Ultrasonographic assessment of airway

Machine learning models based on ultrasound and physical examination for airway assessment

PURPOSE

To demonstrate the utility of machine learning models for predicting difficult airways using clinical and ultrasound parameters.

METHODS

This is a prospective non-consecutive cohort of patients undergoing elective surgery. We collected as predictor variables age, sex, BMI, OSA, Mallampatti, thyromental distance, bite test, cervical circumference, cervical ultrasound measurements, and Cormack-Lehanne class after laryngoscopy. We univariate analyzed the relationship of the predictor variables with the Cormack-Lehanne class to design machine learning models by applying the random forest technique with each predictor variable separately and in combination. We found each design's AUC-ROC, sensitivity, specificity, and positive and negative predictive values.

RESULTS

We recruited 400 patients. Cormack-Lehanne patients≥III had higher age, BMI, cervical circumference, Mallampati class membership≥III, and bite test≥II and their ultrasound measurements were significantly higher. Machine learning models based on physical examination obtained better AUC-ROC values than ultrasound measurements but without reaching statistical significance. The combination of physical variables that we call the "Classic Model" achieved the highest AUC-ROC value among all the models [0.75 (0.67-0.83)], this difference being statistically significant compared to the rest of the ultrasound models.

CONCLUSIONS

The use of machine learning models for diagnosing VAD is a real possibility, although it is still in a very preliminary stage of development.

CLINICAL REGISTRY

ClinicalTrials.gov: NCT04816435.

A Comparison of Airway Ultrasound and Clinical Parameters for Predicting Difficult Laryngoscopy in the Emergency Department: A Study Protocol

BACKGROUND

 Airway assessment plays an important part in airway management. Over the years, ultrasound has emerged as an alternative modality for airway assessment. We aim to assess the accuracy of clinical parameters, ultrasonographic upper airway parameters, and laryngoscopic grade, using the Cormack-Lehane classification, to predict difficult laryngoscopy in the emergency department (ED). The primary objective is to determine the accuracy of ultrasonography parameters compared to Cormack-Lehane grading in predicting difficult laryngoscopy in adults. The secondary objective is to assess the accuracy of clinical parameters compared to Cormack-Lehane grading in predicting difficult laryngoscopy in adults.

METHODS

A sample of 62 adult patients over 18 years who come to the emergency department and require endotracheal intubation will undergo an ultrasonographic examination of the upper airway. During this examination, an emergency medicine physician will measure the skin-to-epiglottis distance and tongue thickness using the GE Healthcare (Chicago, IL) ultrasound and color Doppler (model: Logic E).

RESULTS

The results of the study will be drawn in 2025 upon its completion.

CONCLUSIONS

The conclusion will be drawn regarding the correlation between ultrasound parameters and Cormack-Lehane grading and clinical parameters in predicting difficult laryngoscopy.

Training Requirements in Point-of-Care Ultrasonography of the Upper Airway: A Feasibility Study

OBJECTIVES

Point-of-care ultrasonography of the upper airway can be a useful supplement to conventional pre-anesthetic clinical evaluations. However, the reliability of such examinations is highly operator-dependent and proper training in sonoanatomy and ultrasound operational skills are required. The objective of this study aims to assess the minimum training requirements for applying a predefined upper airway scanning protocol in healthy volunteers by anesthesia trainees.

METHODS

Twenty-two healthy volunteer members of the Operating Room staff participated in the study. A predefined scanning protocol that included the identification of specific structures (hyoid bone, vocal cords, thyrohyoid membrane/epiglottis/pre-epiglottic space, cricothyroid membrane, and thyroid gland), as well as the performance of specific measurements (distance from the hyoid bone to skin, anterior commissure to skin, epiglottis to skin, and thyroid isthmus to skin) was taught in a single-day training course. The trainees' competence was assessed after multiple scanning repetitions performed over a week. Mixed effects regression models were applied for the trainee-instructor differences in all ultrasound measurements.

RESULTS

Cricothyroid membrane visualization had the lowest success rate (88%). Trainee-instructor differences were statistically significant for hyoid bone-to-skin (P < .001) and epiglottis-to-skin distances (P = .016). Measurement of the distance from the epiglottis to the skin required more scanning repetitions to achieve minimum deviance compared with other measurements. Ten or fewer scanning repetitions were sufficient to achieve minimum deviance for all four measurements.

CONCLUSIONS

At least 10 scanning repetitions of a pre-defined upper airway scanning protocol can be used as the minimum standard for training.

A quantitative study of airway ultrasound in predicting difficult laryngoscopy: A prospective study

PURPOSE

As common clinical screening tests cannot effectively predict a difficult airway, and unanticipated difficult laryngoscopy remains a challenge for physicians. We herein used ultrasound to develop some point-of-care predictors for difficult laryngoscopy.

METHODS

This prospective observational study included 502 patients who underwent laryngoscopy and a detailed sonographic assessment. Patients under 18 years old, or with maxillofacial deformities or fractures, limited mouth opening, limited neck movement or history of neck surgery were excluded from the study. Laryngoscopic views of all patients were scored and grouping using the modified Cormack-Lehane (CL) scoring system. The measurements acquired comprised tongue width, the longitudinal cross-sectional area of the tongue, tongue volume, the mandible-hyoid bone distance, the hyoid bone-glottis distance, the mandible-hyoid bone-glottis angle, the skin-thyrohyoid membrane distance, the glottis-superior edge of the thyroid cartilage distance (DGTC), the skin-hyoid bone distance, and the epiglottis midway-skin distance. ANOVA and Chi-square were used to compare differences between groups. Logistic regression was used to identify risk factors for difficult laryngoscopy and it was visualized by receiver operating characteristic curves and nomogram. R version 3.6.3 and SPSS version 26.0 were used for statistical analyses.

RESULTS

Difficult laryngoscopy was indicated in 49 patients (CL grade Ⅲ - Ⅳ) and easy laryngoscopy in 453 patients (CL grade Ⅰ - Ⅱ). The ultrasound-measured mandible-hyoid bone-glottis angle and DGTC significantly differed between the 2 groups (p < 0.001). Difficult laryngoscopy was predicted by an area under the curve (AUC) of 0.930 with a threshold mandible-hyoid bone-glottis angle of 125.5° and by an AUC of 0.722 with a threshold DGTC of 1.22 cm. The longitudinal cross-sectional area of the tongue, tongue width, tongue volume, the mandible-hyoid distance, and the hyoid-glottis distance did not significantly differ between the groups.

CONCLUSION

Difficult laryngoscopy may be anticipated in patients in whom the mandible-hyoid bone-glottis angle is smaller than 125.5° or DGTC is larger than 1.22 cm.

Point-of-Care Ultrasound in Airway Evaluation and Management: A Comprehensive Review

Airway management is a common and critical procedure in acute settings, such as the Emergency Department (ED) or Intensive Care Unit (ICU) of hospitals. Many of the traditional physical examination methods have limitations in airway assessment. Point-of-care ultrasound (POCUS) has emerged as a promising tool for airway management due to its familiarity, accessibility, safety, and non-invasive nature. It can assist physicians in identifying relevant anatomy of the upper airway with objective measurements of airway parameters, and it can guide airway interventions with dynamic real-time images. To date, ultrasound has been considered highly accurate for assessment of the difficult airway, confirmation of proper endotracheal intubation, prediction of post-extubation laryngeal edema, and preparation for cricothyrotomy by identifying the cricothyroid membrane. This review aims to provide a comprehensive overview of the key evidence on the use of ultrasound in airway management. Databases including PubMed and Embase were systematically searched. A search strategy using a combination of the term "ultrasound" combined with several search terms, i.e., "probe", "anatomy", "difficult airway", "endotracheal intubation", "laryngeal edema", and "cricothyrotomy" was performed. In conclusion, POCUS is a valuable tool with multiple applications ranging from pre- and post-intubation management. Clinicians should consider using POCUS in conjunction with traditional exam techniques to manage the airway more efficiently in the acute setting.

Innovations in the Management of the Difficult Airway: A Narrative Review

The difficult airway (DA) remains a perpetual challenge and its implications have led to multiple advances, technological and otherwise in this area. This article investigates the latest developments in the definition, prediction tools and diagnostics like airway and neck Ultrasonography (USG), Magnetic Resonance Imaging (MRI) and Computed tomography (CT) scans, preoperative Virtual endoscopy (VE) and 3D printing. Innovations in airway devices and adjuncts are analysed. Difficult airway society (DAS) guidelines, American Society of Anaesthesiologists (ASA) Practice Guidelines and Vortex approach for the management of DA are explored. Other breakthroughs include novel oxygen supplementation techniques throughout airway management and tools like Anaesthesia Information Management Systems (AIMS) and Clinical Decision Support (CDS) systems. The delivery of DA training and patient counselling has also undergone vast changes with emerging technology like Virtual Reality (VR), mobile applications and toolkits. The enormous, ever-evolving and endless possibilities in this area have only helped improve clinical standards and enhance patient safety.

Airway Ultrasound for Anesthesia and in Intensive Care Patients-A Narrative Review of the Literature

Ultrasound is an everyday diagnostic tool. In anesthesia and intensive care, it has a role as an adjuvant for many procedures, including the evaluation of the airway. Ultrasound airway evaluation can help predict a difficult airway, visualize the proper positioning of an intubation cannula, or evaluate the airway post-intubation. Protocols need to be established for the better integration of ultrasound in the airway evaluation, however until a consensus is reached in this respect, the ultrasound is a reliable aid in anesthesia and intensive care.