reading-derived measures obtained an AUC of 0.93, and the sensitivity/specificity in correctly classifying PSP and PD participants were 0.95 and 0.90, respectively.ConclusionOur study demonstrates the feasibility of differentiating PSP from PD using a digital health technology platform. Further multi-center studies are needed to expand and validate our initial findings.
进行性核上性麻痹言语的声学分析。
影响因子：
2.2
作者：
S. Skodda;Wenke Visser;U. Schlegel
通讯作者：
U. Schlegel
影响因子：
3.1
作者：
Kowalska-Taczanowska, Renata;Friedman, Andrzej;Koziorowski, Dariusz
通讯作者：
Koziorowski, Dariusz