STOP questionnaire to screen for hypoxemia in deep sedation for young and middle-aged colonoscopy

Machine learning-based risk prediction of hypoxemia for outpatients undergoing sedation colonoscopy: a practical clinical tool

OBJECTIVES

Hypoxemia as a common complication in colonoscopy under sedation and may result in serious consequences. Unfortunately, a hypoxemia prediction model for outpatient colonoscopy has not been developed. Consequently, the objective of our study was to develop a practical and accurate model to predict the risk of hypoxemia in outpatient colonoscopy under sedation.

METHODS

In this study, we included patients who received colonoscopy with anesthesia in Nanjing First Hospital from July to September 2021. Risk factors were selected through the least absolute shrinkage and selection operator (LASSO). Prediction models based on logistic regression (LR), random forest classifier (RFC), extreme gradient boosting (XGBoost), support vector machine (SVM), and stacking classifier (SCLF) model were implemented and assessed by standard metrics such as the area under the receiver operating characteristic curve (AUROC), sensitivity and specificity. Then choose the best model to develop an online tool for clinical use.

RESULTS

We ultimately included 839 patients. After LASSO, body mass index (BMI) (coefficient = 0.36), obstructive sleep apnea-hypopnea syndrome (OSAHS) (coefficient = 1.32), basal oxygen saturation (coefficient = -0.14), and remifentanil dosage (coefficient = 0.04) were independent risk factors for hypoxemia. The XGBoost model with an AUROC of 0.913 showed the best performance among the five models.

CONCLUSION

Our study selected the XGBoost as the first model especially for colonoscopy, with over 95% accuracy and excellent specificity. The XGBoost includes four variables that can be quickly obtained. Moreover, an online prediction practical tool has been provided, which helps screen high-risk outpatients with hypoxemia swiftly and conveniently.

An interpretable artificial neural network model for predicting hypoxemia via an online tool in adult (18-64) patients during esophagogastroduodenoscopy

Background

The hypoxemia risk in adult (18-64) patients treated with esophagogastroduodenoscopy (EGD) under sedation often poses a dilemma for anesthesiologists. We aimed to establish an artificial neural network (ANN) model to solve this problem, and introduce the Shapley additive explanations (SHAP) algorithm to further improve the interpretability.

Methods

The relevant data of patients underwent routine anesthesia-assisted EGD were collected. Elastic network was used to filter the optimal features. Airway-ANN and Basic-ANN models were established based on all collected indicators and remaining variables excluding airway assessment indicators, respectively. The performance of Basic-ANN, Airway-ANN and STOP-BANG was evaluated by the area under the precision-recall curve (AUPRC) on temporal validation set. The SHAP was used for revealing the predictive behavior of our best model.

Results

999 patients were eventually included. The AUPRC value of Airway-ANN model was significantly higher than Basic-ANN model in the temporal validation set (0.532 vs 0.429, P < 0.05). And the performance of both two ANN models was significantly better than that of STOP-BANG score (both P < 0.05). The Airway-ANN model was deployed to the cloud (http://njfh-yxb.com.cn:2022/airway_ann).

Conclusion

Our online interpretable Airway-ANN model achieved satisfying ability in identifying the hypoxemia risk in adult (18-64) patients undergoing EGD.

High-Flow Nasal Cannula and Mandibular Advancement Bite Block Decrease Hypoxic Events during Sedative Esophagogastroduodenoscopy: A Randomized Clinical Trial

During sedated endoscopic examinations, upper airway obstruction occurs. Nasal breathing often shifts to oral breathing during open mouth esophagogastroduodenoscopy (EGD). High-flow nasal cannula (HFNC) which delivers humidified 100% oxygen at 30 L min⁻¹ may prevent hypoxemia. A mandibular advancement (MA) bite block with oxygen inlet directed to both mouth and nose may prevent airway obstruction during sedated EGD. The purpose of this study was to evaluate the efficacy of these airway devices versus standard management. One hundred and eighty-nine patients were assessed for eligibility. One hundred and fifty-three were enrolled. This study randomly assigned eligible patients to three arms: the standard bite block and standard nasal cannula, HFNC, and MA bite block groups. EGD was performed after anaesthetic induction. The primary endpoint was the oxygen desaturation area under curve at 90% (AUC_Desat). The secondary endpoints were percentage of patients with hypoxic, upper airway obstruction, and apnoeic and rescue events. One hundred and fifty-three patients were enrolled. AUCdesat was significantly lower for HFNC and MA bite blocks versus the standard management (p= 0.019). The HFNC reduced hypoxic events by 18% despite similar airway obstruction and apnoeic events as standard group. The MA bite block reduced hypoxic events by 12% and airway obstructions by 32%. The HFNC and MA groups both showed a 16% and 14% reduction in the number of patients who received rescue intervention, respectively, compared to the standard group. The HFNC and MA bite block may both reduce degree and duration of hypoxemia. HFNC may decrease hypoxemic events while maintaining nasal patency is crucial during sedative EGD. The MA bite block may prevent airway obstruction and decrease the need for rescue intervention.

Propofol versus midazolam in medical thoracoscopy: a randomized, noninferiority trial

BACKGROUND

Hypoxemia is a surrogate marker for periprocedural endoscopic complications. There are no data comparing the safety of propofol sedation with another sedative regimen in medical thoracoscopy.

OBJECTIVE

To evaluate whether sedation with propofol is as safe and effective as sedation with midazolam.

METHODS

Ninety consecutive patients undergoing medical thoracoscopy were randomly allocated to receive either intravenous propofol or midazolam. Predefined periprocedural complications included hypoxemia, hypotension, bleeding, need for airway insertion, mechanical ventilation, intensive care unit transfer and death. The primary endpoint was the mean lowest oxygen saturation during the procedure.

RESULTS

Randomized groups had similar demographics (64 ± 16 years, 57% male, 91% American Society of Anesthesiologists class III-IV) and a balanced distribution of procedures. The mean lowest oxygen saturation during the procedure was significantly lower in the propofol group as compared to the midazolam group (93 ± 6 vs. 96 ± 3%, p = 0.007). Patients randomized to propofol showed more episodes of hypoxemia (27 vs. 4%, p = 0.007) and hypotension (82 vs. 40%, p < 0.0001). No procedure had to be aborted. None of the patients required an artificial airway, mechanical ventilation or intensive care unit care, and none died.

CONCLUSIONS

As assessed by the surrogate marker hypoxemia, propofol should not be considered the first choice for sedation in medical thoracoscopy.