Nondimensional diabetes indices for accurate diagnosis of diabetic subjects

OBJECTIVES

Nondimensional indices or numbers can provide a generalized approach for integrating several biological parameters into one Nondimensional Physiological Index (NDPI) that can help characterize an abnormal state associated with a particular physiological system. In this paper, we have presented four Nondimensional Physiological Indices (NDI, DBI, DIN, CGMDI) for the accurate detection of diabetes subjects.

METHODOLOGY

The NDI, DBI, and DIN diabetes indices are based on the Glucose-Insulin Regulatory System (GIRS) Model, represented by the governing differential equation of blood glucose concentration response to the glucose input rate. The solutions of this governing differential equation are employed to simulate the clinical data of the Oral Glucose Tolerance Test (OGTT), and thereby evaluate the GIRS model-system parameters, which are distinctly different for the normal and diabetic subjects. Then these GIRS model parameters are combined to form singular nondimensional indices: NDI, DBI, and DIN. When these indices are applied to the OGTT clinical data, we get significantly different values for normal and diabetic subjects. The DIN diabetes index is a more objective index involving extensive clinical studies, incorporating the GIRS model parameters as well as some key clinical-data markers (based on the information gained from the model clinical simulation and parametric identification). We have then developed another CGMDI diabetes index based on the GIRS model, for the assessment of diabetic subjects using the glucose levels measured by wearable continuous glucose monitoring (CGM) devices.

CLINICAL STUDY AND RESULTS

For the DIN diabetes index, our clinical study comprised of 47 subjects (26 normal and 21 diabetics). After applying DIN to the OGTT data, a Distribution Plot of DIN was developed, displaying the ranges of DIN for (i) normal (i.e., non-diabetic) subjects with no risk of becoming diabetic, (ii) normal subjects at risk of becoming diabetic, (iii) borderline diabetic subjects who can become normal (with diet control and treatment), and (iv) distinctly diabetic subjects. This distribution plot is shown to distinctly separate normal subjects from diabetic subjects and also from subjects at risk of becoming diabetic.

CONCLUSIONS

In this paper, we have developed several NDPIs in the form of novel nondimensional diabetes indices for the accurate detection of diabetes and diagnosis of diabetic subjects. These nondimensional diabetes indices can enable precision medical diagnostics of diabetes, and thereby also help to develop interventional guidelines for lowering glucose levels by means of insulin infusion. The novelty of our proposed CGMDI is that it utilizes the glucose value monitored by the CGM wearable device. In the future, an app can be developed to use the CGM data in the CGMDI to enable precision diabetes detection.

Novel Hypertrophic Cardiomyopathy Diagnosis Index Using Deep Features and Local Directional Pattern Techniques

Hypertrophic cardiomyopathy (HCM) is a genetic disorder that exhibits a wide spectrum of clinical presentations, including sudden death. Early diagnosis and intervention may avert the latter. Left ventricular hypertrophy on heart imaging is an important diagnostic criterion for HCM, and the most common imaging modality is heart ultrasound (US). The US is operator-dependent, and its interpretation is subject to human error and variability. We proposed an automated computer-aided diagnostic tool to discriminate HCM from healthy subjects on US images. We used a local directional pattern and the ResNet-50 pretrained network to classify heart US images acquired from 62 known HCM patients and 101 healthy subjects. Deep features were ranked using Student’s t-test, and the most significant feature (SigFea) was identified. An integrated index derived from the simulation was defined as 100·log10(SigFea/2) in each subject, and a diagnostic threshold value was empirically calculated as the mean of the minimum and maximum integrated indices among HCM and healthy subjects, respectively. An integrated index above a threshold of 0.5 separated HCM from healthy subjects with 100% accuracy in our test dataset.

Novel and accurate non-linear index for the automated detection of haemorrhagic brain stroke using CT images

Brain stroke is an emergency medical condition which occurs mainly due to insufficient blood flow to the brain. It results in permanent cellular-level damage. There are two main types of brain stroke, ischemic and hemorrhagic. Ischemic brain stroke is caused by a lack of blood flow, and the haemorrhagic form is due to internal bleeding. The affected part of brain will not function properly after this attack. Hence, early detection is important for more efficacious treatment. Computer-aided diagnosis is a type of non-invasive diagnostic tool which can help in detecting life-threatening disease in its early stage by utilizing image processing and soft computing techniques. In this paper, we have developed one such model to assess intracerebral haemorrhage by employing non-linear features combined with a probabilistic neural network classifier and computed tomography (CT) images. Our model achieved a maximum accuracy of 97.37% in discerning normal versus haemorrhagic subjects. An intracerebral haemorrhage index is also developed using only three significant features. The clinical and statistical validation of the model confirms its suitability in providing for improved treatment planning and in making strategic decisions.

Fusion of spatial gray level dependency and fractal texture features for the characterization of thyroid lesions

Thyroid is a small gland situated at the anterior side of the neck and one of the largest glands of the endocrine system. The abrupt cell growth or malignancy in the thyroid gland may cause thyroid cancer. Ultrasound images distinctly represent benign and malignant lesions, but accuracy may be poor due to subjective interpretation. Computer Aided Diagnosis (CAD) can minimize the errors created due to subjective interpretation and assists to make fast accurate diagnosis. In this work, fusion of Spatial Gray Level Dependence Features (SGLDF) and fractal textures are used to decipher the intrinsic structure of benign and malignant thyroid lesions. These features are subjected to graph based Marginal Fisher Analysis (MFA) to reduce the number of features. The reduced features are subjected to various ranking methods and classifiers. We have achieved an average accuracy, sensitivity and specificity of 97.52%, 90.32% and 98.57% respectively using Support Vector Machine (SVM) classifier. The achieved maximum Area Under Curve (AUC) is 0.9445. Finally, Thyroid Clinical Risk Index (TCRI) a single number is developed using two MFA features to discriminate the two classes. This prototype system is ready to be tested with huge diverse database.

Automated characterization of fatty liver disease and cirrhosis using curvelet transform and entropy features extracted from ultrasound images

Fatty liver disease (FLD) is reversible disease and can be treated, if it is identified at an early stage. However, if diagnosed at the later stage, it can progress to an advanced liver disease such as cirrhosis which may ultimately lead to death. Therefore, it is essential to detect it at an early stage before the disease progresses to an irreversible stage. Several non-invasive computer-aided techniques are proposed to assist in the early detection of FLD and cirrhosis using ultrasound images. In this work, we are proposing an algorithm to discriminate automatically the normal, FLD and cirrhosis ultrasound images using curvelet transform (CT) method. Higher order spectra (HOS) bispectrum, HOS phase, fuzzy, Kapoor, max, Renyi, Shannon, Vajda and Yager entropies are extracted from CT coefficients. These extracted features are subjected to locality sensitive discriminant analysis (LSDA) feature reduction method. Then these LSDA coefficients ranked based on F-value are fed to different classifiers to choose the best performing classifier using minimum number of features. Our proposed technique can characterize normal, FLD and cirrhosis using probabilistic neural network (PNN) classifier with an accuracy of 97.33%, specificity of 100.00% and sensitivity of 96.00% using only six features. In addition, these chosen features are used to develop a liver disease index (LDI) to differentiate the normal, FLD and cirrhosis classes using a single number. This can significantly help the radiologists to discriminate FLD and cirrhosis in their routine liver screening.

Novel risk index for the identification of age-related macular degeneration using radon transform and DWT features

Age-related Macular Degeneration (AMD) affects the central vision of aged people. It can be diagnosed due to the presence of drusen, Geographic Atrophy (GA) and Choroidal Neovascularization (CNV) in the fundus images. It is labor intensive and time-consuming for the ophthalmologists to screen these images. An automated digital fundus photography based screening system can overcome these drawbacks. Such a safe, non-contact and cost-effective platform can be used as a screening system for dry AMD. In this paper, we are proposing a novel algorithm using Radon Transform (RT), Discrete Wavelet Transform (DWT) coupled with Locality Sensitive Discriminant Analysis (LSDA) for automated diagnosis of AMD. First the image is subjected to RT followed by DWT. The extracted features are subjected to dimension reduction using LSDA and ranked using t-test. The performance of various supervised classifiers namely Decision Tree (DT), Support Vector Machine (SVM), Probabilistic Neural Network (PNN) and k-Nearest Neighbor (k-NN) are compared to automatically discriminate to normal and AMD classes using ranked LSDA components. The proposed approach is evaluated using private and public datasets such as ARIA and STARE. The highest classification accuracy of 99.49%, 96.89% and 100% are reported for private, ARIA and STARE datasets. Also, AMD index is devised using two LSDA components to distinguish two classes accurately. Hence, this proposed system can be extended for mass AMD screening.

An integrated index for automated detection of infarcted myocardium from cross-sectional echocardiograms using texton-based features (Part 1)

Cross-sectional view echocardiography is an efficient non-invasive diagnostic tool for characterizing Myocardial Infarction (MI) and stages of expansion leading to heart failure. An automated computer-aided technique of cross-sectional echocardiography feature assessment can aid clinicians in early and more reliable detection of MI patients before subsequent catastrophic post-MI medical conditions. Therefore, this paper proposes a novel Myocardial Infarction Index (MII) to discriminate infarcted and normal myocardium using features extracted from apical cross-sectional views of echocardiograms. The cross-sectional view of normal and MI echocardiography images are represented as textons using Maximum Responses (MR8) filter banks. Fractal Dimension (FD), Higher-Order Statistics (HOS), Hu's moments, Gabor Transform features, Fuzzy Entropy (FEnt), Energy, Local binary Pattern (LBP), Renyi's Entropy (REnt), Shannon's Entropy (ShEnt), and Kapur's Entropy (KEnt) features are extracted from textons. These features are ranked using t-test and fuzzy Max-Relevancy and Min-Redundancy (mRMR) ranking methods. Then, combinations of highly ranked features are used in the formulation and development of an integrated MII. This calculated novel MII is used to accurately and quickly detect infarcted myocardium by using one numerical value. Also, the highly ranked features are subjected to classification using different classifiers for the characterization of normal and MI LV ultrasound images using a minimum number of features. Our current technique is able to characterize MI with an average accuracy of 94.37%, sensitivity of 91.25% and specificity of 97.50% with 8 apical four chambers view features extracted from only single frame per patient making this a more reliable and accurate classification.

A NEW APPROACH FOR ASSESSMENT OF PULSE WAVE VELOCITY AT RADIAL ARTERY IN YOUNG AND MIDDLE-AGED HEALTHY HUMANS

Pulse wave velocity (PWV), based on two-site measurement, is a well-known predictor of arterial stiffness. Interest focused increasingly on simplifying the PWV measurement results in attempts at determining it at a single site. We aimed to validate a new tonometric method (IIM-2010A) for assessment of PWV at radial artery in healthy subjects <65 years of age. PWV measurements were performed in 46 healthy adults (25 men and 21 women) aged 21–65 years (39.6 ± 15.5 years) using Complior device and IIM-2010A respectively. In a subgroup of 21 humans, the measurements were repeated after 1 week using IIM-2010A with the same protocol. There was a strong correlation between PWV obtained by IIM-2010A and PWV obtained by Complior, as well as between pulse transit time (PTT) measurements (r = 0.79 and r = 0.85, respectively, P < 0.01 for both). Although PTT was significantly lower measured by IIM-2010A, no significant difference was found in PWV. The mean difference of PWV with SD was -0.1 ± 1.2 m/s between two repeated measurements at intervals of 1 week. Bland–Altman's plot indicated no trend for the reproducibility of measurements to vary with their underlying mean value. Intraclass correlation coefficient (= 0.87) confirmed this excellent week-to-week reproducibility of PWV. The method provides a simple, easily-obtainable, and reproducible measurement of PWV in young and middle-aged subjects, and has potential to detect premature arterial aging for the management of primary prevention.

CARDIAC ARRHYTHMIA DIAGNOSIS BY HRV SIGNAL PROCESSING USING PRINCIPAL COMPONENT ANALYSIS

An electrocardiogram (ECG) signal represents the sum total of millions of cardiac cells' depolarization potentials. It helps to identify the cardiac health of the subject by inspecting its P-QRS-T wave. The heart rate variability (HRV) data, extracted from the ECG signal, reflects the balance between sympathetic and parasympathetic components of the autonomic nervous system. Hence, HRV signal contains information on the imbalance between these two nervous system components that results in cardiac arrhythmias. Thus in this paper, we have analyzed HRV signal abnormalities to determine and classify arrhythmias. The HRV signals are non-stationary and non-linear in nature. In this work, we have used continuous wavelet transform (CWT) coupled with principal component analysis (PCA) to extract the important features from the heart rate signals. These features are fed to the probabilistic neural network (PNN) classifier, for automated classification. Our proposed system demonstrates an average accuracy of 80% and sensitivity and specificity of 82% and 85.6%, respectively, for arrhythmia detection and classification. Our system can be operated on larger data sets. Our CWT–PCA analysis resulted in eigenvalues which constituted the HRV signal analysis parameters. We have shown and plotted the distribution of the parameters' mean values and the standard deviation for arrhythmia classification. We found some overlap in the distribution of these eigenvalue parameters for the different arrhythmia classes, which mitigates the effective use of these parameters to separate out the various arrhythmia classes. Therefore, we have formulated a HRV Integrated Index (HRVID) of these eigenvalues, and determined and plotted the mean values and standard deviation of HRVID for the various arrhythmia classifications. From this information, it can be seen that the HRVID is able to distinguish among the various arrhythmia classes. Hence, we have made a case for the employment of this HRVID as an index to effectively diagnose arrhythmia disorders.

Atheromatic™: symptomatic vs. asymptomatic classification of carotid ultrasound plaque using a combination of HOS, DWT & texture

Quantitative characterization of carotid atherosclerosis and classification into either symptomatic or asymptomatic is crucial in terms of diagnosis and treatment planning for a range of cardiovascular diseases. This paper presents a computer-aided diagnosis (CAD) system (Atheromatic™, patented technology from Biomedical Technologies, Inc., CA, USA) which analyzes ultrasound images and classifies them into symptomatic and asymptomatic. The classification result is based on a combination of discrete wavelet transform, higher order spectra and textural features. In this study, we compare support vector machine (SVM) classifiers with different kernels. The classifier with a radial basis function (RBF) kernel achieved an accuracy of 91.7% as well as a sensitivity of 97%, and specificity of 80%. Encouraged by this result, we feel that these features can be used to identify the plaque tissue type. Therefore, we propose an integrated index, a unique number called symptomatic asymptomatic carotid index (SACI) to discriminate symptomatic and asymptomatic carotid ultrasound images. We hope this SACI can be used as an adjunct tool by the vascular surgeons for daily screening.

DIABETIC AUTONOMIC NEUROPATHY DETECTION BY HEART-RATE VARIABILITY POWER-SPECTRAL ANALYSIS

Heart rate is a non-stationary signal and provides a powerful interplay between the sympathetic and parasympathetic nervous systems. The heart rate variation signal can reveal disorders associated with how these nervous systems regulate the heart rate, and hence may contain indicators of this disease state, or warnings about impending or future cardiac diseases. These indicators may be present at all times or may occur at random during certain intervals in the time scale. It is difficult and time consuming to pinpoint these abnormalities in a huge cardiac data set. Heart rate variability (HRV) constitutes a tool for assessing the activities of the autonomic nervous system (ANS). In this work, we have proposed a computer based analytical system to determine the HRV, and analyzed it to obtain HRV Power-spectrum for normal, diabetes and diabetes with neuropathy subjects in deep breathing, standing and supine position. We have then designated indices based on the HRV power-spectra power values and frequency shift of these peaks from their normal frequency values. We have shown the efficacy and sensitivity of these indices, to differentiate between normals, diabetics and diabetics with ischemic heart disease. Thus we have demonstrated how effectively these HRV power-spectral indices can enable diagnosis of diabetic autonomic neuropathy. Finally, we have composed an integrated index made up of these power-spectral indices, to facilitate distinguishing and diagnosing diabetic autonomic neuropathy in terms of just one index or number.

DIABETES MELLITUS: ENQUIRY INTO ITS MEDICAL ASPECTS AND BIOENGINEERING OF ITS MONITORING AND REGULATION

Diabetes mellitus (DM) or hyperglycemia (in a more generalized term, high blood sugar) is a metabolic disorder that is now highly prevalent in the world population. Most of the food that people consume is converted into glucose, which enters the bloodstream following absorption–assimilation mechanisms. As a natural process, cells in our body utilize glucose for growth and energy. The glucose balance is maintained by a hormone called insulin that is secreted by the beta cells of pancreas. Hypotheses at the backdrop of DM occurrence are either (i) enough insulin is not produced and secreted resulting in increased level of glucose in blood, or (ii) insulin is insensitive to glucose, or (iii) insulin is non-targeted etc. If DM remains uncontrolled over time, it leads to serious damage to many of the body's systems, especially the nerves and blood vessels. This paper develops an enquiry into diabetes from many angles: (i) Diabetes as a disorder, its complications, causes, diagnostic tests, and treatment; (ii) Analysis of retinal and plantar images to characterize diabetes complications; (iii) How analysis of heart rate variability signals can depict diabetes; (iv) Biomedical engineering of the glucose–insulin regulatory system, and its employment in the modeling of the oral glucose tolerance test data, to detect diabetes as well as persons at risk of being diabetic; (v) Application of the glucose–insulin regulatory system to formulate an insulin delivery system for controlling blood sugar.