Lu Zhou, Sha Jiaojiao, Zhu Xunxia, Shen Xiaoyong, Chen Xiaoyu, Tan Xin, Pan Rouyan, Zhang Shuyi, Liu Shi, Jiang Tao, Xu Jiatuo
School of Traditional Chinese Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai, China.
Department of Acupuncture and Moxibustion, Huadong Hospital, Fudan University, Shanghai, China.
Front Med (Lausanne). 2025 Jan 21;12:1507546. doi: 10.3389/fmed.2025.1507546. eCollection 2025.
Lung cancer-with its global prevalence and critical need for early diagnosis and treatment-is the focus of our study. This study aimed to develop a nomogram based on acoustic-clinical features-a tool that could significantly enhance the clinical prediction of lung cancer.
We reviewed the voice data and clinical information of 350 individuals: 189 pathologically confirmed lung cancer patients and 161 non-lung cancer patients, which included 77 patients with benign pulmonary lesions and 84 healthy volunteers. First, acoustic features were extracted from all participants, and optimal features were selected by least absolute shrinkage and selection operator (LASSO) regression. Subsequently, by integrating acoustic features and clinical features, a nomogram for predicting lung cancer was developed using a multivariate logistic regression model. The performance of the nomogram was evaluated by the area under the receiver operating characteristic curve (AUC) and the calibration curve. The clinical utility was estimated by decision curve analysis (DCA) to confirm the predictive value of the nomogram. Furthermore, the nomogram model was compared with predictive models that were developed using six additional machine-learning (ML) methods.
Our acoustic-clinical nomogram model demonstrated a strong discriminative ability, with AUCs of 0.774 (95% confidence interval [CI], 0.716-0.832) and 0.714 (95% CI: 0.616-0.811) in the training and test sets, respectively. The nomogram achieved an accuracy of 0.642, a sensitivity of 0.673, and a specificity of 0.611 in the test set. The calibration curve showed excellent agreement between the predicted and actual values, and the DCA curve underscored the clinical usefulness of our nomogram. Notably, our nomogram model outperformed other models in terms of AUC, accuracy, and specificity.
The acoustic-clinical nomogram developed in this study demonstrates robust discrimination, calibration, and clinical application value. This nomogram, a unique contribution to the field, provides a reliable tool for predicting lung cancer.
肺癌的全球患病率以及对早期诊断和治疗的迫切需求是我们研究的重点。本研究旨在基于声学临床特征开发一种列线图——一种能够显著提高肺癌临床预测能力的工具。
我们回顾了350名个体的语音数据和临床信息：189例经病理证实的肺癌患者以及161例非肺癌患者，后者包括77例良性肺部病变患者和84名健康志愿者。首先，从所有参与者中提取声学特征，并通过最小绝对收缩和选择算子（LASSO）回归选择最佳特征。随后，通过整合声学特征和临床特征，使用多变量逻辑回归模型开发了一种预测肺癌的列线图。通过受试者操作特征曲线（AUC）下的面积和校准曲线评估列线图的性能。通过决策曲线分析（DCA）估计临床效用，以确认列线图的预测价值。此外，将列线图模型与使用另外六种机器学习（ML）方法开发的预测模型进行比较。
我们的声学临床列线图模型显示出强大的判别能力，在训练集和测试集中的AUC分别为0.774（95%置信区间[CI]，0.716 - 0.832）和0.714（95%CI：0.616 - 0.811）。该列线图在测试集中的准确率为0.642，灵敏度为0.673，特异性为0.611。校准曲线显示预测值与实际值之间具有良好的一致性，DCA曲线强调了我们列线图的临床实用性。值得注意的是，我们的列线图模型在AUC、准确率和特异性方面优于其他模型。
本研究中开发的声学临床列线图显示出强大的判别、校准和临床应用价值。这一独特的列线图为该领域做出了贡献，为预测肺癌提供了一种可靠的工具。
