Accepted for/Published in: JMIR Medical Informatics
Date Submitted: Jan 14, 2021
Date Accepted: Jun 16, 2021
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Development and Validation of Prediction Model of Anastomotic Leakage Among Esophageal Cancer Patients After Receiving Minimally Invasive Esophagectomy: Machine Learning Approach
ABSTRACT
Background:
Minimally invasive esophagectomy (MIE) is an important surgical approach for esophageal cancer patients while anastomotic leakage (AL) is a severe complication after MIE (5%-30%).
Objective:
The aim of this study is to use machine learning techniques to develop and validate a simple risk prediction panel to screen patients with emerging risk factors.
Methods:
In this machine learning risk prediction model, we used data from a retrospective study. We randomly split (9:1) the dataset using a computer algorithm into a training dataset of 639 patients and a testing dataset of 71 patients. We identified independently important diagnostic features of AL using the feature importance and correlation-based feature selection. We assessed multiple classification tools to create a multivariate risk prediction model. Internal validation of the model using the testing dataset was followed.
Results:
Final risk panel included 36 independent risk features. Of those, 10 features were significantly identified by logistic model, including aortic calcification (OR=2.77, 95% CI 1.32-5.81), abdominal dry calcification (OR=2.79, 95% CI 1.20-6.48) , forced expiratory volume (FEV) 1% (OR=0.51, 95% CI 0.30-0.89); TLCO (OR=0.56, 95% CI 0.27-1.18), peripheral vascular disease (OR=4.97, 95% CI 1.44-17.07), laparoscope (OR=3.92, 95% CI 1.23-12.51), post-operative hospital length of stay (OR=1.17, 95% CI 1.13-1.21), vascular permeability activity (OR=0.46, 95% CI 1.14-1.48), incisions fat colliquation or infections (OR=4.36, 95% CI 1.86-10.21). Logistic regression offered the highest prediction quality with accuracy of 87% in the training dataset, same performance was also archived by the testing model.
Conclusions:
Our diagnostic model offers valid predictions of diagnosis of AL, assisting in anastomotic leakage prevention and treatment. It suggests screening patients’ arteriosclerosis related risks factors and continuous monitoring of perioperative hemodynamics. Our risk prediction panel will need further calibration and validation in a prospective study in multi-center settings.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.