To improve the performance of Intensive Care Units (ICUs), the field of biostatistics has developed scores which try to predict the likelihood of negative outcomes. These help evaluate the effectiveness of treatments and clinical practice, and also help to identify patients with unexpected outcomes. However, they have been shown by several studies to offer sub-optimal performance. Alternatively, Deep Learning offers state of the art capabilities in certain prediction tasks and research suggests deep neural networks are able to outperform traditional techniques. Nevertheless, a main impediment for the adoption of Deep Learning in healthcare is its reduced interpretability, for in this field it is crucial to gain insight on the why of predictions, to assure that models are actually learning relevant features instead of spurious correlations. To address this, we propose a deep multi-scale convolutional architecture trained on the Medical Information Mart for Intensive Care III (MIMIC-III) for mortality prediction, and the use of concepts from coalitional game theory to construct visual explanations aimed to show how important these inputs are deemed by the network. Our results show our model attains state of the art performance while remaining interpretable. Supporting code can be found at https://github.com/williamcaicedo/ISeeU.
We aimed to assess clinical and laboratory differences between dengue and chikungunya in children <24 months of age in a comparative study. We collected retrospective clinical and laboratory data confirmed by NS1/IgM for dengue for 19 months (1 January 2013 to 17 August 2014). Prospective data for chikungunya confirmed by real-time polymerase chain reaction were collected for 4 months (22 September 2014-14 December 2014). Sensitivity and specificity [with 95% confidence interval (CI)] were reported for each disease diagnosis. A platelet count <150 000 cells/ml at emergency admission best characterized dengue, with a sensitivity of 67% (95% CI, 53-79) and specificity of 95% (95% CI, 82-99). The algorithm developed with classification and regression tree analysis showed a sensitivity of 93% (95% CI, 68-100) and specificity of 38% (95% CI, 9-76) to diagnose dengue. Our study provides potential differential characteristics between chikungunya and dengue in young children, especially low platelet counts.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.