{"title":"Machine learning models based on ultrasound and physical examination for airway assessment","authors":"","doi":"10.1016/j.redare.2024.05.006","DOIUrl":null,"url":null,"abstract":"<div><h3>Purpose</h3><div>To demonstrate the utility of machine learning models for predicting difficult airways using clinical and ultrasound parameters.</div></div><div><h3>Methods</h3><div><span>This is a prospective non-consecutive cohort of patients undergoing elective surgery. We collected as predictor variables age, sex, </span>BMI<span>, OSA, Mallampatti, thyromental distance<span>, 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.</span></span></div></div><div><h3>Results</h3><div>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.</div></div><div><h3>Conclusions</h3><div>The use of machine learning models for diagnosing VAD is a real possibility, although it is still in a very preliminary stage of development.</div></div><div><h3>Clinical registry</h3><div>ClinicalTrials.gov: NCT04816435.</div></div>","PeriodicalId":94196,"journal":{"name":"Revista espanola de anestesiologia y reanimacion","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Revista espanola de anestesiologia y reanimacion","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S234119292400101X","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
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.