Prediction of endotracheal tube size in pediatric patients: Development and validation of machine learning models

Artificial intelligence in pediatric airway - A scoping review

Artificial intelligence is an ever-growing modality revolutionizing the field of medical science. It utilizes various computational models and algorithms and helps out in different sectors of healthcare. Here, in this scoping review, we are trying to evaluate the use of Artificial intelligence (AI) in the field of pediatric anesthesia, specifically in the more challenging domain, the pediatric airway. Different components within the domain of AI include machine learning, neural networks, deep learning, robotics, and computer vision. Electronic databases like Google Scholar, Cochrane databases, and Pubmed were searched. Different studies had heterogeneity of age groups, so all studies with children under 18 years of age were included and assessed. The use of AI was reviewed in the preoperative, intraoperative, and postoperative domains of pediatric anesthesia. The applicability of AI needs to be supplemented by clinical judgment for the final anticipation in various fields of medicine.

The development of prediction model for cuffed tracheal tube size from the middle finger in pediatrics: a concise and feasible approach

Background

Selecting the optimal tracheal tube size is critically important for pediatric patients. Age-based formulas are often used, but still have limitations. The aim of this prospective study was to investigate whether middle finger measurements correlate with cuffed tracheal tube size and to further develop a prediction model based on these measurements.

Methods

Patients under 12 years of age scheduled for elective surgery involving tracheal intubation were enrolled in the study. The length was determined from the tip of the distal metacarpal to the palm's root on the palm side, while the circumference was measured at the base of the palm using a soft tape measure. The appropriate cuffed tracheal tube size was determined based on specific criteria. If the tube encountered resistance during insertion or required an airway pressure >25 cmH2O to detect an audible leak, it was replaced with a tube 0.5 mm smaller. Conversely, if an audible leak occurred at an airway pressure <10 cmH2O, or peak pressure >25 cmH2O, or the cuff pressure >25 cmH2O to achieve a seal, the tube was exchanged for one with a 0.5 mm larger. Linear regression analysis was used to examine the association between middle finger circumference and length with the cuffed tracheal tube size. Subsequently, regression equations were constructed based on the results of the linear regression analysis and their predictive performance was compared to the conventional age-based formulas, including the Khine formula and Motoyama formula. The predictive performance was evaluated by mean absolute error (MAE), root mean square error (RMSE), and prediction accuracy.

Results

A total of 261 patients were analyzed in our study. The mean age of the patients was 46.19±35.83 months. The linear relationship was observed between the cuffed tracheal tube size and the middle finger circumference and middle finger length with R2 values of 0.77 and 0.73, respectively. In comparison to conventional age-based formulas, both middle finger circumference and middle finger length demonstrated superior predictive performance, characterized by lower MAE and RMSE, as well as higher prediction accuracy. Notably, the regression equation based on the middle finger circumference obtained the higher predictive accuracy of 0.590, with an MAE of 0.259 and an RMSE of 0.333 as opposed to the predictive accuracy of 0.391, MAE of 0.349, and RMSE of 0.473 derived from conventional age-based formulas. Based on the regression coefficients of linear regression, simplified formulas were proposed, with the middle finger circumference-based formula emerging as the most accurate and simple option.

Conclusions

The appropriate cuffed tracheal tube size could be predicted by the middle finger circumference. Our proposed formula 'cuffed tracheal tube internal diameter (mm) = middle finger circumference (cm) - 0.2' has the potential to improve the selection of the cuffed tracheal tube size in pediatric patients.

Predicting optimal endotracheal tube size and depth in pediatric patients using demographic data and machine learning techniques

BACKGROUND

Use of endotracheal tubes (ETTs) with appropriate size and depth can help minimize intubation-related complications in pediatric patients. Existing age-based formulae for selecting the optimal ETT size present several inaccuracies. We developed a machine learning model that predicts the optimal size and depth of ETTs in pediatric patients using demographic data, enabling clinical applications.

METHODS

Data from 37,057 patients younger than 12 years who underwent general anesthesia with endotracheal intubation were retrospectively analyzed. Gradient boosted regression tree (GBRT) model was developed and compared with traditional age-based formulae.

RESULTS

The GBRT model demonstrated the highest macro-averaged F1 scores of 0.502 (95% CI 0.486, 0.568) and 0.669 (95% CI 0.640, 0.694) for predicting the uncuffed and cuffed ETT size (internal diameter [ID]), outperforming the age-based formulae that yielded 0.163 (95% CI 0.140, 0.196, P < 0.001) and 0.392 (95% CI 0.378, 0.406, P < 0.001), respectively. In predicting the ETT depth (distance from tip to lip corner), the GBRT model showed the lowest mean absolute error (MAE) of 0.71 cm (95% CI 0.69, 0.72) and 0.72 cm (95% CI 0.70, 0.74) compared to the age-based formulae that showed an error of 1.18 cm (95% CI 1.16, 1.20, P < 0.001) and 1.34 cm (95% CI 1.31, 1.38, P < 0.001) for uncuffed and cuffed ETT, respectively.

CONCLUSIONS

The GBRT model using only demographic data accurately predicted the ETT size and depth. If these results are validated, the model may be practical for predicting optimal ETT size and depth for pediatric patients.