Marchese Maria Raffaella, Sensoli Federico, Campagnini Silvia, Cianchetti Matteo, Nacci Andrea, Ursino Francesco, D'Alatri Lucia, Galli Jacopo, Carrozza Maria Chiara, Paludetti Gaetano, Mannini Andrea
Unità Operativa Complessa di Otorinolaringoiatria, Dipartimento di Neuroscienze, Organi di Senso e Torace, Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy.
Institute of Biorobotics, Scuola Superiore Sant'Anna, Pontedera, Italy.
Acta Otorhinolaryngol Ital. 2023 Oct;43(5):317-323. doi: 10.14639/0392-100X-N2309. Epub 2023 Jul 28.
The diagnosis of benign lesions of the vocal fold (BLVF) is still challenging. The analysis of the acoustic signals through the implementation of machine learning models can be a viable solution aimed at offering support for clinical diagnosis.
In this study, a support vector machine was trained and cross-validated (10-fold cross-validation) using 138 features extracted from the acoustic signals of 418 patients with polyps, nodules, oedema, and cysts. The model's performance was presented as accuracy and average F1-score. The results were also analysed in male (M) and female (F) subgroups.
The validation accuracy was 55%, 80%, and 54% on the overall cohort, and in M and F, respectively. Better performances were observed in the detection of cysts and nodules (58% and 62%, respectively) vs polyps and oedema (47% and 53%, respectively). The results on each lesion and the different patterns of the model on M and F are in line with clinical observations, obtaining better results on F and detection of sensitive polyps in M.
This study showed moderately accurate detection of four types of BLVF using acoustic signals. The analysis of the diagnostic results on gender subgroups highlights different behaviours of the diagnostic model.
声带良性病变（BLVF）的诊断仍然具有挑战性。通过实施机器学习模型来分析声学信号可能是一种可行的解决方案，旨在为临床诊断提供支持。
在本研究中，使用从418例患有息肉、结节、水肿和囊肿的患者的声学信号中提取的138个特征，对支持向量机进行训练和交叉验证（10折交叉验证）。模型的性能以准确率和平均F1分数表示。结果还在男性（M）和女性（F）亚组中进行了分析。
在整个队列中以及男性和女性亚组中，验证准确率分别为55%、80%和54%。在检测囊肿和结节（分别为58%和62%）方面观察到的性能优于息肉和水肿（分别为47%和53%）。关于每种病变的结果以及模型在男性和女性中的不同模式与临床观察结果一致，在女性中获得了更好的结果，在男性中检测到了敏感性息肉。
本研究表明，使用声学信号对四种类型的声带良性病变进行检测的准确性中等。对性别亚组诊断结果的分析突出了诊断模型的不同行为。
