Randomized controlled trials (RCTs) offer a clear causal interpretation of treatment effects, but are inefficient in terms of information gain per patient. Moreover, because they are intended to test cohort-level effects, RCTs rarely provide information to support precision medicine, which strives to choose the best treatment for an individual patient. If causal information could be efficiently extracted from widely available real-world data, the rapidity of treatment validation could be increased, and its costs reduced. Moreover, inferences could be made across larger, more diverse patient populations. We created a "virtual trial" by fitting a multilevel Bayesian survival model to treatment and outcome records self-reported by 451 brain cancer patients. The model recovers group-level treatment effects comparable to RCTs representing over 3200 patients. The model additionally discovers the feature-treatment interactions needed to make individual-level predictions for precision medicine. By learning from heterogeneous real-world data, virtual trials can generate more causal estimates with fewer patients than RCTs, and they can do so without artificially limiting the patient population. This demonstrates the value of virtual trials as a complement to large randomized controlled trials, especially in highly heterogeneous or rare diseases.

BACKGROUND: We describe a prototype implementation of a platform that could underlie a Precision Oncology Rapid Learning system. RESULTS: We describe the prototype platform, and examine some important issues and details. In the Appendix we provide a complete walk-through of the prototype platform. CONCLUSIONS: The design choices made in this implementation rest upon ten constitutive hypotheses, which, taken together, define a particular view of how a rapid learning medical platform might be defined, organized, and implemented.

Users routinely disclose personal information to obtain the benefits of Personalized Online Services. As a result, personal data is distributed across uncounted and unaccountable remote databases. Data mismanagement, as well as privacy and security flaws undermine individuals' control and privacy of their personal data. Yet revealing detailed private data does not necessarily yield useful service personalization; often this functionality is only modestly dependent upon the accuracy of user-supplied input. We demonstrate knowledge-based input generalization wherein systematically perturbed user data is supplied to a personalized service to gain forward privacy for the user, while retaining the utility of the service's results.

Window management research has aimed to leverage users' tasks to organize the growing number of open windows in a useful manner. This research has largely assumed task classifications to be binary -- either a window is in a task, or not -- and context-independent. We suggest that the continual evolution of tasks can invalidate this approach and instead propose a fuzzy association model in which windows are related to one another by varying degrees. Task groupings are an emergent property of our approach. To support the association model, we introduce the WindowRank algorithm and its use in determining window association. We then describe Taskposé, a prototype window switch visualization embodying these ideas, and report on a week-long user study of the system.

UNLABELLED: BioLingua is an interactive, web-based programming environment that enables biologists to analyze biological systems by combining knowledge and data through direct end-user programming. BioLingua embeds a mature symbolic programming language in a frame-based knowledge environment, integrating genomic and pathway knowledge about a class of similar organisms. The BioLingua language provides interfaces to numerous state-of-the-art bioinformatic tools, making these available as an integrated package through the novel use of web-based programmability and an integrated Wiki-based community code and data store. The pilot instantiation of BioLingua, which has been developed in collaboration with several cyanobacteriologists, integrates knowledge about a subset of cyanobacteria with the Gene Ontology, KEGG and BioCyc knowledge bases. We introduce the BioLingua concept, architecture and language, and give several examples of its use in complex analyses. AVAILABILITY: Extensive documentation is available online at http://nostoc.stanford.edu/Docs/index.html CONTACT: [email protected]

Department of Plant Biology, The Carnegie Instution of Washington, Stanford, CA 94305, USA

In an instructionless environment, there are neither teachers nor books. The only feedback comes from interaction with the target. All information appears from within the subject or from observation of the environment. In this setting, subjects rely upon experimentation to develop an understanding of the target. They form hypotheses by analogy or inference and test these hypotheses via experiments of calibration, replication, confirmation, exploration, and discrimination.