Large, labeled datasets have driven deep learning methods to achieve expert-level performance on a variety of medical imaging tasks. We present CheXpert, a large dataset that contains 224,316 chest radiographs of 65,240 patients. We design a labeler to automatically detect the presence of 14 observations in radiology reports, capturing uncertainties inherent in radiograph interpretation. We investigate different approaches to using the uncertainty labels for training convolutional neural networks that output the probability of these observations given the available frontal and lateral radiographs. On a validation set of 200 chest radiographic studies which were manually annotated by 3 board-certified radiologists, we find that different uncertainty approaches are useful for different pathologies. We then evaluate our best model on a test set composed of 500 chest radiographic studies annotated by a consensus of 5 board-certified radiologists, and compare the performance of our model to that of 3 additional radiologists in the detection of 5 selected pathologies. On Cardiomegaly, Edema, and Pleural Effusion, the model ROC and PR curves lie above all 3 radiologist operating points. We release the dataset to the public as a standard benchmark to evaluate performance of chest radiograph interpretation models. 1
Gratitude is conceptualized as a moral affect that is analogous to other moral emotions such as empathy and guilt. Gratitude has 3 functions that can be conceptualized as morally relevant: (a) a moral barometer function (i.e., it is a response to the perception that one has been the beneficiary of another person's moral actions); (b) a moral motive function (i.e., it motivates the grateful person to behave prosocially toward the benefactor and other people); and (c) a moral reinforcer function (i.e., when expressed, it encourages benefactors to behave morally in the future). The personality and social factors that are associated with gratitude are also consistent with a conceptualization of gratitude as an affect that is relevant to people's cognitions and behaviors in the moral domain.
Psychologists' emerging interest in spirituality and religion as well as the relevance of each phenomenon to issues of psychological importance requires an understanding of the fundamental characteristics of each construct. On the basis of both historical considerations and a limited but growing empirical literature, we caution against viewing spirituality and religiousness as incompatible and suggest that the common tendency to polarize the terms simply as individual vs. institutional or ′good′ vs. ′bad′ is not fruitful for future research. Also cautioning against the use of restrictive, narrow definitions or overly broad definitions that can rob either construct of its distinctive characteristics, we propose a set of criteria that recognizes the constructs' conceptual similarities and dissimilarities. Rather than trying to force new and likely unsuccessful definitions, we offer these criteria as benchmarks for judging the value of existing definitions.
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.