Obstructive Sleep Apnea Increases the Risk of Cardiopulmonary Adverse Events Associated with Ambulatory Colonoscopy Independent of Body Mass Index

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.

Dynamic prediction of hypoxemia risk at different time points based on preoperative and intraoperative features: machine learning applications in outpatients undergoing esophagogastroduodenoscopy

BACKGROUND

Hypoxemia often occurs in outpatients undergoing anesthesia-assisted esophagogastroduodenoscopy (EGD). However, there is a scarcity in tools to predict the hypoxemia risk. We aimed to solve this problem by developing and validating machine learning (ML) models based on preoperative and intraoperative features.

METHODS

All data were retrospectively collected from June 2021 to February 2022. The most appropriate predictive features were selected by the least absolute shrinkage and selection operator, which were incorporated and modelled by 4 ML algorithms. The area under the precision-recall curve (AUPRC) was used as the main evaluation metric to select the best models, and the selected models were compared with the STOP-BANG score. Their predictive performance was visually interpreted by SHapley Additive exPlanations. The primary endpoint of this study was hypoxemia during the procedure, defined as at least one reading of pulse oximetry < 90% without probes misplacement from the anesthesia induction beginning to the end of EGD, while the secondary endpoint was hypoxemia during induction, from the induction beginning to the start of endoscopic intubation.

RESULTS

Of 1160 patients in the derivation cohort, 112 patients (9.6%) developed intraoperative hypoxemia, of which 102 (8.8%) occurred during the induction period. In temporal and external validation, no matter whether based on preoperative variables or still based on preoperative plus intraoperative variables, our models showed excellent predictive performance for the two endpoints, significantly better than STOP-BANG score. In the model interpretation section, preoperative variables (airway assessment indicators, pulse oximeter oxygen saturation and BMI) and intraoperative variables (the induced propofol dose) made the highest contribution to the predictions.

To our knowledge, our ML models were the first to predict hypoxemia risk, which achieved excellent overall predictive ability integrating various clinical indicators. These models have the potential to become an effective tool for adjusting sedation strategies flexibly and reducing the workload of anesthesiologists.KEY MESSAGESThis study is the first model employing ML methods based on preoperative and preoperative plus intraoperative variables for predicting the risk of hypoxemia during induction and the whole EGD procedure respectively.Our four models achieved satisfactory predictive performance and outperformed STOP-BANG score in terms of AUPRC in the temporal and external validation cohorts respectively.We found that the relevant variables of airway assessment should be fully taken into account when analyzing the risk factor of hypoxemia, and the effect of patients' age on their hypoxemia risk should be considered in conjunction with the propofol dose.

Nasal continuous positive pressure versus simple face mask oxygenation for adult obese and obstructive sleep apnea patients undergoing colonoscopy under propofol-based general anesthesia without tracheal intubation: A randomized controlled trial

STUDY OBJECTIVE

To determine if a nasal positive airway pressure (nasal CPAP) mask would decrease the number of hypoxemic events in obese and obstructive sleep apnea patients undergoing colonoscopy.

DESIGN

Single-center prospective randomized controlled trial.

SETTING

Tertiary academic center.

PATIENTS

We enrolled 109 patients with diagnosis of obesity and/or obstructive sleep apnea scheduled to undergo colonoscopy under propofol general anesthesia without planned tracheal intubation.

INTERVENTION

Patients were randomly allocated (1:1 ratio) to receive supplementary oxygen at a flow of 10 L/min, either through a nasal CPAP or a simple facemask.

MEASUREMENTS

The primary endpoint was the difference in the mean percentage of time spent with oxygen saturation below 90% between the two groups. Secondary outcomes included the need for airway maneuvers/interventions, average SpO2 during the case, duration and severity of oxygen desaturation, incidence and duration of procedural interruptions, and satisfaction and tolerance scores.

MAIN RESULTS

54 were allocated to the simple face mask and 55 to the nasal CPAP mask arms, respectively. A total of 6 patients experienced a hypoxemic event. Among these patients, the difference in the percentage of time spent with oxygen saturation below 90% was not clinically relevant (p = 1.0). However, patients in the nasal CPAP group required less chin lift (20% vs. 42.6%; p = 0.01) and oral cannula insertion (12.7% vs.29.6%; p = 0.03). The percentage of patients with at least one airway maneuver was higher in the simple face mask arm (68.5% vs. 41.8%; p = 0.005). Patient tolerance to device score was lower in the nasal CPAP group (8.85 vs. 9.56; p = 0.003).

CONCLUSIONS

A nasal CPAP did not prevent hypoxemia and should not be used routinely for colonoscopy in obese or OSA patients if a simple face mask is an alternative therapy. However, potential advantages of its use include fewer airway maneuvers or interventions, which may be desirable in certain clinical settings.

TRIAL REGISTRATION

Clinicaltrials.gov, identifier: NCT05175573.

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.

Evaluation of Propofol-Sparing Effect of Intravenous Lignocaine in Patients Undergoing Daycare Upper Gastrointestinal Endoscopic Procedures

Background Propofol is the most common sedative for endoscopies. Propofol alone may require larger doses for adequate level of sedation. Lignocaine is known for its anesthetic-sparing effect. We tested whether the addition of intravenous lignocaine to propofol-based sedation reduces its dose. Methods This prospective, randomized study was performed on 90 patients of 18 to 60 years of age, of either sex of the American Society of Anesthesiologists (ASA) Grade-I & II, and was divided into two groups. Group L + P received IV bolus of 1.5 mg/kg 2% lignocaine over 10 minutes followed by 1.5 mg/ kg/ h infusion and group NS + P- received the equivalent volumes of normal saline in bolus and infusion. Patients were induced with fentanyl (2 µg/kg) and propofol (1 mg/kg). To maintain an adequate sedation level, a supplemental bolus of 0.5 mg /kg propofol was administered. The outcomes recorded were the total and supplemental amount of propofol administered, as well as recovery time. Results The mean supplemental propofol for group L + P and group NS + P- 37.00 ± 29.93 and 58.67 ± 19.49 mg, respectively and mean total propofol consumption was 98.22 ± 34.00 mg and 131.11 ± 23.18 mg, respectively, (p < 0.001). Mean recovery time in group L + P was also shorter (5.22 ± 2.14 versus 9.96 ± 2.14). The incidence of adverse events like gag reflux, upper airway obstruction, pain on injection, and hypotension was significantly lower in group L + P (p < 0.05). Conclusion The addition of lignocaine to propofol-based sedation reduced the overall propofol requirement at the same time maintaining hemodynamic stability, spontaneous respiration, and early recovery.

Prevention of pulmonary complications in sedated patients undergoing interventional procedures in the nonoperating room anesthesia setting

PURPOSE OF REVIEW

Nonoperating room anesthesia (NORA) procedures have expanded in number, variety, and complexity. NORA involves all age groups, including frail older adults and patients often considered too sick to tolerate traditional surgical interventions. Postoperative pulmonary complications are a significant source of adverse events in the perioperative setting. We present a review focused on preventing pulmonary complications in the interventional NORA setting.

RECENT FINDINGS

NORA locations should function as independent, autonomous ambulatory units. We discuss a strategic plan involving a thorough preoperative evaluation of patients, including recognizing high-risk patients and their anesthetic management. Finally, we offer guidance on the challenges of conducting sedation and anesthesia in patients with coronavirus disease 2019 (COVID-19) or a history of COVID-19.

SUMMARY

The demands on the interventional NORA anesthesia team are increasing. Strategic planning, checklists, consistent staffing assignments, and scheduled safety drills are valuable tools to improve patient safety. In addition, through quality improvement initiatives and reporting, NORA anesthetists can achieve reductions in periprocedural pulmonary complications.

Validity Analysis of Neck Circumference as a Screening Test for Hypoxia Occurrence in Patients Undergoing Sedative Endoscopy

This study was performed to check the validity of and propose a cutoff point for measuring the neck circumference for screening hypoxia occurrence in patients undergoing sedative endoscopy. Data were collected from 168 patients who visited the Endoscopy Center of G University Hospital between 27 April 2020 and 12 June 2020 to undergo sedative endoscopy. Hypoxia occurrences were measured using sleep questionnaires (STOP-BANG and Berlin questionnaires), and the neck circumference measurements of the patients were compared. Neck circumference as a predictor of hypoxia and its sensitivity and specificity according to the cutoff values were high; thus, it is a valid screening test for hypoxia in patients undergoing sedative endoscopy. The most appropriate cutoff values for sitting neck circumference and lying neck circumference in men were 40.5 and 40.3, respectively, and those for women were 35.3 and 35.8, respectively. Hypoxia can be predicted in patients undergoing sedative endoscopy by measuring their neck circumference.

Impact of intravenous and topical lidocaine on clinical outcomes in patients receiving propofol for gastrointestinal endoscopic procedures: a meta-analysis of randomised controlled trials

BACKGROUND

The efficacy of i.v. or topical lidocaine as an anaesthesia adjunct in improving clinical outcomes in patients receiving gastrointestinal endoscopic procedures under propofol sedation remains unclear.

METHODS

Electronic databases (MEDLINE, EMBASE, and Cochrane Library) were searched for RCTs comparing the clinical outcomes with or without lidocaine application (i.v. or topical) in patients receiving propofol for gastrointestinal endoscopic procedures from inception to 29 March 2021. The primary outcome was propofol dosage, while secondary outcomes included procedure time, recovery time, adverse events (e.g. oxygen desaturation), post-procedural pain, and levels of endoscopist and patient satisfaction.

RESULTS

Twelve trials (1707 patients) published between 2011 and 2020 demonstrated that addition of i.v. (n=7) or topical (n=5) lidocaine to propofol sedation decreased the level of post-procedural pain (standardised mean difference [SMD]=-0.47, 95% confidence interval [CI]: -0.8 to -0.14), risks of gag events (risk ratio [RR]=0.51, 95% CI: 0.35-0.75), and involuntary movement (RR=0.4, 95% CI: 0.16-0.96). Subgroup analysis demonstrated that only i.v. lidocaine reduced propofol dosage required for gastrointestinal endoscopic procedures (SMD=-0.83, 95% CI: -1.19 to -0.47), increased endoscopist satisfaction (SMD=0.75, 95% CI: 0.21-1.29), and shortened the recovery time (SMD=-0.83, 95% CI: -1.45 to -0.21). Intravenous or topical lidocaine did not affect the incidence of oxygen desaturation (RR=0.72, 95% CI: 0.41-1.24) or arterial hypotension (RR=0.6, 95% CI: 0.22-1.65) and procedure time (SMD=0.21, 95% CI: -0.09 to 0.51).

CONCLUSION

This meta-analysis demonstrated that i.v. or topical lidocaine appears safe to use and may be of benefit for improving propofol sedation in patients undergoing gastrointestinal endoscopic procedures. Further large-scale trials are warranted to support our findings.

An algorithm for the sedation of patients with obstructive sleep apnea by non-anesthesiologists

OBJECTIVE

Patients with obstructive sleep apnea (OSA) are at risk for adverse events when moderate sedation is administered by nurse protocols (NAMS) under the guidance of non-anesthesiologists. An algorithm was applied for the appropriate section of patients to receive NAMS and the application of continuous positive airway pressure (CPAP).

METHODS

An algorithm was developed for patients with OSA who were scheduled for gastroenterology, radiology, and cardiology procedures using NAMS. Those with normal airways and without contraindications for NAMS were classified as CPAP-independent (CPAP-I; not routinely used) or CPAP-dependent (CPAP-D; always used). CPAP machines were brought in by CPAP-D patients or supplied by the hospital and set at a patient's routine setting or 10 cm H₂O if not known. CPAP-D patients for procedures for which CPAP could not be applied were done under anesthesia care. We retrospectively examined this program for the 2008-2018 period.

RESULTS

Since the inception of this protocol in 2008, 803 patients with OSA safely underwent procedures using either personal CPAP or CPAP provided by the hospital.

CONCLUSIONS

Patients with OSA can safely have NAMS for procedures when CPAP is applied based on a protocol that considers airway evaluation, the procedure, and whether there is dependence upon CPAP.

Design and Implementation of a Comprehensive Surveillance System for Venous Thromboembolism in a Defined Region Using Electronic and Manual Approaches

BACKGROUND

Systematic surveillance for venous thromboembolism (VTE) in the United States has been recommended by several organizations. Despite adoption of electronic medical records (EMRs) by most health care providers and facilities, however, systematic surveillance for VTE is not available.

OBJECTIVES

This article develops a comprehensive, population-based surveillance strategy for VTE in a defined geographical region.

METHODS

The primary surveillance strategy combined computerized searches of the EMR with a manual review of imaging data at the Duke University Health System in Durham County, North Carolina, United States. Different strategies of searching the EMR were explored. Consolidation of results with autopsy reports (nonsearchable in the EMR) and with results from the Durham Veterans' Administration Medical Center was performed to provide a comprehensive report of new VTE from the defined region over a 2-year timeframe.

RESULTS

Monthly searches of the primary EMR missed a significant number of patients with new VTE who were identified by a separate manual search of radiology records, apparently related to delays in data entry and coding into the EMR. Comprehensive searches incorporating a location-restricted strategy were incomplete due to the assigned residence reflecting the current address and not the address at the time of event. The most comprehensive strategy omitted the geographic restriction step and identified all patients with VTE followed by manual review of individual records to remove incorrect entries (e.g., outside the surveillance time period or geographic location; no evidence for VTE). Consolidation of results from the EMR searches with results from autopsy reports and the separate facility identified additional patients not diagnosed within the Duke system.

CONCLUSION

We identified several challenges with implementing a comprehensive VTE surveillance program that could limit accuracy of the results. Improved electronic strategies are needed to cross-reference patients across multiple health systems and to minimize the need for manual review and confirmation of results.