KDD : proceedings. International Conference on Knowledge Discovery & Data Mining最新文献

Various deep learning models have recently been applied to predictive modeling of Electronic Health Records (EHR). In medical claims data, which is a particular type of EHR data, each patient is represented as a sequence of temporally ordered irregularly sampled visits to health providers, where each visit is recorded as an unordered set of medical codes specifying patient's diagnosis and treatment provided during the visit. Based on the observation that different patient conditions have different temporal progression patterns, in this paper we propose a novel interpretable deep learning model, called Timeline. The main novelty of Timeline is that it has a mechanism that learns time decay factors for every medical code. This allows the Timeline to learn that chronic conditions have a longer lasting impact on future visits than acute conditions. Timeline also has an attention mechanism that improves vector embeddings of visits. By analyzing the attention weights and disease progression functions of Timeline, it is possible to interpret the predictions and understand how risks of future visits change over time. We evaluated Timeline on two large-scale real world data sets. The specific task was to predict what is the primary diagnosis category for the next hospital visit given previous visits. Our results show that Timeline has higher accuracy than the state of the art deep learning models based on RNN. In addition, we demonstrate that time decay factors and attentions learned by Timeline are in accord with the medical knowledge and that Timeline can provide a useful insight into its predictions.

Discovery of causal relationships from observational data is a fundamental problem. Roughly speaking, there are two types of methods for causal discovery, constraint-based ones and score-based ones. Score-based methods avoid the multiple testing problem and enjoy certain advantages compared to constraint-based ones. However, most of them need strong assumptions on the functional forms of causal mechanisms, as well as on data distributions, which limit their applicability. In practice the precise information of the underlying model class is usually unknown. If the above assumptions are violated, both spurious and missing edges may result. In this paper, we introduce generalized score functions for causal discovery based on the characterization of general (conditional) independence relationships between random variables, without assuming particular model classes. In particular, we exploit regression in RKHS to capture the dependence in a non-parametric way. The resulting causal discovery approach produces asymptotically correct results in rather general cases, which may have nonlinear causal mechanisms, a wide class of data distributions, mixed continuous and discrete data, and multidimensional variables. Experimental results on both synthetic and real-world data demonstrate the efficacy of our proposed approach.

This paper presents a new method, which we call SUSTain, that extends real-valued matrix and tensor factorizations to data where values are integers. Such data are common when the values correspond to event counts or ordinal measures. The conventional approach is to treat integer data as real, and then apply real-valued factorizations. However, doing so fails to preserve important characteristics of the original data, thereby making it hard to interpret the results. Instead, our approach extracts factor values from integer datasets as scores that are constrained to take values from a small integer set. These scores are easy to interpret: a score of zero indicates no feature contribution and higher scores indicate distinct levels of feature importance. At its core, SUSTain relies on: a) a problem partitioning into integer-constrained subproblems, so that they can be optimally solved in an efficient manner; and b) organizing the order of the subproblems' solution, to promote reuse of shared intermediate results. We propose two variants, SUSTain _M and SUSTain _T , to handle both matrix and tensor inputs, respectively. We evaluate SUSTain against several state-of-the-art baselines on both synthetic and real Electronic Health Record (EHR) datasets. Comparing to those baselines, SUSTain shows either significantly better fit or orders of magnitude speedups that achieve a comparable fit (up to 425× faster). We apply SUSTain to EHR datasets to extract patient phenotypes (i.e., clinically meaningful patient clusters). Furthermore, 87% of them were validated as clinically meaningful phenotypes related to heart failure by a cardiologist.

Many important problems can be modeled as a system of interconnected entities, where each entity is recording time-dependent observations or measurements. In order to spot trends, detect anomalies, and interpret the temporal dynamics of such data, it is essential to understand the relationships between the different entities and how these relationships evolve over time. In this paper, we introduce the time-varying graphical lasso (TVGL), a method of inferring time-varying networks from raw time series data. We cast the problem in terms of estimating a sparse time-varying inverse covariance matrix, which reveals a dynamic network of interdependencies between the entities. Since dynamic network inference is a computationally expensive task, we derive a scalable message-passing algorithm based on the Alternating Direction Method of Multipliers (ADMM) to solve this problem in an efficient way. We also discuss several extensions, including a streaming algorithm to update the model and incorporate new observations in real time. Finally, we evaluate our TVGL algorithm on both real and synthetic datasets, obtaining interpretable results and outperforming state-of-the-art baselines in terms of both accuracy and scalability.

In this paper, we present a new approach to learning cascaded classifiers for use in computing environments that involve networks of heterogeneous and resource-constrained, low-power embedded compute and sensing nodes. We present a generalization of the classical linear detection cascade to the case of tree-structured cascades where different branches of the tree execute on different physical compute nodes in the network. Different nodes have access to different features, as well as access to potentially different computation and energy resources. We concentrate on the problem of jointly learning the parameters for all of the classifiers in the cascade given a fixed cascade architecture and a known set of costs required to carry out the computation at each node. To accomplish the objective of joint learning of all detectors, we propose a novel approach to combining classifier outputs during training that better matches the hard cascade setting in which the learned system will be deployed. This work is motivated by research in the area of mobile health where energy efficient real time detectors integrating information from multiple wireless on-body sensors and a smart phone are needed for real-time monitoring and the delivery of just-in-time adaptive interventions. We evaluate our framework on mobile sensor-based human activity recognition and mobile health detector learning problems.

Tensor factorization models offer an effective approach to convert massive electronic health records into meaningful clinical concepts (phenotypes) for data analysis. These models need a large amount of diverse samples to avoid population bias. An open challenge is how to derive phenotypes jointly across multiple hospitals, in which direct patient-level data sharing is not possible (e.g., due to institutional policies). In this paper, we developed a novel solution to enable federated tensor factorization for computational phenotyping without sharing patient-level data. We developed secure data harmonization and federated computation procedures based on alternating direction method of multipliers (ADMM). Using this method, the multiple hospitals iteratively update tensors and transfer secure summarized information to a central server, and the server aggregates the information to generate phenotypes. We demonstrated with real medical datasets that our method resembles the centralized training model (based on combined datasets) in terms of accuracy and phenotypes discovery while respecting privacy.

Deep learning methods exhibit promising performance for predictive modeling in healthcare, but two important challenges remain: Data insufficiency: Often in healthcare predictive modeling, the sample size is insufficient for deep learning methods to achieve satisfactory results.Interpretation: The representations learned by deep learning methods should align with medical knowledge. To address these challenges, we propose GRaph-based Attention Model (GRAM) that supplements electronic health records (EHR) with hierarchical information inherent to medical ontologies. Based on the data volume and the ontology structure, GRAM represents a medical concept as a combination of its ancestors in the ontology via an attention mechanism. We compared predictive performance (i.e. accuracy, data needs, interpretability) of GRAM to various methods including the recurrent neural network (RNN) in two sequential diagnoses prediction tasks and one heart failure prediction task. Compared to the basic RNN, GRAM achieved 10% higher accuracy for predicting diseases rarely observed in the training data and 3% improved area under the ROC curve for predicting heart failure using an order of magnitude less training data. Additionally, unlike other methods, the medical concept representations learned by GRAM are well aligned with the medical ontology. Finally, GRAM exhibits intuitive attention behaviors by adaptively generalizing to higher level concepts when facing data insufficiency at the lower level concepts.

Hypothesis generation is becoming a crucial time-saving technique which allows biomedical researchers to quickly discover implicit connections between important concepts. Typically, these systems operate on domain-specific fractions of public medical data. MOLIERE, in contrast, utilizes information from over 24.5 million documents. At the heart of our approach lies a multi-modal and multi-relational network of biomedical objects extracted from several heterogeneous datasets from the National Center for Biotechnology Information (NCBI). These objects include but are not limited to scientific papers, keywords, genes, proteins, diseases, and diagnoses. We model hypotheses using Latent Dirichlet Allocation applied on abstracts found near shortest paths discovered within this network, and demonstrate the effectiveness of MOLIERE by performing hypothesis generation on historical data. Our network, implementation, and resulting data are all publicly available for the broad scientific community.

We present an approach for improving the performance of complex knowledge-based processes by providing data-driven step-by-step recommendations. Our framework uses the associations between similar historic process performances and contextual information to determine the prototypical way of enacting the process. We introduce a novel similarity metric for grouping traces into clusters that incorporates temporal information about activity performance and handles concurrent activities. Our data-driven recommender system selects the appropriate prototype performance of the process based on user-provided context attributes. Our approach for determining the prototypes discovers the commonly performed activities and their temporal relationships. We tested our system on data from three real-world medical processes and achieved recommendation accuracy up to an F1 score of 0.77 (compared to an F1 score of 0.37 using ZeroR) with 63.2% of recommended enactments being within the first five neighbors of the actual historic enactments in a set of 87 cases. Our framework works as an interactive visual analytic tool for process mining. This work shows the feasibility of data-driven decision support system for complex knowledge-based processes.

Evaluating whether machines improve on human performance is one of the central questions of machine learning. However, there are many domains where the data is selectively labeled in the sense that the observed outcomes are themselves a consequence of the existing choices of the human decision-makers. For instance, in the context of judicial bail decisions, we observe the outcome of whether a defendant fails to return for their court appearance only if the human judge decides to release the defendant on bail. This selective labeling makes it harder to evaluate predictive models as the instances for which outcomes are observed do not represent a random sample of the population. Here we propose a novel framework for evaluating the performance of predictive models on selectively labeled data. We develop an approach called contraction which allows us to compare the performance of predictive models and human decision-makers without resorting to counterfactual inference. Our methodology harnesses the heterogeneity of human decision-makers and facilitates effective evaluation of predictive models even in the presence of unmeasured confounders (unobservables) which influence both human decisions and the resulting outcomes. Experimental results on real world datasets spanning diverse domains such as health care, insurance, and criminal justice demonstrate the utility of our evaluation metric in comparing human decisions and machine predictions.