Increasing transparency in machine learning through bootstrap simulation and shapely additive explanations

Abstract

Machine learning methods are widely used within the medical field. However, the reliability and efficacy of these models is difficult to assess, making it difficult for researchers to identify which machine-learning model to apply to their dataset. We assessed whether variance calculations of model metrics (e.g., AUROC, Sensitivity, Specificity) through bootstrap simulation and SHapely Additive exPlanations (SHAP) could increase model transparency and improve model selection. Data from the England National Health Services Heart Disease Prediction Cohort was used. After comparison of model metrics for XGBoost, Random Forest, Artificial Neural Network, and Adaptive Boosting, XGBoost was used as the machine-learning model of choice in this study. Boost-strap simulation (N = 10,000) was used to empirically derive the distribution of model metrics and covariate Gain statistics. SHapely Additive exPlanations (SHAP) to provide explanations to machine-learning output and simulation to evaluate the variance of model accuracy metrics. For the XGBoost modeling method, we observed (through 10,000 completed simulations) that the AUROC ranged from 0.771 to 0.947, a difference of 0.176, the balanced accuracy ranged from 0.688 to 0.894, a 0.205 difference, the sensitivity ranged from 0.632 to 0.939, a 0.307 difference, and the specificity ranged from 0.595 to 0.944, a 0.394 difference. Among 10,000 simulations completed, we observed that the gain for Angina ranged from 0.225 to 0.456, a difference of 0.231, for Cholesterol ranged from 0.148 to 0.326, a difference of 0.178, for maximum heart rate (MaxHR) ranged from 0.081 to 0.200, a range of 0.119, and for Age ranged from 0.059 to 0.157, difference of 0.098. Use of simulations to empirically evaluate the variability of model metrics and explanatory algorithms to observe if covariates match the literature are necessary for increased transparency, reliability, and utility of machine learning methods. These variance statistics, combined with model accuracy statistics can help researchers identify the best model for a given dataset.

Exploring Depression and Nutritional Covariates Amongst US Adults using Shapely Additive Explanations

“…These transparent machine‐learning tools allow for increased confidence that these algorithms are picking up true signal within these covariates to predict the presence of depression rather than just replicating potential biases stemming from systemic data‐quality errors that are present within the data set. Additionally, these SHAP visualizations allow us to interpret that the increase predictive power of these machine‐learning methods is associated with the ability for these nonparametric methods to more accurately capture the nonlinear interactive relationship between the covariates, rather than just over‐fitting the model to get increased accuracy 52,53 …”

Increased vigorous exercise and decreased sedentary activities are associated with decreased depressive symptoms in United States adults: Analysis of The National Health and Nutrition Examination Survey (NHANES) 2017–2020

“…For continuous variables, data were expressed in the following format mean ± standard deviation (SD), and for categorical variables, they were expressed as proportions. For the relevant covariates on demographics and exercise, chi‐squared was used for categorical variables for continuous variables, the Shapiro–Wilk test for normality was performed and t ‐tests were performed for continuous and normally distributed variables and non‐parametric Wilcoxon tests were utilized for non‐normally distributed variables to compare differences amongst those with clinical depression and those without 22 . Univariable models assessed the effect of vigorous exercise and sedentary activity on clinical depression risk.…”

Machine learning in transfusion medicine: A scoping review

“…While the focus of ML is on prediction, and a causal relationship cannot be assumed of the covariates found to have high predictive value, identification of novel risk factors for hypothesis generation and further research can be useful as seen in transfusion-associated lung injury (TRALI) 85 and in pediatric transfusion-associated hyperkalemia. 86 Recognizing that transparency and accountability are essential for clinicians in generating hypotheses, Zhu et al 87,88 focus on explainable AI when presenting adverse events during neonatal hyperbilirubinemia exchange transfusion, particularly through use of SHapley Additive exPlanation (SHAP).…”