On the evaluation of deep learning interpretability methods for medical images under the scope of faithfulness.

BACKGROUND AND OBJECTIVE: Evaluating the interpretability of Deep Learning models is crucial for building trust and gaining insights into their decision-making processes. In this work, we employ class activation map based attribution methods in a setting where only High-Resolution Class Activation Mapping (HiResCAM) is known to produce faithful explanations. The objective is to evaluate the quality of the attribution maps using quantitative metrics and investigate whether faithfulness aligns with the metrics results. METHODS: We fine-tune pre-trained deep learning architectures over four medical image datasets in order to calculate attribution maps. The maps are evaluated on a threefold metrics basis utilizing well-established evaluation scores. RESULTS: Our experimental findings suggest that the Area Over Perturbation Curve (AOPC) and Max-Sensitivity scores favor the HiResCAM maps. On the other hand, the Heatmap Assisted Accuracy Score (HAAS) does not provide insights to our comparison as it evaluates almost all maps as inaccurate. To this purpose we further compare our calculated values against values obtained over a diverse group of models which are trained on non-medical benchmark datasets, to eventually achieve more responsive results. CONCLUSION: This study develops a series of experiments to discuss the connection between faithfulness and quantitative metrics over medical attribution maps. HiResCAM preserves the gradient effect on a pixel level ultimately producing high-resolution, informative and resilient mappings. In turn, this is depicted in the results of AOPC and Max-Sensitivity metrics, successfully identifying the faithful algorithm. In regards to HAAS, our experiments yield that it is sensitive over complex medical patterns, commonly characterized by strong color dependency and multiple attention areas.

Integrating IoT Wearable Devices in Telemonitoring Platforms for Continuous Assisted Living Services.

Assisted living services have become increasingly important in recent years as the population ages and the demand for personalized care rises. In this paper, we present the integration of wearable IoT devices in a remote monitoring platform for elderly people that enables seamless data collection, analysis, and visualization while in parallel, alarms and notification functionalities are provided in the context of a personalized monitoring and care plan. The system has been implemented using state-of-the-art technologies and methods to facilitate robust operation, increased usability and real-time communication. The user has the ability to record and visualise their activity, health and alarm data using the tracking devices, and additionally settle an ecosystem of relatives and informal carers to provide assistance daily or support in cases of emergencies.

Enriching Remote Monitoring and Care Platforms with Personalized Recommendations to Enhance Gamification and Coaching.

Patients' remote monitoring platforms can be enhanced with intelligent recommendations and gamification functionalities to support their adherence to care plans. The current paper aims to present a methodology for creating personalized recommendations, which can be used to improve patient remote monitoring and care platforms. The current pilot system design is aimed to support patients by providing recommendations for Sleep, Physical Activity, BMI, Blood sugar, Mental Health, Heart Health, and Chronic Obstructive Pulmonary Disease aspects. The users, through the application, can select the types of recommendations they are interested in. Thus, personalized recommendations based on data obtained by the patients' records anticipated to be a valuable and a safe approach for patient coaching. The paper discusses the main technical details and provides some initial results.

MedSecurance Project: Advanced Security-for-Safety Assurance for Medical Device IoT (IoMT).

The MedSecurance project focus on identifying new challenges in cyber security with focus on hardware and software medical devices in the context of emerging healthcare architectures. In addition, the project will review best practice and identify gaps in the guidance, particularly the guidance stipulated by the medical device regulation and directives. Finally, the project will develop comprehensive methodology and tooling for the engineering of trustworthy networks of inter-operating medical devices, that shall have security-for-safety by design, with a strategy for device certification and certifiable dynamic network composition, ensuring that patient safety is safeguarded from malicious cyber actors and technology "accidents".

Smartwatch digital phenotypes predict positive and negative symptom variation in a longitudinal monitoring study of patients with psychotic disorders.

Introduction: Monitoring biometric data using smartwatches (digital phenotypes) provides a novel approach for quantifying behavior in patients with psychiatric disorders. We tested whether such digital phenotypes predict changes in psychopathology of patients with psychotic disorders. Methods: We continuously monitored digital phenotypes from 35 patients (20 with schizophrenia and 15 with bipolar spectrum disorders) using a commercial smartwatch for a period of up to 14 months. These included 5-min measures of total motor activity from an accelerometer (TMA), average Heart Rate (HRA) and heart rate variability (HRV) from a plethysmography-based sensor, walking activity (WA) measured as number of total steps per day and sleep/wake ratio (SWR). A self-reporting questionnaire (IPAQ) assessed weekly physical activity. After pooling phenotype data, their monthly mean and variance was correlated within each patient with psychopathology scores (PANSS) assessed monthly. Results: Our results indicate that increased HRA during wakefulness and sleep correlated with increases in positive psychopathology. Besides, decreased HRV and increase in its monthly variance correlated with increases in negative psychopathology. Self-reported physical activity did not correlate with changes in psychopathology. These effects were independent from demographic and clinical variables as well as changes in antipsychotic medication dose. Discussion: Our findings suggest that distinct digital phenotypes derived passively from a smartwatch can predict variations in positive and negative dimensions of psychopathology of patients with psychotic disorders, over time, providing ground evidence for their potential clinical use.

E-Prevention: Advanced Support System for Monitoring and Relapse Prevention in Patients with Psychotic Disorders Analyzing Long-Term Multimodal Data from Wearables and Video Captures.

Wearable technologies and digital phenotyping foster unique opportunities for designing novel intelligent electronic services that can address various well-being issues in patients with mental disorders (i.e., schizophrenia and bipolar disorder), thus having the potential to revolutionize psychiatry and its clinical practice. In this paper, we present e-Prevention, an innovative integrated system for medical support that facilitates effective monitoring and relapse prevention in patients with mental disorders. The technologies offered through e-Prevention include: (i) long-term continuous recording of biometric and behavioral indices through a smartwatch; (ii) video recordings of patients while being interviewed by a clinician, using a tablet; (iii) automatic and systematic storage of these data in a dedicated Cloud server and; (iv) the ability of relapse detection and prediction. This paper focuses on the description of the e-Prevention system and the methodologies developed for the identification of feature representations that correlate with and can predict psychopathology and relapses in patients with mental disorders. Specifically, we tackle the problem of relapse detection and prediction using Machine and Deep Learning techniques on all collected data. The results are promising, indicating that such predictions could be made and leading eventually to the prediction of psychopathology and the prevention of relapses.

Exploiting Augmented Reality and Computer Vision for Healthcare Education: The Case of Pharmaceutical Substances Visualization and Information Retrieval.

Augmented Reality (AR) is already used as the primary visualization and user interaction tool in several scientific and business areas. At the same time new AR technologies and frameworks considerably facilitate both the development of innovative applications and also their wide adoption in different domains of everyday life. In the area of healthcare AR solutions make use of mobile or wearable devices and glasses to support, among others, education and healthcare professionals training. The aim of this paper is to present a prototype mHealth app for education, which uses AR and computer vision technologies for pharmaceutical substances recognition on drug packaging. The conceptual design of the system includes three main components which are responsible for a) Text recognition, b) Drug identification and c) AR operations for interactivity. The prototype application is available in Android or iOS platforms and has been evaluated in real-world scenarios. Camera and screen of the mobile phones fulfill the text recognition and AR operations, which eliminates the need for special equipment, while PubChem and 3D Model databases provide assets required for the drug identification and AR visualizations. The results highlight the value of AR for educational purposes, especially when combined with advanced image recognition technologies to build interactive AR encyclopedias.

Image Analysis in Digital Pathology Utilizing Machine Learning and Deep Neural Networks.

Detection of regions of interest (ROIs) in whole slide images (WSIs) in a clinical setting is a highly subjective and a labor-intensive task. In this work, recent developments in machine learning and computer vision algorithms are presented to assess their possible usage and performance to enhance and accelerate clinical pathology procedures, such as ROI detection in WSIs. In this context, a state-of-the-art deep learning framework (Detectron2) was trained on two cases linked to the TUPAC16 dataset for object detection and on the JPATHOL dataset for instance segmentation. The predictions were evaluated against competing models and further possible improvements are discussed.

Using mHealth Technologies to Promote Public Health and Well-Being in Urban Areas with Blue-Green Solutions.

European and International cities face crucial global geopolitical, economic, environmental, and other changes. All these intensify threats to and inequalities in citizens' health. The implementation of Blue-Green Solutions in urban and rural areas have been broadly used to tackle the above challenges. The Mobile health (mHealth) technologies contribution in people's well-being has found to be significant. In addition, several mHealth applications have been used to support patients with mental health or cardiovascular diseases with very promising results. The patients' remote monitoring can be a valuable asset in chronic diseases management for patients suffering from diabetes, hypertension or arrhythmia, depression, asthma, allergies and others. The scope of this paper is to present the specifications, the design and the development of a mobile application which collects health-related and location data of users visiting areas with Blue-Green Solutions. The mobile application has been developed to record the citizens' and patients' physical activity and vital signs using wearable devices. The proposed application can also monitor patients physical, physiological, and emotional status as well as motivate them to engage in social and self-caring activities. Additional features include the analysis of the patients' behavior to improve self-management. The "HEART by BioAsssist" application could be used as a health and other data collection tool as well as an "intelligent assistant" to monitor and promote patient's physical activity.

Intelligent Pervasive Monitoring Solution of COVID-19 Patients.

The COVID-19 pandemic transforms the healthcare delivery models and accelerates the implementation and the adoption of telemedicine solutions at all levels of the healthcare system. Telehealth services ensure the continuity of care and treatment of both inpatients and outpatients during this pandemic, while reducing the spread of the virus through hospitals. The aim of this paper is to present an intelligent remote monitoring system with innovative data analytics features for COVID-19 patients. The i-COVID platform provides remote COVID-19 patients monitoring. The presented solution is addressed to patients with mild COVID-19 symptoms, as well as it can be used for post intensive-care monitoring. The platform offers advanced analytic capabilities using Proactive AI, to detect health condition deterioration, and automatically trigger personalized support workflows. Remote monitoring of COVID-19 patients using bio-sensors, seems to be an effective tool against the COVID-19 pandemic, as reduces the number of visits to patient screening centres and hospital admissions.

Gamification and Coaching in Remote Monitoring and Care Platforms.

Nowadays, several e-health systems are equipped with advanced features for patients monitoring and care. Among these features, gamification and operations supporting the patients' adherence to therapeutic and care plans have been found to be quite useful and valuable. Among others, the introduction of intelligent patient coaching and the provisions of recommendations are very popular. The aim of this paper is to present specific gamification and coaching approaches that could be employed in the context of an existing eHealth system for remote monitoring and care for elders. The "Points, Badges and Leaderboards" gamification approach was followed. Specifically, parameters related to the application usage (daily points), the physical activity (number of daily steps), the sleep quality (sleep score) and other measurements (i.e. weight) were utilized to accommodate elders needs for motivation and engagement. Regarding the coaching, motivational messages and notification for the mobile devices were selected to deliver the relative information to the elders. A prototype health information system with a corresponding mobile application was adapted to include gamification and coaching features to motivate elders in order to achieve the maximum adherence on their monitoring and care health plans. The paper presents the design issues and summarizes the technical details.

Pervasive Monitoring of Public Health and Well-Being in Urban Areas with Blue-Green Solutions.

The urban environment seems to affect the citizens' health. The implementation of Blue-Green Solutions (BGS) in urban areas have been used to promote public health and citizens well-being. The aim of this paper is to present the development of an mHealth app for monitoring patients and citizens health status in areas where BGS will be applied. The "HEART by BioAsssist" application could be used as a health and other data collection tool as well as an "intelligent assistant" to monitor and promote patient's physical activity in areas with Blue-Green Solutions.

An IoT-Enabled Platform for the Assessment of Physical and Mental Activities Utilizing Augmented Reality Exergaming.

Augmented reality (AR) and Internet of Things (IoT) are among the core technological elements of modern information systems and applications in which advanced features for user interactivity and monitoring are required. These technologies are continuously improving and are available nowadays in all popular programming environments and platforms, allowing for their wide adoption in many different business and research applications. In the fields of healthcare and assisted living, AR is extensively applied in the development of exergames, facilitating the implementation of innovative gamification techniques, while IoT can effectively support the users' health monitoring aspects. In this work, we present a prototype platform for exergames that combines AR and IoT on commodity mobile devices for the development of serious games in the healthcare domain. The main objective of the solution was to promote the utilization of gamification techniques to boost the users' physical activities and to assist the regular assessment of their health and cognitive statuses through challenges and quests in the virtual and real world. With the integration of sensors and wearable devices by design, the platform has the capability of real-time monitoring the users' biosignals and activities during the game, collecting data for each session, which can be analyzed afterwards by healthcare professionals. The solution was validated in real world scenarios and the results were analyzed in order to further improve the performance and usability of the prototype.

Introducing Gamification in eHealth Platforms for Promoting Wellbeing.

Gamification techniques are adopted by IT systems and applications in order to facilitate their adoption and motivate users to take advantage of specific application features. The current work presents a modern approach for the effective implementation of gamification features in a prototype eHealth application which encourages the daily use of the application, endorses the users to continuously monitor their health and promotes a healthier lifestyle. The implementation of this approach is modular and flexible in order to be easily applied in any similar system and tailor the provided features for user activity monitoring, analysis, feedback, and interactivity, to the specific requirements of the different usage scenarios.

Quantifying Citizens' Well-Being in Areas with Natural Based Solutions Using Mobile Computing.

Urban planners, architects and civil engineers are integrating Nature-Based Solutions (NBS) to address contemporary environmental, social, health and economic challenges. Many studies claim that NBS are poised to improve citizens' well-being in urban areas. NBS can also benefit Public Health, as they can contribute to optimising environmental parameters (such as urban heat island effects, floods, etc.), as well as to the reduction of diseases, as for example cardiovascular ones and the overall mortality rate. In addition, the usage of mobile health (mHealth) solutions has been broadly applied to support citizens' well-being as they can offer monitoring of their physical and physiological status and promote a healthier lifestyle. The aim of this paper is to present the specifications, the design and the development of a mobile app for monitoring citizens' well-being in areas where NBS have been applied. The users' physical activity and vital signs are recorded by wearable devices and the users' locations are recorded by the proposed mobile application. All collected data are transferred to the cloud platform where data management mechanisms aggregate data from different sources for combined analysis. The mobile application is currently available for Android and iOS devices and it is compatible with most smart devices and wearables. The "euPOLIS by BioAssist" application can be used as a health and other data collection tool to investigate citizen's well-being improvement in areas with NBS.

Speech Based Affective Analysis of Patients Embedded in Telemedicine Platforms.

Speech is a basic means of human expression, not only due to the combination of words that exits our mouth, but also because of the different way we express these words. Apart from the main objective of speech, which is the communication of information, emotions flow in human speech as various vocal characteristics (prosodic, spectral, tonal). By processing these characteristics, Speech Emotion Recognition aims to analyze and assess the human emotional status to complement medical data captured during telemedicine sessions. Driven by the latest developments in Computer Vision concerning Deep Learning techniques, EfficientNets are exploited to extract features and classify imagery representations of human speech into emotions as a web service along with an interpretation scheme. The developed web service will be consumed during video conferences between medical staff and patients for the near real-time assessment of emotional status of patients during video teleconsultations.

Machine-Learning-Derived Model for the Stratification of Cardiovascular risk in Patients with Ischemic Stroke.

Background Stratification of cardiovascular risk in patients with ischemic stroke is important as it may inform management strategies. We aimed to develop a machine-learning-derived prognostic model for the prediction of cardiovascular risk in ischemic stroke patients. MATERIALS AND METHODS: Two prospective stroke registries with consecutive acute ischemic stroke patients were used as training/validation and test datasets. The outcome assessed was major adverse cardiovascular event, defined as non-fatal stroke, non-fatal myocardial infarction, and cardiovascular death during 2-year follow-up. The variables selection was performed with the LASSO technique. The algorithms XGBoost (Extreme Gradient Boosting), Random Forest and Support Vector Machines were selected according to their performance. The evaluation of the classifier was performed by bootstrapping the dataset 1000 times and performing cross-validation by splitting in 60% for the training samples and 40% for the validation samples. RESULTS: The model included age, gender, atrial fibrillation, heart failure, peripheral artery disease, arterial hypertension, statin treatment before stroke onset, prior anticoagulant treatment (in case of atrial fibrillation), creatinine, cervical artery stenosis, anticoagulant treatment at discharge (in case of atrial fibrillation), and statin treatment at discharge. The best accuracy was measured by the XGBoost classifier. In the validation dataset, the area under the curve was 0.648 (95%CI:0.619-0.675) and the balanced accuracy was 0.58 ± 0.14. In the test dataset, the corresponding values were 0.59 and 0.576. CONCLUSIONS: We propose an externally validated machine-learning-derived model which includes readily available parameters and can be used for the estimation of cardiovascular risk in ischemic stroke patients.

A Fully Open-Source Approach to Intelligent Edge Computing: AGILE's Lesson.

In this paper, we describe the main outcomes of AGILE (acronym for "Adaptive Gateways for dIverse muLtiple Environments"), an EU-funded project that recently delivered a modular hardware and software framework conceived to address the fragmented market of embedded, multi-service, adaptive gateways for the Internet of Things (IoT). Its main goal is to provide a low-cost solution capable of supporting proof-of-concept implementations and rapid prototyping methodologies for both consumer and industrial IoT markets. AGILE allows developers to implement and deliver a complete (software and hardware) IoT solution for managing non-IP IoT devices through a multi-service gateway. Moreover, it simplifies the access of startups to the IoT market, not only providing an efficient and cost-effective solution for industries but also allowing end-users to customize and extend it according to their specific requirements. This flexibility is the result of the joint experience of established organizations in the project consortium already promoting the principles of openness, both at the software and hardware levels. We illustrate how the AGILE framework can provide a cost-effective yet solid and highly customizable, technological foundation supporting the configuration, deployment, and assessment of two distinct showcases, namely a quantified self application for individual consumers, and an air pollution monitoring station for industrial settings.

An Integrated Platform for Skin Cancer Heterogenous and Multilayered Data Management.

Electronic health record (EHR) systems improve health care services by allowing the combination of health data with clinical decision support features and clinical image analyses. This study presents a modular and distributed platform that is able to integrate and accommodate heterogeneous, multidimensional (omics, histological images and clinical) data for the multi-angled portrayal and management of skin cancer patients. The proposed design offers a layered analytical framework as an expansion of current EHR systems, which can integrate high-volume molecular -omics data, imaging data, as well as relevant clinical observations. We present a case study in the field of dermatology, where we attempt to combine the multilayered information for the early detection and characterization of melanoma. The specific architecture aspires to lower the barrier for the introduction of personalized therapeutic approaches, towards precision medicine. The paper describes the technical issues of implementation, along with an initial evaluation of the system and discussion.

Novel Cost Function Definition for Minimum-Cost Tractography in MR Diffusion Tensor Imaging.

Magnetic resonance imaging (MRI) is an established clinical technique that measures diffusion-weighted signals, applied primarily in brain studies. Diffusion tensor imaging (DTI) is a technique that uses the diffusion-weighted signals to obtain information about tissue connectivity, which recently started to become established in clinical use. The extraction of tracts (tractography) is an issue under active research. In this work we present an algorithm for recovering tracts, based on Dijkstra's minimum-cost path. A novel cost definition algorithm is presented that allows tract reconstruction, considering the tract's curvature, as well as its alignment with the diffusion vector field. The proposed cost function is able to adapt to linear, planar, and spherical diffusion. Thus, it can handle issues of fiber crossing, which pose considerable problems to tractography algorithms. A simple method for generating synthetic diffusion - weighted MR signals from known fibers - is also presented and utilized in this work. Results are shown for two (2D)- and three-dimensional (3D) synthetic data, as well as for a clinical MRI-DTI brain study.