Background. Imposter syndrome, associated with self-doubt and fear despite clear accomplishments and competencies, is frequently detected in medical students and has a negative impact on their well-being. This study aimed to predict the students’ IS using the machine learning ensemble approach. Methods. This study was a cross-sectional design among medical students in Bangladesh. Data were collected from February to July 2020 through snowball sampling technique across medical colleges in Bangladesh. In this study, we employed three different machine learning techniques such (...) as neural network, random forest, and ensemble learning to compare the accuracy of prediction of the IS. Results. In total, 500 students completed the questionnaire. We used the YIS scale to determine the presence of IS among medical students. The ensemble model has the highest accuracy of this predictive model, with 96.4%, while the individual accuracy of random forest and neural network is 93.5% and 96.3%, respectively. We used different performance matrices to compare the results of the models. Finally, we compared feature importance scores between neural network and random forest model. The top feature of the neural network model is Y7, and the top feature of the random forest model is Y2, which is second among the top features of the neural network model. Conclusions. Imposter syndrome is an emerging mental illness in Bangladesh and requires the immediate attention of researchers. For instance, in order to reduce the impact of IS, identifying key factors responsible for IS is an important step. Machine learning methods can be employed to identify the potential sources responsible for IS. Similarly, determining how each factor contributes to the IS condition among medical students could be a potential future direction. (shrink)

Income is a primary determinant of social mobility, career progression, and personal happiness. It has been shown to vary with demographic variables like age and education, with more oblique variables such as height, and with behaviors such as delay discounting, i.e., the propensity to devalue future rewards. However, the relative contribution of each these salary-linked variables to income is not known. Further, much of past research has often been underpowered, drawn from populations of convenience, and produced findings that have not (...) always been replicated. Here we tested a large (n = 2,564), heterogeneous sample, and employed a novel analytic approach: using three machine learning algorithms to model the relationship between income and age, gender, height, race, zip code, education, occupation, and discounting. We found that delay discounting is more predictive of income than age, ethnicity, or height. We then used a holdout data set to test the robustness of our findings. We discuss the benefits of our methodological approach, as well as possible explanations and implications for the prominent relationship between delay discounting and income. (shrink)

The study investigates the possibility of applying texture analysis (TA) for testing Duchenne Muscular Dystrophy (DMD) therapies. The work is based on the Golden Retriever Muscular Dystrophy (GRMD) canine model, in which 3 phases of canine growth and/or dystrophy development are identified: the first phase (0–4 months of age), the second phase (from over 4 to 6 months), and the third phase (from over 6 months to death). Two differentiation problems are posed: (i) the first phase vs. the second phase (...) and (ii) the second phase vs. the third phase. Textural features are derived from T2-weighted Magnetic Resonance Imaging (MRI) images. In total, 37 features provided by 8 different TA methods (statistical, filter-based, and model-based) have been tested. The work focuses on finding such textural features that evolve along with the dog’s growth. These features are indicated by means of statistical analyses and eliminated from further investigation, as they may disturb the correct assessment of response to treatment in dystrophy. The relative importance of each remaining feature is then assessed with the use of the Monte Carlo (MC) procedure. Furthermore, feature selection based on the MC procedure is employed to find the optimal subset of age-independent features. Finally, three classifiers are used for evaluating different sets of textural features: Adaptive Boosting (AB), back-propagation Neural Network (NN), and nonlinear Support Vector Machines (SVM). The best subsets of age-independent features ensure 80.0% and 78.5% of correctly identified phases of dystrophy progression, for the first (i) and second (ii) differentiation problem respectively. (shrink)

Deep learning and other black-box models are becoming more and more popular today. Despite their high performance, they may not be accepted ethically or legally because of their lack of explainability. This paper presents the increasing number of legal requirements on machine learning model interpretability and explainability in the context of private and public decision making. It then explains how those legal requirements can be implemented into machine-learning models and concludes with a call for more inter-disciplinary research on explainability.