Abstract

Abstract

Abstract
In this paper, we evaluate the performance and analyze the explainability of machine learning models boosted by feature selection in predicting COVID-19-positive cases from self-reported information. In essence, this work describes a methodology to identify COVID-19 infections that considers the large amount of information collected by the University of Maryland Global COVID-19 Trends and Impact Survey (UMD-CTIS). More precisely, this methodology performs a feature selection stage based on the recursive feature elimination (RFE) method to reduce the number of input variables without compromising detection accuracy. A tree-based supervised machine learning model is then optimized with the selected features to detect COVID-19-active cases. In contrast to previous approaches that use a limited set of selected symptoms, the proposed approach builds the detection engine considering a broad range of features including self-reported symptoms, local community information, vaccination acceptance, and isolation measures, among others. To implement the methodology, three different supervised classifiers were used: random forests (RF), light gradient boosting (LGB), and extreme gradient boosting (XGB). Based on data collected from the UMD-CTIS, we evaluated the detection performance of the methodology for four countries (Brazil, Canada, Japan, and South Africa) and two periods (2020 and 2021). The proposed approach was assessed in terms of various quality metrics: F1-score, sensitivity, specificity, precision, receiver operating characteristic (ROC), and area under the ROC curve (AUC). This work also shows the normalized daily incidence curves obtained by the proposed approach for the four countries. Finally, we perform an explainability analysis using Shapley values and feature importance to determine the relevance of each feature and the corresponding contribution for each country and each country/year.

Abstract
Objectives: The purpose of this study was to field-test a recently developed AR-based serious game designed to promote SSE self-efficacy, called Spot. Methods: Thirty participants played the game and answered 3 questionnaires: a baseline questionnaire, a second questionnaire immediately after playing the game, and a third questionnaire 1 week later (follow-up). Results: The majority of participants considered that the objective quality of the game was high, and considered that the game could have a real impact in SSE promotion. Participants showed statistically significant increases in SSE self-efficacy and intention at follow-up. Of the 24 participants that had never performed a SSE or had done one more than 3 months ago, 12 (50.0%) reported doing a SSE at follow-up. Conclusions: This study provides supporting evidence to the use of serious games in combination with AR to educate and motivate users to perform SSE. Spot seems to be an inconspicuous but effective strategy to promote SSE, a cancer prevention behavior, among healthy individuals. Practice implications: Patient education is essential to tackle skin cancer, particularly melanoma. Serious games, such as Spot, have the ability to effectively educate and motivate patients to perform a cancer prevention behavior.

Abstract
Canvas have for long been embraced as a popular design tool. Initially aimed towards, business model development, the model of a one page, visual and collaborative tool has spread to the design of many different artifacts. Digital platforms, with its conjugation of business, technical, and social facets have benefited from the canvas model for its design practices, from both scholars and practitioners. Nonetheless, the recent push for more industry-specific and holistic digital platform research agenda is bound to have an impact in the tools used for platform design. In this paper, we apply a literature review method to examine existing canvas, inspired by the Business Model Canvas, as tools for the design of digital platforms. Using conceptual platform design research as a frame of reference, we review eight canvas specific for digital platform design, highlighting four critical limitations in their application regarding (1) adopted broad platform conceptualizations; (2) a restricted focus on business elements; (3) a lack of focus on platform evolution; and (4) a lack of guidance in the translation of canvas to explicit platform design propositions and requirements. By addressing these limitations, we set a path for the evolution of canvas as collaborative tools that can better support the more comprehensive and nuanced approaches required for the design of digital platforms acting in an evermore non-linear, volatile, uncertain, complex, and ambiguous environments.

Abstract