Machine Learning Algorithms for Predicting Surgical Outcomes after Colorectal Surgery: A Systematic Review

Abstract

Background Machine learning (ML) has been introduced in various fields of healthcare. In colorectal surgery, the role of ML has yet to be reported. In this systematic review, an overview of machine learning models predicting surgical outcomes after colorectal surgery is provided. Methods Databases PubMed, EMBASE, Cochrane, and Web of Science were searched for studies using machine learning models for patients undergoing colorectal surgery. To be eligible for inclusion, studies needed to apply machine learning models for patients undergoing colorectal surgery. Absence of machine learning or colorectal surgery or studies reporting on reviews, children, study abstracts were excluded. The Probast risk of bias tool was used to evaluate the methodological quality of machine learning models. Results A total of 1821 studies were analysed, resulting in the inclusion of 31 articles. A vast proportion of ML algorithms have been used to predict the course of disease and response to neoadjuvant chemoradiotherapy. Radiomics have been applied most frequently, along with predictive accuracies up to 91%. However, most studies included a retrospective study design without external validation or calibration. Conclusions Machine learning models have shown promising potential in predicting surgical outcomes after colorectal surgery. However, large-scale data is warranted to bridge the gap between calibration and external validation. Clinical implementation is needed to demonstrate the contribution of ML within daily practice.

Identification and Evaluation of Blood-Based Biomarkers for Abdominal Aortic Aneurysm

“…The model chosen was random forest, an ensemble learning method that operates through multiple decision trees, which classify populations into branch-like segments to develop prediction algorithms for a target outcome using multiple covariates . This model was selected because it is widely used in literature and demonstrates good performance for predicting health outcomes. − …”

Predicting Outcomes Following Endovascular Abdominal Aortic Aneurysm Repair Using Machine Learning

“…Six ML models were trained to predict 30-day primary and secondary outcomes: Extreme Gradient Boosting (XGBoost), random forest, Naive Bayes classifier, support vector machine (SVM), multilayer perceptron (MLP) artificial neural network (ANN), and logistic regression. These were chosen because they demonstrate the best performance for predicting surgical outcomes in the literature 18,19 . Logistic regression was the baseline comparator to assess relative model performance because it is the most common modeling technique used in traditional risk prediction tools 20 …”

“…These were chosen because they demonstrate the best performance for predicting surgical outcomes in the literature. 18,19 Logistic regression was the baseline comparator to assess relative model performance because it is the most common modeling technique used in traditional risk prediction tools. 20 Our data were split into training (70%) and test (30%) sets.…”

Using Machine Learning (XGBoost) to Predict Outcomes following Infrainguinal Bypass for Peripheral Artery Disease

“…We trained 6 different ML models to predict primary and secondary outcomes: Extreme Gradient Boosting (XGBoost), random forest, Naïve Bayes classifier, radial basis function support vector machine, multilayer perceptron artificial neural network with a single hidden layer, sigmoid activation function, cross-entropy loss function, and logistic regression. These models were selected based on their demonstrated efficacy in predicting surgical outcomes 17,18 . Logistic regression was used as the baseline comparator to assess relative model performance, as it is the most widely employed statistical technique in traditional risk prediction tools 19 …”

“…These models were selected based on their demonstrated efficacy in predicting surgical outcomes. 17,18 Logistic regression was used as the baseline comparator to assess relative model performance, as it is the most widely employed statistical technique in traditional risk prediction tools. 19 The data were divided into 2 subsets: training (70%) and testing (30%).…”