A5039978080- Diabetes Management and Research
- Context-Aware Activity Recognition Systems
- Hyperglycemia and glycemic control in critically ill and hospitalized patients
- Diabetes, Cardiovascular Risks, and Lipoproteins
- Data Stream Mining Techniques
- Machine Learning in Healthcare
- Human Pose and Action Recognition
- Medication Adherence and Compliance
- Artificial Intelligence in Healthcare
- Anomaly Detection Techniques and Applications
- Neurological disorders and treatments
- Nutritional Studies and Diet
- Pharmaceutical Practices and Patient Outcomes
- Blood Pressure and Hypertension Studies
- Mobile Crowdsensing and Crowdsourcing
Arizona State University
2022-2025
Managing Type 1 Diabetes (T1D) demands constant vigilance as individuals strive to regulate their blood glucose levels avert the dangers of dysglycemia (hyperglycemia or hypoglycemia). Despite advent sophisticated technologies such automated insulin delivery (AID) systems, achieving optimal glycemic control remains a formidable task. AID systems integrate continuous subcutaneous infusion (CSII) and monitors (CGM) data, offering promise in reducing variability increasing time-in-range....
Multitask learning models provide benefits by reducing model complexity and improving accuracy concurrently multiple tasks with shared representations. Leveraging inductive knowledge transfer, these mitigate the risk of overfitting on any specific task, leading to enhanced overall performance. However, supervised multitask models, like many neural networks, require substantial amounts labeled data. Given cost associated data labeling, there is a need for an efficient label acquisition...
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 internet-of-things era limited adoption activity models for use across different devices. This lack cross-domain adaptation is particularly notable modalities where mapping sensor traditional feature level highly challenging. To address this...
Effective prevention and management of diabetes relies on maintaining a normal blood glucose level, thus avoiding abnormal events such as hyperglycemia hypoglycemia. Predicting anomalous beforehand can potentially help patients caregivers intervene to prevent through modifiable behaviors exercise, diet, medication. Although Continuous Glucose Monitor (CGM) sensors have been used monitor forecast current research lacks computational approach that recommends behavioral intervention bring the...
Regulating blood glucose concentration is crucial for every individual, particularly patients with diabetes or prediabetes to manage their metabolic health. Poor control results in dysglycemia. Frequent dysglycemia exposure increases the risk of cardiovascular disease, seizures, loss consciousness, and potentially death. Patients often struggle due a multitude interrelated behavioral, physiological, biological factors such as food, insulin intake, metabolism rate. There need solution that...
Postprandial hyperglycemia (PPHG) is detrimental to health and increases risk of cardiovascular diseases, reduced eyesight, life-threatening conditions like cancer. Detecting PPHG events before they occur can potentially help with providing early interventions. Prior research suggests that be predicted based on information about diet. However, such computational approaches (1) are data hungry requiring significant amounts for algorithm training; (2) work as a black-box lack interpretability,...
Maintaining normal blood glucose levels through lifestyle behaviors is central to maintaining health and preventing disease. Frequent exposure dysglycemia (i.e., abnormal events such as hyperlycemia hypoglycemia) leads chronic complications including diabetes, kidney disease need for dialysis, myocardial infarction, stroke, amputation, death. Therefore, a tool capable of predicting offering users actionable feedback about how make changes in their diet, exercise, medication prevent glycemic...
Effective diagnosis of neuro-degenerative diseases is critical to providing early treatments, which in turn can lead substantial savings medical costs. Machine learning models help with the such like Parkinson's and aid assessing disease symptoms. This work introduces a novel system that integrates pervasive computing, mobile sensing, machine classify hand-drawn images provide diagnostic insights for screening patients. We designed computational framework combines data augmentation...