Empirical investigation of multi-tier ensembles for the detection of cardiac autonomic neuropathy using subsets of the Ewing Features

This article is devoted to an empirical investigation of per- formance of several new large multi-tier ensembles for the detection of cardiac autonomic neuropathy (CAN) in diabetes patients using subsets of the Ewing features. We used new data collected by the diabetes screening research initiative (DiScRi) project, which is more than ten times larger than the data set originally used by Ewing in the investigation of CAN. The results show that new multi-tier ensembles achieved better performance compared with the outcomes published in the literature previously. The best accuracy 97.74% of the detection of CAN has been achieved by the novel multi-tier combination of AdaBoost and Bagging, where AdaBoost is used at the top tier and Bagging is used at the middle tier, for the set consisting of the following four Ewing features: the deep breathing heart rate change, the Valsalva manoeuvre heart rate change, the hand grip blood pressure change and the lying to standing blood pressure change.

Improving classifications for cardiac autonomic neuropathy using multi-level ensemble classifiers and feature selection based on random forest

This paper is devoted to empirical investigation of novel multi-level ensemble meta classifiers for the detection and monitoring of progression of cardiac autonomic neuropathy, CAN, in diabetes patients. Our experiments relied on an extensive database and concentrated on ensembles of ensembles, or multi-level meta classifiers, for the classification of cardiac autonomic neuropathy progression. First, we carried out a thorough investigation comparing the performance of various base classifiers for several known sets of the most essential features in this database and determined that Random Forest significantly and consistently outperforms all other base classifiers in this new application. Second, we used feature selection and ranking implemented in Random Forest. It was able to identify a new set of features, which has turned out better than all other sets considered for this large and well-known database previously. Random Forest remained the very best classier for the new set of features too. Third, we investigated meta classifiers and new multi-level meta classifiers based on Random Forest, which have improved its performance. The results obtained show that novel multi-level meta classifiers achieved further improvement and obtained new outcomes that are significantly better compared with the outcomes published in the literature previously for cardiac autonomic neuropathy.

Enhancing predictive accuracy of cardiac autonomic neuropathy using blood biochemistry features and iterative multitier ensembles

Blood biochemistry attributes form an important class of tests, routinely collected several times per year for many patients with diabetes. The objective of this study is to investigate the role of blood biochemistry for improving the predictive accuracy of the diagnosis of cardiac autonomic neuropathy (CAN) progression. Blood biochemistry contributes to CAN, and so it is a causative factor that can provide additional power for the diagnosis of CAN especially in the absence of a complete set of Ewing tests. We introduce automated iterative multitier ensembles (AIME) and investigate their performance in comparison to base classifiers and standard ensemble classifiers for blood biochemistry attributes. AIME incorporate diverse ensembles into several tiers simultaneously and combine them into one automatically generated integrated system so that one ensemble acts as an integral part of another ensemble. We carried out extensive experimental analysis using large datasets from the diabetes screening research initiative (DiScRi) project. The results of our experiments show that several blood biochemistry attributes can be used to supplement the Ewing battery for the detection of CAN in situations where one or more of the Ewing tests cannot be completed because of the individual difficulties faced by each patient in performing the tests. The results show that AIME provide higher accuracy as a multitier CAN classification paradigm. The best predictive accuracy of 99.57% has been obtained by the AIME combining decorate on top tier with bagging on middle tier based on random forest. Practitioners can use these findings to increase the accuracy of CAN diagnosis.

Analyzing systolic-diastolic interval interaction characteristics in diabetic cardiac autonomic neuropathy progression

Cardiac autonomic neuropathy (CAN), one of the major complications in diabetes, if detected at the subclinical stage allows for effective treatment and avoiding further complication including cardiovascular pathology. Surface ECG (Electrocardiogram)-based diagnosis of CAN is useful to overcome the limitation of existing cardiovascular autonomic reflex tests traditionally used for CAN identification in clinical settings. The aim of this paper is to analyze the changes in the mechanical function of the ventricles in terms of systolic-diastolic interval interaction (SDI) from a surface ECG to assess the severity of CAN progression [no CAN, early CAN (ECAN) or subclinical CAN, and definite CAN (DCAN) or clinical CAN]. ECG signals recorded in supine resting condition from 72 diabetic subjects without CAN (CAN-) and 70 diabetic subjects with CAN were analyzed in this paper. The severity of CAN was determined by Ewing's Cardiovascular autonomic reflex tests. Fifty-five subjects of the CAN group had ECAN and 15 subjects had DCAN. In this paper, we propose an improved version of the SDI parameter (i.e., TQ/RR interval ratio) measured from the electrical diastolic interval (i.e., TQ interval) and the heart rate interval (i.e., RR interval). The performance of the proposed SDI measure was compared with the performance of the existing SDI measure (i.e., QT/TQ interval ratio). The proposed SDI parameter showed significant differences among three groups (no CAN, ECAN, and DCAN). In addition, the proposed SDI parameter was found to be more sensitive in detecting CAN progression than other ECG interval-based features traditionally used for CAN diagnosis. The modified SDI parameter might be used as an alternative measure for the Ewing autonomic reflex tests to identify CAN progression for those subjects who are unable to perform the traditional tests. These findings could also complement the echocardiographic findings of the left ventricular diastolic dysfunction by providing additional information about alteration in systolic and diastolic intervals in heart failure.

Detecting subclinical diabetic cardiac autonomic neuropathy by analyzing ventricular repolarization dynamics

In this study, a linear parametric modeling technique was applied to model ventricular repolarization (VR) dynamics. Three features were selected from the surface ECG recordings to investigate the changes in VR dynamics in healthy and cardiac autonomic neuropathy (CAN) participants with diabetes including heart rate variability (calculated from RR intervals), repolarization variability (calculated from QT intervals), and respiration [calculated by ECG-derived respiration (EDR)]. Surface ECGs were recorded in a supine resting position from 80 age-matched participants (40 with no cardiac autonomic neuropathy (NCAN) and 40 with CAN). In the CAN group, 25 participants had early/subclinical CAN (ECAN) and 15 participants were identified with definite/clinical CAN (DCAN). Detecting subclinical CAN is crucial for designing an effective treatment plan to prevent further cardiovascular complications. For CAN diagnosis, VR dynamics was analyzed using linear parametric autoregressive bivariate (ARXAR) and trivariate (ARXXAR) models, which were estimated using 250 beats of derived QT, RR, and EDR time series extracted from the first 5 min of the recorded ECG signal. Results showed that the EDR-based models gave a significantly higher fitting value (p < 0.0001) than models without EDR, which indicates that QT-RR dynamics is better explained by respiratory-information-based models. Moreover, the QT-RR-EDR model fitting values gradually decreased from the NCAN group to ECAN and DCAN groups, which indicate a decoupling of QT from RR and the respiration signal with the increase in severity of CAN. In this study, only the EDR-based model significantly distinguished ECAN and DCAN groups from the NCAN group (p < 0.05) with large effect sizes (Cohen's d > 0.75) showing the effectiveness of this modeling technique in detecting subclinical CAN. In conclusion, the EDR-based trivariate QT-RR-EDR model was found to be better in detecting the presence and severity of CAN than the bivariate QT-RR model. This finding also establishes the importance of adding respiratory information for analyzing the gradual deterioration of normal VR dynamics in pathological conditions, such as diabetic CAN.

Multi-layer attribute selection and classification algorithm for the diagnosis of cardiac autonomic neuropathy based on HRV attributes

Cardiac autonomic neuropathy (CAN) poses an important clinical problem, which often remains undetected due difficulty of conducting the current tests and their lack of sensitivity. CAN has been associated with growth in the risk of unexpected death in cardiac patients with diabetes mellitus. Heart rate variability (HRV) attributes have been actively investigated, since they are important for diagnostics in diabetes, Parkinson's disease, cardiac and renal disease. Due to the adverse effects of CAN it is important to obtain a robust and highly accurate diagnostic tool for identification of early CAN, when treatment has the best outcome. Use of HRV attributes to enhance the effectiveness of diagnosis of CAN progression may provide such a tool. In the present paper we propose a new machine learning algorithm, the Multi-Layer Attribute Selection and Classification (MLASC), for the diagnosis of CAN progression based on HRV attributes. It incorporates our new automated attribute selection procedure, Double Wrapper Subset Evaluator with Particle Swarm Optimization (DWSE-PSO). We present the results of experiments, which compare MLASC with other simpler versions and counterpart methods. The experiments used our large and well-known diabetes complications database. The results of experiments demonstrate that MLASC has significantly outperformed other simpler techniques.

Risk stratification of cardiac autonomic neuropathy based on multi-lag tone-entropy

Cardiac autonomic neuropathy (CAN) is an irreversible condition affecting the autonomic nervous system, which leads to abnormal functioning of the visceral organs and affects critical body functions such as blood pressure, heart rate and kidney filtration. This study presents multi-lag Tone-Entropy (T-E) analysis of heart rate variability (HRV) at multiple lags as a screening tool for CAN. A total of 41 ECG recordings were acquired from diabetic subjects with definite CAN (CAN+) and without CAN (CAN-) and analyzed. Tone and entropy values of each patient were calculated for different beat sequence lengths (len: 50-900) and lags (m: 1-8). The CAN- group was found to have a lower mean tone value compared to that of CAN+ group for all m and len, whereas the mean entropy value was higher in CAN- than that in CAN+ group. Leave-one-out (LOO) cross-validation tests using a quadratic discriminant (QD) classifier were applied to investigate the performance of multi-lag T-E features. We obtained 100 % accuracy for tone and entropy with len = 250 and m = {2, 3} settings, which is better than the performance of T-E technique based on lag m = 1. The results demonstrate the usefulness of multi-lag T-E analysis over single lag analysis in CAN diagnosis for risk stratification and highlight the change in autonomic nervous system modulation of the heart rate associated with cardiac autonomic neuropathy.

Empirical investigation of decision tree ensembles for monitoring cardiac complications of diabetes

Cardiac complications of diabetes require continuous monitoring since they may lead to increased morbidity or sudden death of patients. In order to monitor clinical complications of diabetes using wearable sensors, a small set of features have to be identified and effective algorithms for their processing need to be investigated. This article focuses on detecting and monitoring cardiac autonomic neuropathy (CAN) in diabetes patients. The authors investigate and compare the effectiveness of classifiers based on the following decision trees: ADTree, J48, NBTree, RandomTree, REPTree, and SimpleCart. The authors perform a thorough study comparing these decision trees as well as several decision tree ensembles created by applying the following ensemble methods: AdaBoost, Bagging, Dagging, Decorate, Grading, MultiBoost, Stacking, and two multi-level combinations of AdaBoost and MultiBoost with Bagging for the processing of data from diabetes patients for pervasive health monitoring of CAN. This paper concentrates on the particular task of applying decision tree ensembles for the detection and monitoring of cardiac autonomic neuropathy using these features. Experimental outcomes presented here show that the authors' application of the decision tree ensembles for the detection and monitoring of CAN in diabetes patients achieved better performance parameters compared with the results obtained previously in the literature.

Severe hypoglycaemia in type 1 diabetes mellitus: underlying drivers and potential strategies for successful prevention

Hypoglycaemia remains an over-riding factor limiting optimal glycaemic control in type 1 diabetes. Severe hypoglycaemia is prevalent in almost half of those with long-duration diabetes and is one of the most feared diabetes-related complications. In this review, we present an overview of the increasing body of literature seeking to elucidate the underlying pathophysiology of severe hypoglycaemia and the limited evidence behind the strategies employed to prevent episodes. Drivers of severe hypoglycaemia including impaired counter-regulation, hypoglycaemia-associated autonomic failure, psychosocial and behavioural factors and neuroimaging correlates are discussed. Treatment strategies encompassing structured education, insulin analogue regimens, continuous subcutaneous insulin infusion pumps, continuous glucose sensing and beta-cell replacement therapies have been employed, yet there is little randomized controlled trial evidence demonstrating effectiveness of new technologies in reducing severe hypoglycaemia. Optimally designed interventional trials evaluating these existing technologies and using modern methods of teaching patients flexible insulin use within structured education programmes with the specific goal of preventing severe hypoglycaemia are required. Individuals at high risk need to be monitored with meticulous collection of data on awareness, as well as frequency and severity of all hypoglycaemic episodes.

A clustering-based multi-layer distributed ensemble for neurological diagnostics in cloud services

This paper investigates the problem of minimizing data transfer between different data centers of the cloud during the neurological diagnostics of cardiac autonomic neuropathy (CAN). This problem has never been considered in the literature before. All classifiers considered for the diagnostics of CAN previously assume complete access to all data, which would lead to enormous burden of data transfer during training if such classifiers were deployed in the cloud. We introduce a new model of clustering-based multi-layer distributed ensembles (CBMLDE). It is designed to eliminate the need to transfer data between different data centers for training of the classifiers. We conducted experiments utilizing a dataset derived from an extensive DiScRi database. Our comprehensive tests have determined the best combinations of options for setting up CBMLDE classifiers. The results demonstrate that CBMLDE classifiers not only completely eliminate the need in patient data transfer, but also have significantly outperformed all base classifiers and simpler counterpart models in all cloud frameworks.

Tone entropy analysis of foetal heart rate variability

Development of the foetal autonomic nervous system can be indirectly understood by looking at the changes in beat to beat variability in foetal heart rates. This study presents Tone-Entropy (T-E) analysis of foetal heart rate variability (HRV) at multiple lags (1–8) to understand the influence of gestational ages (early and late) on the development of the foetal autonomic nervous system (ANS). The analysis was based on foetal electrocardiograms (FECGs) of 46 healthy foetuses of 20–32 weeks (early group) and 22 foetuses of 35–41 weeks (late group). Tone represents sympatho-vagal balance and entropy the total autonomic activities. Results show that tone increases and entropy decreases at all lags for the late foetus group. On the other hand, tone decreases and entropy increases at lags 1–4 in the early foetus group. Increasing tone in late foetuses might represent significant maturation of sympathetic nervous systems because foetuses approaching to delivery period need increased sympathetic activity. T-E could be quantitative clinical index to determine the early foetuses from late ones on the basis of maturation of autonomic nervous system.

Multi-lag HRV analysis discriminates disease progression of post-infarct people with no diabetes versus diabetes

Diabetes mellitus is associated with multi-organ system dysfunction including the cardiovascular and autonomic nervous system. Although it is well documented that post-infarct patients are at higher risk of sudden cardiac death, diabetes adds an additional risk associated with autonomic neuropathy. However it is not known how the presence of diabetes in post-infarct patients affects cardiac rhythm. The majority of HRV algorithms for determining cardiac inter-beat interval changes describe only beat-to-beat variation determined over the whole heart rate recording and therefore do not consider the ability of a heart beat to influence a train of succeeding beats nor whether or how the temporal dynamics of the inter-beat intervals changes. This study used Poincaré Plot derived features and incorporated increased lag intervals to compare post-infarct patients with no history of prior infarct with or without diabetes and found that for the nondiabetic post-infarct patients only increased lag of short term correlation (SD1) predicted mortality, whereas in the diabetic post-infarct group only long-term correlations (SD2) significantly predicted mortality at a follow-up period of eight years. Temporal dynamics measured as a complex correlation measure (CCM) was also a significant predictor of mortality only in the diabetic post-infarct cohort. This study highlights the different pathophysiological progression and risk profile associated with presence of diabetes in a post-infarct patient population at eight year follow-up.