Postprandial hyperglycemia, marked by the blood glucose level exceeding the normal range after consuming a meal, is a critical indicator of progression toward type 2 diabetes in people with prediabetes and in healthy individuals. A key metric for understanding blood glucose dynamics after eating is the postprandial Area Under the Curve (AUC). Predicting postprandial AUC in advance based on a person’s lifestyle factors, such as diet and physical activity level, and explaining the factors that affect postprandial blood glucose could allow an individual to adjust their behavioral choices accordingly to maintain normal glucose levels. In this work, we develop an explainable machine learning solution, GlucoLens, that takes sensor-driven inputs and utilizes advanced data processing, large language models, and trainable machine learning models to estimate postprandial AUC and predict hyperglycemia from diet, physical activity, and recent glucose patterns. We use data obtained using wearables in a five-week clinical trial of 10 adults who worked full-time to develop and evaluate the proposed computational model that integrates wearable sensing, multimodal data, and machine learning. Our machine learning model takes multimodal data from wearable activity and glucose monitoring sensors, along with food and work logs, and provides an interpretable prediction of the postprandial glucose patterns. GlucoLens achieves a normalized root mean squared error (NRMSE) of 0.123 in its best configuration. On average, the proposed technology provides a 16% better predictive performance compared to the comparison models. Additionally, our technique predicts hyperglycemia with an accuracy of 79% and an F1 score of 0.749 and recommends different treatment options to help avoid hyperglycemia through diverse counterfactual explanations. With systematic experiments and discussion supported by established prior research, we show that our method is generalizable and consistent with clinical understanding.
13 January 2024 in ACM Transactions on Computing for Healthcare
Inter-beat interval (IBI) measurement enables estimation of heart-tare variability (HRV) which, in turn, can provide early indication of potential cardiovascular diseases (CVDs). However, extracting IBIs from noisy signals is challenging since the morphology of the signal gets distorted in the presence of noise. Electrocardiogram (ECG) of a person in heavy motion is highly corrupted with noise, known as motion-artifact, and IBI extracted from it is inaccurate. As a part of remote health monitoring and wearable system development, denoising ECG signals and estimating IBIs correctly from them have become an emerging topic among signal-processing researchers. Apart from conventional methods, deep-learning techniques have been successfully used in signal denoising recently, and diagnosis process has become easier, leading to accuracy levels that were previously unachievable. We propose a deep-learning approach leveraging tiramisu autoencoder model to suppress motion-artifact noise and make the R-peaks of the ECG signal prominent even in the presence of high-intensity motion. After denoising, IBIs are estimated more accurately expediting diagnosis tasks. Results illustrate that our method enables IBI estimation from noisy ECG signals with SNR up to -30 dB with average root mean square error (RMSE) of 13 milliseconds for estimated IBIs. At this noise level, our error percentage remains below 8% and outperforms other state-of-the-art techniques.
Activity recognition using data collected with smart devices such as mobile and wearable sensors has become a critical component of many emerging applications ranging from behavioral medicine to gaming. However, an unprecedented increase in the diversity of smart devices in the internet-of-things era has limited the adoption of activity recognition models for use across different devices. This lack of cross-domain adaptation is particularly notable across sensors of different modalities where the mapping of the sensor data in the traditional feature level is highly challenging. To address this challenge, we propose ActiLabel, a combinatorial framework that learns structural similarities among the events that occur in a target domain and those of a source domain and identifies an optimal mapping between the two domains at their structural level. The structural similarities are captured through a graph model, referred to as the dependency graph, which abstracts details of activity patterns in low-level signal and feature space. The activity labels are then autonomously learned in the target domain by finding an optimal tiered mapping between the dependency graphs. We carry out an extensive set of experiments on three large datasets collected with wearable sensors involving human subjects. The results demonstrate the superiority of ActiLabel over state-of-the-art transfer learning and deep learning methods. In particular, ActiLabel outperforms such algorithms by average F1-scores of , , and for cross-modality, cross-location, and cross-subject activity recognition, respectively.
Multitask learning models provide benefits by reducing model complexity and improving accuracy by concurrently learning multiple tasks with shared representations. Leveraging inductive knowledge transfer, these models mitigate the risk of overfitting on any specific task, leading to enhanced overall performance. However, supervised multitask learning models, like many neural networks, require substantial amounts of labeled data. Given the cost associated with data labeling, there is a need for an efficient label acquisition mechanism, known as multitask active learning (MTAL). In wearable sensor systems, success of MTAL largely hinges on its query strategies because active learning in such settings involves interaction with end-users (e.g., patients) for annotation. However, these strategies have not been studied in mobile health settings and wearable systems to date. While strategies like one-sided sampling, alternating sampling, and rank-combination-based sampling have been proposed in the past, their applicability in mobile sensor settings—a domain constrained by label deficit—remains largely unexplored. This study investigates the MTAL querying approaches and addresses crucial questions related to the choice of sampling methods and the effectiveness of multitask learning in mobile health applications. Utilizing two datasets on activity recognition and emotion classification, our findings reveal that rank-based sampling outperforms other techniques, particularly in tasks with high correlation. However, sole reliance on informativeness for sample selection may introduce biases into models. To address this issue, we also propose a Clustered Stratified Sampling (CSS) method in tandem with the multitask active learning query process. CSS identifies clustered mini-batches of samples, optimizing budget utilization and maximizing performance. When employed alongside rank-based query selection, our proposed CSS algorithm demonstrates up to 9% improvement in accuracy over traditional querying approaches for a 2000-query budget.
Frequent and long-term exposure to hyperglycemia (i.e., high blood glucose) increases the risk of chronic complications such as neuropathy, nephropathy, and cardiovascular disease. Current technologies like continuous subcutaneous insulin infusion (CSII) and continuous glucose monitoring (CGM) primarily model specific aspects of glycemic control-like hypoglycemia prediction or insulin delivery. Similarly, most digital twin approaches in diabetes management simulate only physiological processes. These systems lack the ability to offer alternative treatment scenarios that support proactive behavioral interventions. To address this, we propose GlyTwin, a novel digital twin framework that uses counterfactual explanations to simulate optimal treatments for glucose regulation. Our approach helps patients and caregivers modify behaviors like carbohydrate intake and insulin dosing to avoid abnormal glucose events. GlyTwin generates behavioral treatment suggestions that proactively prevent hyperglycemia by recommending small adjustments to daily choices, reducing both frequency and duration of these events. Additionally, it incorporates stakeholder preferences into the intervention design, making recommendations patient-centric and tailored. We evaluate GlyTwin on AZT1D, a newly constructed dataset with longitudinal data from 21 type 1 diabetes (T1D) patients on automated insulin delivery systems over 26 days. Results show GlyTwin outperforms state-of-the-art counterfactual methods, generating 76.6% valid and 86% effective interventions. These findings demonstrate the promise of counterfactual-driven digital twins in delivering personalized healthcare.