Clinical knowledge graphs (KG) are often incomplete in their early stages of development, prone to human error, and have limited quality control. Due to continuous human updates to these clinical large-scale graphs, data errors are very high and costly. These errors originate in the form of biases, experiences, and assumptions leading to noise. Hence, enterprise-grade clinical knowledge graphs deployed in practical settings must be evaluated to remove errors and assist human maintainers to enrich the KG using predictive techniques. In this study, we propose a novel application of a neighborhood- based relationship entity embedding method to simultaneously predict both noisy and missing links between the disease and symptom entities in a clinical knowledge graph. The relationship or link embedding method is a derivation of a knowledge graph embedding framework. Our evaluations and experiments demonstrate that the proposed methodology achieves substantial improvements in comparison to state-of-the-art baseline methods in clinical KG link prediction. In practical settings, the clinical missing link and noise correction method has reduced the manual data review process for clinicians and also predicted potential relationships that existed between a disease and a symptom in the clinical KG.

Appearance features have been widely used in video anomaly detection even though they contain complex entangled factors. We propose a new method to model the normal patterns of human movements in surveillance video for anomaly detection using dynamic skeleton features. We decompose the skeletal movements into two sub-components: global body movement and local body posture. We model the dynamics and interaction of the coupled features in our novel Message-Passing Encoder-Decoder Recurrent Network. We observed that the decoupled features collaboratively interact in our spatio-temporal model to accurately identify human-related irregular events from surveillance video sequences. Compared to traditional appearance-based models, our method achieves superior outlier detection performance. Our model also offers “open-box” examination and decision explanation made possible by the semantically understandable features and a network architecture supporting interpretability.

Deep autoencoder has been extensively used for anomaly detection. Training on the normal data, the autoencoder is expected to produce higher reconstruction error for the abnormal inputs than the normal ones, which is adopted as a criterion for identifying anomalies. However, this assumption does not always hold in practice. It has been observed that sometimes the autoencoder "generalizes" so well that it can also reconstruct anomalies well, leading to the miss detection of anomalies. To mitigate this drawback for autoencoder based anomaly detector, we propose to augment the autoencoder with a memory module and develop an improved autoencoder called memory-augmented autoencoder, i.e. MemAE. Given an input, MemAE firstly obtains the encoding from the encoder and then uses it as a query to retrieve the most relevant memory items for reconstruction. At the training stage, the memory contents are updated and are encouraged to represent the prototypical elements of the normal data. At the test stage, the learned memory will be fixed, and the reconstruction is obtained from a few selected memory records of the normal data. The reconstruction will thus tend to be close to a normal sample. Thus the reconstructed errors on anomalies will be strengthened for anomaly detection. MemAE is free of assumptions on the data type and thus general to be applied to different tasks. Experiments on various datasets prove the excellent generalization and high effectiveness of the proposed MemAE.

Health analysis often involves prediction of multiple outcomes of mixed type. The existing work is restrictive to either a limited number or specific outcome types. We propose a framework for mixed-type multioutcome prediction. Our proposed framework proposes a cumulative loss function composed of a specific loss function for each outcome type-as an example, least square (continuous outcome), hinge (binary outcome), Poisson (count outcome), and exponential (nonnegative outcome). To model these outcomes jointly, we impose a commonality across the prediction parameters through a common matrix normal prior. The framework is formulated as iterative optimization problems and solved using an efficient block-coordinate descent method. We empirically demonstrate both scalability and convergence. We apply the proposed model to a synthetic dataset and then on two real-world cohorts: a cancer cohort and an acute myocardial infarction cohort collected over a two-year period. We predict multiple emergency-related outcomes-as example, future emergency presentations (binary), emergency admissions (count), emergency length of stay days (nonnegative), and emergency time to next admission day (nonnegative). We show that the predictive performance of the proposed model is better than several state-of-the-art baselines.

Mortality prediction of rare cancer types with a small number of high-dimensional samples is a challenging task. We propose a transfer learning model where both classes in rare cancers (target task) are modeled in a joint framework by transferring knowledge from the source task. The knowledge transfer is at the data level where only “related” data points are chosen to train the target task. Moreover, both positive and negative class in training enhances the discrimination power of the proposed framework. Overall, this approach boosts the generalization performance of target task with a small number of data points. The formulation of the proposed framework is convex and expressed as a primal problem. We convert this to a dual problem and efficiently solve by alternating direction multipliers method. Our experiments with both synthetic and three real-world datasets show that our framework outperforms state-of-the-art single-task, multi-task, and transfer learning baselines.

Mental illness has a deep impact on individuals, families, and by extension, society as a whole. Social networks allow individuals with mental disorders to communicate with others sufferers via online communities, providing an invaluable resource for studies on textual signs of psychological health problems. Mental disorders often occur in combinations, e.g., a patient with an anxiety disorder may also develop depression. This co-occurring mental health condition provides the focus for our work on classifying online communities with an interest in depression. For this, we have crawled a large body of 620 000 posts made by 80 000 users in 247 online communities. We have extracted the topics and psycholinguistic features expressed in the posts, using these as inputs to our model. Following a machine learning technique, we have formulated a joint modeling framework in order to classify mental health-related co-occurring online communities from these features. Finally, we performed empirical validation of the model on the crawled dataset where our model outperforms recent state-of-the-art baselines.

Electronic Medical Records (EMR) are increasingly used for risk prediction. EMR analysis is complicated by missing entries. There are two reasons - the “primary reason for admission” is included in EMR, but the co-morbidities (other chronic diseases) are left uncoded, and, many zero values in the data are accurate, reflecting that a patient has not accessed medical facilities. A key challenge is to deal with the peculiarities of this data - unlike many other datasets, EMR is sparse, reflecting the fact that patients have some, but not all diseases. We propose a novel model to fill-in these missing values, and use the new representation for prediction of key hospital events. To “fill-in” missing values, we represent the feature-patient matrix as a product of two low rank factors, preserving the sparsity property in the product. Intuitively, the product regularization allows sparse imputation of patient conditions reflecting common comorbidities across patients. We develop a scalable optimization algorithm based on Block coordinate descent method to find an optimal solution. We evaluate the proposed framework on two real world EMR cohorts: Cancer (7000 admissions) and Acute Myocardial Infarction (2652 admissions). Our result shows that the AUC for 3 months admission prediction is improved significantly from (0.741 to 0.786) for Cancer data and (0.678 to 0.724) for AMI data. We also extend the proposed method to a supervised model for predicting of multiple related risk outcomes (e.g. emergency presentations and admissions in hospital over 3, 6 and 12 months period) in an integrated framework. For this model, the AUC averaged over outcomes is improved significantly from (0.768 to 0.806) for Cancer data and (0.685 to 0.748) for AMI data.

Many vision problems deal with high-dimensional data, such as motion segmentation and face clustering. However, these high-dimensional data usually lie in a low-dimensional structure. Sparse representation is a powerful principle for solving a number of clustering problems with high-dimensional data. This principle is motivated from an ideal modeling of data points according to linear algebra theory. However, real data in computer vision are unlikely to follow the ideal model perfectly. In this paper, we exploit the mixed norm regularization for sparse subspace clustering. This regularization term is a convex combination of the ℓ1norm, which promotes sparsity at the individual level and the block norm ℓ2/1which promotes group sparsity. Combining these powerful regularization terms will provide a more accurate modeling, subsequently leading to a better solution for the affinity matrix used in sparse subspace clustering. This could help us achieve better performance on motion segmentation and face clustering problems. This formulation also caters for different types of data corruptions. We derive a provably convergent algorithm based on the alternating direction method of multipliers (ADMM) framework, which is computationally efficient, to solve the formulation. We demonstrate that this formulation outperforms other state-of-arts on both motion segmentation and face clustering.

We propose in this paper a novel sparse subspace clustering method that regularizes sparse subspace representation by exploiting the structural sharing between tasks and data points via group sparse coding. We derive simple, provably convergent, and computationally efficient algorithms for solving the proposed group formulations. We demonstrate the advantage of the framework on three challenging benchmark datasets ranging from medical record data to image and text clustering and show that they consistently outperforms rival methods.

We present a novel approach to improving subspace clustering by exploiting the spatial constraints. The new method encourages the sparse solution to be consistent with the spatial geometry of the tracked points, by embedding weights into the sparse formulation. By doing so, we are able to correct sparse representations in a principled manner without introducing much additional computational cost. We discuss alternative ways to treat the missing and corrupted data using the latest theory in robust lasso regression and suggest numerical algorithms so solve the proposed formulation. The experiments on the benchmark Johns Hopkins 155 dataset demonstrate that exploiting spatial constraints significantly improves motion segmentation.

We present a novel method for document clustering using sparse representation of documents in conjunction with spectral clustering. An ℓ1-norm optimization formulation is posed to learn the sparse representation of each document, allowing us to characterize the affinity between documents by considering the overall information instead of traditional pair wise similarities. This document affinity is encoded through a graph on which spectral clustering is performed. The decomposition into multiple subspaces allows documents to be part of a sub-group that shares a smaller set of similar vocabulary, thus allowing for cleaner clusters. Extensive experimental evaluations on two real-world datasets from Reuters-21578 and 20Newsgroup corpora show that our proposed method consistently outperforms state-of-the-art algorithms. Significantly, the performance improvement over other methods is prominent for this datasets.

We identify and formulate a novel problem: cross channel anomaly detection from multiple data channels. Cross channel anomalies are common amongst the individual channel anomalies, and are often portent of significant events. Using spectral approaches, we propose a two-stage detection method: anomaly detection at a single-channel level, followed by the detection of cross-channel anomalies from the amalgamation of single channel anomalies. Our mathematical analysis shows that our method is likely to reduce the false alarm rate. We demonstrate our method in two applications: document understanding with multiple text corpora, and detection of repeated anomalies in video surveillance. The experimental results consistently demonstrate the superior performance of our method compared with related state-of-art methods, including the one-class SVM and principal component pursuit. In addition, our framework can be deployed in a decentralized manner, lending itself for large scale data stream analysis.

This paper addresses a major challenge in data mining applications where the full information about the underlying processes, such as sensor networks or large online database, cannot be practically obtained due to physical limitations such as low bandwidth or memory, storage, or computing power. Motivated by the recent theory on direct information sampling called compressed sensing (CS), we propose a framework for detecting anomalies from these large-scale data mining applications where the full information is not practically possible to obtain. Exploiting the fact that the intrinsic dimension of the data in these applications are typically small relative to the raw dimension and the fact that compressed sensing is capable of capturing most information with few measurements, our work show that spectral methods that used for volume anomaly detection can be directly applied to the CS data with guarantee on performance. Our theoretical contributions are supported by extensive experimental results on large datasets which show satisfactory performance.