Food recommendation using machine learning for physical activities in patients with type 1 diabetes (original) (raw)
Related papers
Applied Sciences
Background. Since physical activity has a high impact on patients with type 1 diabetes and the risk of hypoglycemia (low blood glucose levels) is significantly higher during and after physical activities, an automatic method to provide a personalized recommendation is needed to improve the blood glucose management and harness the benefits of physical activities. This paper aims to reduce the risk of hypoglycemia and hyperglycemia (high blood glucose levels), and empowers type 1 diabetes patients to make decisions regarding food choices connected with physical activities. Methods. Traditional and Bayesian feedforward neural network models are developed to provide accurate predictions of the blood glucose outcome and the risks of hyperglycemia and hypoglycemia with uncertainty information. Using the proposed models, safe actions that minimize the risk of both hypoglycemia and hyperglycemia are provided as food recommendations to the patient. Results. The predicted blood glucose respon...
2020
Close control of blood glucose levels reduces the risk of microvascular and micro fibrillary confusions in patients with type 1 diabetes. In any case, this is troublesome due to the enormous intrasingular fluctuation and other factors that influence blood glucose control. The fundamental limiting factor in achieving severe glucose control in patients on concentrated insulin therapy is the danger of severe hypoglycemia. Thus, hypoglycemia is the major wellness issue in the treatment of type 1 diabetes, influencing the personal satisfaction of patients with this infection. Our current research was conducted at Jinnah Hospital, Lahore from March 2019 to February 2020. Choice aids that rely on AI techniques have achieved a practical approach to improve patient well-being by predicting unfriendly blood glucose functions. This survey proposes the use of four AI calculations to address the issue of well-being in executive diabetes: (1) language advancement for constant medium-term expectation of blood glucose levels, (2) maintenance of vector machines to predict hypoglycemic functions during postprandial periods, (3) false neural organization to predict short-term hypoglycemic scenes, and (4) information extraction to profile diabetes situations at the board level. The proposal includes the blending of standby and order capabilities of the updated approaches. The resulting framework fundamentally reduces the number of hypoglycemic scenes, improving well-being and giving patients greater confidence in the dynamics.
Design and Development of Diabetes Management System Using Machine Learning
International Journal of Telemedicine and Applications
This paper describes the design and implementation of a software system to improve the management of diabetes using a machine learning approach and to demonstrate and evaluate its effectiveness in controlling diabetes. The proposed approach for this management system handles the various factors that affect the health of people with diabetes by combining multiple artificial intelligence algorithms. The proposed framework factors the diabetes management problem into subgoals: building a Tensorflow neural network model for food classification; thus, it allows users to upload an image to determine if a meal is recommended for consumption; implementing K-Nearest Neighbour (KNN) algorithm to recommend meals; using cognitive sciences to build a diabetes question and answer chatbot; tracking user activity, user geolocation, and generating pdfs of logged blood sugar readings. The food recognition model was evaluated with cross-entropy metrics that support validation using Neural networks wit...
2012 IEEE 14th International Conference on e-Health Networking, Applications and Services (Healthcom), 2012
Diabetes is a common but serious chronic disease. Nearly 8% of Americans who are aged 65 and older (about 10.9 million) suffer from this deadly disease. Self-management of this disease is possible, yet the older population lack knowledge, have denial and often lack motivation to do so. Recently we have demonstrated sensor-based network architecture within the home to monitor daily activities and biological vital parameters [25]. The data is mined to find patterns and abnormal values. Through daily text messages that are sent to the subjects, we have achieved to influence behavior change using persuasive principles. In this paper, we analyze the daily data and demonstrate that a model to profile the subject's daily behavior is possible using Artificial Neural Networks (ANN). Such a profiling has the advantage of knowing the situations, when the subject's daily activity deviates from its "normal profile", which may be a possible indication of an onset of some health condition or disease. Lastly we develop an ANN based model to predict blood sugar level based on previous day's activity and diet intake. Such a model can be used to help a subject with high blood sugar to adjust daily activity to reach a target blood sugar level and also gives a care-giver advance notice to intervene in adverse situations.
GLUCAGON: AI-Based Insulin Dosage Prediction Application
The automation of insulin treatment is the most challenging aspect of glucose management for type 1 diabetes owing to unexpected exogenous events (e.g., meal intake). In this article, we propose a reinforcement learning (RL) algorithm based on artificial intelligence (AI) for an application which predicts the optimized insulin dosage using the datasets obtained from CGM and activity band which continuously collects data from the victim. A bio-inspired RL designing method was developed for automated data integration. This strategy uses reward functions to represent the temporal homeostatic goal, as well as discount factors to represent an individual's unique pharmacological profile. The proposed strategy was tested in virtual patients from the FDA-approved UVA/Padova simulator with unscheduled meal intakes using a training method based on an RL algorithm. The trained policy demonstrated fully automated regulation in both the basal and postprandial phases for a single-meal experiment with pre-prandial fasting. The layer-by-layer relevance propagation gives interpret-able data on AI-driven decisions for sensor noise robustness, automatic postprandial management, and avoidance of insulin stacking. The accuracy of the application was also tested by comparing with conventional manner of blood glucose checking.
A Food Recommender System for Patients with Diabetes and Hypertension
Diabetes and hypertension are examples of non-communicable diseases that are becoming a severe problem in the world today. A number of diseases have been connected to unhealthy eating habits. In this study, a recommender system that uses nutritional knowledge to suggest meals that are nutrient-dense to patients suffering from either ailments or one of it. The Study looked into computer models for tailored meal suggestions based on dietary data and user data in recent years. It examined physical traits, physiological data, and other personal information. A general framework for daily eating plan selections is presented in this article. The system used machine learning methodologies and techniques to generate recommendations for the necessary food items. Kmeans clustering and Random Forest classification technique were used which concentrates on providing meal recommendations that help the user maintain and enhance his or her health. The model was able to achieve an accuracy of 95% with 100 decision trees.
Diet Recommendation System based on Different Machine Learners
International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2022
In today's culture, many people suffer from a range of ailments and illnesses. It's not always simple to recommend a diet right away. The majority of individuals are frantically trying to reduce weight, gain weight, or keep their health in check. Time has also become a potential stumbling block. The study relies on a database that has the exact amounts of a variety of nutrients. As a result of the circumstance, we set out to create a program that would encourage individuals to eat healthier. Only three sorts of goods are recommended: weight loss, weight gain, and staying healthy. The Diet Recommendation System leverages user inputs such as medical data and the option of vegetarian or non-vegetarian meals from the two categories above to predict food items. We'll discuss about food classification, parameters, and machine learning in this post. This research includes different machine learner K-nearest neighbor, Support vector machine, Decision Tree, Navier buyers, Random Forest and Extra tree classifier comparative analysis for future diet plan prediction.
Lifestyle interventions aimed at reducing caloric intake and increasing physical activity have the potential to prevent Type 2 Diabetes (T2D). The use of new technologies may enhance the success of lifestyle interventions, improve metabolic health, and prevent T2D. 2,217 participants, ranging from normoglycemic to T2D, were enrolled in the Season-of-Me Program in which glucose patterns were captured over 28 consecutive days via continuous glucose monitoring (CGM). Food intake, activity, and body weight were logged by participants and integrated with wearables data using a smartphone-based app which continuously provided insights to participants, including overlaying daily glucose patterns with activity and food intake, as well as summarizing macronutrient breakdown, glycemic index (GI), glycemic load, and activity measures. The mobile app also used machine learning to provide personalized recommendations based on users’ preferences, including their adherence to recommendations, thei...
Dietetics Prediction System Using Machine Learning
ijarsct, 2022
Diabetes is a severe disease that can strike at any time and affect a large number of people. Age, obesity, sedentary lifestyle, poor diet, and high blood pressure are just few of the factors that contribute to the development of type 2 diabetes. There are a number of health problems that are more common among diabetics than in the general population. Patients with diabetes are currently being diagnosed and treated using a variety of diagnostic methods, including blood testing, urine tests, and more. In the healthcare industry, big data analytics is essential. The healthcare industry has a colossal amount of data stored in databases. Using big data analytics, users can acquire insight and make predictions about the future by examining large datasets and uncovering hidden information and trends. The current method isn't very good at classifying and forecasting. To better classify diabetes, we present a diabetes prediction model in this article that incorporates a few extrinsic parameters that cause diabetes, as well as regular components such as glucose, creatinine ratio, urea, fasting lipid profile, body mass index, age, insulin, and so on. Both datasets, each with eight variables, were subjected to the identical tests. The accuracy of a dataset with 12 variables is higher, so the conclusion is that the more information we have, the more accuracy we can attain.