HEARTEN KMS - A knowledge management system targeting the management of patients with heart failure.

The aim of this work is to present the HEARTEN Knowledge Management System, one of the core modules of the HEARTEN platform. The HEARTEN platform is an mHealth collaborative environment enabling the Heart Failure patients to self-manage the disease and remain adherent, while allowing the other ecosystem actors (healthcare professionals, caregivers, nutritionists, physical activity experts, psychologists) to monitor the patient's health progress and offer personalized, predictive and preventive disease management. The HEARTEN Knowledge Management System is a tool which provides multiple functionalities to the ecosystem actors for the assessment of the patient's condition, the estimation of the patient's adherence, the prediction of potential adverse events, the calculation of Heart Failure related scores, the extraction of statistics, the association of patient clinical and non-clinical data and the provision of alerts and suggestions. The innovation of this tool lays in the analysis of multi-parametric personal data coming from different sources, including for the first time breath and saliva biomarkers, and the use of machine learning techniques. The HEARTEN Knowledge Management System consists of nine modules. The accuracy of the KMS modules ranges from 78% to 95% depending on the module/functionality.

The Evolution of mHealth Solutions for Heart Failure Management.

In the last decade, the uptake of information and communication technologies and the advent of mobile internet resulted in improved connectivity and penetrated different fields of application. In particular, the adoption of the mobile devices is expected to reform the provision and delivery of healthcare, overcoming geographical, temporal, and other organizational limitations. mHealth solutions are able to provide meaningful clinical information allowing effective and efficient management of chronic diseases, such as heart failure. A variety of data can be collected, such as lifestyle, sensor/biosensor, and health-related information. The analysis of these data empowers patients and the involved ecosystem actors, improves the healthcare delivery, and facilitates the transformation of existing health services. The aim of this study is to provide an overview of (i) the current practice in the management of heart failure, (ii) the available mHealth solutions, either in the form of the commercial applications, research projects, or related studies, and (iii) the several challenges related to the patient and healthcare professionals' acceptance, the payer and provider perspective, and the regulatory constraints.

The Potential Role of Salivary NT-proBNP in Heart Failure.

BACKGROUND: Serum natriuretic peptides (NPs) have an established role in heart failure (HF) diagnosis. Saliva NT-proBNP that may be easily acquired has been studied little. METHODS: Ninety-nine subjects were enrolled; thirty-six obese or hypertensive with dyspnoea but no echocardiographic HF findings or raised NPs served as controls, thirteen chronic HF (CHF) patients and fifty patients with acute decompensated HF (ADHF) requiring hospital admission. Electrocardiogram, echocardiogram, 6 min walking distance (6MWD), blood and saliva samples, were acquired in all participants. RESULTS: Serum NT-proBNP ranged from 60-9000 pg/mL and saliva NT-proBNP from 0.64-93.32 pg/mL. Serum NT-proBNP was significantly higher in ADHF compared to CHF (p = 0.007) and in CHF compared to controls (p < 0.05). There was no significant difference in saliva values between ADHF and CHF, or between CHF and controls. Saliva and serum levels were positively associated only in ADHF patients (R = 0.352, p = 0.012). Serum NT-proBNP was positively associated with NYHA class (R = 0.506, p < 0.001) and inversely with 6MWD (R = -0.401, p = 0.004) in ADHF. Saliva NT-proBNP only correlated with age in ADHF patients. CONCLUSIONS: In the current study, saliva NT-proBNP correlated with serum values in ADHF patients, but could not discriminate between HF and other causes of dyspnoea. Further research is needed to explore the value of saliva NT-proBNP.

Segmentation and volume quantification of MR Images for the detection and monitoring multiple sclerosis progression.

Multiple Sclerosis (MS) lesions detection and disease's progression monitoring at the same time, play an important role. The purpose of this research is to demonstrate a method for detecting MS plaques and volume estimation from MR Images for monitoring the progression of the disease and the brain atrophy caused. In the proposed research, a clustering-based method is utilized in order to delineate MS plaques in brain, based on anatomical information, brain geometry and lesion features. In addition to volumetric information concerning lesions and whole brain volume, volume quantification is employed to estimate MS atrophy by measuring Brain Parenchymal Fraction (BPF). In the present study, Fluid Attenuated Inversion Recovery (FLAIR) images were utilized for the detection of MS lesions and BPF evaluation, while Tl-weighted MR Images utilized in volume estimation. 30 MS patients were included in a dataset consisted of 3D FLAIR and T1-weighted MR images in order to evaluate the proposed technique. MRI scans performed in two different clinical visits, a baseline and a visit after 6 months. The results extracted in segmentation of MS lesions in terms of sensitivity is 73.80 %. The BPF at baseline estimated to 0.82 ± 0.01, and at 1stfollow up, 0.83 ± 0.01. Finally, the brain volume loss between baseline and after 6 months is 0.4%.

White Matter Lesion Segmentation for Multiple Sclerosis Patients implementing deep learning.

The aim of this work is to address the problem of White Matter Lesion (WML) segmentation employing Magnetic Resonance Imaging (MRI) images from Multiple Sclerosis (MS) patients through the application of deep learning. A U-net based architecture containing a contrastive path and an expanding path prior to the final pixel-wise classification is implemented. The data are provided by the Ippokratio Radiology Center of Ioannina and include Fluid-Attenuated Inversion Recovery (FLAIR) MRI images from 30 patients in three phases, baseline and two follow ups. The prediction results are quite significant in terms of pixel-wise classification. The implemented deep learning model demonstrates Dice coefficient 0.7292, Precision 75.92% and Recall 70.16% in 2D slices of FLAIR MRI non-skull stripped images.

A User-Centric approach for Personalization based on Human Activity Recognition.

The objective of this work focuses on multiple independent user profiles that capture behavioral, emotional, medical, and physical patterns in the working and living environment resulting in one general user profile. Depending on the user's current activity (e.g. walking, eating, etc.), medical history, and other influential factors, the developed framework acts as a supplemental assistant to the user by providing not only the ability to enable supportive functionalities (e.g. image filtering, magnification, etc.) but also informative recommendations (e.g. diet, alcohol, etc.). The personalization of such a profile lies within the user's past preferences using human activity recognition as a base, and it is achieved through a statistical model, the Bayesian belief network. Training and real-time methodological pipelines are introduced and validated. The employed deep learning techniques for identifying human activities are presented and validated in publicly available and in-house datasets. The overall accuracy of human activity recognition reaches up to 86.96 %.

Real Time Human Activity Recognition Using Acceleration and First-Person Camera data.

The aim of this work is to present an automated method, working in real time, for human activity recognition based on acceleration and first-person camera data. A Long-Short-Term-Memory (LSTM) model has been built for recognizing locomotive activities (i.e. walking, sitting, standing, going upstairs, going downstairs) from acceleration data, while a ResNet model is employed for the recognition of stationary activities (i.e. eating, reading, writing, watching TV working on PC). The outcomes of the two models are fused in order for the final decision, regarding the performed activity, to be made. For the training, testing and evaluation of the proposed models, a publicly available dataset and an "in-house" dataset are utilized. The overall accuracy of the proposed algorithmic pipeline reaches 87.8%.

Heart Failure diagnosis based on deep learning techniques.

The aim of the study is to address the heart failure (HF) diagnosis with the application of deep learning approaches. Seven deep learning architectures are implemented, where stacked Restricted Boltzman Machines (RBMs) and stacked Autoencoders (AEs) are used to pre-train Deep Belief Networks (DBN) and Deep Neural Networks (DNN). The data is provided by the University College Dublin and the 2nd Department of Cardiology from the University Hospital of Ioannina. The features recorded are grouped into: general demographic information, physical examination, classical cardiovascular risk factors, personal history of cardiovascular disease, symptoms, medications, echocardiographic features, laboratory findings, lifestyle/habits and other diseases. The total number of subjects utilized is 422. The deep learning methods provide quite high results with the Autoencoder plus DNN approach to demonstrate accuracy 91.71%, sensitivity 90.74%, specificity 92.31% and f-score 89.36%.

A Machine Learning Approach for Chronic Heart Failure Diagnosis.

The aim of this study was to address chronic heart failure (HF) diagnosis with the application of machine learning (ML) approaches. In the present study, we simulated the procedure that is followed in clinical practice, as the models we built are based on various combinations of feature categories, e.g., clinical features, echocardiogram, and laboratory findings. We also investigated the incremental value of each feature type. The total number of subjects utilized was 422. An ML approach is proposed, comprising of feature selection, handling class imbalance, and classification steps. The results for HF diagnosis were quite satisfactory with a high accuracy (91.23%), sensitivity (93.83%), and specificity (89.62%) when features from all categories were utilized. The results remained quite high, even in cases where single feature types were employed.

Salivary Biomarkers for Diagnosis and Therapy Monitoring in Patients with Heart Failure. A Systematic Review.

The aim of this study was to perform a systematic review on the potential value of saliva biomarkers in the diagnosis, management and prognosis of heart failure (HF). The correlation between saliva and plasma values of these biomarkers was also studied. PubMed was searched to collect relevant literature, i.e., case-control, cross-sectional studies that either compared the values of salivary biomarkers among healthy subjects and HF patients, or investigated their role in risk stratification and prognosis in HF patients. No randomized control trials were included. The search ended on 31st of December 2020. A total of 15 studies met the inclusion criteria. 18 salivary biomarkers were analyzed and the levels of all biomarkers studied were found to be higher in HF patients compared to controls, except for amylase, sodium, and chloride that had smaller saliva concentrations in HF patients. Natriuretic peptides are the most commonly used plasma biomarkers in the management of HF. Their saliva levels show promising results, although the correlation of saliva to plasma values is weakened in higher plasma values. In most of the publications, differences in biomarker levels between HF patients and controls were found to be statistically significant. Due to the small number of patients included, larger studies need to be conducted in order to facilitate the use of saliva biomarkers in clinical practice.

A six stage approach for the diagnosis of the Alzheimer's disease based on fMRI data.

The aim of this work is to present an automated method that assists in the diagnosis of Alzheimer's disease and also supports the monitoring of the progression of the disease. The method is based on features extracted from the data acquired during an fMRI experiment. It consists of six stages: (a) preprocessing of fMRI data, (b) modeling of fMRI voxel time series using a Generalized Linear Model, (c) feature extraction from the fMRI data, (d) feature selection, (e) classification using classical and improved variations of the Random Forests algorithm and Support Vector Machines, and (f) conversion of the trees, of the Random Forest, to rules which have physical meaning. The method is evaluated using a dataset of 41 subjects. The results of the proposed method indicate the validity of the method in the diagnosis (accuracy 94%) and monitoring of the Alzheimer's disease (accuracy 97% and 99%).

Point-of-Care Testing Devices for Heart Failure Analyzing Blood and Saliva Samples.

Heart failure (HF) is the most rapidly growing cardiovascular condition with an estimated prevalence of >37.7 million individuals globally. HF is associated with increased mortality and morbidity and confers a substantial burden, in terms of cost and quality of life, for the individuals and the healthcare systems, highlighting thus the need for early and accurate diagnosis of HF. The accuracy of HF diagnosis, severity estimation, and prediction of adverse events has improved by the utilization of blood tests measuring biomarkers. The contribution of biomarkers for HF management is intensified by the fact that they can be measured in short time at the point-of-care. This is allowed by the development of portable analytical devices, commonly known as point-of-care testing (POCT) devices, which exploit the advancements in the area of microfluidics and nanotechnology. The aim of this review paper is to present a review of POCT devices used for the measurement of biomarkers facilitating decision making when managing HF patients. The devices are either commercially available or in the form of prototypes under development. Both blood and saliva samples are considered. The challenges concerning the implementation of POCT devices and the barriers for their adoption in clinical practice are discussed.

KardiaSoft Architecture - A Software Supporting Diagnosis and Therapy Monitoring of Heart Failure Patients Exploiting Saliva Biomarkers.

The aim of this work is to present the architecture of the KardiaSoft software, a clinical decision support tool allowing the healthcare professionals to monitor patients with heart failure by providing useful information and suggestions in terms of the estimation of the presence of heart failure (heart failure diagnosis), stratification-patient profiling, long term patient condition evaluation and therapy response monitoring. KardiaSoft is based on predictive modeling techniques that analyze data that correspond to four saliva biomarkers, measured by a point-of-care device, along with other patient's data. The KardiaSoft is designed based on the results of a user requirements elicitation process. A small clinical scale study with 135 subjects and an early clinical study with 90 subjects will take place in order to build and validate the predictive models, respectively.

KardiaTool: An Integrated POC Solution for Non-invasive Diagnosis and Therapy Monitoring of Heart Failure Patients.

The aim of this work is to present KardiaTool platform, an integrated Point of Care (POC) solution for noninvasive diagnosis and therapy monitoring of Heart Failure (HF) patients. The KardiaTool platform consists of two components, KardiaPOC and KardiaSoft. KardiaPOC is an easy to use portable device with a disposable Lab-on-Chip (LOC) for the rapid, accurate, non-invasive and simultaneous quantitative assessment of four HF related biomarkers, from saliva samples. KardiaSoft is a decision support software based on predictive modeling techniques that analyzes the POC data and other patient's data, and delivers information related to HF diagnosis and therapy monitoring. It is expected that identifying a source comparable to blood, for biomarker information extraction, such as saliva, that is cost-effective, less invasive, more convenient and acceptable for both patients and healthcare professionals would be beneficial for the healthcare community. In this work the architecture and the functionalities of the KardiaTool platform are presented.

Automated segmentation and quantification of inflammatory tissue of the hand in rheumatoid arthritis patients using magnetic resonance imaging data.

OBJECTIVES: The aim of this paper is the development of an automated method for the segmentation and quantification of inflammatory tissue of the hand in patients suffering form rheumatoid arthritis using contrast enhanced T1-weighted magnetic resonance images. METHODS AND MATERIALS: The proposed automatic method consists of four stages: (a) preprocessing of images, (b) identification of the number of clusters, by minimizing the appropriate validity index, (c) segmentation using the fuzzy C-means algorithm employing four features which are related to intensity and the location of pixels and (d) postprocessing, where defuzzification is performed and small objects and vessels are eliminated and quantification takes place. RESULTS: The proposed method is evaluated using a dataset of image sequences obtained from 25 patients suffering from rheumatoid arthritis. For 17 of them we have obtained follow-up images after 1 year treatment. The obtained sensitivity and positive predictive rate is 97.71% and 83.35%, respectively. In addition, quantification of inflammation before and after treatment, as well as, comparison with manual segmentation is carried out. CONCLUSIONS: The proposed method performs very well and results in high detection and quantification accuracy. However, the reduction of false positives and the identification of old inflammation must be addressed.

Heart Failure: Diagnosis, Severity Estimation and Prediction of Adverse Events Through Machine Learning Techniques.

Heart failure is a serious condition with high prevalence (about 2% in the adult population in developed countries, and more than 8% in patients older than 75 years). About 3-5% of hospital admissions are linked with heart failure incidents. Heart failure is the first cause of admission by healthcare professionals in their clinical practice. The costs are very high, reaching up to 2% of the total health costs in the developed countries. Building an effective disease management strategy requires analysis of large amount of data, early detection of the disease, assessment of the severity and early prediction of adverse events. This will inhibit the progression of the disease, will improve the quality of life of the patients and will reduce the associated medical costs. Toward this direction machine learning techniques have been employed. The aim of this paper is to present the state-of-the-art of the machine learning methodologies applied for the assessment of heart failure. More specifically, models predicting the presence, estimating the subtype, assessing the severity of heart failure and predicting the presence of adverse events, such as destabilizations, re-hospitalizations, and mortality are presented. According to the authors' knowledge, it is the first time that such a comprehensive review, focusing on all aspects of the management of heart failure, is presented.

A computational approach for the estimation of heart failure patients status using saliva biomarkers.

The aim of this work is to present a computational approach for the estimation of the severity of heart failure (HF) in terms of New York Heart Association (NYHA) class and the characterization of the status of the HF patients, during hospitalization, as acute, progressive or stable. The proposed method employs feature selection and classification techniques. However, it is differentiated from the methods reported in the literature since it exploits information that biomarkers fetch. The method is evaluated on a dataset of 29 patients, through a 10-fold-cross-validation approach. The accuracy is 94 and 77% for the estimation of HF severity and the status of HF patients during hospitalization, respectively.

A computer-aided automated methodology for the detection and classification of occlusal caries from photographic color images.

The aim of this work is to present a computer-aided automated methodology for the assessment of carious lesions, according to the International Caries Detection and Assessment System (ICDAS II), which are located on the occlusal surfaces of posterior permanent teeth from photographic color tooth images. The proposed methodology consists of two stages: (a) the detection of regions of interest and (b) the classification of the detected regions according to ICDAS ΙΙ. In the first stage, pre-processing, segmentation and post-processing mechanisms were employed. For each pixel of the detected regions, a 15×15 neighborhood is used and a set of intensity-based and texture-based features were extracted. A correlation based technique was applied to select a subset of 36 features which were given as input into the classification stage, where five classifiers (J48, Random Tree, Random Forests, Support Vector Machines and Naïve Bayes) were compared to conclude to the best one, in our case, to Random Forests. The methodology was evaluated on a set of 103 digital color images where 425 regions of interest from occlusal surfaces of extracted permanent teeth were manually segmented and classified, based on visual assessments by two experts. The methodology correctly detected 337 out of 340 regions in the detection stage with accuracy of detection 80%. For the classification stage an overall accuracy 83% is achieved. The proposed methodology provides an objective and fully automated caries diagnostic system for occlusal carious lesions with similar or better performance of a trained dentist taking into consideration the available medical knowledge.

Occlusal caries detection using random walker algorithm: a graph approach.

The aim of this work is to present a modification of the Random Walker algorithm for the segmentation of occlusal caries from photographic color images. The modification improves the detection and time execution performance of the classical Random Walker algorithm and also deals with the limitations and difficulties that the specific type of images impose to the algorithm. The proposed modification consists of eight steps: 1) definition of the seed points, 2) conversion of the image to gray scale, 3) application of watershed transformation, 4) computation of the centroid of each region, 5) construction of the graph, 6) application of the Random Walker algorithm, 7) smoothing and extraction of the perimeter of the regions of interest and 8) overlay of the results. The algorithm was evaluated using a set of 96 images where 339 areas of interest were manually segmented by an expert. The obtained segmentation accuracy is 93%.

Automatic detection of freezing of gait events in patients with Parkinson's disease.

The aim of this study is to detect freezing of gait (FoG) events in patients suffering from Parkinson's disease (PD) using signals received from wearable sensors (six accelerometers and two gyroscopes) placed on the patients' body. For this purpose, an automated methodology has been developed which consists of four stages. In the first stage, missing values due to signal loss or degradation are replaced and then (second stage) low frequency components of the raw signal are removed. In the third stage, the entropy of the raw signal is calculated. Finally (fourth stage), four classification algorithms have been tested (Naïve Bayes, Random Forests, Decision Trees and Random Tree) in order to detect the FoG events. The methodology has been evaluated using several different configurations of sensors in order to conclude to the set of sensors which can produce optimal FoG episode detection. Signals recorded from five healthy subjects, five patients with PD who presented the symptom of FoG and six patients who suffered from PD but they do not present FoG events. The signals included 93 FoG events with 405.6s total duration. The results indicate that the proposed methodology is able to detect FoG events with 81.94% sensitivity, 98.74% specificity, 96.11% accuracy and 98.6% area under curve (AUC) using the signals from all sensors and the Random Forests classification algorithm.