Vouzouneraki Konstantina, Nylén Fredrik, Holmberg Jenny, Olsson Tommy, Berinder Katarina, Höybye Charlotte, Petersson Maria, Bensing Sophie, Åkerman Anna-Karin, Borg Henrik, Ekman Bertil, Robért Jonas, Engström Britt Edén, Ragnarsson Oskar, Burman Pia, Dahlqvist Per
Department of Public Health and Clinical Medicine, Umeå University, SE-901 87 Umeå, Sweden.
Department of Clinical Sciences, Umeå University, SE-901 87 Umeå, Sweden.
J Clin Endocrinol Metab. 2025 Mar 17;110(4):983-990. doi: 10.1210/clinem/dgae689.
There is a considerable diagnostic delay in acromegaly, contributing to increased morbidity. Voice changes due to orofacial and laryngeal changes are common in acromegaly.
Our aim was to explore the use of digital voice analysis as a biomarker for acromegaly using broad acoustic analysis and machine learning.
Voice recordings from patients with acromegaly and matched controls were collected using a mobile phone at Swedish university hospitals. Anthropometric and clinical data and the Voice Handicap Index (VHI) were assessed. Digital voice analysis of a sustained and stable vowel [a] resulted in 3274 parameters, which were used for training of machine learning models classifying the speaker as "acromegaly" or "control." The machine learning models were trained with 76% of the data and the remaining 24% was used to assess their performance. For comparison, voice recordings of 50 pairs of participants were assessed by 12 experienced endocrinologists.
We included 151 Swedish patients with acromegaly (13% biochemically active and 10% newly diagnosed) and 139 matched controls. The machine learning model identified patients with acromegaly more accurately (area under the receiver operating curve [ROC AUC] 0.84) than experienced endocrinologists (ROC AUC 0.69). Self-reported voice problems were more pronounced in patients with acromegaly than matched controls (median VHI 6 vs 2, P < .01) with higher prevalence of clinically significant voice handicap (VHI ≥20: 22.5% vs 3.6%).
Digital voice analysis can identify patients with acromegaly from short voice recordings with high accuracy. Patients with acromegaly experience more voice disorders than matched controls.
肢端肥大症存在相当长的诊断延迟，这导致发病率增加。肢端肥大症患者因口面部和喉部改变而出现声音变化很常见。
我们的目的是通过广泛的声学分析和机器学习来探索将数字语音分析用作肢端肥大症生物标志物的方法。
在瑞典大学医院使用手机收集肢端肥大症患者和匹配对照的语音记录。评估人体测量和临床数据以及嗓音障碍指数（VHI）。对持续且稳定的元音[a]进行数字语音分析产生了3274个参数，这些参数用于训练将说话者分类为“肢端肥大症”或“对照”的机器学习模型。机器学习模型使用76%的数据进行训练，其余24%用于评估其性能。为作比较，12位经验丰富的内分泌学家评估了50对参与者的语音记录。
我们纳入了151例瑞典肢端肥大症患者（13%为生化活性型，10%为新诊断患者）和139名匹配对照。机器学习模型识别肢端肥大症患者的准确性（受试者工作特征曲线下面积[ROC AUC]为0.84）高于经验丰富的内分泌学家（ROC AUC为0.69）。肢端肥大症患者自我报告的嗓音问题比匹配对照更明显（VHI中位数为6比2，P <.01），具有临床显著嗓音障碍（VHI≥20：22.5%比3.6%）的患病率更高。
数字语音分析可以从短语音记录中高精度地识别肢端肥大症患者。肢端肥大症患者比匹配对照经历更多的嗓音障碍。
