Background In the context of rising healthcare costs, formal education on treatment-related financial hardship is lacking in many medical schools, leaving future physicians undereducated and unprepared to engage in high-value care. Method We performed a prospective cohort study to characterize medical student knowledge regarding treatment-related financial hardship from 2019 to 2020 and 2020–2021, with the latter cohort receiving a targeted educational intervention to increase cost awareness. Using Kirkpatrick’s four-level training evaluation model, survey data was analyzed to characterize the acceptability of the intervention and the impact of the intervention on student knowledge, attitudes, and self-reported preparedness to engage in cost-conscious care. Results Overall, N = 142 medical students completed the study survey; 61 (47.3%) in the non-intervention arm and 81 (66.4%) in the intervention arm. Of the 81 who completed the baseline survey in the intervention arm, 65 (80.2%) completed the immediate post-intervention survey and 39 (48.1%) completed the two-month post-intervention survey. Following the educational intervention, students reported a significantly increased understanding of common financial terms, access to cost-related resources, and level of comfort and preparedness in engaging in discussions around cost compared to their pre-intervention responses. The majority of participants (97.4%) reported that they would recommend the intervention to future students. A greater proportion of financially stressed students reported considering patient costs when making treatment decisions compared to their non-financially stressed peers. Conclusions Targeted educational interventions to increase cost awareness have the potential to improve both medical student knowledge and preparedness to engage in cost-conscious care. Student financial stress may impact high-value care practices. Robust curricula on high-value care, including treatment-related financial hardship, should be formalized and universal within medical school training.

SAS Visual Data Mining and Machine Learning in SAS Viya offers a number of algorithms for training powerful predictive models, such as gradient boosting, forest, and deep learning models. Although these models are powerful, they are often too complex for people to understand by directly inspecting the model parameters. The “black-box” nature of these models limits their use in highly regulated industries such as banking, insurance, and health care. This paper introduces various model-agnostic interpretability techniques available in SAS Viya that enable you to explain and understand machine learning models. Methods include partial dependency (PD) plots, independent conditional expectation (ICE) plots, local interpretable model-agnostic explanations (LIME), and Shapley values. This paper introduces these methods and demonstrates their use in two scenarios: a business-centered modeling task and a health-care modeling task. Also shown are the two different interfaces to these methods in SAS Viya: Model Studio and the SAS Viya programming interface.

Regression problems with many potential candidate predictor variables occur in a wide variety of scientific fields and business applications. These problems require you to perform statistical model selection to find an optimal model, one that is as simple as possible while still providing good predictive performance. Traditional stepwise selection methods, such as forward and backward selection, suffer from high variability and low prediction accuracy, especially when there are many predictor variables or correlated predictor variables (or both). In the last decade, the higher prediction accuracy and computational efficiency of penalized regression methods have made them an attractive alternative to traditional selection methods. This paper first provides a brief review of the LASSO, adaptive LASSO, and elastic net penalized model selection methods. Then it explains how to perform model selection by applying these techniques with the GLMSELECT procedure, which includes extensive customization options and powerful graphs for steering statistical model selection.

We develop an approach to tuning of penalized regression variable selection methods by calculating the sparsest estimator contained in a confidence region of a specified level. Because confidence intervals/regions are generally understood, tuning penalized regression methods in this way is intuitive and more easily understood by scientists and practitioners. More importantly, our work shows that tuning to a fixed confidence level often performs better than tuning via the common methods based on Akaike information criterion. (AIC), Bayesian information criterion (BIC), or cross-validation (CV) over a wide range of sample sizes and levels of sparsity. Additionally, we prove that by tuning with a sequence of confidence levels converging to one, asymptotic selection consistency is obtained, and with a simple two-stage procedure, an oracle property is achieved. The confidence-region-based tuning parameter is easily calculated using output from existing penalized regression computer packages. Our work also shows how to map any penalty parameter to a corresponding confidence coefficient. This mapping facilitates comparisons of tuning parameter selection methods such as AIC, BIC, and CV, and reveals that the resulting tuning parameters correspond to confidence levels that are extremely low, and can vary greatly across datasets. Supplemental materials for the article are available online.