Dataset Information

Development and validation of a difficult laryngoscopy prediction model using machine learning of neck circumference and thyromental height.

ABSTRACT:

Background

Predicting difficult airway is challengeable in patients with limited airway evaluation. The aim of this study is to develop and validate a model that predicts difficult laryngoscopy by machine learning of neck circumference and thyromental height as predictors that can be used even for patients with limited airway evaluation.

Methods

Variables for prediction of difficulty laryngoscopy included age, sex, height, weight, body mass index, neck circumference, and thyromental distance. Difficult laryngoscopy was defined as Grade 3 and 4 by the Cormack-Lehane classification. The preanesthesia and anesthesia data of 1677 patients who had undergone general anesthesia at a single center were collected. The data set was randomly stratified into a training set (80%) and a test set (20%), with equal distribution of difficulty laryngoscopy. The training data sets were trained with five algorithms (logistic regression, multilayer perceptron, random forest, extreme gradient boosting, and light gradient boosting machine). The prediction models were validated through a test set.

Results

The model's performance using random forest was best (area under receiver operating characteristic curve = 0.79 [95% confidence interval: 0.72-0.86], area under precision-recall curve = 0.32 [95% confidence interval: 0.27-0.37]).

Conclusions

Machine learning can predict difficult laryngoscopy through a combination of several predictors including neck circumference and thyromental height. The performance of the model can be improved with more data, a new variable and combination of models.

SUBMITTER: Kim JH

PROVIDER: S-EPMC8059322 | biostudies-literature | 2021 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development and validation of a difficult laryngoscopy prediction model using machine learning of neck circumference and thyromental height.

Kim Jong Ho JH Kim Haewon H Jang Ji Su JS Hwang Sung Mi SM Lim So Young SY Lee Jae Jun JJ Kwon Young Suk YS

BMC anesthesiology 20210421 1

<h4>Background</h4>Predicting difficult airway is challengeable in patients with limited airway evaluation. The aim of this study is to develop and validate a model that predicts difficult laryngoscopy by machine learning of neck circumference and thyromental height as predictors that can be used even for patients with limited airway evaluation.<h4>Methods</h4>Variables for prediction of difficulty laryngoscopy included age, sex, height, weight, body mass index, neck circumference, and thyroment ...[more]

PMID: 33882838

Similar Datasets

Project description:The thyromental height test (TMHT) has been proposed as a novel single clinical test for predicting difficult laryngoscopy (DL), though consequent studies have put forward various estimates when verifying its reliability. This systematic review and meta-analysis aimed to provide a comprehensive evaluation of the predictive value of TMHT for DL. A computerized search of CNKI, CQVIP, EBSCO, PubMed, SinoMed, and Wanfang Data was conducted on 1 June 2022. Prospective cohort studies reporting diagnostic properties of TMHT in relation to Cormack and Lehane grading in patients aged more than 16 years, either sex, scheduled for surgery under general anesthesia, requiring tracheal intubation with direct laryngoscopy were included in this analysis. Data was extracted or calculated, and meta-analysis was done by the Stata MIDAS module. A total of 23 studies with 5896 patients were included in this analysis. Summary estimates of all included studies are as follows: sensitivity 74% (95% CI, 68-79%); specificity 88% (95% CI, 81-92%); diagnostic odd ratio, 20 (95% CI, 10-40); positive likelihood ratio, 5.9 (95% CI, 3.6-9.6); and negative likelihood ratio, 0.30 (95% CI, 0.23-0.39). Summary sensitivity and specificity for studies with a prespecified threshold were 82% (95% CI, 71-89%) and 94% (95% CI, 87-98%), respectively. The estimated area under curve (AUC) was 85% (95% CI, 81-88%). There was no significant threshold effect but significant heterogeneity in both sensitivity and specificity. Heterogeneity in sensitivity became insignificant after removing two outliers of sensitivity analysis. It is concluded that THMT has an overall optimal predictive value for DL in adult patients with diverse ethnicity and various risk factors, displaying better predictive values in a large patient population comparing to other recent reported bedside assessments and a previous meta-analysis. As significant heterogeneity brought by un-standardized application of external laryngeal manipulations in the included studies may have biased the results of this meta-analysis, the actual predictive value of TMHT for DL still awaits further studies with good designs and large sample sizes for better determination.

Project description:INTRODUCTION:Difficult tracheal intubation (DTI) contributes to perioperative morbidity and mortality. There are conflicting study results about the most predictive DTI risk criteria in patients undergoing thyroid surgery. MATERIALS AND METHODS:We conducted a prospective observational study on 500 consecutive patients aged ≥18 years to identify predictors for DTI. Body weight, body mass index (BMI), inability to prognath, head movement, mouth opening, Mallampati score, neck circumference (NC), thyromental distance (TMD), neck circumference to thyromental distance ratio (NC/TMD), tracheal deviation apparent on chest x-ray, mediastinal goiter, histology and history of DTI were measured as possible predictors of DTI. Spearman's rank correlation test and multiple logistic regression analysis were performed. RESULTS:DTI was observed in 9.6% of all patients. Compared with the group of patients without DTI, the group of patients with DTI had significantly greater median values for body weight, BMI, NC, NC/TMD, Mallampati score, el-Ganzouri score, incidence of mediastinal goiter, and had reduced TMD and mouth opening. Significant correlations between BMI ≥30 kg/m2 and the Mallampati score ≥3 (R = 0.124, p = 0.00541), Cormack-Lehane ≥3 (R = 0.128, p = 0.00409), NC ≥40 cm (R = 0.376, p<0.001), and NC/TMD ≥5 (R = 0.103, p = 0.0207) were found. The logistic regression analysis revealed that an NC ≥40 cm at the goiter level, but not an NC/TMD ratio ≥5, was the strongest predictor of DTI (p<0.001). The area under the receiver operating characteristic curve for NC/TMD was better than the curve for NC. The sensitivity and specificity of NC/TMD were also greater, compared with NC. An NC of 40.00 cm and an NC/TMD of 5.85 were the estimated cut-off points. DISCUSSION:This study found that NC was a strong predictor of DTI. The results also suggested that NC/TMD could be used as a measure to stratify the risk of DTI in patients undergoing thyroid surgery.

Project description:BackgroundEmergency endotracheal intubation is a critical skill for managing airway emergencies in the emergency department (ED). Accurate prediction of difficult laryngoscopy is essential for improving first-attempt success, minimizing complications, optimizing resource utilization, and enhancing patient outcomes. Traditional methods, such as the LEMON criteria, have limited predictive accuracy. Machine learning (ML) offers advanced predictive capabilities by analyzing large datasets and identifying complex variable interactions. This study aimed to develop and validate the performance of ML models for predicting difficult laryngoscopy in the ED, comparing it with a conventional regression model.MethodsA retrospective cohort study was conducted on 4,370 adult patients who underwent intubation in the ED at Thammasat University Hospital. Difficult laryngoscopy was defined as a Cormack-Lehane grade III or IV. Patients were divided into development (training, 70%) and validation (testing, 30%) cohorts. Predictors of difficult laryngoscopy were identified using multivariable stepwise backward elimination logistic regression and were used to develop ML models, including Logistic Regression, Decision Tree, Random Forest, and XGBoost. Model performance was evaluated using the area under the receiver operating characteristic curve (AuROC), accuracy, precision, recall, and F1-score. Validation was performed on the validation cohort to confirm model accuracy.ResultsNine significant predictors were identified: male sex, trauma, absence of neuromuscular blocking agents, large incisors, large tongue, limited mouth opening, short thyrohyoid distance, obstructed airway, and poor neck mobility. The Random Forest model demonstrated the highest predictive performance, with an AuROC of 0.82 (95% CI: 0.78-0.85), accuracy of 0.89, recall of 0.89, and F1-score of 0.87, outperforming conventional regression (AuROC 0.76, 95% CI: 0.73-0.78) and other ML models. DeLong's test confirmed a statistically significant difference in AuROC between the two models (p = 0.002). The Decision Tree showed limited performance due to overfitting, while XGBoost demonstrated strong precision. No significant differences were found when comparing the two models with conventional regression (p = 0.498 and 0.496, respectively).ConclusionThe Random Forest model provides the most robust prediction of difficult laryngoscopy, outperforming both conventional and other ML methods. While ML models improve predictive accuracy, logistic regression remains a practical option in resource-limited settings. Integrating ML into clinical workflows could enhance decision-making, resource allocation, and patient safety in emergency airway management. Future research should prioritize external validation and real-world implementation.

Dataset Information

Development and validation of a difficult laryngoscopy prediction model using machine learning of neck circumference and thyromental height.

Background

Methods

Results

Conclusions

Publications

Development and validation of a difficult laryngoscopy prediction model using machine learning of neck circumference and thyromental height.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets