Comparative analysis of popular predictors for difficult laryngoscopy using hybrid intelligent detection methods
Difficult laryngoscopy is associated with airway injury, and asphyxia. There are no guidelines or gold standards for detecting difficult laryngoscopy. There are many opinions on which predictors to use to detect difficult laryngoscopy exposure, and no comprehensively unified comparative analysis has...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-11-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844022030493 |
| _version_ | 1811321674434347008 |
|---|---|
| author | Xiaoxiao Liu Colin Flanagan Jingchao Fang Yiming Lei Launcelot McGrath Jun Wang Xiangyang Guo Jiangzhen Guo Harry McGrath Yongzheng Han |
| author_facet | Xiaoxiao Liu Colin Flanagan Jingchao Fang Yiming Lei Launcelot McGrath Jun Wang Xiangyang Guo Jiangzhen Guo Harry McGrath Yongzheng Han |
| author_sort | Xiaoxiao Liu |
| collection | DOAJ |
| description | Difficult laryngoscopy is associated with airway injury, and asphyxia. There are no guidelines or gold standards for detecting difficult laryngoscopy. There are many opinions on which predictors to use to detect difficult laryngoscopy exposure, and no comprehensively unified comparative analysis has been conducted. The efficacy and accuracy of deep learning (DL)-based models and machine learning (ML)-based models for predicting difficult laryngoscopy need to be evaluated and compared, under the circumstance that the flourishing of deep neural networks (DNN) has increasingly left ML less concentrated and uncreative. For the first time, the performance of difficult laryngoscopy prediction for a dataset of 671 patients, under single index and integrated multiple indicators was consistently verified under seven ML-based models and four DL-based approaches. The top dog was a simple traditional machine learning model, Naïve Bayes, outperforming DL-based models, the best test accuracy is 86.6%, the F1 score is 0.908, and the average precision score is 0.837. Three radiological variables of difficult laryngoscopy were all valuable separately and combinedly and the ranking was presented. There is no significant difference in performance among the three radiological indicators individually (83.06% vs. 83.20% vs. 83.33%) and comprehensively (83.74%), suggesting that anesthesiologists can flexibly choose appropriate measurement indicators according to the actual situation to predict difficult laryngoscopy. Adaptive spatial interaction was imposed to the model to boost the performance of difficult laryngoscopy prediction with preoperative cervical spine X-ray. |
| first_indexed | 2024-04-13T13:21:52Z |
| format | Article |
| id | doaj.art-88bbc32279574c83a5f0d21e6ac24cf7 |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-04-13T13:21:52Z |
| publishDate | 2022-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-88bbc32279574c83a5f0d21e6ac24cf72022-12-22T02:45:17ZengElsevierHeliyon2405-84402022-11-01811e11761Comparative analysis of popular predictors for difficult laryngoscopy using hybrid intelligent detection methodsXiaoxiao Liu0Colin Flanagan1Jingchao Fang2Yiming Lei3Launcelot McGrath4Jun Wang5Xiangyang Guo6Jiangzhen Guo7Harry McGrath8Yongzheng Han9Electronic and Computer Engineering, University of Limerick, Limerick, IrelandElectronic and Computer Engineering, University of Limerick, Limerick, IrelandDepartment of Radiology, Peking University Third Hospital, Beijing, ChinaResearch Centre of Digital Hospital Systems, Peking University, Ministry of Education, Beijing, ChinaNorthern Hospital Melbourne, AustraliaDepartment of Anaesthesiology, Peking University Third Hospital, Beijing, ChinaDepartment of Anaesthesiology, Peking University Third Hospital, Beijing, ChinaSchool of Engineering Medicine, Beihang University, Beijing, China; Corresponding author.Department of Anesthesiology, University Hospital Limerick, Limerick, Ireland; Corresponding author.Department of Anaesthesiology, Peking University Third Hospital, Beijing, China; Corresponding author.Difficult laryngoscopy is associated with airway injury, and asphyxia. There are no guidelines or gold standards for detecting difficult laryngoscopy. There are many opinions on which predictors to use to detect difficult laryngoscopy exposure, and no comprehensively unified comparative analysis has been conducted. The efficacy and accuracy of deep learning (DL)-based models and machine learning (ML)-based models for predicting difficult laryngoscopy need to be evaluated and compared, under the circumstance that the flourishing of deep neural networks (DNN) has increasingly left ML less concentrated and uncreative. For the first time, the performance of difficult laryngoscopy prediction for a dataset of 671 patients, under single index and integrated multiple indicators was consistently verified under seven ML-based models and four DL-based approaches. The top dog was a simple traditional machine learning model, Naïve Bayes, outperforming DL-based models, the best test accuracy is 86.6%, the F1 score is 0.908, and the average precision score is 0.837. Three radiological variables of difficult laryngoscopy were all valuable separately and combinedly and the ranking was presented. There is no significant difference in performance among the three radiological indicators individually (83.06% vs. 83.20% vs. 83.33%) and comprehensively (83.74%), suggesting that anesthesiologists can flexibly choose appropriate measurement indicators according to the actual situation to predict difficult laryngoscopy. Adaptive spatial interaction was imposed to the model to boost the performance of difficult laryngoscopy prediction with preoperative cervical spine X-ray.http://www.sciencedirect.com/science/article/pii/S2405844022030493Difficult laryngoscopyAnesthesiologyLaryngoscope exposureAirway managementMachine learning |
| spellingShingle | Xiaoxiao Liu Colin Flanagan Jingchao Fang Yiming Lei Launcelot McGrath Jun Wang Xiangyang Guo Jiangzhen Guo Harry McGrath Yongzheng Han Comparative analysis of popular predictors for difficult laryngoscopy using hybrid intelligent detection methods Heliyon Difficult laryngoscopy Anesthesiology Laryngoscope exposure Airway management Machine learning |
| title | Comparative analysis of popular predictors for difficult laryngoscopy using hybrid intelligent detection methods |
| title_full | Comparative analysis of popular predictors for difficult laryngoscopy using hybrid intelligent detection methods |
| title_fullStr | Comparative analysis of popular predictors for difficult laryngoscopy using hybrid intelligent detection methods |
| title_full_unstemmed | Comparative analysis of popular predictors for difficult laryngoscopy using hybrid intelligent detection methods |
| title_short | Comparative analysis of popular predictors for difficult laryngoscopy using hybrid intelligent detection methods |
| title_sort | comparative analysis of popular predictors for difficult laryngoscopy using hybrid intelligent detection methods |
| topic | Difficult laryngoscopy Anesthesiology Laryngoscope exposure Airway management Machine learning |
| url | http://www.sciencedirect.com/science/article/pii/S2405844022030493 |
| work_keys_str_mv | AT xiaoxiaoliu comparativeanalysisofpopularpredictorsfordifficultlaryngoscopyusinghybridintelligentdetectionmethods AT colinflanagan comparativeanalysisofpopularpredictorsfordifficultlaryngoscopyusinghybridintelligentdetectionmethods AT jingchaofang comparativeanalysisofpopularpredictorsfordifficultlaryngoscopyusinghybridintelligentdetectionmethods AT yiminglei comparativeanalysisofpopularpredictorsfordifficultlaryngoscopyusinghybridintelligentdetectionmethods AT launcelotmcgrath comparativeanalysisofpopularpredictorsfordifficultlaryngoscopyusinghybridintelligentdetectionmethods AT junwang comparativeanalysisofpopularpredictorsfordifficultlaryngoscopyusinghybridintelligentdetectionmethods AT xiangyangguo comparativeanalysisofpopularpredictorsfordifficultlaryngoscopyusinghybridintelligentdetectionmethods AT jiangzhenguo comparativeanalysisofpopularpredictorsfordifficultlaryngoscopyusinghybridintelligentdetectionmethods AT harrymcgrath comparativeanalysisofpopularpredictorsfordifficultlaryngoscopyusinghybridintelligentdetectionmethods AT yongzhenghan comparativeanalysisofpopularpredictorsfordifficultlaryngoscopyusinghybridintelligentdetectionmethods |