Zhou Lu ^1,2 Jiaojiao Sha ¹ Xunxia Zhu ³ Xiaoyong Shen ³ Xiaoyu Chen ³ Xin Tan ⁴ Rouyan Pan ¹ Shuyi Zhang ¹ Shi Liu ¹ Tao Jiang ^1* Jiatuo Xu ^1*

• ¹ School of Traditional Chinese Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai, Shanghai Municipality, China
• ² Department of Acupuncture and Moxibustion, Huadong Hospital, Fudan University, Shanghai, Shanghai Municipality, China
• ³ Department of Thoracic Surgery, Huadong Hospital, Fudan University, Shanghai, Shanghai Municipality, China
• ⁴ Department of Computer Science and Technology, School of Computer Science and Software Engineering, East China Normal University, Shanghai, China

Lung cancer has the highest incidence of all malignant tumors worldwide, and early diagnosis and treatment are crucial for improving patient survival rates. The aim of this study is to develop a nomogram based on acoustic and clinical features, providing a tool for clinical prediction of lung cancer.We reviewed the voice data and clinical data from 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 of all, 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 developed using six additional machine learning methods.The acoustic-clinical nomogram model exhibited a good 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 good agreement between the predicted and actual values and the DCA curve demonstrated the nomogram had good clinical usefulness. The nomogram model outperformed other models in terms of AUC, accuracy, and specificity. Conclusions The acoustic-clinical nomogram constructed in this study demonstrated good discrimination, calibration, and clinical application value, providing a tool to predict lung cancer.