Data-Driven Blood Glucose Pattern Classification and Anomalies Detection: Machine-Learning Applications in Type 1 Diabetes (Preprint)

BACKGROUND Diabetes mellitus is a chronic metabolic disorder that results in abnormal blood glucose (BG) regulations. The BG level is preferably maintained close to normality through self-management practices, which involves actively tracking BG levels and taking proper actions including adjusting diet and insulin medications. BG anomalies could be defined as any undesirable reading because of either a precisely known reason (normal cause variation) or an unknown reason (special cause variation) to the patient. Recently, machine-learning applications have been widely introduced within diabetes research in general and BG anomaly detection in particular. However, irrespective of their expanding and increasing popularity, there is a lack of up-to-date reviews that materialize the current trends in modeling options and strategies for BG anomaly classification and detection in people with diabetes. OBJECTIVE This review aimed to identify, assess, and analyze the state-of-the-art machine-learning strategies and their hybrid systems focusing on BG anomaly classification and detection including glycemic variability (GV), hyperglycemia, and hypoglycemia in type 1 diabetes within the context of personalized decision support systems and BG alarm events applications, which are important constituents for optimal diabetes self-management. METHODS A rigorous literature search was conducted between September 1 and October 1, 2017, and October 15 and November 5, 2018, through various Web-based databases. Peer-reviewed journals and articles were considered. Information from the selected literature was extracted based on predefined categories, which were based on previous research and further elaborated through brainstorming. RESULTS The initial results were vetted using the title, abstract, and keywords and retrieved 496 papers. After a thorough assessment and screening, 47 articles remained, which were critically analyzed. The interrater agreement was measured using a Cohen kappa test, and disagreements were resolved through discussion. The state-of-the-art classes of machine learning have been developed and tested up to the task and achieved promising performance including artificial neural network, support vector machine, decision tree, genetic algorithm, Gaussian process regression, Bayesian neural network, deep belief network, and others. CONCLUSIONS Despite the complexity of BG dynamics, there are many attempts to capture hypoglycemia and hyperglycemia incidences and the extent of an individual’s GV using different approaches. Recently, the advancement of diabetes technologies and continuous accumulation of self-collected health data have paved the way for popularity of machine learning in these tasks. According to the review, most of the identified studies used a theoretical threshold, which suffers from inter- and intrapatient variation. Therefore, future studies should consider the difference among patients and also track its temporal change over time. Moreover, studies should also give more emphasis on the types of inputs used and their associated time lag. Generally, we foresee that these developments might encourage researchers to further develop and test these systems on a large-scale basis.

Download Full-text

Data-driven modeling and prediction of blood glucose dynamics: Machine learning applications in type 1 diabetes

Artificial Intelligence in Medicine ◽

10.1016/j.artmed.2019.07.007 ◽

2019 ◽

Vol 98 ◽

pp. 109-134 ◽

Cited By ~ 18

Author(s):

Ashenafi Zebene Woldaregay ◽

Eirik Årsand ◽

Ståle Walderhaug ◽

David Albers ◽

Lena Mamykina ◽

...

Keyword(s):

Machine Learning ◽

Type 1 Diabetes ◽

Blood Glucose ◽

Data Driven ◽

Modeling And Prediction ◽

Machine Learning Applications ◽

Data Driven Modeling ◽

Glucose Dynamics

Download Full-text

Data-Driven Blood Glucose Pattern Classification and Anomalies Detection: Machine-Learning Applications in Type 1 Diabetes

Journal of Medical Internet Research ◽

10.2196/11030 ◽

2019 ◽

Vol 21 (5) ◽

pp. e11030 ◽

Cited By ~ 14

Author(s):

Ashenafi Zebene Woldaregay ◽

Eirik Årsand ◽

Taxiarchis Botsis ◽

David Albers ◽

Lena Mamykina ◽

...

Keyword(s):

Machine Learning ◽

Type 1 Diabetes ◽

Blood Glucose ◽

Pattern Classification ◽

Data Driven ◽

Machine Learning Applications

Download Full-text

A Comparison of Feature Selection and Forecasting Machine Learning Algorithms for Predicting Glycaemia in Type 1 Diabetes Mellitus

Applied Sciences ◽

10.3390/app11041742 ◽

2021 ◽

Vol 11 (4) ◽

pp. 1742

Author(s):

Ignacio Rodríguez-Rodríguez ◽

José-Víctor Rodríguez ◽

Wai Lok Woo ◽

Bo Wei ◽

Domingo-Javier Pardo-Quiles

Keyword(s):

Diabetes Mellitus ◽

Machine Learning ◽

Type 1 Diabetes ◽

Feature Selection ◽

Blood Glucose ◽

Type 1 Diabetes Mellitus ◽

Support Vector ◽

Chronic Hyperglycemia ◽

Predictive Algorithms

Type 1 diabetes mellitus (DM1) is a metabolic disease derived from falls in pancreatic insulin production resulting in chronic hyperglycemia. DM1 subjects usually have to undertake a number of assessments of blood glucose levels every day, employing capillary glucometers for the monitoring of blood glucose dynamics. In recent years, advances in technology have allowed for the creation of revolutionary biosensors and continuous glucose monitoring (CGM) techniques. This has enabled the monitoring of a subject’s blood glucose level in real time. On the other hand, few attempts have been made to apply machine learning techniques to predicting glycaemia levels, but dealing with a database containing such a high level of variables is problematic. In this sense, to the best of the authors’ knowledge, the issues of proper feature selection (FS)—the stage before applying predictive algorithms—have not been subject to in-depth discussion and comparison in past research when it comes to forecasting glycaemia. Therefore, in order to assess how a proper FS stage could improve the accuracy of the glycaemia forecasted, this work has developed six FS techniques alongside four predictive algorithms, applying them to a full dataset of biomedical features related to glycaemia. These were harvested through a wide-ranging passive monitoring process involving 25 patients with DM1 in practical real-life scenarios. From the obtained results, we affirm that Random Forest (RF) as both predictive algorithm and FS strategy offers the best average performance (Root Median Square Error, RMSE = 18.54 mg/dL) throughout the 12 considered predictive horizons (up to 60 min in steps of 5 min), showing Support Vector Machines (SVM) to have the best accuracy as a forecasting algorithm when considering, in turn, the average of the six FS techniques applied (RMSE = 20.58 mg/dL).

Download Full-text

A Comparison of Machine Learning Algorithms in Blood Glucose Prediction for People with Type 1 Diabetes

10.1145/3500931.3500993 ◽

2021 ◽

Author(s):

Yiyang Wang

Keyword(s):

Machine Learning ◽

Type 1 Diabetes ◽

Blood Glucose ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Glucose Prediction

Download Full-text

Multi-Hour Blood Glucose Prediction in Type 1 Diabetes: A Patient-Specific Approach Using Shallow Neural Network Models

Diabetes Technology & Therapeutics ◽

10.1089/dia.2020.0061 ◽

2020 ◽

Vol 22 (12) ◽

pp. 883-891 ◽

Cited By ~ 1

Author(s):

Taisa Kushner ◽

Marc D. Breton ◽

Sriram Sankaranarayanan

Keyword(s):

Neural Network ◽

Type 1 Diabetes ◽

Blood Glucose ◽

Network Models ◽

Patient Specific ◽

Neural Network Models ◽

Specific Approach ◽

Glucose Prediction

Download Full-text

Using Absorption Models for Insulin and Carbohydrates and Deep Leaning to Improve Glucose Level Predictions

Sensors ◽

10.3390/s21165273 ◽

2021 ◽

Vol 21 (16) ◽

pp. 5273

Author(s):

Laura Martínez-Delgado ◽

Mario Munoz-Organero ◽

Paula Queipo-Alvarez

Keyword(s):

Machine Learning ◽

Type 1 Diabetes ◽

Blood Glucose ◽

Glucose Level ◽

The Body ◽

World Health ◽

Glucose Levels ◽

Preventive Actions ◽

Health Organization

Diabetes is a chronic disease caused by the inability of the pancreas to produce insulin or problems in the body to use it efficiently. It is one of the fastest growing health challenges affecting more than 400 million people worldwide, according to the World Health Organization. Intensive research is being carried out on artificial intelligence methods to help people with diabetes to optimize the way in which they use insulin, carbohydrate intakes, or physical activity. By predicting upcoming levels of blood glucose concentrations, preventive actions can be taken. Previous research studies using machine learning methods for blood glucose level predictions have mainly focused on the machine learning model used. Little attention has been given to the pre-processing of insulin and carbohydrate signals in order to mimic the human absorption processes. In this manuscript, a recurrent neural network (RNN) based model for predicting upcoming blood glucose levels in people with type 1 diabetes is combined with several carbohydrate and insulin absorption curves in order to optimize the prediction results. The proposed method is applied to data from real patients suffering type 1 diabetes mellitus (T1DM). The achieved results are encouraging, obtaining accuracy levels around 0.510 mmol/L (9.2 mg/dl) in the best scenario.

Download Full-text

Hybrid Closed-Loop Insulin Delivery Systems for People With Type 1 Diabetes

Canadian Journal of Health Technologies ◽

10.51731/cjht.2021.50 ◽

2021 ◽

Vol 1 (3) ◽

Author(s):

CADTH Health Technology Assessment Service

Keyword(s):

Type 1 Diabetes ◽

Blood Glucose ◽

Closed Loop ◽

Insulin Pump ◽

Insulin Delivery ◽

Blood Glucose Monitoring ◽

Self Management ◽

Publicly Funded ◽

Delivery Methods

Blood glucose monitoring and insulin delivery are essential parts of the management of type 1 diabetes. Hybrid closed-loop insulin delivery (HCL) systems are a treatment option for people with type 1 diabetes and consist of an insulin pump, a continuous glucose monitor (CGM), and a computer program (algorithm) that allows the devices to communicate with each other and calculates insulin needs. CADTH conducted a Health Technology Assessment (HTA) of the use of HCL systems compared to other insulin delivery methods in people with type 1 diabetes to inform decisions regarding whether HCL systems have a place in the management of type 1 diabetes. HCL therapy generally improved the amount of time a person spent in target blood glucose ranges. Additionally, people who used HCL systems had improved average blood glucose levels (glycated hemoglobin [A1C]) over the preceding 2 or 3 months. However, the effectiveness or safety of HCL systems based on age, sex, race, glucose management, or other clinical features (e.g., those who are pregnant or planning pregnancy, or who have hypoglycemia unawareness or a history of severe hypoglycemia) is unknown. HCL systems were generally as safe as other insulin delivery methods. Additional studies with longer follow-up periods and more participants are needed to confirm the clinical effectiveness and safety of HCL systems. From a pan-Canadian, publicly funded health care system perspective, the cost of covering HCL systems for individuals with type 1 diabetes who are eligible for insulin pumps in their jurisdictions was estimated to be an additional $822,635,045 over 3 years compared with diabetes supplies that are currently covered. If HCL systems are covered for all individuals with type 1 diabetes, regardless of their current insulin-pump eligibility, the budget impact will be higher. HCL systems can help provide distance from demanding self-management and monitoring tasks for people living with type 1 diabetes; however, in order to do this, people using these systems must navigate complex relationships built on trust and collaboration. Given that type 1 diabetes self-management to date has required considerable attention to blood glucose numbers and technical tasks, developing these relationships of trust and collaboration will require a shift in understanding what it means to care for someone who has — or to self-manage — type 1 diabetes. It is not possible to conclude whether HCL systems will improve overall population health over the longer-term because the data for this are not available. It is also unclear which people with type 1 diabetes would benefit most from HCL systems. Eligibility criteria for the existing public insulin-pump program may be useful in making coverage decisions; trial periods may be considered to ensure HCL systems are working well for new users. Education and support are needed for people living with type 1 diabetes when they start to use HCL systems. Clinicians noted the need for interactions between diabetes educators and HCL system pump users. User-friendly devices and understandable reports are key to effective use. Eligibility for access through any publicly funded program for HCL systems should be based on evidence. The criteria for coverage should be consistent with broader public health goals and should not contribute to existing inequities in diabetes management.

Download Full-text

Protein sequence design with a learned potential

10.1101/2020.01.06.895466 ◽

2020 ◽

Cited By ~ 5

Author(s):

Namrata Anand-Achim ◽

Raphael R. Eguchi ◽

Alexander Derry ◽

Russ B. Altman ◽

Po-Ssu Huang

Keyword(s):

Neural Network ◽

Machine Learning ◽

Deep Learning ◽

Amino Acid ◽

Protein Design ◽

Protein Sequence ◽

State Of The Art ◽

The State ◽

Energy Functions ◽

Sequence Design

AbstractThe primary challenge of fixed-backbone protein design is to find a distribution of sequences that fold to the backbone of interest. This task is central to nearly all protein engineering problems, as achieving a particular backbone conformation is often a prerequisite for hosting specific functions. In this study, we investigate the capability of a deep neural network to learn the requisite patterns needed to design sequences. The trained model serves as a potential function defined over the space of amino acid identities and rotamer states, conditioned on the local chemical environment at each residue. While most deep learning based methods for sequence design only produce amino acid sequences, our method generates full-atom structural models, which can be evaluated using established sequence quality metrics. Under these metrics we are able to produce realistic and variable designs with quality comparable to the state-of-the-art. Additionally, we experimentally test designs for a de novo TIM-barrel structure and find designs that fold, demonstrating the algorithm’s generalizability to novel structures. Overall, our results demonstrate that a deep learning model can match state-of-the-art energy functions for guiding protein design.SignificanceProtein design tasks typically depend on carefully modeled and parameterized heuristic energy functions. In this study, we propose a novel machine learning method for fixed-backbone protein sequence design, using a learned neural network potential to not only design the sequence of amino acids but also select their side-chain configurations, or rotamers. Factoring through a structural representation of the protein, the network generates designs on par with the state-of-the-art, despite having been entirely learned from data. These results indicate an exciting future for protein design driven by machine learning.

Download Full-text

Self-Reported Compensation Techniques for Carbohydrate, Exercise, and Alcohol Behaviors in Patients With Type 1 Diabetes on Insulin Pump Therapy

Journal of Diabetes Science and Technology ◽

10.1177/1932296817718848 ◽

2017 ◽

Vol 12 (2) ◽

pp. 412-414 ◽

Cited By ~ 3

Author(s):

Danielle Groat ◽

Hiral Soni ◽

Maria Adela Grando ◽

Bithika Thompson ◽

Curtiss B. Cook

Keyword(s):

Type 1 Diabetes ◽

Blood Glucose ◽

Insulin Pump ◽

Insulin Pump Therapy ◽

Self Management ◽

Pump Therapy ◽

Electronic Survey ◽

Alcohol Behaviors ◽

Management Behaviors

Studies have found variability in self-care behaviors in patients with type 1 diabetes, particularly when incorporating exercise and alcohol consumption. The objective of this study was to provide results from a survey to understand (1) insulin pump behaviors, (2) reported self-management behaviors for exercise and alcohol, and (3) perceptions of the effects of exercise and alcohol on blood glucose (BG) control. Fourteen participants from an outpatient endocrinology practice were recruited and administered an electronic survey. Compensation techniques for exercise and alcohol, along with reasons for employing the techniques were identified. Also identified were factors that participants said affected BG control with regard to exercise and alcohol. These results confirm the considerable inconsistency patients have about incorporating exercise and alcohol into decisions about self-management behaviors.

Download Full-text