A machine learning stacking model accurately estimating gastric fluid volume in patients undergoing elective sedated gastrointestinal endoscopy

ABSTRACT

Background

The current point-of-care ultrasound (POCUS) assessment of gastric fluid volume primarily relies on the traditional linear approach, which often suffers from moderate accuracy. This study aimed to develop an advanced machine learning (ML) model to estimate gastric fluid volume more accurately.

Methods

We retrospectively analyzed the clinical data and POCUS data (D1: craniocaudal diameter, D2: anteroposterior diameter) of 1386 patients undergoing elective sedated gastrointestinal endoscopy (GIE) at Nanjing First Hospital to predict gastric fluid volume using ML techniques, including six different ML models and a stacking model. We evaluated the models using the adjusted Coefficient of Determination (R²), mean absolute error (MAE) and root mean square error (RMSE). The SHapley Additive exPlanations (SHAP) method was used to interpret the importance of the variables. Finally, a web calculator was constructed to facilitate its clinical application.

Results

The stacking model (Linear regression + Multilayer perceptron) performed best, with the highest adjusted R² of 0.718 (0.632 to 0.804). The mean prediction bias was 4 ml (MAE: 4.008 (3.68 to 4.336)), which is better than that of the linear model. D1 and D2 ranked high in the SHAP plot and performed better in the right lateral decubitus (RLD) than in the supine position. The web calculator can be accessed at https://cheason.shinyapps.io/Stacking_regressor/.

Conclusion

The stacking model and its web calculator can serve as practical tools for accurately estimating gastric fluid volume in patients undergoing elective sedated GIE. It is recommended that anesthesiologists measure D1 and D2 in the patient’s RLD position.

KEYWORDS:

• Machine learning
• point-of-care ultrasound
• stacking model
• gastrointestinal endoscopy
• gastric fluid volume

Disclosure 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. Peer reviewers on this manuscript have no relevant financial or other relationships to disclose.

Acknowledgments

The authors would like to thank all the anesthesiologists, endoscopists and sonographers for their helping collecting data during their surgeries.

Author contributions

Yuqing Yan, Yuzhan Jin, and Yaoyi Guo designed this study; Yaoyi Guo, Mingtao Ma, Yue Feng and Yi Zhong collected the data; Yuzhan Jin conducted the data analysis and developed the machine learning models; Yuqing Yan and Yuzhan Jin wrote the original draft; Chen Chen, Chun Ge, Jianjun Zou and Yanna Si provided guidance and amendments; all authors approved the final manuscript.

Data availability statement

The datasets used and analyzed during the current study are available from the corresponding author on reasonable request.

Supplementary material

Supplemental data for this article can be accessed online at https://doi.org/10.1080/00325481.2024.2333720

Additional information

Funding

This study was supported by the National Natural Science Foundation of China [Grant Number 81873954, 82173899], the Six Talent Peaks Project in Jiangsu [Grant Number WSW-106], Nanjing Medical Science and Technical Development Foundation [Grant Number ZKX22030], and Jiangsu Pharmaceutical Association [Grant Number H202108, A2021024, Q202202, JY202207, Z04JKM2023E040, A202309].