IMPORTANCE Mammography screening currently relies on subjective human interpretation. Artificial intelligence (AI) advances could be used to increase mammography screening accuracy by reducing missed cancers and false positives. OBJECTIVE To evaluate whether AI can overcome human mammography interpretation limitations with a rigorous, unbiased evaluation of machine learning algorithms. DESIGN, SETTING, AND PARTICIPANTS In this diagnostic accuracy study conducted between September 2016 and November 2017, an international, crowdsourced challenge was hosted to foster AI algorithm development focused on interpreting screening mammography. More than 1100 participants comprising 126 teams from 44 countries participated. Analysis began November 18, 2016. MAIN OUTCOMES AND MEASUREMENTS Algorithms used images alone (challenge 1) or combined images, previous examinations (if available), and clinical and demographic risk factor data (challenge 2) and output a score that translated to cancer yes/no within 12 months. Algorithm accuracy for breast cancer detection was evaluated using area under the curve and algorithm specificity compared with radiologists' specificity with radiologists' sensitivity set at 85.9% (United States) and 83.9% (Sweden). An ensemble method aggregating top-performing AI algorithms and radiologists' recall assessment was developed and evaluated. RESULTS Overall, 144 231 screening mammograms from 85 580 US women (952 cancer positive Յ12 months from screening) were used for algorithm training and validation. A second independent validation cohort included 166 578 examinations from 68 008 Swedish women (780 cancer positive). The top-performing algorithm achieved an area under the curve of 0.858 (United States) and 0.903 (Sweden) and 66.2% (United States) and 81.2% (Sweden) specificity at the radiologists' sensitivity, lower than community-practice radiologists' specificity of 90.5% (United States) and 98.5% (Sweden). Combining top-performing algorithms and US radiologist assessments resulted in a higher area under the curve of 0.942 and achieved a significantly improved specificity (92.0%) at the same sensitivity. CONCLUSIONS AND RELEVANCE While no single AI algorithm outperformed radiologists, an ensemble of AI algorithms combined with radiologist assessment in a single-reader screening environment improved overall accuracy. This study underscores the potential of using machine (continued)

Digital Preservation deals with ensuring that digital data stored today can be read and interpreted tens or hundreds of years from now. At the heart of any solution to the preservation problem lies a storage component. This paper characterizes the requirements for such a component, defines its desirable properties and presents the need for preservation-aware storage systems. Our research is conducted as part of CASPAR , a new European Union (EU) integrated project on the preservation of data for very long periods of time. The position presented was developed while designing the storage foundation for the CASPAR software framework.

The use of Extensible Markup Language (XML) to implement data sharing and semantic interoperability in healthcare and life sciences has become ubiquitous in recent years. Because in many areas there was no preexisting data format, XML has been readily embraced and is having a great impact. Biomedical data is very heterogeneous, varying from administrative information to clinical data, and recently to genomic data, making information exchange a great challenge. In particular, it is hard to achieve semantic interoperability among disparate and dispersed systems-a common constellation in the fragmented world of healthcare. Moreover, the emerging patient-centric and information-based medicine approach is posing another challenge-the development and use of an integrated health record for each patient. This means that diverse data from many systems has to be generated, integrated, and become available at the point of care. This paper presents the case that XML is becoming the integration ''glue'' for biomedical information interoperability, which can lead to improvements in pharmaceuticals, genomic-based clinical research, and personalized medicine, which, for the first time, can be fine-tuned to serve individuals through their longitudinal electronic health records.