The Future of Airway Management: A Comparative Analysis of Machine Learning and Ensemble Algorithms for Predicting Associated Factors of Difficult Intubation
-
Senobar Naderian
,
Mojtaba Mohammadzadeh Lame
,
Ata Mahmoodpoor
,
Arezoo Nejabatian
,
Kavous Shahsavarinia
,
Maryam Soleimanpour
,
Hassan Soleimanpour
Abstract
Background: This study aimed to evaluate the effectiveness of machine learning (ML) models in predicting difficult intubation among maxillofacial surgery patients by using clinical data from a previous study involving 132 patients. The study sought to enhance anesthesiologists' ability to identify patients at risk of difficult intubation, a critical concern in surgical settings.
Methods: The research applied various ML algorithms, including decision trees (DT), random forests (RF), Naive Bayes (NB), neural networks (NN), support vector machines (SVM), K-nearest neighbors (KNN), and ensemble voting methods, to the existing clinical dataset. This dataset contained a range of factors potentially associated with DI, such as the Mallampati score, Upper Lip Bite Test (ULBT) results, facial angle, and other relevant variables. A comprehensive approach was taken to explore the impact of different data preprocessing techniques, with a particular focus on feature selection and normalization methods.
Results: The study found that the combination of mutual information-based feature selection and robust scaler normalization consistently yielded high predictive accuracy. Notably, the decision tree algorithm achieved an accuracy of 0.84 and precision, sensitivity, and specificity scores of 0.95. The analysis also highlighted the strength of ensemble learning, which, by combining multiple classifiers, achieved an accuracy of 0.82. The results suggest that ML models, especially random forests and ensemble voting methods, can be highly accurate in predicting difficult intubation when trained on existing clinical data.
Conclusion: The research underscores the importance of data preprocessing in enhancing algorithmic performance, particularly the effectiveness of mutual information-based feature selection combined with robust scaler normalization. However, the study also indicates the need for further research to refine these models, ensuring their applicability and reliability in real-world clinical settings.
[1] Al Senani Y, Al Shammery AJ, Al Nafea A, Al Absi N, Al Kadhi O, Al-Shammery D. Influence of Fixed Orthodontic Therapy on Pharyngeal Airway Dimensions after Correction of Class-I, -II and -III Skeletal Profiles in Adolescents. Int J Environ Res Public Health, 2021. 18(2):517.
[2] Zhou C, Wang X, Jiang H, Xu H. [The efficacy of using cephalometrics to predict difficult intubation of patients with obstructive sleep apnea hypopnea syndrome]. Shanghai Kou Qiang Yi Xue. 2019;28(3):317-20. Chinese.
[3] Nout E, Bannink N, Koudstaal MJ, Veenland JF, Joosten KF, Poublon RM, et al. Upper airway changes in syndromic craniosynostosis patients following midface or monobloc advancement: correlation between volume changes and respiratory outcome. J Craniomaxillofac Surg. 2012; 40(3):209-14.
[4] Harila-Kaera V, Grön M, Heikkinen T, Alvesalo L. Sagittal occlusal relationships and asymmetry in prematurely born children. Eur J Orthod. 2002;24(6):615-25.
[5] Gupta S, Sharma KR, Jain D. Airway assessment: predictors of difficult airway. Indian J Anaesth. 2004;49(4):257-62.
[6] Costa F, Robiony M, Toro C, Sembronio S, Polini F, Politi M. Simultaneous functional endoscopic sinus surgery and esthetic rhinoplasty in orthognathic patients. J Oral Maxillofac Surg. 2008;66(7):1370-7.
[7] Balafar M, Pouraghaei M, Paknezhad SP, Abad SNA, Soleimanpour H. Evaluation the quality of bag-mask ventilation by E/C, T/E and hook technique (a new proposed technique). BMC Anesthesiol. 2023; 23(1):384.
[8] Mahmoodpoor A, Soleimanpour H, Golzari SE, Nejabatian A, Pourlak T, Amani M, et al. Determination of the diagnostic value of the modified Mallampati score, upper lip bite test and facial angle in predicting difficult intubation: a prospective descriptive study. J Clin Anesth. 2017;37:99-102.
[9] Luckscheiter A, Zink W, Lohs T, Eisenberger J, Thiel M, Viergutz T. Machine learning for the prediction of preclinical airway management in injured patients: a registry-based trial. Clin Exp Emerg Med. 2022; 9(4):304-313.
[10] Mahmoodpoor A, Soleimanpour H, Nia KS, Panahi JR, Afhami M, Golzari SE, et al. Sensitivity of palm print, modified Mallampati score and 3-3-2 rule in prediction of difficult intubation. Int J Prev Med. 2013;4(9):1063-9.
[11] Zhou C, Wang X, Jiang H, Xu H. [The efficacy of using cephalometrics to predict difficult intubation of patients with obstructive sleep apnea hypopnea syndrome]. Shanghai Kou Qiang Yi Xue. 2019; 28(3):317-320.
[12] Urbizu A, Ferré A, Poca MA, Rovira A, Sahuquillo J, Martin BA, et al. Cephalometric oropharynx and oral cavity analysis in Chiari malformation Type I: a retrospective case-control study. J Neurosurg. 2017; 126(2):626-633.
[13] Kohjitani A, Miyawaki T, Miyawaki S, Nakamura N, Iwase Y, Nishihara K, et al. Features of lateral cephalograms associated with difficult laryngoscopy in Japanese children undergoing oral and maxillofacial surgery. Paediatr Anaesth. 2013;23(11):994-1001.
[14] Soleimanpour M, Rahmani F, Morteza Bagi HR, Ala A, Mahmoodpoor A, Hassani F, et al. Comparison of three techniques on facility of bag-mask ventilation: Thenar eminence, E-O and E-C. Anesth Pain Med. 2018;8(4):e74226.
[15] Kim J, Im KS, Lee JM, Ro J, Yoo KY, Kim JB. Relevance of radiological and clinical measurements in predicting difficult intubation using light wand (Surch-lite™) in adult patients. J Int Med Res. 2016; 44(1):136-46.
[16] Amisha, Malik P, Pathania M, Rathaur VK. Overview of artificial intelligence in medicine. J Family Med Prim Care. 2019; 8(7):2328-2331.
[17] Sarker IH. Machine learning: algorithms, real-world applications and research directions. SN Comput Sci. 2021;2(3):160.
[18] Haneef R, Kab S, Hrzic R, Fuentes S, Fosse-Edorh S, Cosson E, et al. Use of artificial intelligence for public health surveillance: a case study to develop a machine Learning-algorithm to estimate the incidence of diabetes mellitus in France. Arch Public Health. 2021 Sep 22;79(1):168.
[19] Hasan KMZ, Hasan M. Performance evaluation of ensemble based machine learning techniques for prediction of chronic kidney disease. ERCICA. 2018; 1(2019): 415-426. Springer Singapore.
[20] Nahar N, Ara F, Neloy MA, Barua V, Hossain MS, Andersson K. A comparative analysis of the ensemble method for liver disease prediction. 2019.
[21] Gong H, Wang M, Zhang H, Elahe MF, Jin M. An explainable AI approach for the rapid diagnosis of COVID-19 using ensemble learning algorithms. Front Public Health. 2022;10:874455.
[22] Tavolara TE, Gurcan MN, Segal S, Niazi MK. Identification of difficult to intubate patients from frontal face images using an ensemble of deep learning models. Comput Biol Med. 2021;136:104737.
[23] Wang G, Li C, Tang F, Wang Y, Wu S, Zhi H, et al. A fully-automatic semi-supervised deep learning model for difficult airway assessment. Heliyon. 2023;9(5):e15629.
[24] Kim JH, Choi JW, Kwon YS, Kang SS. Predictive model for difficult laryngoscopy using machine learning: retrospective cohort study. Braz J Anesthesiol. 2022;72(5):622-8.
[25] Yamanaka S, Goto T, Morikawa K, Watase H, Okamoto H, Hagiwara Y, et al. Machine learning approaches for predicting difficult airway and first-pass success in the emergency department: multicenter prospective observational study. Interact J Med Res. 2021;11.
[26] Zhou CM, Wang Y, Xue Q, Yang JJ, Zhu Y. Predicting difficult airway intubation in thyroid surgery using multiple machine learning and deep learning algorithms. Front Public Health. 2022;10.
[27] Sikri A, Singh NP, Dalal S. Chi-square method of feature selection: impact of pre-processing of data. Int J Intell Syst Appl Eng. 2023;11(3s):241-8.
[28] Suleiman M, Labadin J. Feature selection based on mutual information. 2015:1-6.
[29] Zhou H, Wang X, Zhu R. Feature selection based on mutual information with correlation coefficient. Appl Intell. 2022;52(5):5457-74.
[30] Elkhouly A, Andrew AM, Rahim HA, Abdulaziz N, Malek MFA, Siddique S. Data-driven audiogram classifier using data normalization and multi-stage feature selection. Sci Rep. 2023;13(1):1854.
[31] Al-Sarem M, Saeed F, Alkhammash EH, Alghamdi NS. An aggregated mutual information based feature selection with machine learning methods for enhancing IoT botnet attack detection. Sensors (Basel). 2021;22(1).
[32] Xia M, Jin C, Zheng Y, Wang J, Zhao M, Cao S, et al. Deep learning-based facial analysis for predicting difficult videolaryngoscopy: a feasibility study. Anaesthesia. 2024;79(4):399-409.
[33] Brown MS, Wong KP, Shrestha L, Wahi-Anwar M, Daly M, Foster G, et al. Automated endotracheal tube placement check using semantically embedded deep neural networks. Acad Radiol. 2023;30(3):412-20.
[34] Faramarzi E, Soleimanpour H, Khan ZH, Mahmoodpoor A, Sanaie S. Upper lip bite test for prediction of difficult airway: a systematic review. Pak J Med Sci. 2018;34(4):1019-23.
[35] Stutz EW, Rondeau B. Mallampati Score. In: StatPearls. Treasure Island (FL): StatPearls Publishing; 2024.
[36] Wang LY, Zhang KD, Zhang ZH, Zhang DX, Wang HL, Qi F. Evaluation of the reliability of the upper lip bite test and the modified Mallampati test in predicting difficult intubation under direct laryngoscopy in apparently normal patients: a prospective observational clinical study. BMC Anesthesiol. 2022;22(1):314.
[37] Dawood AS, Talib BZ, Sabri IS. Prediction of difficult intubation by using upper lip bite, thyromental distance and Mallampati score in comparison to Cormack and Lehane classification system. Wiad Lek. 2021;74(9 pt 2):2305-14.
[38] Kar S, Senapati LK, Samanta P, Satapathy GC. Predictive value of modified Mallampati test and upper lip bite test concerning Cormack and Lehane's laryngoscopy grading in the anticipation of difficult intubation: a cross-sectional study at a tertiary care hospital, Bhubaneswar, India. Cureus. 2022;14(9):e28754.
[39] Tang X, Dong Z, Xu J, Cheng P, Wang M, Wang B, et al. Observation of the validity of the upper lip bite test in predicting difficult intubation. Sci Rep. 2023;13(1):22160.
[2] Zhou C, Wang X, Jiang H, Xu H. [The efficacy of using cephalometrics to predict difficult intubation of patients with obstructive sleep apnea hypopnea syndrome]. Shanghai Kou Qiang Yi Xue. 2019;28(3):317-20. Chinese.
[3] Nout E, Bannink N, Koudstaal MJ, Veenland JF, Joosten KF, Poublon RM, et al. Upper airway changes in syndromic craniosynostosis patients following midface or monobloc advancement: correlation between volume changes and respiratory outcome. J Craniomaxillofac Surg. 2012; 40(3):209-14.
[4] Harila-Kaera V, Grön M, Heikkinen T, Alvesalo L. Sagittal occlusal relationships and asymmetry in prematurely born children. Eur J Orthod. 2002;24(6):615-25.
[5] Gupta S, Sharma KR, Jain D. Airway assessment: predictors of difficult airway. Indian J Anaesth. 2004;49(4):257-62.
[6] Costa F, Robiony M, Toro C, Sembronio S, Polini F, Politi M. Simultaneous functional endoscopic sinus surgery and esthetic rhinoplasty in orthognathic patients. J Oral Maxillofac Surg. 2008;66(7):1370-7.
[7] Balafar M, Pouraghaei M, Paknezhad SP, Abad SNA, Soleimanpour H. Evaluation the quality of bag-mask ventilation by E/C, T/E and hook technique (a new proposed technique). BMC Anesthesiol. 2023; 23(1):384.
[8] Mahmoodpoor A, Soleimanpour H, Golzari SE, Nejabatian A, Pourlak T, Amani M, et al. Determination of the diagnostic value of the modified Mallampati score, upper lip bite test and facial angle in predicting difficult intubation: a prospective descriptive study. J Clin Anesth. 2017;37:99-102.
[9] Luckscheiter A, Zink W, Lohs T, Eisenberger J, Thiel M, Viergutz T. Machine learning for the prediction of preclinical airway management in injured patients: a registry-based trial. Clin Exp Emerg Med. 2022; 9(4):304-313.
[10] Mahmoodpoor A, Soleimanpour H, Nia KS, Panahi JR, Afhami M, Golzari SE, et al. Sensitivity of palm print, modified Mallampati score and 3-3-2 rule in prediction of difficult intubation. Int J Prev Med. 2013;4(9):1063-9.
[11] Zhou C, Wang X, Jiang H, Xu H. [The efficacy of using cephalometrics to predict difficult intubation of patients with obstructive sleep apnea hypopnea syndrome]. Shanghai Kou Qiang Yi Xue. 2019; 28(3):317-320.
[12] Urbizu A, Ferré A, Poca MA, Rovira A, Sahuquillo J, Martin BA, et al. Cephalometric oropharynx and oral cavity analysis in Chiari malformation Type I: a retrospective case-control study. J Neurosurg. 2017; 126(2):626-633.
[13] Kohjitani A, Miyawaki T, Miyawaki S, Nakamura N, Iwase Y, Nishihara K, et al. Features of lateral cephalograms associated with difficult laryngoscopy in Japanese children undergoing oral and maxillofacial surgery. Paediatr Anaesth. 2013;23(11):994-1001.
[14] Soleimanpour M, Rahmani F, Morteza Bagi HR, Ala A, Mahmoodpoor A, Hassani F, et al. Comparison of three techniques on facility of bag-mask ventilation: Thenar eminence, E-O and E-C. Anesth Pain Med. 2018;8(4):e74226.
[15] Kim J, Im KS, Lee JM, Ro J, Yoo KY, Kim JB. Relevance of radiological and clinical measurements in predicting difficult intubation using light wand (Surch-lite™) in adult patients. J Int Med Res. 2016; 44(1):136-46.
[16] Amisha, Malik P, Pathania M, Rathaur VK. Overview of artificial intelligence in medicine. J Family Med Prim Care. 2019; 8(7):2328-2331.
[17] Sarker IH. Machine learning: algorithms, real-world applications and research directions. SN Comput Sci. 2021;2(3):160.
[18] Haneef R, Kab S, Hrzic R, Fuentes S, Fosse-Edorh S, Cosson E, et al. Use of artificial intelligence for public health surveillance: a case study to develop a machine Learning-algorithm to estimate the incidence of diabetes mellitus in France. Arch Public Health. 2021 Sep 22;79(1):168.
[19] Hasan KMZ, Hasan M. Performance evaluation of ensemble based machine learning techniques for prediction of chronic kidney disease. ERCICA. 2018; 1(2019): 415-426. Springer Singapore.
[20] Nahar N, Ara F, Neloy MA, Barua V, Hossain MS, Andersson K. A comparative analysis of the ensemble method for liver disease prediction. 2019.
[21] Gong H, Wang M, Zhang H, Elahe MF, Jin M. An explainable AI approach for the rapid diagnosis of COVID-19 using ensemble learning algorithms. Front Public Health. 2022;10:874455.
[22] Tavolara TE, Gurcan MN, Segal S, Niazi MK. Identification of difficult to intubate patients from frontal face images using an ensemble of deep learning models. Comput Biol Med. 2021;136:104737.
[23] Wang G, Li C, Tang F, Wang Y, Wu S, Zhi H, et al. A fully-automatic semi-supervised deep learning model for difficult airway assessment. Heliyon. 2023;9(5):e15629.
[24] Kim JH, Choi JW, Kwon YS, Kang SS. Predictive model for difficult laryngoscopy using machine learning: retrospective cohort study. Braz J Anesthesiol. 2022;72(5):622-8.
[25] Yamanaka S, Goto T, Morikawa K, Watase H, Okamoto H, Hagiwara Y, et al. Machine learning approaches for predicting difficult airway and first-pass success in the emergency department: multicenter prospective observational study. Interact J Med Res. 2021;11.
[26] Zhou CM, Wang Y, Xue Q, Yang JJ, Zhu Y. Predicting difficult airway intubation in thyroid surgery using multiple machine learning and deep learning algorithms. Front Public Health. 2022;10.
[27] Sikri A, Singh NP, Dalal S. Chi-square method of feature selection: impact of pre-processing of data. Int J Intell Syst Appl Eng. 2023;11(3s):241-8.
[28] Suleiman M, Labadin J. Feature selection based on mutual information. 2015:1-6.
[29] Zhou H, Wang X, Zhu R. Feature selection based on mutual information with correlation coefficient. Appl Intell. 2022;52(5):5457-74.
[30] Elkhouly A, Andrew AM, Rahim HA, Abdulaziz N, Malek MFA, Siddique S. Data-driven audiogram classifier using data normalization and multi-stage feature selection. Sci Rep. 2023;13(1):1854.
[31] Al-Sarem M, Saeed F, Alkhammash EH, Alghamdi NS. An aggregated mutual information based feature selection with machine learning methods for enhancing IoT botnet attack detection. Sensors (Basel). 2021;22(1).
[32] Xia M, Jin C, Zheng Y, Wang J, Zhao M, Cao S, et al. Deep learning-based facial analysis for predicting difficult videolaryngoscopy: a feasibility study. Anaesthesia. 2024;79(4):399-409.
[33] Brown MS, Wong KP, Shrestha L, Wahi-Anwar M, Daly M, Foster G, et al. Automated endotracheal tube placement check using semantically embedded deep neural networks. Acad Radiol. 2023;30(3):412-20.
[34] Faramarzi E, Soleimanpour H, Khan ZH, Mahmoodpoor A, Sanaie S. Upper lip bite test for prediction of difficult airway: a systematic review. Pak J Med Sci. 2018;34(4):1019-23.
[35] Stutz EW, Rondeau B. Mallampati Score. In: StatPearls. Treasure Island (FL): StatPearls Publishing; 2024.
[36] Wang LY, Zhang KD, Zhang ZH, Zhang DX, Wang HL, Qi F. Evaluation of the reliability of the upper lip bite test and the modified Mallampati test in predicting difficult intubation under direct laryngoscopy in apparently normal patients: a prospective observational clinical study. BMC Anesthesiol. 2022;22(1):314.
[37] Dawood AS, Talib BZ, Sabri IS. Prediction of difficult intubation by using upper lip bite, thyromental distance and Mallampati score in comparison to Cormack and Lehane classification system. Wiad Lek. 2021;74(9 pt 2):2305-14.
[38] Kar S, Senapati LK, Samanta P, Satapathy GC. Predictive value of modified Mallampati test and upper lip bite test concerning Cormack and Lehane's laryngoscopy grading in the anticipation of difficult intubation: a cross-sectional study at a tertiary care hospital, Bhubaneswar, India. Cureus. 2022;14(9):e28754.
[39] Tang X, Dong Z, Xu J, Cheng P, Wang M, Wang B, et al. Observation of the validity of the upper lip bite test in predicting difficult intubation. Sci Rep. 2023;13(1):22160.
| Files | ||
| Issue | Article in Press |
|
| Section | Research Article(s) | |
| Keywords | ||
| Difficult Intubation Machine Learning Ensemble Learning Mallampati score Upper Lip Bite Test Feature-Selection | ||
| Rights and permissions | |
|
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
How to Cite
1.
Naderian S, Mohammadzadeh Lame M, Mahmoodpoor A, Nejabatian A, Shahsavarinia K, Soleimanpour M, Soleimanpour H. The Future of Airway Management: A Comparative Analysis of Machine Learning and Ensemble Algorithms for Predicting Associated Factors of Difficult Intubation. Arch Anesth & Crit Care. 2025;.
