Search for: All records

We present a multitask learning approach to the problem of hypoglycemia (HG) prediction in diabetes. The approach is based on a state-of-the-art time series forecasting model, N-BEATS, and extends it by adding a classification task so that the model performs both glucose forecasting (i.e., predicting future glucose values) and HG prediction (i.e., probability of future HG events sometime within the prediction horizon). We also propose an alternative loss function that penalizes forecasting errors in the HG range. We evaluate the approach on a dataset containing over 1.6M recordings from 112 patients with type 1 diabetes who wore a continuous glucose monitor (CGM) for 90 days. Our results show that the classification branch significantly outperforms the forecasting branch on the problem of HG prediction, and that the new loss function is more effective at reducing forecasting errors in the HG range than multi-task learning. 

Background: Monitoring glucose excursions is important in diabetes management. This can be achieved using continuous glucose monitors (CGMs). However, CGMs are expensive and invasive. Thus, alternative low-cost noninvasive wearable sensors capable of predicting glycemic excursions could be a game changer to manage diabetes. Methods: In this article, we explore two noninvasive sensor modalities, electrocardiograms (ECGs) and accelerometers, collected on five healthy participants over two weeks, to predict both hypoglycemic and hyperglycemic excursions. We extract 29 features encompassing heart rate variability features from the ECG, and time- and frequency-domain features from the accelerometer. We evaluated two machine-learning approaches to predict glycemic excursions: a classification model and a regression model. Results: The best model for both hypoglycemia and hyperglycemia detection was the regression model based on ECG and accelerometer data, yielding 76% sensitivity and specificity for hypoglycemia and 79% sensitivity and specificity for hyperglycemia. This had an improvement of 5% in sensitivity and specificity for both hypoglycemia and hyperglycemia when compared with using ECG data alone. Conclusions: Electrocardiogram is a promising alternative not only to detect hypoglycemia but also to predict hyperglycemia. Supplementing ECG data with contextual information from accelerometer data can improve glucose prediction. 

We used Natural Language Processing (NLP) to design an adaptive computer dialogue that engages students in a conversation to reflect on and revise their written explanations of a science dilemma. We study the accuracy of the NLP idea detection. We analyze how 98 12-13 year-olds interacted with the dialogue as a part of a Diagnostic Inventory. We study students’ initial and revised science explanations along with their logged responses to the dialogue. The dialogue led to a high rate of student revision compared to prior studies of adaptive guidance. The adaptive prompt encouraged students to reflect on prior experiences, to consider new variables, and to raise scientific questions. Students incorporated these new ideas when revising their initial explanations. We discuss how these adaptive dialogues can strengthen science instruction. 

This design-based research takes advantage of advanced technologies to support teachers to rapidly respond to evidence about student ideas generated in their classrooms. Leveraging advances in natural language processing methods, the Teacher Action Planner (TAP) analyzes students’ written explanations embedded in web-based inquiry projects to provide teachers with a report on student progress in developing the three-dimensional understanding called for by the Next Generation Science Standards. Based on the pattern in student scores, the TAP recommends research-based ways for teachers to customize instruction. This study examines how ten middle school teachers in 4 schools used the analysis of student ideas and suggestions for instructional customization presented in the TAP. This paper reports on how well their implemented customizations addressed student learning needs. It concludes with a discussion of the implications of the findings for redesign of the TAP. 

With the widespread adoption of the Next Generation Science Standards (NGSS), science teachers and online learning environments face the challenge of evaluating students’ integration of different dimensions of science learning. Recent advances in representation learning in natural language processing have proven effective across many natural language processing tasks, but a rigorous evaluation of the relative merits of these methods for scoring complex constructed response formative assessments has not previously been carried out. We present a detailed empirical investigation of feature-based, recurrent neural network, and pre-trained transformer models on scoring content in real-world formative assessment data. We demonstrate that recent neural methods can rival or exceed the performance of feature-based methods. We also provide evidence that different classes of neural models take advantage of different learning cues, and pre-trained transformer models may be more robust to spurious, dataset-specific learning cues, better reflecting scoring rubrics. 

The Next Generation Science Standards (NGSS) emphasize integrating three dimensions of science learning: disciplinary core ideas, cross-cutting concepts, and science and engineering practices. In this study, we develop formative assessments that measure student understanding of the integration of these three dimensions along with automated scoring methods that distinguish among them. The formative assessments allow students to express their emerging ideas while also capturing progress in integrating core ideas, cross-cutting concepts, and practices. We describe how item and rubric design can work in concert with an automated scoring system to independently score science explanations from multiple perspectives. We describe item design considerations and provide validity evidence for the automated scores.