MONITORING OF DIABETES OF AGED PEOPLE

Project Title

MONITORING OF DIABETES OF AGED PEOPLE

Project Area of Specialization Artificial IntelligenceProject Summary

The elderly represent a distinct yet heterogeneous group of persons with diabetes. Their unique physiology, pathophysiology, clinical features, needs, and challenges suggest that they need individualized diabetes care. Based on their functional ability and medico-surgical comorbidities, the elderly aim for relaxed targets, with a strategy to remain cognizant of geriatric syndromes, and avoid hypoglycemia. Tools used must be safe, well-tolerated, and easy to administer while requiring minimal monitoring. To avoid the complications of diabetes, you must control your blood glucose very well to minimize the risk of hyperglycemia. This will allow you to prevent the complications of diabetes. Monitoring your glucose levels daily, also known as self-testing is an essential part of managing diabetes. In short, to avoid such a serious condition, we will use this device for monitoring diabetes on daily bases which help out the patient to treatment on time before goes to any tragedy.

Project Objectives

In this study, a personalized health care monitoring system was developed to help patients to better self-manage their chronic condition. The proposed system records various health-related activities. Moreover, it can be considered as a health care information platform that achieves interaction between patients, medical institutions, and medical devices over a wireless network. The main idea behind the system is to collect users vital signs data using sensors and then transfer the data over a wireless network service platform. After this, with the help of a machine- learning methods, it can help users to review their ongoing health patterns and predict future changes in health status. Aged people such as people above than 60 age. They have a lot of issues bout their diabetes. These diseases occur due to not regular checking of their sugar or glucose level. This occurs due to the lag in technology. Because the patient will either go to a laboratory for a checkup and the second option is to cut his figure with the help of a device and take a blood sample to get the level of glucose. These two processes are a very difficult process for aged persons. We will design a device which will be based on machine learning algorithm which will monitor the glucose level and will inform the patient on time. If the sugar level of the patient is high the machine learning algorithm will inform the patient to take insulin. If the sugar level is low it will inform the patent on time to take glucose. The report will be stored on daily bases so you can easily go through it. The use of this device provides ambulatory glucose profiles. This information can be viewed on a computer or in your android

Project Implementation Method Architecture and Environment

This project is based on software and hardware. We will be using python Ide software in which there will be a machine learning algorithm. On the hardware side, we will be using a sensory hardware to gather the required data. The Machine learning algorithm will transmit the data to the receiver. The receiver will be an android mobile or computer. With the help of python Ide software, we will generate an Machine learning algorithm which will analyze the data and will take decision based on it.

Implementation Issues and Challenges

Our main issue which we will be facing is to design such a machine learning algorithm. Which will be more accurate.

Deliverables

Our project will make the care level of health in society very high. Because everyone can wear the band in which there will be sensor inside it. The sugar level of the subject will be measure on daily basis. They will be informed earlier before it cost some damage. The main advantage of this project is there will be no finger-pricking for monitoring the level of glucose.

Benefits of the Project

To the best of our knowledge, the present study is the ?rst focusing on smartphone, real-time data processing and machine learning-based methods to predict diabetes and BG levels. The proposed model is expected to help users monitor their vital signs data from sensor using their smartphone. Additionally, the proposed model helps users to discover the risk of diabetes at an early stage as well as help patients to obtain future predictions of their BG levels. Therefore, users can avoid the worst conditions in the future. Machine learning-based algorithms to help diabetic patients to better self-manage their chronic condition. (MLA) and sensor were used to gather users vital signs data such as blood glucose (BG) from sensor nodes to smartphones, while real-time data processing was utilized to manage the large amount of continuously generated sensor data

Old age is connected to numerous health problems. To evaluate a patient with diabetes it is necessary to take into account For this purpose this monitoring instrument is very useful to inform the patient on time to take step earlier before goes any accident and the patient will aware of health condition and take necessary step for yourself on time. Many people have issues with their blood sugar levels nowadays, and doctors believe that there are many undiagnosed cases of diabetes. This is a serious chronic disease that eventually affects the blood vessels and can result in blindness, very poor wound healing, and in severe cases, amputation of the foot due to a condition called diabetic foot. With so many blood sugar issues in the general population, it was only a matter of time before home health devices caught up with a smart health monitor for blood glucose levels. This technology uses arm patches that monitor blood sugar levels with a sensor that can be attached to the skin. This technology is as accurate as a prick test, but it can be connected to your phone.

Technical Details of Final Deliverable

Older people with diabetes are at high risk of harm from hypoglycemia, particularly there are coexisting memory problems. Continuous glucose monitoring (CGM) offers important benefits in terms of detecting hypoglycemia, but the feasibility of use and extent of data capture has not been tested in the patient group. Our objective is to investigate the feasibility of trailing a CGM intervention in the community setting in older people. Over the coming decades, this will pose a significant healthcare burden, especially in a worldwide expectation that 2045, 629 million people with being living with diabetes. In this vulnerable group, the healthcare system should consider different approaches by for the monitoring of day to day glucose readings. Conventional methods, such as self-monitoring of blood glucose (SMBG), may not be appropriate in older people, as they may not be able to recognize symptoms of changing blood sugars. Nocturnal and asymptomatic hypoglycemia events are not reliably captured because SMBG only provides a snapshot of the glucose level at a single point in time where the user or has taken action to do finger testing. Newer technologies, such as continuous glucose monitoring (CGM), have gained momentum in the management of diabetes, in particular in children and younger adults. We aim to design a device which will monitor the glucose level of the human body. The device will gather the data and will send it to the machine learning algorithm. Machine learning algorithms will take a decision rather the patient should take glucose or insulin. It will also store the report in the cloud. So that we can easily check the daily report of our glucose leve.

Final Deliverable of the Project Software SystemCore Industry MedicalOther IndustriesCore Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Good Health and Well-Being for PeopleRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	70000
Latest Laptop + Protected shield + GSM module + Testing strips + Bluetooth Module + Charger + Insulin and Glucose	Equipment	1	50000	50000
GSM sensors	Equipment	2	10000	20000