A Comparative Study of Machine Learning Algorithms in Predicting Severe Complications after Bariatric Surgery

Abstract

Background: Severe obesity is a global public health threat of growing proportions. Accurate models to predict severe postoperative complications could be of value in the preoperative assessment of potential candidates for bariatric surgery. So far, traditional statistical methods have failed to produce high accuracy. We aimed to find a useful machine learning (ML) algorithm to predict the risk for severe complication after bariatric surgery. Methods: We trained and compared 29 supervised ML algorithms using information from 37,811 patients that operated with a bariatric surgical procedure between 2010 and 2014 in Sweden. The algorithms were then tested on 6250 patients operated in 2015. We performed the synthetic minority oversampling technique tackling the issue that only 3% of patients experienced severe complications. Results: Most of the ML algorithms showed high accuracy (>90%) and specificity (>90%) in both the training and test data. However, none of the algorithms achieved an acceptable sensitivity in the test data. We also tried to tune the hyperparameters of the algorithms to maximize sensitivity, but did not yet identify one with a high enough sensitivity that can be used in clinical praxis in bariatric surgery. However, a minor, but perceptible, improvement in deep neural network (NN) ML was found. Conclusion: In predicting the severe postoperative complication among the bariatric surgery patients, ensemble algorithms outperform base algorithms. When compared to other ML algorithms, deep NN has the potential to improve the accuracy and it deserves further investigation. The oversampling technique should be considered in the context of imbalanced data where the number of the interested outcome is relatively small.

Evaluation of the impact of body mass index on venous thromboembolism risk factors

“…In medical science, supervised classification techniques have been employed to identify risk factors for a specific disease or to predict disease occurrence such as VTE. Among a large number of available supervised ML techniques, kernel machine learning [30], various decision trees [31,32], artificial neural networks [33][34][35], random forest [36,37], support vector machines [38,39], Bayesian decision rules [40,41], supervised principal component analysis [42], penalized regression models [43] have been applied in medical science. Although the choice of ML techniques is often based on the minimum loss function, it is difficult to make an informed decision on the most appropriate method.…”

Prediction of Vestibular Dysfunction by Applying Machine Learning Algorithms to Postural Instability

“…The reason for this was that the number of cases in our dataset was not big enough to sufficiently train the model (33). The multiple algorithms should be evaluated individually with each clinical dataset because a specific algorithm does not necessarily fit any dataset (34,35).…”

“…The hyperparameters of the machine-learning algorithms are set values which can greatly affect the performance of the prediction model (34)(35)(36). Thus, optimization of the hyperparameters is important for achieving the best prediction results from machine learning algorithms.…”

Predictive Value of Odor Identification for Incident Dementia: The Shanghai Aging Study

“…Evaluation: The metrics, including sensitivity, specificity, accuracy, and area under the receiver operating characteristic (ROC) curve, were used to evaluate the models' predictive ability. Terminology and derivations of the metrics are given in detail elsewhere (Cao et al, 2019). The acceptable, good, and great prediction models for incident dementia are defined as the area under the ROC curve (AUC) of a model greater than 0.7, 0.8, and 0.9, respectively (Marzban, 2004;Mandrekar, 2010).…”