Accurate seizure prediction will transform epilepsy management by offering warnings to patients or triggering interventions. However, state-of-the-art algorithm design relies on accessing adequate long-term data. Crowd-sourcing ecosystems leverage quality data to enable cost-effective, rapid development of predictive algorithms. A crowd-sourcing ecosystem for seizure prediction is presented involving an international competition, a follow-up held-out data evaluation, and an online platform, Epilepsyecosystem.org, for yielding further improvements in prediction performance. Crowd-sourced algorithms were obtained via the 'Melbourne-University AES-MathWorks-NIH Seizure Prediction Challenge' conducted at kaggle.com. Long-term continuous intracranial electroencephalography (iEEG) data (442 days of recordings and 211 lead seizures per patient) from prediction-resistant patients who had the lowest seizure prediction performances from the NeuroVista Seizure Advisory System clinical trial were analysed. Contestants (646 individuals in 478 teams) from around the world developed algorithms to distinguish between 10-min inter-seizure versus pre-seizure data clips. Over 10 000 algorithms were submitted. The top algorithms as determined by using the contest data were evaluated on a much larger held-out dataset. The data and top algorithms are available online for further investigation and development. The top performing contest entry scored 0.81 area under the classification curve. The performance reduced by only 6.7% on held-out data. Many other teams also showed high prediction reproducibility. Pseudo-prospective evaluation demonstrated that many algorithms, when used alone or weighted by circadian information, performed better than the benchmarks, including an average increase in sensitivity of 1.9 times the original clinical trial sensitivity for matched time in warning. These results indicate that clinically-relevant seizure prediction is possible in a wider range of patients than previously thought possible. Moreover, different algorithms performed best for different patients, supporting the use of patient-specific algorithms and long-term monitoring. The crowd-sourcing ecosystem for seizure prediction will enable further worldwide community study of the data to yield greater improvements in prediction performance by way of competition, collaboration and synergism.10.1093/brain/awy210_video1awy210media15817489051001.

Abstract. Discharge summaries and other free-text reports in healthcare transfer information between working shifts and geographic locations. Patients are likely to have difficulties in understanding their content, because of their medical jargon, non-standard abbreviations, and ward-specific idioms. This paper reports on an evaluation lab with an aim to support the continuum of care by developing methods and resources that make clinical reports in English easier to understand for patients, and which helps them in finding information related to their condition. This ShARe/CLEFeHealth2013 lab offered student mentoring and shared tasks: identification and normalisation of disorders (1a and 1b) and normalisation of abbreviations and acronyms (2) Overview of the ShARe/CLEF eHealth Evaluation Lab 2013 213 reports with respect to terminology standards in healthcare as well as information retrieval (3) to address questions patients may have when reading clinical reports. The focus on patients' information needs as opposed to the specialised information needs of physicians and other healthcare workers was the main feature of the lab distinguishing it from previous shared tasks. De-identified clinical reports for the three tasks were from US intensive care and originated from the MIMIC II database. Other text documents for Task 3 were from the Internet and originated from the Khresmoi project. Task 1 annotations originated from the ShARe annotations. For Tasks 2 and 3, new annotations, queries, and relevance assessments were created. 64, 56, and 55 people registered their interest in Tasks 1, 2, and 3, respectively. 34 unique teams (3 members per team on average) participated with 22, 17, 5, and 9 teams in Tasks 1a, 1b, 2 and 3, respectively. The teams were from Australia, China, France, India, Ireland, Republic of Korea, Spain, UK, and USA. Some teams developed and used additional annotations, but this strategy contributed to the system performance only in Task 2. The best systems had the F1 score of 0.75 in Task 1a; Accuracies of 0.59 and 0.72 in Tasks 1b and 2; and Precision at 10 of 0.52 in Task 3. The results demonstrate the substantial community interest and capabilities of these systems in making clinical reports easier to understand for patients. The organisers have made data and tools available for future research and development.

Pseudo-relevance feedback (PRF) via query-expansion has been proven to be effective in many information retrieval (IR) tasks. In most existing work, the top-ranked documents from an initial search are assumed to be relevant and used for PRF. One problem with this approach is that one or more of the top retrieved documents may be non-relevant, which can introduce noise into the feedback process. Besides, existing methods generally do not take into account the significantly different types of queries that are often entered into an IR system. Intuitively, Wikipedia can be seen as a large, manually edited document collection which could be exploited to improve document retrieval effectiveness within PRF. It is not obvious how we might best utilize information from Wikipedia in PRF, and to date, the potential of Wikipedia for this task has been largely unexplored. In our work, we present a systematic exploration of the utilization of Wikipedia in PRF for query dependent expansion. Specifically, we classify TREC topics into three categories based on Wikipedia: 1) entity queries, 2) ambiguous queries, and 3) broader queries. We propose and study the effectiveness of three methods for expansion term selection, each modeling the Wikipedia based pseudo-relevance information from a different perspective. We incorporate the expansion terms into the original query and use language modeling IR to evaluate these methods. Experiments on four TREC test collections, including the large web collection GOV2, show that retrieval performance of each type of query can be improved.In addition, we demonstrate that the proposed method outperforms the baseline relevance model in terms of precision and robustness.

No abstract

been shown to operate as high-speed photodetectors [3] with response times comparable to conventional silicon-based devices, but the absence of a bandgap and lack of significant gain mechanism limits their use for ultrasensitive light detection. Hybrid structures of graphene with semiconductor materials such as quantum dots, [4][5][6] chlorophyll molecules, [7] and MoS 2 [8][9][10] have been shown to enhance light absorption and provide an internal gain mechanism. However, these implementations typically have a limited operational bandwidth of less than 10 Hz which hampers their use in real world applications.Slow response times in these systems are produced by the long-lived trapping of charges, often manifested as hysteresis in gate-voltage sweeps. This has been observed in organic, carbon nanotubes, graphene, and more recently in transitionmetal dichalcogenide (TMD) field-effect transistors and is typically attributed to unavoidable intrinsic and/or extrinsic charge traps, e.g., SiO 2 surface states [11][12][13][14] and atmospheric contamination. [12,13,[15][16][17] To reduce the impact of such traps, various solutions have been explored including gate-voltage pulses, [11,18,19] vacuum annealing, [20,21] and ionic-liquid gating. [22,23] Although ionic-liquid gating has been utilized in WS 2 phototransistors [24] and MoTe 2 -graphene photodetectors, [25] the beneficial effect of poly mer gating on the performance of photodetectors consisting of atomically thin heterostructures has not yet been explored.In this work, we report the first study of WS 2 -graphene heterostructure photodetectors with an ionic-polymer gate. We demonstrate a gate-tunable responsivity up to 10 6 A W −1 , which is comparable with other heterostructure devices, [4][5][6][7]9,10] and surpasses that of graphene or TMD photodetectors by at least four orders of magnitude. Our devices reach a −3 dB bandwidth of 1.5 kHz, without the need for gatevoltage pulses, leading to sub-millisecond rise and fall times. The observed 10 3 -fold increase of photodetection bandwidth, when compared to other heterostructure photodetectors, is enabled by the enhanced screening properties of the mobile ions in our ionic polymer top gate, which act to compensate the charge traps limiting the speed of previous devices. Our devices have a detectivity of D* = 3.8 × 10 11 Jones, which is approaching that of single-photon counters, and are able to operate on a broad spectral range (400-700 nm). These properties make ionic-polymer-gated WS 2 -graphene photodetectors highly suitable for video-frame-rate imaging applicationsThe combination of graphene with semiconductor materials in heterostructure photodetectors enables amplified detection of femtowatt light signals using micrometer-scale electronic devices. Presently, long-lived charge traps limit the speed of such detectors, and impractical strategies, e.g., the use of large gatevoltage pulses, have been employed to achieve bandwidths suitable for applications such as video-frame-rate imaging. Here, atomically thin gr...