基于深度学习方法的突发性聋预后分类研究
|
摘要
目的:运用深信度网络(DBN)构建突发性聋患者预后预测模型,并探索不同听力结局分类标准对模型性能的影响。方法:回顾性分析1 220例突发性聋患者的临床特征、听力学数据和血清学指标,从中提取并衍生出228个变量(即潜在预测因子)。突发性聋的听力结局按"中国标准"和"Siegel标准"进行四分类和二分类,基于4种不同的结局分类法构建DBN预后预测模型,运用受试者工作特征曲线下面积(ROC-AUC)、准确率来比较不同模型的预测性能。结果:以二分类结局构建的DBN模型预测性能均优于以四分类结局构建者。随着迭代次数的增加,DBN模型预测分类的准确率和AUC均有所上升。同样经过500次迭代运算,Siegel标准二分类结局构建的预测模型性能最佳,其准确性为76.25%,AUC为0.81。无论疗效如何分类,DBN根据第1层神经网络权重系数排序得出的对预后有影响的特征主要集中于凝血指标、血液系统相关指标、一般人口学指标及治疗前听力状况4个子类。结论:DBN对于包含丰富、复杂变量特征的突发性聋数据集能提供强大的预后预测功能,尤其是以Siegel标准做二分类结局预测时性能最为优越。这种先进的深度学习技术也可自动提取并排序有价值的预测因子,与此前通过传统统计学方法得出的预后预测因素基本吻合。上述优势使得DBN有助于今后应用于耳科其他疾病的预后预测或疾病精细分类。
Objective:This study aimed to develop predictive models for sudden sensorineural hearing loss through deep belief network(DBN)and explore whether the model performances differ when adopting different outcome criteria.Method:228 potential predictors involving the clinical characteristics,audio logical data,and serological parameters out of 1 220 hospitalized SSHL patients who were admitted from June 2008 to December 2015 were analyzed retrospectively.The hearing data of sudden deafness were classified into two or four categories based on Chinese criteria and Siegel criteria,which were used to develop the DBN models.The area under the receiver operating characteristic curve(ROC-AUC)and accuracy were used to compare the predictive performance of different models.Result:The DBN model developed for predicting the dichotomized outcomes had better performance than that of the four-category outcomes.When the iteration number reached 500 times,DBN model constructed for prediction of dichotomized outcomes based on Siegel's criteria had demonstrated the best performance with an accuracy of 76.25% and an AUC of 0.81.According to indices from first layer weights,DBN gave a rank of top 10 sensitive features for hearing outcome prediction focusing on indicators regarding coagulation,demographics and pre-treatment hearing levels independent of the outcome assessment criteria.Conclusion:DBN provides a robust outcome prediction ability in SSHL datasets with rich and complex variables,especially when utilized to predict dichotomized outcomes based on the Siegel criteria.In addition,this advanced deep learning technique can automatically extract valuable predictors,which is consistent with those that had been verified in previous studies by traditional statistical methods.This study provides further evidence for extending the use of DBN algorithm to the field of developing prediction or classification models for other otological diseases in the future.
Objective:This study aimed to develop predictive models for sudden sensorineural hearing loss through deep belief network(DBN)and explore whether the model performances differ when adopting different outcome criteria.Method:228 potential predictors involving the clinical characteristics,audio logical data,and serological parameters out of 1 220 hospitalized SSHL patients who were admitted from June 2008 to December 2015 were analyzed retrospectively.The hearing data of sudden deafness were classified into two or four categories based on Chinese criteria and Siegel criteria,which were used to develop the DBN models.The area under the receiver operating characteristic curve(ROC-AUC)and accuracy were used to compare the predictive performance of different models.Result:The DBN model developed for predicting the dichotomized outcomes had better performance than that of the four-category outcomes.When the iteration number reached 500 times,DBN model constructed for prediction of dichotomized outcomes based on Siegel's criteria had demonstrated the best performance with an accuracy of 76.25% and an AUC of 0.81.According to indices from first layer weights,DBN gave a rank of top 10 sensitive features for hearing outcome prediction focusing on indicators regarding coagulation,demographics and pre-treatment hearing levels independent of the outcome assessment criteria.Conclusion:DBN provides a robust outcome prediction ability in SSHL datasets with rich and complex variables,especially when utilized to predict dichotomized outcomes based on the Siegel criteria.In addition,this advanced deep learning technique can automatically extract valuable predictors,which is consistent with those that had been verified in previous studies by traditional statistical methods.This study provides further evidence for extending the use of DBN algorithm to the field of developing prediction or classification models for other otological diseases in the future.
引文
[1]中华耳鼻咽喉头颈外科杂志编辑委员会,中华医学会耳鼻咽喉头颈外科学分会.突发性聋诊断和治疗指南(2015)[J].中华耳鼻咽喉头颈外科杂志,2015,50(6):443-447.
[2]SCHREIBER B E,AGRUP C,HASKARD D O,et al.Sudden sensorineural hearing loss[J].Lancet,2010,375:1203-1211.
[3]DE F C,DE C B,TASSI R,et al.Non-functioning posterior communicating arteries of circle of Willis in idiopathic sudden hearing loss[J].Lancet,2000,356:1237-1238.
[4]BING D,YING J,MIAO J,et al.Predicting the hearing outcome in sudden sensorineural hearing loss via machine learningmodels[J].Clin Otolaryngol,2018,43:868-874.
[5]SIEGEL L G.The treatment of idiopathic sudden sensorineural hearing loss[J].Otolaryngol Clin North Am,1975,8:467-473.
[6]STEYERBERG E W,VAN VEEN M.Imputation is beneficial for handling missing data in predictive models[J].J Clin Epidemiol,2007,60:979-979.
[7]YING J,DUTTA J,GUO N,et al.Classification of Exacerbation Frequency in the COPDGene Cohort Using Deep Learning with Deep Belief Networks[J].IEEE J Biomed Health Inform,2016,[Epub ahead of print]
[8]OW G S,KUZNETSOV V A.Big genomics and clinical data analytics strategies for precision cancer prognosis[J].Sci Rep,2016,6:36493.
[2]SCHREIBER B E,AGRUP C,HASKARD D O,et al.Sudden sensorineural hearing loss[J].Lancet,2010,375:1203-1211.
[3]DE F C,DE C B,TASSI R,et al.Non-functioning posterior communicating arteries of circle of Willis in idiopathic sudden hearing loss[J].Lancet,2000,356:1237-1238.
[4]BING D,YING J,MIAO J,et al.Predicting the hearing outcome in sudden sensorineural hearing loss via machine learningmodels[J].Clin Otolaryngol,2018,43:868-874.
[5]SIEGEL L G.The treatment of idiopathic sudden sensorineural hearing loss[J].Otolaryngol Clin North Am,1975,8:467-473.
[6]STEYERBERG E W,VAN VEEN M.Imputation is beneficial for handling missing data in predictive models[J].J Clin Epidemiol,2007,60:979-979.
[7]YING J,DUTTA J,GUO N,et al.Classification of Exacerbation Frequency in the COPDGene Cohort Using Deep Learning with Deep Belief Networks[J].IEEE J Biomed Health Inform,2016,[Epub ahead of print]
[8]OW G S,KUZNETSOV V A.Big genomics and clinical data analytics strategies for precision cancer prognosis[J].Sci Rep,2016,6:36493.