Predicting Glucose Levels in Patients with Type1 Diabetes Based on Physiological and Activity Data

Vahedi, Mohammad; MacBride, Koenrad B.; Wunsik, Woo; Kim, Yosep; Fong, Chris; Padilla, Andrew J.; Pourhomayoun, Mohammad; Zhong, Alex; Kulkarni, Sameer S.; Arunachalam, Siddharth; Jiang, Bingbing

doi:10.1145/3220127.3220133

Cited by 15 publications

(7 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hypoglycemia was predicted from breath samples using ML techniques by Siegel et al [ 27 ]. Vahedi et al [ 33 ] predicted BG levels from BG and PA while BG levels were estimated from PPG signals using the mobile phone camera of a patient and the BG data in a study proposed by Zhang et al [ 38 ].…”

Section: Resultsmentioning

confidence: 99%

“…These studies have employed multiple variants of ANN such as RNN, DL, CNN, MLPs, etc. ANNs were used by Bertachi et al [ 41 ], Vahedi et al [ 33 ], Zhu et al [ 64 ], Mosquera-Lopez et al [ 81 ], San et al [ 35 ], Jin et al [ 36 ], Mhaskar et al [ 63 ], Li et al [ 74 ], Li et al [ 78 ], Bertachi et al [ 51 ], Güemes et al [ 60 ], Oviedo et al [ 53 ], Vehi et al [ 59 ], Quan et al [ 50 ], and Amar et al [ 75 ]. Unlike other ML models, ANNs extract their own features from the inputs based on their hidden parameters.…”

Section: Resultsmentioning

confidence: 99%

“…This approach fixes the over-fitting problem of decision trees. Seo et al [ 43 ], Güemes et al [ 60 ], Vahedi et al [ 33 ], G Noaro et al [ 72 ], Vu et al [ 47 ], Reddy et al [ 40 ], Chen et al [ 30 ], Dave et al [ 52 ], Calhoun et al [ 45 ], Amar et al [ 75 ], Hidalgo et al [ 77 ], and Rodriguez et al [ 79 ] have all used RF for predicting/detecting hypoglycemia. Ruan et al [ 31 ] and Cappon et al [ 66 ] used the XGboost algorithm.…”

Section: Resultsmentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning Techniques for Hypoglycemia Prediction: Trends and Challenges

Mujahid

Contreras

Vehı́

2021

Sensors

View full text Add to dashboard Cite

(1) Background: the use of machine learning techniques for the purpose of anticipating hypoglycemia has increased considerably in the past few years. Hypoglycemia is the drop in blood glucose below critical levels in diabetic patients. This may cause loss of cognitive ability, seizures, and in extreme cases, death. In almost half of all the severe cases, hypoglycemia arrives unannounced and is essentially asymptomatic. The inability of a diabetic patient to anticipate and intervene the occurrence of a hypoglycemic event often results in crisis. Hence, the prediction of hypoglycemia is a vital step in improving the life quality of a diabetic patient. The objective of this paper is to review work performed in the domain of hypoglycemia prediction by using machine learning and also to explore the latest trends and challenges that the researchers face in this area; (2) Methods: literature obtained from PubMed and Google Scholar was reviewed. Manuscripts from the last five years were searched for this purpose. A total of 903 papers were initially selected of which 57 papers were eventually shortlisted for detailed review; (3) Results: a thorough dissection of the shortlisted manuscripts provided an interesting split between the works based on two categories: hypoglycemia prediction and hypoglycemia detection. The entire review was carried out keeping this categorical distinction in perspective while providing a thorough overview of the machine learning approaches used to anticipate hypoglycemia, the type of training data, and the prediction horizon.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Techniques for Hypoglycemia Prediction: Trends and Challenges

Mujahid

Contreras

Vehı́

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Vahedi et al [16] investigated the adaption of a machine learning-based model that predicts continuous glucose levels and aims to prevent hypoglycemia through using physiological and physical exercise data. They used the Medtronic MiniMed 530G insulin delivery device, along with the Enlite sensor, to collect 4 months of physiological measures, physical activity, and nutrition data from 93 individuals with T1D.…”

Section: Activity Wearablesmentioning

confidence: 99%

Type 1 Diabetes Hypoglycemia Prediction Algorithms: Systematic Review

Tsichlaki¹,

Koumakis²,

Tsiknakis³

2022

JMIR Diabetes

View full text Add to dashboard Cite

Background Diabetes is a chronic condition that necessitates regular monitoring and self-management of the patient’s blood glucose levels. People with type 1 diabetes (T1D) can live a productive life if they receive proper diabetes care. Nonetheless, a loose glycemic control might increase the risk of developing hypoglycemia. This incident can occur because of a variety of causes, such as taking additional doses of insulin, skipping meals, or overexercising. Mainly, the symptoms of hypoglycemia range from mild dysphoria to more severe conditions, if not detected in a timely manner. Objective In this review, we aimed to report on innovative detection techniques and tactics for identifying and preventing hypoglycemic episodes, focusing on T1D. Methods A systematic literature search following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines was performed focusing on the PubMed, GoogleScholar, IEEEXplore, and ACM Digital Library to find articles on technologies related to hypoglycemia detection in patients with T1D. Results The presented approaches have been used or devised to enhance blood glucose monitoring and boost its efficacy in forecasting future glucose levels, which could aid the prediction of future episodes of hypoglycemia. We detected 19 predictive models for hypoglycemia, specifically on T1D, using a wide range of algorithmic methodologies, spanning from statistics (1.9/19, 10%) to machine learning (9.88/19, 52%) and deep learning (7.22/19, 38%). The algorithms used most were the Kalman filtering and classification models (support vector machine, k-nearest neighbors, and random forests). The performance of the predictive models was found to be satisfactory overall, reaching accuracies between 70% and 99%, which proves that such technologies are capable of facilitating the prediction of T1D hypoglycemia. Conclusions It is evident that continuous glucose monitoring can improve glucose control in diabetes; however, predictive models for hypo- and hyperglycemia using only mainstream noninvasive sensors such as wristbands and smartwatches are foreseen to be the next step for mobile health in T1D. Prospective studies are required to demonstrate the value of such models in real-life mobile health interventions.

show abstract

“…They use statistical analyses like sensitivity and specificity to evaluate their method. In [16], prediction is again achieved by random forests and incorporating a wide variety of additional input features such as physiological and physical activity parameters. Mean Absolute Percentage Error (MAPE) is used as assessment methodology.…”

Section: Prior Workmentioning

confidence: 99%

A Function Approximation Approach to the Prediction of Blood Glucose Levels

Mhaskar

Pereverzyev

Walt

2021

Front. Appl. Math. Stat.

View full text Add to dashboard Cite

The problem of real time prediction of blood glucose (BG) levels based on the readings from a continuous glucose monitoring (CGM) device is a problem of great importance in diabetes care, and therefore, has attracted a lot of research in recent years, especially based on machine learning. An accurate prediction with a 30, 60, or 90 min prediction horizon has the potential of saving millions of dollars in emergency care costs. In this paper, we treat the problem as one of function approximation, where the value of the BG level at time t+h (where h the prediction horizon) is considered to be an unknown function of d readings prior to the time t. This unknown function may be supported in particular on some unknown submanifold of the d-dimensional Euclidean space. While manifold learning is classically done in a semi-supervised setting, where the entire data has to be known in advance, we use recent ideas to achieve an accurate function approximation in a supervised setting; i.e., construct a model for the target function. We use the state-of-the-art clinically relevant PRED-EGA grid to evaluate our results, and demonstrate that for a real life dataset, our method performs better than a standard deep network, especially in hypoglycemic and hyperglycemic regimes. One noteworthy aspect of this work is that the training data and test data may come from different distributions.

show abstract

Predicting Glucose Levels in Patients with Type1 Diabetes Based on Physiological and Activity Data

Cited by 15 publications

References 1 publication

Machine Learning Techniques for Hypoglycemia Prediction: Trends and Challenges

Machine Learning Techniques for Hypoglycemia Prediction: Trends and Challenges

Type 1 Diabetes Hypoglycemia Prediction Algorithms: Systematic Review

A Function Approximation Approach to the Prediction of Blood Glucose Levels

Contact Info

Product

Resources

About