Early detection is a crucial goal in the study of Alzheimer's Disease (AD). In this work, we describe several techniques to boost the performance of 3D convolutional neural networks trained to detect AD using structural brain MRI scans. Specifically, we provide evidence that (1) instance normalization outperforms batch normalization, (2) early spatial downsampling negatively affects performance, (3) widening the model brings consistent gains while increasing the depth does not, and (4) incorporating age information yields moderate improvement. Together, these insights yield an increment of approximately 14% in test accuracy over existing models when distinguishing between patients with AD, mild cognitive impairment, and controls in the ADNI dataset. Similar performance is achieved on an independent dataset.

Conditional Random Fields (CRF) are frequently applied for labeling and segmenting sequence data. Morency et al. (2007) introduced hidden state variables in a labeled CRF structure in order to model the latent dynamics within class labels, thus improving the labeling performance. Such a model is known as Latent-Dynamic CRF (LDCRF). We present Factored LDCRF (FLDCRF), a structure that allows multiple latent dynamics of the class labels to interact with each other. Including such latent-dynamic interactions leads to improved labeling performance on single-label and multi-label sequence modeling tasks. We apply our FLDCRF models on two single-label (one nested cross-validation) and one multi-label sequence tagging (nested cross-validation) experiments across two different datasets - UCI gesture phase data and UCI opportunity data. FLDCRF outperforms all state-of-the-art sequence models, i.e., CRF, LDCRF, LSTM, LSTM-CRF, Factorial CRF, Coupled CRF and a multi-label LSTM model in all our experiments. In addition, LSTM based models display inconsistent performance across validation and test data, and pose diffculty to select models on validation data during our experiments. FLDCRF offers easier model selection, consistency across validation and test performance and lucid model intuition. FLDCRF is also much faster to train compared to LSTM, even without a GPU. FLDCRF outshines the best LSTM model by ~4% on a single-label task on UCI gesture phase data and outperforms LSTM performance by ~2% on average across nested cross-validation test sets on the multi-label sequence tagging experiment on UCI opportunity data. The idea of FLDCRF can be extended to joint (multi-agent interactions) and heterogeneous (discrete and continuous) state space models.

Sleep stage classification constitutes an important element of sleep disorder diagnosis. It relies on the visual inspection of polysomnography records by trained sleep technologists. Automated approaches have been designed to alleviate this resource-intensive task. However, such approaches are usually compared to a single human scorer annotation despite an inter-rater agreement of about 85 % only. The present study introduces two publicly-available datasets, DOD-H including 25 healthy volunteers and DOD-O including 55 patients suffering from obstructive sleep apnea (OSA). Both datasets have been scored by 5 sleep technologists from different sleep centers. We developed a framework to compare automated approaches to a consensus of multiple human scorers. Using this framework, we benchmarked and compared the main literature approaches. We also developed and benchmarked a new deep learning method, SimpleSleepNet, inspired by current state-of-the-art. We demonstrated that many methods can reach human-level performance on both datasets. SimpleSleepNet achieved an F1 of 89.9 % vs 86.8 % on average for human scorers on DOD-H, and an F1 of 88.3 % vs 84.8 % on DOD-O. Our study highlights that using state-of-the-art automated sleep staging outperforms human scorers performance for healthy volunteers and patients suffering from OSA. Consideration could be made to use automated approaches in the clinical setting.

Pathology reports contain useful information such as the main involved organ, diagnosis, etc. These information can be identified from the free text reports and used for large-scale statistical analysis or serve as annotation for other modalities such as pathology slides images. However, manual classification for a huge number of reports on multiple tasks is labor-intensive. In this paper, we have developed an automatic text classifier based on BERT and we propose a human-centric metric to evaluate the model. According to the model confidence, we identify low-confidence cases that require further expert annotation and high-confidence cases that are automatically classified. We report the percentage of low-confidence cases and the performance of automatically classified cases. On the high-confidence cases, the model achieves classification accuracy comparable to pathologists. This leads a potential of reducing 80% to 98% of the manual annotation workload.

Clinical notes contain a large amount of clinically valuable information that is ignored in many clinical decision support systems due to the difficulty that comes with mining that information. Recent work has found success leveraging deep learning models for the prediction of clinical outcomes using clinical notes. However, these models fail to provide clinically relevant and interpretable information that clinicians can utilize for informed clinical care. In this work, we augment a popular convolutional model with an attention mechanism and apply it to unstructured clinical notes for the prediction of ICU readmission and mortality. We find that the addition of the attention mechanism leads to competitive performance while allowing for the straightforward interpretation of predictions. We develop clear visualizations to present important spans of text for both individual predictions and high-risk cohorts. We then conduct a qualitative analysis and demonstrate that our model is consistently attending to clinically meaningful portions of the narrative for all of the outcomes that we explore.

The enormous amount of data and computation required to train DNNs have led to the rise of various parallelization strategies. Broadly, there are two strategies: 1) Data-Parallelism -- replicating the DNN on multiple processes and training on different training samples, and 2) Model-Parallelism -- dividing elements of the DNN itself into partitions across different processes. While data-parallelism has been extensively studied and developed, model-parallelism has received less attention as it is non-trivial to split the model across processes. In this paper, we propose HyPar-Flow: a framework for scalable and user-transparent parallel training of very large DNNs (up to 5,000 layers). We exploit TensorFlow's Eager Execution features and Keras APIs for model definition and distribution. HyPar-Flow exposes a simple API to offer data, model, and hybrid (model + data) parallel training for models defined using the Keras API. Under the hood, we introduce MPI communication primitives like send and recv on layer boundaries for data exchange between model-partitions and allreduce for gradient exchange across model-replicas. Our proposed designs in HyPar-Flow offer up to 3.1x speedup over sequential training for ResNet-110 and up to 1.6x speedup over Horovod-based data-parallel training for ResNet-1001; a model that has 1,001 layers and 30 million parameters. We provide an in-depth performance characterization of the HyPar-Flow framework on multiple HPC systems with diverse CPU architectures including Intel Xeon(s) and AMD EPYC. HyPar-Flow provides 110x speed up on 128 nodes of the Stampede2 cluster at TACC for hybrid-parallel training of ResNet-1001.

The advent of the Internet era has led to an explosive growth in the Electronic Health Records (EHR) in the past decades. The EHR data can be regarded as a collection of clinical events, including laboratory results, medication records, physiological indicators, etc, which can be used for clinical outcome prediction tasks to support constructions of intelligent health systems. Learning patient representation from these clinical events for the clinical outcome prediction is an important but challenging step. Most related studies transform EHR data of a patient into a sequence of clinical events in temporal order and then use sequential models to learn patient representations for outcome prediction. However, clinical event sequence contains thousands of event types and temporal dependencies. We further make an observation that clinical events occurring in a short period are not constrained by any temporal order but events in a long term are influenced by temporal dependencies. The multi-scale temporal property makes it difficult for traditional sequential models to capture the short-term co-occurrence and the long-term temporal dependencies in clinical event sequences. In response to the above challenges, this paper proposes a Multi-level Representation Model (MRM). MRM first uses a sparse attention mechanism to model the short-term co-occurrence, then uses interval-based event pooling to remove redundant information and reduce sequence length and finally predicts clinical outcomes through Long Short-Term Memory (LSTM). Experiments on real-world datasets indicate that our proposed model largely improves the performance of clinical outcome prediction tasks using EHR data.

Requests come in a variety of size and constraints, from the urgent monitoring of small areas to large area coverage. In this work we are particularly interested in the latter case, with requests covering whole countries or even continents. Depending on weather conditions, such requests may take several months to complete, even with multiple satellites. In order to shorten the time required to fulfill requests, the mission orchestrator shall schedule acquisitions with both a short and a long-term strategy. Determining a strategy robust to an uncertain environment is a complex task, this is why current solutions mainly consist of heuristics configured by human-experts. This paper demonstrates that Reinforcement Learning (RL) might be well-suited for such a challenge. RL has proven to be of great value since these algorithms have mastered several games such as Pong on Atari 2600 (Mnih et al. 2013), Go with AlphaGo (Silver et al. 2017) and more recently Starcraft (Arulkumaran, Cully, and Togelius 2019).c

Knowledge distillation is a widely used technique for model compression. We posit that the teacher model used in a distillation setup, captures relationships between classes, that extend beyond the original dataset. We empirically show that a teacher model can transfer this knowledge to a student model even on an {\it out-of-distribution} dataset. Using this approach, we show promising results on MNIST, CIFAR-10, and Caltech-256 datasets using unlabeled image data from different sources. Our results are encouraging and help shed further light from the perspective of understanding knowledge distillation and utilizing unlabeled data to improve model quality.

Neural network pruning techniques have demonstrated it is possible to remove the majority of weights in a network with surprisingly little degradation to test set accuracy. However, this measure of performance conceals significant differences in how different classes and images are impacted by pruning. We find that certain examples, which we term pruning identified exemplars (PIEs), and classes are systematically more impacted by the introduction of sparsity. Removing PIE images from the test-set greatly improves top-1 accuracy for both pruned and non-pruned models. These hard-to-generalize-to images tend to be mislabelled, of lower image quality, depict multiple objects or require fine-grained classification. These findings shed light on previously unknown trade-offs, and suggest that a high degree of caution should be exercised before pruning is used in sensitive domains.