Ghasemzadeh Hamzeh, Hillman Robert E, Van Stan Jarrad H, Mehta Daryush D
Center for Laryngeal Surgery and Voice Rehabilitation, Massachusetts General Hospital, Boston.
Department of Surgery, Harvard Medical School, Boston, MA.
J Speech Lang Hear Res. 2025 Feb 4;68(2):518-530. doi: 10.1044/2024_JSLHR-24-00237. Epub 2025 Jan 13.
The Daily Phonotrauma Index (DPI) can quantify pathophysiological mechanisms associated with daily voice use in individuals with phonotraumatic vocal hyperfunction (PVH). Since DPI was developed based on weeklong ambulatory voice monitoring, this study investigated if DPI can achieve comparable performance using (a) short laboratory speech tasks and (b) fewer than 7 days of ambulatory data.
An ambulatory voice monitoring system recorded the vocal function/behavior of 134 females with PVH and vocally healthy matched controls in two different conditions. In the laboratory, the participants read the first paragraph of the Rainbow Passage and produced spontaneous speech (in-lab data). They were then monitored for 7 days (in-field data). Separate DPI models were trained from the in-lab and in-field data using the standard deviation of the difference between the magnitude of the first two harmonics (H1-H2) and the skewness of neck-surface acceleration magnitude. First, 10-fold cross-validation evaluated the classification performance of the in-lab and in-field DPIs. Second, the effect of the number of ambulatory monitoring days on the accuracy of in-field DPI classification was quantified.
The average in-lab DPI accuracy computed from the Rainbow Passage and spontaneous speech were 57.9% and 48.9%, respectively, which are close to chance performance. The average classification accuracy of the in-field DPI was significantly higher with a very large effect size (73.4%, Cohen's = 1.8). Next, the average in-field DPI accuracy increased from 66.5% for 1 day to 75.0% for 7 days, with the gain of including an additional day on accuracy dropping below 1 percentage point after 4 days.
The DPI requires ambulatory monitoring data as its discriminative power diminished significantly once computed from short in-lab recordings. Additionally, ambulatory monitoring should sample multiple days to achieve robust performance. The result of this research note can be used to make an informed decision about the trade-off between classification accuracy and cost of data collection.
每日发声创伤指数（DPI）可量化发声创伤性嗓音功能亢进（PVH）患者日常嗓音使用相关的病理生理机制。由于DPI是基于为期一周的动态嗓音监测开发的，本研究调查了DPI是否能通过以下方式实现可比的性能：（a）简短的实验室言语任务，以及（b）少于7天的动态数据。
一个动态嗓音监测系统记录了134名PVH女性患者和嗓音健康的匹配对照组在两种不同条件下的嗓音功能/行为。在实验室中，参与者朗读《彩虹篇章》的第一段并进行自发言语（实验室数据）。然后对他们进行7天的监测（现场数据）。使用前两个谐波幅度之差（H1-H2）的标准差和颈部表面加速度幅度的偏度，从实验室数据和现场数据中分别训练单独的DPI模型。首先，10折交叉验证评估实验室DPI和现场DPI的分类性能。其次，量化动态监测天数对现场DPI分类准确性的影响。
根据《彩虹篇章》和自发言语计算的实验室DPI平均准确率分别为57.9%和48.9%，接近随机水平。现场DPI的平均分类准确率显著更高，效应量非常大（73.4%，科恩d值 = 1.8）。接下来，现场DPI的平均准确率从1天的66.5%增加到7天的75.0%，在4天后，每增加一天准确率的提升低于1个百分点。
DPI需要动态监测数据，因为一旦从简短的实验室记录中计算，其判别能力会显著下降。此外，动态监测应进行多天采样以实现稳健的性能。本研究报告的结果可用于在分类准确性和数据收集成本之间进行权衡时做出明智的决策。
