Search results
(1 - 2 of 2)
- Title
- Assessment of Sleep Characteristics and Their Effects in People with Type 1 Diabetes for the Development of a Sleep Module for the Multivariable Artificial Pancreas System
- Creator
- Brandt, Rachel
- Date
- 2021
- Description
-
his work is focused on the relationship between sleep and blood glucose control in people with Type 1 Diabetes and on the development of a...
Show morehis work is focused on the relationship between sleep and blood glucose control in people with Type 1 Diabetes and on the development of a sleep module incorporating new variables and rules for use in automated insulin delivery and advisory systems. Through this research, sleep effects were identified, quantified and incorporated into a multivariable artificial pancreas system (mvAP) that is currently being developed. The mvAP uses different physiological signals acquired through non-invasive wearable sensors along with a continuous glucose monitor (CGM) to detect the state of the user to predict future blood glucose values to aid in insulin dosing decisions. The overall objective of the research was to develop and add a module to further improve the successful mvAP by incorporating sleep related information while retaining the functionality and safety of the system and improving the effectiveness in maintaining good glycemic control. Two types of sleep effects were studied: effects of sleep characteristics and stages in real-time (during sleep) and effects of sleep on glucose metabolism the next day. It was found that poor sleep quality was related to higher glycemic variability overnight in adults with Type 1 Diabetes. However, in adults without diabetes, there were no consistent relationships found between sleep stages and changes in blood glucose levels overnight. For adults with Type 1 Diabetes, it was determined that Sleep Quality, Total Sleep Time, Wake After Sleep Onset (WASO), Number of Awakenings >5 minutes, and amount of Deep sleep could be used in conjunction with insulin on board and the amount of time that has passed since the user has woken up to predict how much more insulin may be needed at the first meal of the day. This Insulin Multiplier Algorithm was tested and validated in replay simulations. Finally, in order to incorporate these relationships into the mvAP, a sleep stage detection algorithm was developed using the Empatica E4 wristband.
Show less
- Title
- Incorporating Real-Time Estimates of Physiological States in Artificial Pancreas Systems
- Creator
- Sevil, Mert
- Date
- 2020
- Description
-
Type-1 diabetes is a chronic disease that has a negative impact on the life of a person with diabetes causing other chronic diseases, reducing...
Show moreType-1 diabetes is a chronic disease that has a negative impact on the life of a person with diabetes causing other chronic diseases, reducing the quality of life, and the possibility of causing dangerous reductions in blood glucose levels that may lead to coma or death. More than 100 million U.S. adults are now living with diabetes or pre-diabetes. Diabetes is one of the most expensive public health problems in the U.S. at $327 billion in 2017. Thus, alternative solutions or novel proposals are crucial to more effective treatments and cure. Artificial pancreas systems are one of the common treatment techniques of Type-1 Diabetes, which reduce the risk of diabetes-related complications and make diabetics' lives easier and make it convenient. Artificial pancreas systems aim to maintain blood glucose concentrations in a tighter target blood glucose range, which is a challenging problem. Several factors affect blood glucose concentrations including intensity of exercise, type of exercise, acute psychological stress and the physical state of a person with diabetes. These factors are unknown disturbances for artificial pancreas control systems. In this project, a single non-invasive wrist-worn device is used to obtain different biosignals in-real time. Biosignals are utilized with the development energy expenditure estimation model, psychological stress detection and physical state classification models. Several machine learning methods are tested and validated until the best classification and estimation accuracy is achieved for each estimate. Obtained models are incorporated with the current artificial pancreas design to improve its glycemic control performance. The controller is aware of such measurable disturbances with the proposed method, which allows for providing accurate and timely control action. Additional estimates are utilized to improve blood glucose concentration prediction model accuracy. Clinical trials are used to test and validate the proposed work. In summary, the presented work illustrates different machine learning techniques and algorithms that can enhance automated insulin delivery by a multivariable artificial pancreas system and enhance the quality of life of people with Type 1 diabetes.
Show less