Prediction of Difficult Tracheal Intubation by Artificial Intelligence: A Prospective Observational Study

Abstract

Aim: Many predictive clinical tests are used together for preoperative detection of patients with difficult airway risk. In this study, we aimed to predict difficult intubation with different artificial intelligence algorithms using various clinical tests and anthropometric measurements, besides, to evaluate the accuracy performance of Cormack and Lehane (C-L) classification with artificial intelligence. Material and Methods: This study was conducted as a single-blind prospective observational study between 2016 and 2019. A total of 1486 patients with American Society of Anesthesiologists physical status I-III, scheduled to undergo elective surgery and requiring endotracheal intubation, were included. Demographic variables, clinical tests and anthropometric measurements of the patients were recorded. Difficult intubation was evaluated using the 4-grade C-L system according to the easy and difficult intubation criteria. Difficult intubation was tried to predict using 16 different artificial intelligence algorithms. Results: The highest success rate among artificial intelligence algorithms was obtained by the RandomForest method. With this method, difficult intubation was predicted with 92.85% sensitivity, 96.94% specificity, 93.69% positive predictive value and 96.52% negative predictive value. C-L classification accuracy performance also determined as 95.60%. Conclusion: Artificial intelligence has been considerably successful in predicting difficult intubation. Besides, C-L classifications of easy and difficult intubated patients were successfully predicted with artificial intelligence algorithms. Using a 6-grade modified C-L classification for laryngeal view may provide stronger difficult intubation prediction. A safer and more potent prediction in training artificial intelligence can be achieved by adding individual differences and clinical features that support the definition of difficult intubation.

Keywords

• Tracheal intubation prediction
• difficult intubation
• artificial intelligence
• intubation
• anesthesia
• Cormack-Lehane

Yapay Zekâ ile Zor Trakeal Entübasyon Tahmini: Prospektif Gözlemsel Bir Çalışma

Abstract

Amaç: Zor hava yolu riski olan hastaların preoperatif tespiti için birçok prediktif klinik test birlikte kullanılmaktadır. Bu çalışmada, çeşitli klinik testler ve antropometrik ölçümler kullanarak farklı yapay zekâ algoritmaları ile zor entübasyonun tahmin edilmesi, ayrıca Cormack ve Lehane (C-L) sınıflandırmasının doğruluk performansının yapay zekâ ile değerlendirilmesi amaçlanmıştır. Gereç ve Yöntemler: Bu çalışma, 2016 ve 2019 yılları arasında tek kör prospektif gözlemsel bir çalışma olarak gerçekleştirildi. Elektif cerrahi planlanan ve endotrakeal entübasyon gerektiren, Amerikan Anesteziyologlar Derneği fiziksel durumu I-III olan toplam 1486 hasta dahil edildi. Hastaların demografik değişkenleri, klinik testleri ve antropometrik ölçümleri kaydedildi. Zor entübasyon 4 dereceli C-L sistemi ile kolay ve zor entübasyon kriterlerine göre değerlendirildi. Zor entübasyon, 16 farklı yapay zekâ algoritması kullanılarak tahmin edilmeye çalışıldı. Bulgular: Yapay zekâ algoritmaları arasında en yüksek başarı oranı RandomForest yöntemi ile elde edilmiştir. Bu yöntemle zor entübasyon %92,85 duyarlılık, %96,94 özgüllük, %93,69 pozitif öngörü değeri ve%96,52 negatif öngörü değeri ile tahmin edildi. C-L sınıflandırması doğruluk performansı ise %95,60 olarak belirlendi. Sonuç: Yapay zekâ, zor entübasyonu tahmin etmede oldukça başarılı olmuştur. Ayrıca yapay zekâ algoritmaları ile kolay ve zor entübe hastaların C-L sınıflandırmaları başarıyla tahmin edilmiştir. Laringeal görünüm için 6 dereceli modifiye C-L sınıflandırması kullanmak, daha güçlü zor entübasyon tahmini sağlayabilir. Yapay zekâ eğitiminde daha güvenli ve daha güçlü bir tahmin, zor entübasyon tanımını destekleyen bireysel farklılıklar ve klinik özellikler eklenerek elde edilebilir.

Keywords

• Trakeal entübasyon tahmini
• zor entübasyon
• yapay zeka
• Cormack-Lehane
• entübasyon
• anestezi

References

1. Cook TM, MacDougall-Davis SR. Complications and failure of airway management. Br J Anaesth. 2012;109(Suppl 1):i68-i85.
2. Cook TM, Scott S, Mihai R. Litigation related to airway and respiratory complications of anaesthesia: an analysis of claims against the NHS in England 1995-2007. Anaesthesia. 2010;65(6):556-63.
3. Cook TM, Woodall N, Frerk C, Fourth National Audit Project. Major complications of airway management in the UK: results of the Fourth National Audit Project of the Royal College of Anaesthetists and the Difficult Airway Society. Part 1: anaesthesia. Br J Anaesth. 2011;106(5):617-31.
4. Peterson GN, Domino KB, Caplan RA, Posner KL, Lee LA, Cheney FW. Management of the difficult airway: a closed claims analysis. Anesthesiology. 2005;103(1):33-9.
5. Kayhan Z. Endotrakeal Entübasyon. In: Klinik Anestezi Genişletilmiş 3. Baskı. İstanbul: Logos Yayıncılık; 2004. p.243-73.
6. de Carvalho CC, da Silva DM, de Carvalho Junior AD, Santos Neto JM, Rio BR, Neto CN, et al. Pre-operative voice evaluation as a hypothetical predictor of difficult laryngoscopy. Anaesthesia. 2019;74(9):1147-52.
7. Frerk C, Mitchell VS, McNarry AF, Mendonca C, Bhagrath R, Patel A, et al. Difficult Airway Society 2015 guidelines for management of unanticipated difficult intubation in adults. Br J Anaesth. 2015;115(6):827-48.
8. Marshall SD, Pandit JJ. Radical evolution: the 2015 Difficult Airway Society guidelines for managing unanticipated difficult or failed tracheal intubation. Anaesthesia 2016 71(2):131-7.

9. Roth D, Pace NL, Lee A, Hovhannisyan K, Warenits AM, Arrich J, et al. Bedside tests for predicting difficult airways: an abridged Cochrane diagnostic test accuracy systematic review. Anaesthesia. 2019;74(7):915-28.
10. Karkouti K, Rose DK, Wrigglesworth D, Cohen MM. Predicting difficult intubation; a multivariable analysis. Can J Anesth. 2000;47(8):730-9.
11. Srivilaithon W, Muengtaweepongsa S, Sittichanbuncha Y, Patumanond J. Predicting difficult intubation in emergency department by intubation assessment score. J Clin Med Res. 2018;10(3):247-53.
12. Cattano D, Panicucci E, Paolicchi A, Forfori F, Giunta F, Hagberg C. Risk factors assessment of the difficult airway: an Italian survey of 1956 patients. Anesth Analg. 2004;99(6):1774-9.
13. Wilson ME, Spiegelhalter D, Robertson JA, Lesser P. Predicting difficult intubation. Br J Anaesth. 1988;61(2):211-6.
14. Yildiz TS, Korkmaz F, Solak M, Toker K, Erciyes N, Bayrak F, et al. Prediction of difficult tracheal intubation in Turkish patients: a multi-center methodological study. Eur J Anaesthesiol 2007;24(12):1034-40.
15. Savva D. Prediction of difficult tracheal intubation. Br J Anaesth. 1994;73(2):149-53.
16. Demirhan A, Kılıç YA, Güler İ. Artificial intelligence applications in medicine. Yoğun Bakım Dergisi. 2010;9(1):31-41.
17. Connor CW. Artificial intelligence and machine learning in anesthesiology. Anesthesiology. 2019;131(6):1346-59.
18. Mallampati SR, Gatt SP, Gugino LD, Desai SP, Waraksa B, Freiberger D, et al. A clinical sign to predict difficult tracheal intubation: a prospective study. Can Anaesth Soc J. 1985;32(4):429-34.
19. Samsoon GL, Young JR. Difficult tracheal intubation: a retrospective study. Anaesthesia. 1987;42(5):487-90.
20. Kandemir T, Şavlı S, Ünver S, Kandemir E. Sensitivity of the combination of mallampati scores with anthropometric measurements and the presence of malignancy to predict difficult intubation. Turk J Anaesthesiol Reanim. 2015;43(1):7-12.
21. Khan ZH, Kashfi A, Ebrahimkhani E. A comparison of the upper lip bite test (a simple new technique) with modified Mallampati classification in predicting difficulty in endotracheal intubation: a prospective blinded study. Anesth Analg. 2003;96(2):595-9.
22. Acer N, Akkaya A, Tugay BU, Öztürk A. A comparison of cormeck-lehane and mallampati tests with mandibular and neck measurements for predicting difficult intubation. Balkan Med J. 2011;28(2):157-63.
23. Cormack RS, Lehane J. Difficult tracheal intubation in obstetrics. Anaesthesia 1984;39(11):1105-11.
24. Aydemir E. Weka ile yapay zeka. Ankara: Seçkin Yayınevi; 2018.
25. Yan HM, Wei XC, Zhang H, Chen XF, Luo EQ. Predicting Cormack classification based on neural network with multiple anthropometric features. The 2010 International Conference on Apperceiving Computing and Intelligence Analysis Proceeding. 2010:52-5. doi: 10.1109/ICACIA.2010.5709849.
26. Yan Q, Yan H, Han F, Wei X, Zhu T. SVM-based decision support system for clinic aided tracheal intubation predication with multiple features. Expert Syst Appl. 2009;36(3):6588-92.
27. Lazouni MEA, Settouti N, Daho MEH, Mahmoudi S, Chikh, A. Automatic detection of difficult tracheal intubation. 2014 International Conference on Multimedia Computing and Systems (ICMCS). 2014:453-8. doi: 10.1109/ICMCS.2014.6911235.
28. Cook TM. A new practical classification of laryngeal view. Anaesthesia. 2000;55(3):274-9.
29. Yentis SM, Lee DJ. Evaluation of an improved scoring system for the grading of direct laryngoscopy. Anaesthesia. 1998;53(11):1041-4.