BACKGROUND: The timeliness of detection of a sepsis incidence in progress is a crucial factor in the outcome for the patient. Machine learning models built from data in electronic health records can be used as an effective tool for improving this timeliness, but so far, the potential for clinical implementations has been largely limited to studies in intensive care units. This study will employ a richer data set that will expand the applicability of these models beyond intensive care units. Furthermore, we will circumvent several important limitations that have been found in the literature: (1) Model evaluations neglect the clinical consequences of a decision to start, or not start, an intervention for sepsis. (2) Models are evaluated shortly before sepsis onset without considering interventions already initiated. (3) Machine learning models are built on a restricted set of clinical parameters, which are not necessarily measured in all departments. (4) Model performance is limited by current knowledge of sepsis, as feature interactions and time dependencies are hard-coded into the model. METHODS: In this study, we present a model to overcome these shortcomings using a deep learning approach on a diverse multicenter data set. We used retrospective data from multiple Danish hospitals over a seven-year period. Our sepsis detection system is constructed as a combination of a convolutional neural network and a long short-term memory network. We assess model quality by standard concepts of accuracy as well as clinical usefulness, and we suggest a retrospective assessment of interventions by looking at intravenous antibiotics and blood cultures preceding the prediction time. RESULTS: Results show performance ranging from AUROC 0.856 (3 h before sepsis onset) to AUROC 0.756 (24 h before sepsis onset). Evaluating the clinical utility of the model, we find that a large proportion of septic patients did not receive antibiotic treatment or blood culture at the time of the sepsis prediction, and the model could, therefore, facilitate such interventions at an earlier point in time. CONCLUSION: We present a deep learning system for early detection of sepsis that can learn characteristics of the key factors and interactions from the raw event sequence data itself, without relying on a labor-intensive feature extraction work. Our system outperforms baseline models, such as gradient boosting, which rely on specific data elements and therefore suffer from many missing values in our dataset.

In this paper, we explore the problem of classification where class labels exhibit a hierarchical tree structure.Many multiclass classification algorithms assume a flat label space, where hierarchical structures are ignored.We take advantage of hierarchical structures and the interdependencies between labels.In our setting, labels are structured in a product and service hierarchy, with a focus on spend analysis.We define a novel distance measure between classes in a hierarchical label tree.This measure penalizes paths though high levels in the hierarchy.We use a known classification algorithm that aims to minimize distance between labels, given any symmetric distance measure.The approach is global in that it constructs a single classifier for an entire hierarchy by embedding hierarchical distances into a lower-dimensional space.Results show that combining our novel distance measure with the classifier induces a trade-off between accuracy and lower hierarchical distances on misclassifications.This is useful in a setting where erroneous predictions vastly change the context of a label.

Remarkably easy implementation and guaranteed convergence has made the EM algorithm one of the most used algorithms for mixture modeling. On the downside, the E-step is linear in both the sample size and the number of mixture components, making it impractical for large-scale data. Based on the variational EM framework, we propose a fast alternative that uses component-specific data partitions to obtain a sub-linear E-step in sample size, while the algorithm still maintains provable convergence. Our approach builds on previous work, but is significantly faster and scales much better in the number of mixture components. We demonstrate this speedup by experiments on large-scale synthetic and real data.

The small physical size of mobile devices imposes dramatic restrictions on the user interface (UI). With the ever increasing capacity of these devices as well as access to large online stores it becomes increasingly important to help the user select a particular item efficiently. Thus, we propose binary search with character pinning, where users can constrain their search to match selected prefix characters while making simple binary decisions about the position of their intended item in the lexicographic order. The underlying index for our method is based on a ternary search tree that is optimal under certain user-oriented constraints. To better scale to larger indexes, we analyze several heuristics that rapidly construct good trees. A user study demonstrates that our method helps users conduct rapid searches, using less keystrokes, compared to other methods.

As users enter web queries, real-time query expansion (RTQE) interfaces offer suggestions based on an index garnered from query logs. In selecting a suggestion, users can potentially reduce keystrokes, which can be very beneficial on mobile devices with deficient input means. Unfortunately, RTQE interfaces typically provide little assistance when only parts of an intended query appear among the suggestion choices. In this paper, we introduce Phrase Builder, an RTQE interface that reduces keystrokes by facilitating the selection of individual query words and by leveraging back-off query techniques to offer completions for out-of-index queries. We describe how we implemented a small memory footprint index and retrieval algorithm, and discuss lessons learned from three versions of the user interface, which was iteratively designed through user studies. Compared to standard auto-completion and typing, the last version of Phrase Builder reduced more keystrokes-per-character, was perceived to be faster, and was overall preferred by users.

Internet usage on mobile devices continues to grow as users seek anytime, anywhere access to information. Because users frequently search for businesses, directory assistance has been the focus of many voice search applications utilizing speech as the primary input modality. Unfortunately, mobile settings often contain noise which degrades performance. As such, we present Search Vox, a mobile search interface that not only facilitates touch and text refinement whenever speech fails, but also allows users to assist the recognizer via text hints. Search Vox can also take advantage of any partial knowledge users may have about the business listing by letting them express their uncertainty in an intuitive way using verbal wildcards. In simulation experiments conducted on real voice search data, leveraging multimodal refinement resulted in a 28% relative reduction in error rate. Providing text hints along with the spoken utterance resulted in even greater relative reduction, with dramatic gains in recovery for each additional character.

Suppose you are on a mobile device with no keyboard (e.g., a cell phone) and you want to perform a "near me" search. Where is the nearest pizza? How do you enter queries quickly? T9? The Wild Thing encourages users to enter patterns with implicit and explicit wild cards (regular expressions). The search engine uses Microsoft Local Live logs to find the most likely queries for a particular location. For example, 7#6 is short-hand for the regular expression: /^[PQRS].*[ ][MNO].*/, which matches "post office" in many places (but "Space Needle" in Seattle). Some queries are more local than others. Pizza is likely everywhere, whereas "Boeing Company," is very likely in Seattle and Chicago, moderately likely nearby, and somewhat likely elsewhere. Smoothing is important. Not every query is observed everywhere.