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

ABSTRACT

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.

Plain Language Summary

Colonoscopy under sedation is an effective technique for the inspection and treatment of alimentary canal diseases, but hypoxemia associated with this process cannot be ignored, since prolonged or severe hypoxemia may result in several serious consequences.

We wanted to develop a practical and accurate model to predict the risk of hypoxemia for outpatient colonoscopy under sedation, which could help clinicians make more accurate and objective judgments to prevent patients from being harmed.

A total of 839 patients were included in our study and we constructed five machine learning models and selected the best one, which demonstrated satisfactory performance. On this basis, a user-friendly data interface has been developed for convenient application. Clinicians can log in to this interface at any time and it will automatically calculate the patient’s risk of hypoxemia when entering patient information.

This study offers evidence that machine learning algorithms can accurately predict the risk of hypoxemia for outpatient colonoscopy under sedation and the model we developed is a practical and interpretable tool that could be used as a clinical decision-making aid.

KEYWORDS:

• Hypoxemia
• colonoscopy
• anesthesia
• machine learning
• prediction
• outpatient

Abbreviations

AUPRC, the area under the precision-recall curve; AUROC, the area under the receiver operating characteristic; ASA, American Society of Anesthesiologists class; BMI, body mass index; BQ, Berlin Questionnaire; COPD, chronic obstructive pulmonary disease; DCA, decision curve analysis; ECG, electrocardiogram; EHRs, electronic health records; HFNC, high-flow nasal cannula; IQR, interquartile range; LASSO, the least absolute shrinkage and selection operator; LR, logistic regression; ML, machine learning; MOAA/S, the modified observer-assessed alertness/sedation scale; NPV, negative predictive value; OSAHS, obstructive sleep apnea-hypopnea syndrome; PPV, positive predictive value; RFC, random forest classifier; SCLF, stacking classifier; SHAP, Shapley additive explanations; SMD, sternomental distance; SpO2, pulse oximetry oxygen saturation; SVM, support vector machine; TMD, thyromental distance; TMH, thyromental height; XGBoost, extreme gradient boosting.

Supplementary material

Supplemental data for this article can be accessed online at https://doi.org/10.1080/00325481.2024.2313448

Declaration of financial/other relationships

The authors have no relevant affiliations or financial involvement with any organization or entity with a financial interest in or financial conflict with the subject matter or materials discussed in the manuscript. This includes employment, consultancies, honoraria, stock ownership or options, expert testimony, grants or patents received or pending, or royalties. A reviewer on this manuscript has disclosed being a medical consultant to Odin Vision. Peer reviewers on this manuscript have no other relevant financial relationships or otherwise to disclose.

Acknowledgments

The authors thank all the participants and their families.

Ethics statement

The Ethics Committee of Nanjing First Hospital approved our study protocols. Moreover, informed permission was exempted due to the retrospective study design and anonymous data collection.

Data availability statement

The original database containing confidential patient information cannot be made public. If required, the corresponding author can be contacted directly.

Author contributions

YNS and JJZ conceived, designed and supervised the study; WL and YLT analyzed data and prepared results; WL, YLT, and XXZ wrote the paper with input from all authors; CC and KZH revised the paper; XXZ, YF, YZ and ZJF were involved in data acquisition. All authors finally approved the paper.

Additional information

Funding

This work was supported by National Natural Science Foundation of China [81873954, 82173899], the Six Talent Peaks Project of Jiangsu [WSW-106], Nanjing Medical Science and Technical Development Foundation [ZKX22030] and Jiangsu Pharmaceutical Association [H202108, A2021024, Q202202, JY202207].