Construction and Validation of a Nomogram for Predicting the Risk of Hearing Loss in Military Aviation Flight Pilots

ZHAI Xiaomin; ZHANG Honglei; DONG Jiajia; LIANG Yazhu; YU Xiao; XUE Rong; ZHANG Hao; PU Yu; HUO Xiaoxiu; GUO Rui

doi:10.3969/j.issn.1672-2922.2025.01.015

Abstract：Objective To develop and validate nomogram for predicting the risk of hearing loss in military aviation pilots and evaluation of its clinical application.Methods A cross-sectional study,total of 210 aviation military flight personnel who underwent medical examinations at the Air Force Medical Centre from January 2019 to January 2020 were selected..Hearing thresholds were measured using pure-tone audiometry.Based on the strict inclusion and exclusion principle,the flight crew meeting the criteria were randomly divided into training and validation sets in a ratio of 7:3.LASSO regression and binary logistic regression were used to identify risk factors for hearing loss in pilots.Based on a binary logistic regression model and clinical practice experience,a monogram was constructed to predict the risk factors for hearing loss in flight crews.The model was differentiated and calibrated using validation methods such as consistency indices,the area under the ROC curve,and the calibration lot.The area under the ROC curve was 0.72 and 0.80 for the training and validation sets,respectively,indicating that the model has a good discriminatory ability.Results The consistency indices for the training and validation sets were 0.72(95%CI 0.63~0.80)and 0.80(95%CI 0.67~0.92),respectively.The areas under the ROC curves of the training set and the validation set are 0.72 and 0.80,respectively.The results of this study show that the model has good discriminatory power.The calibration curve also shows that the model has good discriminatory power.Conclusion A nomogram based on age,flight time,and aircraft type help clinicians predict the risk of hearing loss disease in aviation military fliers.