Electrocardiographic signals and swarm-based support vector machine for hypoglycemia detection

A novel hypoglycemia alarm framework for type 2 diabetes with high glycemic variability

In patients with type 2 diabetes (T2D), accurate prediction of hypoglycemic events is crucial for maintaining glycemic control and reducing their frequency. However, individuals with high blood glucose variability experience significant fluctuations over time, posing a challenge for early warning models that rely on static features. This article proposes a novel hypoglycemia early alarm framework based on dynamic feature selection. The framework incorporates domain knowledge and introduces multi-scale blood glucose features, including predicted values, essential for early warnings. To address the complexity of the feature matrix, a dynamic feature selection mechanism (Relief-SVM-RFE) is designed to effectively eliminate redundancy. Furthermore, the framework employs online updates for the random forest model, enhancing the learning of more relevant features. The effectiveness of the framework was evaluated using a clinical dataset. For T2D patients with a high coefficient of variation (CV), the framework achieved a sensitivity of 81.15% and specificity of 98.14%, accurately predicting most hypoglycemic events. Notably, the proposed method outperformed other existing approaches. These results indicate the feasibility of anticipating hypoglycemic events in T2D patients with high CV using this innovative framework.

Machine Learning Models for Blood Glucose Level Prediction in Patients With Diabetes Mellitus: Systematic Review and Network Meta-Analysis

BACKGROUND

Machine learning (ML) models provide more choices to patients with diabetes mellitus (DM) to more properly manage blood glucose (BG) levels. However, because of numerous types of ML algorithms, choosing an appropriate model is vitally important.

OBJECTIVE

In a systematic review and network meta-analysis, this study aimed to comprehensively assess the performance of ML models in predicting BG levels. In addition, we assessed ML models used to detect and predict adverse BG (hypoglycemia) events by calculating pooled estimates of sensitivity and specificity.

METHODS

PubMed, Embase, Web of Science, and Institute of Electrical and Electronics Engineers Explore databases were systematically searched for studies on predicting BG levels and predicting or detecting adverse BG events using ML models, from inception to November 2022. Studies that assessed the performance of different ML models in predicting or detecting BG levels or adverse BG events of patients with DM were included. Studies with no derivation or performance metrics of ML models were excluded. The Quality Assessment of Diagnostic Accuracy Studies tool was applied to assess the quality of included studies. Primary outcomes were the relative ranking of ML models for predicting BG levels in different prediction horizons (PHs) and pooled estimates of the sensitivity and specificity of ML models in detecting or predicting adverse BG events.

RESULTS

In total, 46 eligible studies were included for meta-analysis. Regarding ML models for predicting BG levels, the means of the absolute root mean square error (RMSE) in a PH of 15, 30, 45, and 60 minutes were 18.88 (SD 19.71), 21.40 (SD 12.56), 21.27 (SD 5.17), and 30.01 (SD 7.23) mg/dL, respectively. The neural network model (NNM) showed the highest relative performance in different PHs. Furthermore, the pooled estimates of the positive likelihood ratio and the negative likelihood ratio of ML models were 8.3 (95% CI 5.7-12.0) and 0.31 (95% CI 0.22-0.44), respectively, for predicting hypoglycemia and 2.4 (95% CI 1.6-3.7) and 0.37 (95% CI 0.29-0.46), respectively, for detecting hypoglycemia.

CONCLUSIONS

Statistically significant high heterogeneity was detected in all subgroups, with different sources of heterogeneity. For predicting precise BG levels, the RMSE increases with a rise in the PH, and the NNM shows the highest relative performance among all the ML models. Meanwhile, current ML models have sufficient ability to predict adverse BG events, while their ability to detect adverse BG events needs to be enhanced.

TRIAL REGISTRATION

PROSPERO CRD42022375250; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=375250.

Cuffless Hypertension Detection using Swarm Support Vector Machine Utilizing Photoplethysmogram and Electrocardiogram

Background

Hypertension is associated with severe complications, and its detection is important to provide early information about a hypertension event, which is essential to prevent further complications.

Objective

This study aimed to investigate a strategy for hypertension detection without a cuff using parameters of bioelectric signals, i.e., Electrocardiogram (ECG), Photoplethysmogram (PPG,) and an algorithm of Swarm-based Support Vector Machine (SSVM).

Material and Methods

This experimental study was conducted to develop a hypertension detection system. ECG and PPG bioelectrical records were collected from the Medical Information Mart for Intensive Care (MIMIC) from normal and hypertension participants and processed to find the parameters, used for the inputs of SSVM and comprised Pulse Arrival Time (PAT) and the characteristics of PPG signal derivatives. The SSVM was n Support Vector Machine (SVM) algorithm optimized using particle swarm optimization with Quantum Delta-potential-well (QDPSO). The SSVMs with different inputs were investigated to find the optimal detection performance.

Results

The proposed strategy was performed at 96% in terms of F1-score, accuracy, sensitivity, and specificity with better performance than the other methods tested and methods and also could develop a cuff-free hypertension monitoring system.

Conclusion

Hypertension using SSVM, ECG, and PPG parameters is acceptably performed. The hypertension detection had lower performance utilizing only PPG than both ECG and PPG.

Development of an artificial intelligence system to identify hypoglycaemia via ECG in adults with type 1 diabetes: protocol for data collection under controlled and free-living conditions

INTRODUCTION

Hypoglycaemia is a harmful potential complication in people with type 1 diabetes mellitus (T1DM) and can be exacerbated in patients receiving treatment, such as insulin therapies, by the very interventions aiming to achieve optimal blood glucose levels. Symptoms can vary greatly, including, but not limited to, trembling, palpitations, sweating, dry mouth, confusion, seizures, coma, brain damage or even death if untreated. A pilot study with healthy (euglycaemic) participants previously demonstrated that hypoglycaemia can be detected non-invasively with artificial intelligence (AI) using physiological signals obtained from wearable sensors. This protocol provides a methodological description of an observational study for obtaining physiological data from people with T1DM. The aim of this work is to further improve the previously developed AI model and validate its performance for glycaemic event detection in people with T1DM. Such a model could be suitable for integrating into a continuous, non-invasive, glucose monitoring system, contributing towards improving surveillance and management of blood glucose for people with diabetes.

METHODS AND ANALYSIS

This observational study aims to recruit 30 patients with T1DM from a diabetes outpatient clinic at the University Hospital Coventry and Warwickshire for a two-phase study. The first phase involves attending an inpatient protocol for up to 36 hours in a calorimetry room under controlled conditions, followed by a phase of free-living, for up to 3 days, in which participants will go about their normal daily activities unrestricted. Throughout the study, the participants will wear wearable sensors to measure and record physiological signals (eg, ECG and continuous glucose monitor). Data collected will be used to develop and validate an AI model using state-of-the-art deep learning methods.

ETHICS AND DISSEMINATION

This study has received ethical approval from National Research Ethics Service (ref: 17/NW/0277). The findings will be disseminated via peer-reviewed journals and presented at scientific conferences.

TRIAL REGISTRATION NUMBER

NCT05461144.

Non-invasive method for blood glucose monitoring using ECG signal

Introduction: Tight glucose monitoring is crucial for diabetic patients by using a Continuous Glucose Monitor (CGM). The existing CGMs measure the Blood Glucose Concentration (BGC) from the interstitial fluid. These technologies are quite expensive, and most of them are invasive. Previous studies have demonstrated that hypoglycemia and hyperglycemia episodes affect the electrophysiology of the heart. However, they did not determine a cohort relationship between BGC and ECG parameters.

Material and method: In this work, we propose a new method for determining the BGC using surface ECG signals. Recurrent Convolutional Neural Networks (RCNN) were applied to segment the ECG signals. Then, the extracted features were employed to determine the BGC using two mathematical equations. This method has been tested on 04 patients over multiple days from the D1namo dataset, using surface ECG signals instead of intracardiac signal.

Results: We were able to segment the ECG signals with an accuracy of 94% using the RCNN algorithm. According to the results, the proposed method was able to estimate the BGC with a Mean Absolute Error (MAE) of 0.0539, and a Mean Squared Error (MSE) of 0.1604. In addition, the linear relationship between BGC and ECG features has been confirmed in this paper.

Conclusion: In this paper, we propose the potential use of ECG features to determine the BGC. Additionally, we confirmed the linear relationship between BGC and ECG features. That fact will open new perspectives for further research, namely physiological models. Furthermore, the findings point to the possible application of ECG wearable devices for non-invasive continuous blood glucose monitoring via machine learning.

Blood glucose estimation based on ECG signal

Successful self-management of diabetes requires Continuous Glucose Monitors (CGMs). These CGMs have several limitations such as being invasive, expensive and limited in terms of use. Many techniques, in vain, have been proposed to overcome these limitations. Nowadays, with the help of the Internet of Medical Things (IoMT) technologies, researchers are working to find alternative solutions. They succeed to predict hypoglycemia and hyperglycemia peaks using Electrocardiogram (ECG) signals. However, they failed to use it to estimate the Blood Glucose Concentration (BGC) directly and in real time. Three patients with 08 days of measurements from the D1namo dataset contributed to the study. A new technique has been proposed to estimate the BGC curves based on ECG signals. We used a convolutional neural network to segment the different regions of ECG signals as well as we extracted ECG features that were required for the next step. Then, five regression models have been employed to estimate BGC using as input sixth ECG parameters. We were able to segment the ECG signals with an accuracy of 94% using the convolutional neural network algorithm. The best performance among all simulated models was provided by Exponential Gaussian Process Regression (GPR) with Root Mean Squared Error (RMSE) values of 0.32, 0.41, 0.67 and R-squared (R²) values of 98%, 80%, and 70% for patients 01, 02 and 03 respectively. The method indicates the potential use of ECG wearable devices as non-invasive for continuous blood glucose monitoring, which is affordable and durable.

Diabetes Detection and Management through Photoplethysmographic and Electrocardiographic Signals Analysis: A Systematic Review

(1) Background: Diabetes mellitus (DM) is a chronic, metabolic disease characterized by elevated levels of blood glucose. Recently, some studies approached the diabetes care domain through the analysis of the modifications of cardiovascular system parameters. In fact, cardiovascular diseases are the first leading cause of death in diabetic subjects. Thanks to their cost effectiveness and their ease of use, electrocardiographic (ECG) and photoplethysmographic (PPG) signals have recently been used in diabetes detection, blood glucose estimation and diabetes-related complication detection. This review's aim is to provide a detailed overview of all the published methods, from the traditional (non machine learning) to the deep learning approaches, to detect and manage diabetes using PPG and ECG signals. This review will allow researchers to compare and understand the differences, in terms of results, amount of data and complexity that each type of approach provides and requires. (2) Method: We performed a systematic review based on articles that focus on the use of ECG and PPG signals in diabetes care. The search was focused on keywords related to the topic, such as "Diabetes", "ECG", "PPG", "Machine Learning", etc. This was performed using databases, such as PubMed, Google Scholar, Semantic Scholar and IEEE Xplore. This review's aim is to provide a detailed overview of all the published methods, from the traditional (non machine learning) to the deep learning approaches, to detect and manage diabetes using PPG and ECG signals. This review will allow researchers to compare and understand the differences, in terms of results, amount of data and complexity that each type of approach provides and requires. (3) Results: A total of 78 studies were included. The majority of the selected studies focused on blood glucose estimation (41) and diabetes detection (31). Only 7 studies focused on diabetes complications detection. We present these studies by approach: traditional, machine learning and deep learning approaches. (4) Conclusions: ECG and PPG analysis in diabetes care showed to be very promising. Clinical validation and data processing standardization need to be improved in order to employ these techniques in a clinical environment.

Machine Learning and Smart Devices for Diabetes Management: Systematic Review

(1) Background: The use of smart devices to better manage diabetes has increased significantly in recent years. These technologies have been introduced in order to make life easier for patients with diabetes by allowing better control of the stability of blood sugar levels and anticipating the occurrence of dangerous events (hypo/hyperglycemia), etc. That being said, the main objectives of the self-management of diabetes is to improve the lifestyle and life quality of patients with diabetes; (2) Methods: We performed a systematic review based on articles that focus on the use of smart devices for the monitoring and better management of diabetes. The search was focused on keywords related to the topic, such as “Diabetes”, “Technology”, “Self-management”, “Artificial Intelligence”, etc. This was performed using databases, such as Scopus, Google Scholar, and PubMed; (3) Results: A total of 89 studies, published between 2011 and 2021, were included. The majority of the selected research aims to solve a diabetes management problem (e.g., blood glucose prediction, early detection of risk events, and the automatic adjustment of insulin doses, etc.). In these studies, wearable devices were used in combination with artificial intelligence (AI) techniques; (4) Conclusions: Wearable devices have attracted a great deal of scientific interest in the field of healthcare for people with chronic conditions, such as diabetes. They are capable of assisting in the management of diabetes, as well as preventing complications associated with this condition. Furthermore, the usage of these devices has improved illness management and quality of life.

Machine learning approach in mortality rate prediction for hemodialysis patients

Kernel support vector machine algorithm and K-means clustering algorithm are used to determine the expected mortality rate for hemodialysis patients. The national nephrology database of Montenegro has been used to conduct this research. Mortality rate prediction is realized with accuracy up to 94.12% and up to 96.77%, when a complete database is observed and when a reduced database (that contains data for the three most common basic diseases) is observed, respectively. Additionally, it is shown that just a few parameters, most of which are collected during the sole patient examination, are enough for satisfying results.

Ability of Current Machine Learning Algorithms to Predict and Detect Hypoglycemia in Patients With Diabetes Mellitus: Meta-analysis

Background

Machine learning (ML) algorithms have been widely introduced to diabetes research including those for the identification of hypoglycemia.

Objective

The objective of this meta-analysis is to assess the current ability of ML algorithms to detect hypoglycemia (ie, alert to hypoglycemia coinciding with its symptoms) or predict hypoglycemia (ie, alert to hypoglycemia before its symptoms have occurred).

Methods

Electronic literature searches (from January 1, 1950, to September 14, 2020) were conducted using the Dialog platform that covers 96 databases of peer-reviewed literature. Included studies had to train the ML algorithm in order to build a model to detect or predict hypoglycemia and test its performance. The set of 2 × 2 data (ie, number of true positives, false positives, true negatives, and false negatives) was pooled with a hierarchical summary receiver operating characteristic model.

Results

A total of 33 studies (14 studies for detecting hypoglycemia and 19 studies for predicting hypoglycemia) were eligible. For detection of hypoglycemia, pooled estimates (95% CI) of sensitivity, specificity, positive likelihood ratio (PLR), and negative likelihood ratio (NLR) were 0.79 (0.75-0.83), 0.80 (0.64-0.91), 8.05 (4.79-13.51), and 0.18 (0.12-0.27), respectively. For prediction of hypoglycemia, pooled estimates (95% CI) were 0.80 (0.72-0.86) for sensitivity, 0.92 (0.87-0.96) for specificity, 10.42 (5.82-18.65) for PLR, and 0.22 (0.15-0.31) for NLR.

Conclusions

Current ML algorithms have insufficient ability to detect ongoing hypoglycemia and considerate ability to predict impeding hypoglycemia in patients with diabetes mellitus using hypoglycemic drugs with regard to diagnostic tests in accordance with the Users’ Guide to Medical Literature (PLR should be ≥5 and NLR should be ≤0.2 for moderate reliability). However, it should be emphasized that the clinical applicability of these ML algorithms should be evaluated according to patients’ risk profiles such as for hypoglycemia and its associated complications (eg, arrhythmia, neuroglycopenia) as well as the average ability of the ML algorithms. Continued research is required to develop more accurate ML algorithms than those that currently exist and to enhance the feasibility of applying ML in clinical settings.

Trial Registration

PROSPERO International Prospective Register of Systematic Reviews CRD42020163682; http://www.crd.york.ac.uk/PROSPERO/display_record.php?ID=CRD42020163682

Automatic Detection of Dynamic and Static Activities of the Older Adults Using a Wearable Sensor and Support Vector Machines

Although Support Vector Machines (SVM) are widely used for classifying human motion patterns, their application in the automatic recognition of dynamic and static activities of daily life in the healthy older adults is limited. Using a body mounted wireless inertial measurement unit (IMU), this paper explores the use of SVM approach for classifying dynamic (walking) and static (sitting, standing and lying) activities of the older adults. Specifically, data formatting and feature extraction methods associated with IMU signals are discussed. To evaluate the performance of the SVM algorithm, the effects of two parameters involved in SVM algorithm—the soft margin constant C and the kernel function parameter γ—are investigated. The changes associated with adding white-noise and pink-noise on these two parameters along with adding different sources of movement variations (i.e., localized muscle fatigue and mixed activities) are further discussed. The results indicate that the SVM algorithm is capable of keeping high overall accuracy by adjusting the two parameters for dynamic as well as static activities, and may be applied as a tool for automatically identifying dynamic and static activities of daily life in the older adults.

Automatic Detection of Dynamic and Static Activities of the Older Adults Using a Wearable Sensor and Support Vector Machines

Although Support Vector Machines (SVM) are widely used for classifying human motion patterns, their application in the automatic recognition of dynamic and static activities of daily life in the healthy older adults is limited. Using a body mounted wireless inertial measurement unit (IMU), this paper explores the use of SVM approach for classifying dynamic (walking) and static (sitting, standing and lying) activities of the older adults. Specifically, data formatting and feature extraction methods associated with IMU signals are discussed. To evaluate the performance of the SVM algorithm, the effects of two parameters involved in SVM algorithm—the soft margin constant C and the kernel function parameter γ—are investigated. The changes associated with adding white-noise and pink-noise on these two parameters along with adding different sources of movement variations (i.e., localized muscle fatigue and mixed activities) are further discussed. The results indicate that the SVM algorithm is capable of keeping high overall accuracy by adjusting the two parameters for dynamic as well as static activities, and may be applied as a tool for automatically identifying dynamic and static activities of daily life in the older adults.

Automatic Detection of Dynamic and Static Activities of the Older Adults Using a Wearable Sensor and Support Vector Machines

Although Support Vector Machines (SVM) are widely used for classifying human motion patterns, their application in the automatic recognition of dynamic and static activities of daily life in the healthy older adults is limited. Using a body mounted wireless inertial measurement unit (IMU), this paper explores the use of an SVM approach for classifying dynamic (walking) and static (sitting, standing and lying) activities of the older adults. Specifically, data formatting and feature extraction methods associated with IMU signals are discussed. To evaluate the performance of the SVM algorithm, the effects of two parameters involved in SVM algorithm—the soft margin constant C and the kernel function parameter γ —are investigated. The changes associated with adding white-noise and pink-noise on these two parameters along with adding different sources of movement variations (i.e., localized muscle fatigue and mixed activities) are further discussed. The results indicate that the SVM algorithm is capable of keeping high overall accuracy by adjusting the two parameters for dynamic as well as static activities, and may be applied as a tool for automatically identifying dynamic and static activities of daily life in the older adults.

A Comparison of Different Models of Glycemia Dynamics for Improved Type 1 Diabetes Mellitus Management with Advanced Intelligent Analysis in an Internet of Things Context

The metabolic disease Type 1 Diabetes Mellitus (DM1) is caused by a reduction in the production of pancreatic insulin, which causes chronic hyperglycemia. Patients with DM1 are required to perform multiple blood glucose measurements on a daily basis to monitor their blood glucose dynamics through the use of capillary glucometers. In more recent times, technological developments have led to the development of cutting-edge biosensors and Continuous Glucose Monitoring (CGM) systems that can monitor patients’ blood glucose levels on a real-time basis. This offers medical providers access to glucose oscillations modeling interventions that can enhance DM1 treatment and management approaches through the use of novel disruptive technologies, such as Cloud Computing (CC), big data, Intelligent Data Analysis (IDA) and the Internet of Things (IoT). This work applies some advanced modeling techniques to a complete data set of glycemia-related biomedical features—obtained through an extensive, passive monitoring campaign undertaken with 25 DM1 patients under real-world conditions—in order to model glucose level dynamics through the proper identification of patterns. Hereby, four methods, which are run through CC due to the high volume of data collected, are applied and compared within an IoT context. The results show that Bayesian Regularized Neural Networks (BRNN) offer the best performance (0.83 R2) with a reduced Root Median Squared Error (RMSE) of 14.03 mg/dL.

Automatic Detection of Dynamic and Static Activities of the Elderly using a Wearable Sensor and Support Vector Machines

Although Support Vector Machines (SVM) are widely used for classifying human motion patterns, their application in the automatic recognition of dynamic and static activities of daily life in the elderly is limited. Using a body mounted wireless inertial measurement unit (IMU), this paper explores the use of an SVM approach for classifying dynamic (walking) and static (sitting, standing and lying) activities of the elderly. Specifically, data formatting and feature extraction methods associated with IMU signals are discussed. To evaluate the performance of the SVM algorithm, the effects of two parameters involved in SVM algorithm—the soft margin constant C and the kernel function parameter —are investigated. The changes associated with adding white-noise and pink-noise on these two parameters along with adding different sources of movement variations (i.e., localized muscle fatigue and mixed activities) are further discussed. The results indicate that the SVM algorithm is capable of keeping high overall accuracy by adjusting the two parameters for dynamic as well as static activities, and may be applied as a tool for automatically identifying static and dynamic activities of daily life in the elderly.

Utility of Big Data in Predicting Short-Term Blood Glucose Levels in Type 1 Diabetes Mellitus Through Machine Learning Techniques

Machine learning techniques combined with wearable electronics can deliver accurate short-term blood glucose level prediction models. These models can learn personalized glucose–insulin dynamics based on the sensor data collected by monitoring several aspects of the physiological condition and daily activity of an individual. Until now, the prevalent approach for developing data-driven prediction models was to collect as much data as possible to help physicians and patients optimally adjust therapy. The objective of this work was to investigate the minimum data variety, volume, and velocity required to create accurate person-centric short-term prediction models. We developed a series of these models using different machine learning time series forecasting techniques suitable for execution within a wearable processor. We conducted an extensive passive patient monitoring study in real-world conditions to build an appropriate data set. The study involved a subset of type 1 diabetic subjects wearing a flash glucose monitoring system. We comparatively and quantitatively evaluated the performance of the developed data-driven prediction models and the corresponding machine learning techniques. Our results indicate that very accurate short-term prediction can be achieved by only monitoring interstitial glucose data over a very short time period and using a low sampling frequency. The models developed can predict glucose levels within a 15-min horizon with an average error as low as 15.43 mg/dL using only 24 historic values collected within a period of sex hours, and by increasing the sampling frequency to include 72 values, the average error is reduced to 10.15 mg/dL. Our prediction models are suitable for execution within a wearable device, requiring the minimum hardware requirements while at simultaneously achieving very high prediction accuracy.

Feature Selection for Blood Glucose Level Prediction in Type 1 Diabetes Mellitus by Using the Sequential Input Selection Algorithm (SISAL)

Feature selection is a primary exercise to tackle any forecasting task. Machine learning algorithms used to predict any variable can improve their performance by lessening their computational effort with a proper dataset. Anticipating future glycemia in type 1 diabetes mellitus (DM1) patients provides a baseline in its management, and in this task, we need to carefully select data, especially now, when novel wearable devices offer more and more information. In this paper, a complete characterization of 25 diabetic people has been carried out, registering innovative variables like sleep, schedule, or heart rate in addition to other well-known ones like insulin, meal, and exercise. With this ground-breaking data compilation, we present a study of these features using the Sequential Input Selection Algorithm (SISAL), which is specially prepared for time series data. The results rank features according to their importance, regarding their relevance in blood glucose level prediction as well as indicating the most influential past values to be taken into account and distinguishing features with person-dependent behavior from others with a common performance in any patient. These ideas can be used as strategies to select data for predicting glycemia depending on the availability of computational power, required speed, or required accuracy. In conclusion, this paper tries to analyze if there exists symmetry among the different features that can affect blood glucose levels, that is, if their behavior is symmetric in terms of influence in glycemia.

Text preprocessing for improving hypoglycemia detection from clinical notes - A case study of patients with diabetes

BACKGROUND AND OBJECTIVE

Hypoglycemia is a common safety event when attempting to optimize glycemic control in diabetes (DM). While electronic medical records provide a natural ground for detecting and analyzing hypoglycemia, ICD codes used in the databases may be invalid, insensitive or non-specific in detecting new hypoglycemic events. We developed text preprocessing methods to improve automatic detection of hypoglycemia from analysis of clinical encounter text notes.

METHODS

We set out to improve hypoglycemia detection from clinical notes by introducing three preprocessing methods: stop word filtering, medication signaling, and ICD narrative enrichment. To test the proposed methods, we selected clinical notes from VA Maryland Healthcare System, based on various combinations of three criteria that are suggestive of hypoglycemia, including ICD-9 code of diabetes and hypoglycemia, laboratory glucose values < 70 md/dL, and text reference to a proximate hypoglycemia event. In addition, we constructed one dataset of 395 clinical notes from year 2009 and another of 460 notes from year 2014 to test the generality of the proposed methods. For each of the datasets, two physician judges manually reviewed individual clinical notes to determine whether hypoglycemia was present or absent. A third physician judge served as a final adjudicator for disagreements.

RESULTS

Each of the proposed preprocessing methods contributed to the performance of hypoglycemia detection by significantly increasing the F1 score in the range of 5.3∼7.4% on one dataset (p < .01). Among the methods, stop word filtering contributed most to the performance improvement (7.4%). Combining all the preprocessing methods led to greater performance gain (p < .001) compared with using each method individually. Similar patterns were observed for the other dataset with the F1 score being increased in the range of 7.7%∼9.4% by individual methods (p < .001). Nevertheless, combining the three methods did not yield additional performance gain.

CONCLUSION

The proposed text preprocessing methods improved the performance of hypoglycemia detection from clinical text notes. Stop word filtering achieved the most performance improvement. ICD narrative enrichment boosted the recall of detection. Combining the three preprocessing methods led to additional performance gains.

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

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.

Prediction of hip fracture in post-menopausal women using artificial neural network approach

Hip fracture is one of the most serious health problems among post-menopausal women with osteoporosis. It is very difficult to predict hip fracture, because it is affected by multiple risk factors. Existing statistical models for predicting hip fracture risk yield area under the receiver operating characteristic curve (AUC) ~0.7-0.85. In this study, we trained an artificial neural network (ANN) to predict hip fracture in one cohort, and validated its predictive performance in another cohort. The data for training and validation included age, bone mineral density (BMD), clinical factors, and lifestyle factors which had been obtained from a longitudinal study that involved 1167 women aged 60 years and above. The women had been followed up for up to 10 years, and during the period, the incidence of new hip fractures was ascertained. We applied feed-forward neural networks to learn from the data, and then used the learning for predicting hip fracture. Results of prediction showed that the accuracy of model I (which included only lumbar spine and femoral neck BMD) and model II (which included non-BMD factors) was 82% and 84%, respectively. When both BMD and non-BMD factors were combined (Model III), the accuracy increased to 87%. The AUC for model III was 0.94. These findings indicate that ANNs are able to predict hip fracture more accurately than any existing statistical models, and that ANNs can help stratify individuals for clinical management.

Sensor Monitoring of Physical Activity to Improve Glucose Management in Diabetic Patients: A Review

Diabetic individuals need to tightly control their blood glucose concentration. Several methods have been developed for this purpose, such as the finger-prick or continuous glucose monitoring systems (CGMs). However, these methods present the disadvantage of being invasive. Moreover, CGMs have limited accuracy, notably to detect hypoglycemia. It is also known that physical exercise, and even daily activity, disrupt glucose dynamics and can generate problems with blood glucose regulation during and after exercise. In order to deal with these challenges, devices for monitoring patients’ physical activity are currently under development. This review focuses on non-invasive sensors using physiological parameters related to physical exercise that were used to improve glucose monitoring in type 1 diabetes (T1DM) patients. These devices are promising for diabetes management. Indeed they permit to estimate glucose concentration either based solely on physical activity parameters or in conjunction with CGM or non-invasive CGM (NI-CGM) systems. In these last cases, the vital signals are used to modulate glucose estimations provided by the CGM and NI-CGM devices. Finally, this review indicates possible limitations of these new biosensors and outlines directions for future technologic developments.

Neural network approach for non-invasive detection of hyperglycemia using electrocardiographic signals

Hyperglycemia or high blood glucose (sugar) level is a common dangerous complication among patients with Type 1 diabetes mellitus (T1DM). Hyperglycemia can cause serious health problems if left untreated such as heart disease, stroke, vision and nerve problems. Based on the electrocardiographic (ECG) parameters, we have identified hyperglycemic and normoglycemic states in T1DM patients. In this study, a classification unit is introduced with the approach of feed forward multi-layer neural network to detect the presences of hyperglycemic/normoglycemic episodes using ECG parameters as inputs. A practical experiment using the real T1DM patients' data sets collected from Department of Health, Government of Western Australia is studied. Experimental results show that proposed ECG parameters contributed significantly to the good performance of hyperglycemia detections in term of sensitivity, specificity and geometric mean (70.59%, 65.38%, and 67.94%, respectively). From these results, it is proved that hyperglycemic events in T1DM can be detected non-invasively and effectively by using ECG signals and ANN approach.

Hypo- and Hyperglycemic Alarms: Devices and Algorithms

Soon after the discovery that insulin regulates blood glucose by Banting and Best in 1922, the symptoms and risks associated with hypoglycemia became widely recognized. This article reviews devices to warn individuals of impending hypo- and hyperglycemia; biosignals used by these devices include electroencephalography, electrocardiography, skin galvanic resistance, diabetes alert dogs, and continuous glucose monitors (CGMs). While systems based on other technology are increasing in performance and decreasing in size, CGM technology remains the best method for both reactive and predictive alarming of hypo- or hyperglycemia.

Evolvable rough-block-based neural network and its biomedical application to hypoglycemia detection system

This paper focuses on the hybridization technology using rough sets concepts and neural computing for decision and classification purposes. Based on the rough set properties, the lower region and boundary region are defined to partition the input signal to a consistent (predictable) part and an inconsistent (random) part. In this way, the neural network is designed to deal only with the boundary region, which mainly consists of an inconsistent part of applied input signal causing inaccurate modeling of the data set. Owing to different characteristics of neural network (NN) applications, the same structure of conventional NN might not give the optimal solution. Based on the knowledge of application in this paper, a block-based neural network (BBNN) is selected as a suitable classifier due to its ability to evolve internal structures and adaptability in dynamic environments. This architecture will systematically incorporate the characteristics of application to the structure of hybrid rough-block-based neural network (R-BBNN). A global training algorithm, hybrid particle swarm optimization with wavelet mutation is introduced for parameter optimization of proposed R-BBNN. The performance of the proposed R-BBNN algorithm was evaluated by an application to the field of medical diagnosis using real hypoglycemia episodes in patients with Type 1 diabetes mellitus. The performance of the proposed hybrid system has been compared with some of the existing neural networks. The comparison results indicated that the proposed method has improved classification performance and results in early convergence of the network.

Evaluation of an Algorithm for Retrospective Hypoglycemia Detection Using Professional Continuous Glucose Monitoring Data

BACKGROUND

People with type 1 diabetes (T1D) are unable to produce insulin and thus rely on exogenous supply to lower their blood glucose. Studies have shown that intensive insulin therapy reduces the risk of late-diabetic complications by lowering average blood glucose. However, the therapy leads to increased incidence of hypoglycemia. Although inaccurate, professional continuous glucose monitoring (PCGM) can be used to identify hypoglycemic events, which can be useful for adjusting glucose-regulating factors. New pattern classification approaches based on identifying hypoglycemic events through retrospective analysis of PCGM data have shown promising results. The aim of this study was to evaluate a new pattern classification approach by comparing the performance with a newly developed PCGM calibration algorithm.

METHODS

Ten male subjects with T1D were recruited and monitored with PCGM and self-monitoring blood glucose during insulin-induced hypoglycemia. A total of 19 hypoglycemic events occurred during the sessions.

RESULTS

The pattern classification algorithm detected 19/19 hypoglycemic events with 1 false positive, while the PCGM with the new calibration algorithm detected 17/19 events with 2 false positives.

CONCLUSIONS

We can conclude that even after the introduction of new calibration algorithms, the pattern classification approach is still a valuable addition for improving retrospective hypoglycemia detection using PCGM.

A novel adaptive-weighted-average framework for blood glucose prediction

BACKGROUND

Blood glucose (BG) prediction plays a very important role in daily BG management of patients with diabetes mellitus. Several algorithms, such as autoregressive (AR) models and artificial neural networks, have been proposed for BG prediction. However, every algorithm has its own subject range (i.e., one algorithm might work well for one diabetes patient but poorly for another patient). Even for one individual patient, this algorithm might perform well during the preprandial period but poorly during the postprandial period.

MATERIALS AND METHODS

A novel framework was proposed to combine several BG prediction algorithms. The main idea of the novel framework is that an adaptive weight is given to each algorithm where one algorithm's weight is inversely proportional to the sum of the squared prediction errors. In general, this framework can be applied to combine any BG prediction algorithms.

RESULTS

As an example, the proposed framework was used to combine an AR model, extreme learning machine, and support vector regression. The new algorithm was compared with these three prediction algorithms on the continuous glucose monitoring system (CGMS) readings of 10 type 1 diabetes mellitus patients; the CGMS readings of each patient included 860 CGMS data points. For each patient, the algorithms were evaluated in terms of root-mean-square error, relative error, Clarke error-grid analysis, and J index. Of the 40 evaluations, the new adaptive-weighted algorithm achieved the best prediction performance in 37 (92.5%).

CONCLUSIONS

Thus, we conclude that the adaptive-weighted-average framework proposed in this study can give satisfactory predictions and should be used in BG prediction. The new algorithm has great robustness with respect to variations in data characteristics, patients, and prediction horizons. At the same time, it is universal.

Professional continuous glucose monitoring in subjects with type 1 diabetes: retrospective hypoglycemia detection

BACKGROUND

An important task in diabetes management is detection of hypoglycemia. Professional continuous glucose monitoring (CGM), which produces a glucose reading every 5 min, is a powerful tool for retrospective identification of unrecognized hypoglycemia. Unfortunately, CGM devices tend to be inaccurate, especially in the hypoglycemic range, which limits their applicability for hypoglycemia detection. The objective of this study was to develop an automated pattern recognition algorithm to detect hypoglycemic events in retrospective, professional CGM.

METHOD

Continuous glucose monitoring and plasma glucose (PG) readings were obtained from 17 data sets of 10 type 1 diabetes patients undergoing insulin-induced hypoglycemia. The CGM readings were automatically classified into a hypoglycemic group and a nonhypoglycemic group on the basis of different features from CGM readings and insulin injection. The classification was evaluated by comparing the automated classification with PG using sample-based and event-based sensitivity and specificity measures.

RESULTS

With an event-based sensitivity of 100%, the algorithm produced only one false hypoglycemia detection. The sample-based sensitivity and specificity levels were 78% and 96%, respectively.

CONCLUSIONS

The automated pattern recognition algorithm provides a new approach for detecting unrecognized hypoglycemic events in professional CGM data. The tool may assist physicians and diabetologists in conducting a more thorough evaluation of the diabetes patient's glycemic control and in initiating necessary measures for improving glycemic control.

NON-INVASIVE NOCTURNAL HYPOGLYCEMIA DETECTION FOR INSULIN-DEPENDENT DIABETES MELLITUS USING GENETIC FUZZY LOGIC METHOD

Hypoglycemia, or low blood glucose, is the most common complication experienced by Type 1 diabetes mellitus (T1DM) patients. It is dangerous and can result in unconsciousness, seizures and even death. The most common physiological parameter to be effected from hypoglycemic reaction are heart rate (HR) and correct QT interval (QTc) of the electrocardiogram (ECG) signal. Based on physiological parameters, a genetic algorithm based fuzzy reasoning model is developed to recognize the presence of hypoglycemia. To optimize the parameters of the fuzzy model in the membership functions and fuzzy rules, a genetic algorithm is used. A validation strategy based adjustable fitness is introduced in order to prevent the phenomenon of overtraining (overfitting). For this study, 15 children with 569 sampling data points with Type 1 diabetes volunteered for an overnight study. The effectiveness of the proposed algorithm is found to be satisfactory by giving better sensitivity and specificity compared with other existing methods for hypoglycemia detection.