A Semantic Parsing Pipeline for Context-Dependent Question Answering over Temporally Structured Data.

We propose a new setting for question answering in which users can query the system using both natural language and direct interactions within a graphical user interface that displays multiple time series associated with an entity of interest. The user interacts with the interface in order to understand the entity's state and behavior, entailing sequences of actions and questions whose answers may depend on previous factual or navigational interactions. We describe a pipeline implementation where spoken questions are first transcribed into text which is then semantically parsed into logical forms that can be used to automatically extract the answer from the underlying database. The speech recognition module is implemented by adapting a pre-trained LSTM-based architecture to the user's speech, whereas for the semantic parsing component we introduce an LSTM-based encoder-decoder architecture that models context dependency through copying mechanisms and multiple levels of attention over inputs and previous outputs. When evaluated separately, with and without data augmentation, both models are shown to substantially outperform several strong baselines. Furthermore, the full pipeline evaluation shows only a small degradation in semantic parsing accuracy, demonstrating that the semantic parser is robust to mistakes in the speech recognition output. The new question answering paradigm proposed in this paper has the potential to improve the presentation and navigation of the large amounts of sensor data and life events that are generated in many areas of medicine.

LSTMs and Deep Residual Networks for Carbohydrate and Bolus Recommendations in Type 1 Diabetes Management.

To avoid serious diabetic complications, people with type 1 diabetes must keep their blood glucose levels (BGLs) as close to normal as possible. Insulin dosages and carbohydrate consumption are important considerations in managing BGLs. Since the 1960s, models have been developed to forecast blood glucose levels based on the history of BGLs, insulin dosages, carbohydrate intake, and other physiological and lifestyle factors. Such predictions can be used to alert people of impending unsafe BGLs or to control insulin flow in an artificial pancreas. In past work, we have introduced an LSTM-based approach to blood glucose level prediction aimed at "what-if" scenarios, in which people could enter foods they might eat or insulin amounts they might take and then see the effect on future BGLs. In this work, we invert the "what-if" scenario and introduce a similar architecture based on chaining two LSTMs that can be trained to make either insulin or carbohydrate recommendations aimed at reaching a desired BG level in the future. Leveraging a recent state-of-the-art model for time series forecasting, we then derive a novel architecture for the same recommendation task, in which the two LSTM chain is used as a repeating block inside a deep residual architecture. Experimental evaluations using real patient data from the OhioT1DM dataset show that the new integrated architecture compares favorably with the previous LSTM-based approach, substantially outperforming the baselines. The promising results suggest that this novel approach could potentially be of practical use to people with type 1 diabetes for self-management of BGLs.

The OhioT1DM Dataset for Blood Glucose Level Prediction: Update 2020.

This paper documents the OhioT1DM Dataset, which was developed to promote and facilitate research in blood glucose level prediction. It contains eight weeks' worth of continuous glucose monitoring, insulin, physiological sensor, and self-reported life-event data for each of 12 people with type 1 diabetes. An associated graphical software tool allows researchers to visualize the integrated data. The paper details the contents and format of the dataset and tells interested researchers how to obtain it. The OhioT1DM Dataset was first released in 2018 for the first Blood Glucose Level Prediction (BGLP) Challenge. At that time, the dataset was half its current size, containing data for only six people with type 1 diabetes. Data for an additional six people is being released in 2020 for the second BGLP Challenge. This paper subsumes and supersedes the paper which documented the original dataset.

LSTMs and Neural Attention Models for Blood Glucose Prediction: Comparative Experiments on Real and Synthetic Data.

We have shown in previous work that LSTM networks are effective at predicting blood glucose levels in patients with type I diabetes, outperforming human experts and an SVR model trained with features computed by manually engineered physiological models. In this paper we present the results of a much larger set of experiments on real and synthetic datasets in what-if, agnostic, and inertial scenarios. Experiments on a more recent real-patient dataset, which we are releasing to the research community, demonstrate that LSTMs are robust to noise and can easily incorporate additional features, such as skin temperature, heart rate and skin conductance, without any change in the architecture. A neural attention module that we designed specifically for time series prediction improves prediction performance on synthetic data; however, the improvements do not transfer to real data. Conversely, using time of day as an additional input feature consistently improves the LSTM performance on real data but not on synthetic data. These and other differences show that behavior on synthetic data cannot be assumed to always transfer to real data, highlighting the importance of evaluating physiological models on data from real patients.

Using LSTMs to learn physiological models of blood glucose behavior.

For people with type 1 diabetes, good blood glucose control is essential to keeping serious disease complications at bay. This entails carefully monitoring blood glucose levels and taking corrective steps whenever they are too high or too low. If blood glucose levels could be accurately predicted, patients could take proactive steps to prevent blood glucose excursions from occurring. However, accurate predictions require complex physiological models of blood glucose behavior. Factors such as insulin boluses, carbohydrate intake, and exercise influence blood glucose in ways that are difficult to capture through manually engineered equations. In this paper, we describe a recursive neural network (RNN) approach that uses long short-term memory (LSTM) units to learn a physiological model of blood glucose. When trained on raw data from real patients, the LSTM networks (LSTMs) obtain results that are competitive with a previous state-of-the-art model based on manually engineered physiological equations. The RNN approach can incorporate arbitrary physiological parameters without the need for sophisticated manual engineering, thus holding the promise of further improvements in prediction accuracy.

Case-based reasoning in the health sciences: What's next?

OBJECTIVES: This paper presents current work in case-based reasoning (CBR) in the health sciences, describes current trends and issues, and projects future directions for work in this field. METHODS AND MATERIAL: It represents the contributions of researchers at two workshops on case-based reasoning in the health sciences. These workshops were held at the Fifth International Conference on Case-Based Reasoning (ICCBR-03) and the Seventh European Conference on Case-Based Reasoning (ECCBR-04). RESULTS: Current research in CBR in the health sciences is marked by its richness. Highlighted trends include work in bioinformatics, support to the elderly and people with disabilities, formalization of CBR in biomedicine, and feature and case mining. CONCLUSION: CBR systems are being better designed to account for the complexity of biomedicine, to integrate into clinical settings and to communicate and interact with diverse systems and methods.