Challenges in Early Diagnosis of Melanoma Using Tele-Dermatology.

Numerous classification systems have been developed over the years, systems which not only provide assistance to dermatologists, but also enable individuals, especially those living in areas with low medical access, to get a diagnosis. In this paper, a Machine Learning model, which performs a binary classification, and, which for the remainder of this paper will be abbreviated as ML model, is trained and tested, so as to evaluate its effectiveness in giving the right diagnosis, as well as to point out the limitations of the given method, which include, but are not limited to, the quality of smartphone images, and the lack of FAIR image datasets for model training. The results indicate that there are many measures to be taken and improvements to be made, if such a system were to become a reliable tool in real-life circumstances.

Recovery Gestures Classification Using KNN and LDA Models.

Hand and joint mobility recovery involve performing a set of exercises. Gestures are often used in the hand mobility recovery process. This paper discusses the selection and the use of 2 models of neural networks for the classification of data that describe Leap Motion gestures. The gestures are: the hand opening and closing gesture and the palm rotation gesture. The purpose is the optimal selection of the neural network model to be used in the classification of the data describing the recovery gestures. The models chosen for the classification of the two gestures were: Linear Discriminant Analysis (LDA) and K-neighbors Classifier (KNN). The accuracies achieved in the classification of the gestures for each model are: 0.91 - LDA and 0.98 - KNN.

Comparison of Data Classification Results in Serious Gaming for Rehabilitation of Rheumatoid Arthritis.

Rheumatoid arthritis is a common disease which affects the joints of the wrist, fingers, feet and in the end the daily activities. Nowadays, gestures and virtual reality are used in many activities supporting recovery, games, learning as technology is present more and more in different fields. This paper presents results related to the grip movement detected by a Leap Motion device using binary classification and machine learning algorithms. We used 2 models to compare the results: Naïve Bayes and Random Forest Classifier. The metrics for comparison were: accuracy, precision, recall and f1-score. Also, we create a confusion matrix for a clear visualization of the results. We used 5000 data to train the algorithm and 1500 data to test. The accuracy and the precision were bigger than 97% in all the cases.

A Custom Image Recognition Model in the Cloud for Skin Diseases Identification.

In the context of global warming and increasing exposure to UV radiation, skin diseases are becoming more prevalent. Some of the most widespread skin conditions are solar lentigo and actinic keratosis. In this paper, we propose a technical approach related to the use of Azure Custom Vision services to classify these two conditions. The main advantage of using this service is the computational power offered by Azure. Additionally, generating a convolutional neural network model does not require a large dataset to achieve a good performance. For training the model, we used a dataset of 600 images from the ISIC database. The limitations of these approaches are imposed by the manual image labeling part that needs to be performed. As a result, we provide a trained model on a series of images that can be used for classifying images related to these two conditions. The performance of our neural network on the pre-trained images is 94%.

Application for Screening to Monitor and Assess Pregnancy Potential Risks.

Research in the field of maternal-fetal medicine brings a new approach, by involving several fields: genetics, informatics, teratology, imaging, obstetric diagnosis, maternal-fetal physiology, endocrinology, and aims to determine the relationships that appear between the maternal medical pathology and the fetal one. In this article, we present an application for monitoring and calculating risk in Trisomy-21 for pregnant women. To calculate the risk, we used 2 methods, one mathematical and one using neural networks to investigate which one offers higher precision. Following the experimental results, due to the use of several variables that increase the risk for Trisomy-21, the conclusion is that the method using neural networks is better, having an accuracy of 95%.

Mind Note - Application for Mental Health Support.

This paper presents a mobile application supporting mental health combining techniques to detect different mental health disorder symptoms. It provides different interactions, using affirmations, emotions, based on unloading techniques such as writing, drawing, and monitoring associated emotions, providing modalities to save and track progress.

Explanation Relevance Index - A New Way of Assessing the Quality of Explanations Based on Learned Features.

The XAI methods began to emerge as a response for the black-box methods used to make decisions that could not be explained, even if checked by humans they were correct. This created the need for a better evaluation for these methods. In this paper we propose a new method for evaluation based on features. The main advantage of applying ERI to CNNs explanations are: a fully automated way to measure the quality of an explanation and the fact that the score uses the same information as the CNN, in this way being able to offer a measure of the quality of explanation that can be validated automatically.

Increasing Trust in AI Using Explainable Artificial Intelligence for Histopathology - An Overview.

Digital Pathology is an area that could benefit a lot from the automatic classification of scanned microscopic slides. One of the main problems with this is that the experts need to understand and trust the decisions of the system. This paper is an overview of the current state of the art methods used in histopathological practice for explaining CNN classification useful for histopathological experts and ML engineers that work with histopathological images. This paper is an overview of the current state of the art methods used in the histopathological practice for explain. The search was performed using SCOPUS database and revealed that there are few applications of CNNs for digital pathology. The 4-term search yielded 99 results. This research sheds light on the main methods that can be used for histopathology classification and offers a good starting point for future works.

Towards FAIR Data Standardization Using FHIR Genomics Resources Integration in Obstetrics-Gynecology Department Systems.

The paper presents a current situation of the FHIR Genomics resource and an assessment of FAIR data usage and possible future directions. FHIR Genomics forges a path towards data interoperability. By integrating both the FAIR principles and the FHIR resources, we can achieve a higher standardization across healthcare data collection and a smoother data exchange. By exemplifying on the FHIR Genomics resource, we want to pave the way towards the integration of genomic data into an Obstetrics-Gynecology Information system as a future direction to be able to identify possible disease predisposition in fetus.

Medical informatics and digital health multilingual ontology (MIMO): A tool to improve international collaborations.

BACKGROUND: Even if English is the leading language for international communication, it is essential to keep in mind that research runs at the local level by local teams generally communicating in their local/national language, especially in Europe among European projects. OBJECTIVE: Therefore, the European Federation for Medical Informatics - Working Group on Health Informatics for Inter-regional Cooperation" has one objective: To develop a multilingual ontology focusing on Health Informatics and Digital Health as a collaboration tool that improves international and, in particular, European collaborations. RESULTS: We have developed the Medical Informatics and Digital Health Multilingual Ontology (MIMO). Hosted on the Health Terminology/Ontology Portal (HeTOP), MIMO contains around 1,000 concepts, 460 MeSH Descriptors, 220 MeSH Concepts, and more than 300 newly created concepts. MIMO is continuously updated to comprise as recent as possible concepts and their translations in more than 30 languages. Moreover, the MIMO's development team constantly improves MIMO content and supporting information. Thus, during workshop discussions and one-on-one exchanges, the MIMO team has collected domain experts' opinions about the community's interests and suggestions for future enhancements. Moreover, MIMO will be integrated to support the annotation and categorization of research products into the HosmartAI European project involving more than 20 countries around Europe and worldwide. CONCLUSION: MIMO is hosted by HeTOP (Health Terminology/Ontology Portal), which integrates 100 terminologies and ontologies in 55 languages. MIMO is freely available online. MIMO is portable to other knowledge platforms as part of MIMO's main aims to facilitate communication between medical librarians, translators, and researchers as well as to support students' self-learning.

Comparison of Data Classification Results for Leap Motion Recovery Gestures.

Static and dynamic gestures are frequently used in activities supporting learning, recovery healthcare, engineering, and 3D games to increase the interactivity between man and machine. The gestures are detected via hardware devices and data is processed using different software methods. This paper presents the manner of detection and interpretation of two gestures, a hand rotation gesture and a palm closing and opening gesture, using the Leap Motion device. These two dynamic gestures are very often used in hand recovery exercises. For comparing the two gestures we use data classification methods, Support Vector Machine (SVM) and Multilayer Perceptron (MLP). The data for the gesture classification were 80% training data and 20% testing data. The metrics for comparison are precision, recall, F1-score, and the total number of testing cases (support). The SVM classifier gives an accuracy of 99.4% and the MLP classifier a 96.2%. We built two confusion matrices for better visualizing the results.

Serious Gaming and Artificial Intelligence in Rehabilitation of Rheumatoid Arthritis.

This paper presents a current situation of studies and applications which are using serious games and artificial intelligence (AI) in rehabilitation of rheumatoid arthritis, and possible future directions. The objectives of this paper are: to highlight the technologies used for recovery of patients with rheumatoid arthritis (RA), to summarize the state of the art of existing applications and to present the authors work, a software application that aims contributing to the recovery of the specific patients. At this stage the application was tested by a group of 10 patients from Medical Centre Sf. Mary of Timisoara. Most of the patients reported that the physical and psychical effort were between easy-very easy. The patients confirmed that they would use the application in their rehabilitation process and are very excited about this type of rehabilitation that stimulates curiosity and a state of wellbeing. The application works based on the leap motion device that proved to be the most suitable device in terms of precision and the manner of interaction in virtual reality games.

Sharing the IT Educational Experience of Developing 3D Applications for Medical Students Training.

The importance of using the new technologies to develop educational and training applications for medical students is given by the times we live in and also by the continued development of the IT industry. New concepts used in 3D applications such as gamification bring added value to the use of learning applications. The introduction of technologies-based on virtual and augmented reality contributes to increasing of the interactivity. This paper presents an overview of the students' experience in developing a complex 3D application for medical students. The application development methodology is explained by splitting the design and development of the 3D learning application into steps. The main users' benefits provided by such applications are increased interactivity and learning benefits, and the continuous availability of the application wherein virtual laboratories within a medical clinic are simulated.

Application Using Standard Communication Between Medical Facilities.

The web-based application described in this paper will support the patient to receive the treatment quicker and the physician to generate the prescription easier. The patient will have a real time information if their treatment/prescription is available in the pharmacy. Using a cloud solution will have all the information always available and without delays, the only requirement is the Internet connectivity. Using standardized communication as HL7 FHIR, the information exchanged is easier understanded by different medical units, and in the future other medical units can access the patient treatment/prescription and have a medical history, in this way the patient will receive better quality in treatment and health care.

Serious Gaming and AI Supporting Treatment in Rheumatoid Arthritis.

This paper presents a complex application for rehabilitation of patients with first and second stage rheumatoid arthritis (RA). The application contains a module for the doctor, for the kinetotherapist, and a module as a game matching the symptoms for each stage of RA. The purpose of this application is to achieve the rehabilitation of the RA hand with support of digital technology and multimodal interaction: leap motion, serious gaming, and neuronal networks. The neural network offers support for patients to perform the exercises at home classifying the correct movement with accuracy of 95%. During the development of the application, various challenges were encountered in terms of populating the database, raising the cubes within the game related to second stage of RA, and the implementation of the neural network. The application was tested by a group of students, resulting in the fact that the degree of mental stress, fatigue in the fingers, wrists and physical exertion were insignificant in most cases.

Environment Monitoring System Raising Awareness of Sensitive Inhabitants Based on Regression Predictive Modelling.

The system described in this paper notifies the user about possible indoor environmental hazards through a smartphone application. Events such as house fires or increasing levels of dangerous substances are detected; thus, raising the awareness level in regard to the quality of the indoor environment. Our solution is a system that monitors the environment within a room in order to avoid undesired health hazards. It consists of a data collection subsystem, a cloud database which stores the collected information and a mobile application that displays and notifies the user in case of critical events that might negatively affect the health condition.

A Practical Experience on the Amazon Alexa Integration in Smart Offices.

Smart offices are dynamically evolving spaces meant to enhance employees' efficiency, but also to create a healthy and proactive working environment. In a competitive business world, the challenge of providing a balance between the efficiency and wellbeing of employees may be supported with new technologies. This paper presents the work undertaken to build the architecture needed to integrate voice assistants into smart offices in order to support employees in their daily activities, like ambient control, attendance system and reporting, but also interacting with project management services used for planning, issue tracking, and reporting. Our research tries to understand what are the most accepted tasks to be performed with the help of voice assistants in a smart office environment, by analyzing the system based on task completion and sentiment analysis. For the experimental setup, different test cases were developed in order to interact with the office environment formed by specific devices, as well as with the project management tool tasks. The obtained results demonstrated that the interaction with the voice assistant is reasonable, especially for easy and moderate utterances.

Evaluating Interactivity in VR Healthcare Applications Using Analytics.

Currently, Virtual Reality-based 3D applications are more and more in use. Education is a field that makes use of this technology providing the users with a pleasant way of learning. Thus, the human-computer/smart phone interactivity increases. To measure the human-computer interactivity in a Virtual Reality-based 3D application, certain metrics may be considered (e.g.: application usage time, speed of execution of certain tasks). In this paper we use Google Analytics to observe and measure the interactivity in a medical application created for educational purposes. The application is based on Virtual Reality, and the user may observe and handle the bones of the human skeleton. The main actions monitored via Google Analytics to observe interactivity are: skeleton parts selection, zooming in/zooming out, rotation. An 80% usage percentage (measure of interaction) was achieved for the skeleton selection (foot bones), while for the other actions and selections the achieved percentage was of 100%.

Continuous Monitoring and Statistical Modelling of Heart Rate Variability.

The paper presents a sensor network system implemented to continuously monitor and detect cardiovascular diseases experienced in patients at high-risk. The device is designed to capture and transmit the ECG signals and pulse to the patientÂts mobile phone. Later interpretation of the single-lead ECG signals will result into a HRV analysis and heart-rate detection that is compared with the pulse oximeter results for validation. The fastest alert will be issued to doctors, relatives and hospitals, using the proposed data processing algorithm implemented in the patient's mobile phone. The continuous usage of this monitoring system provides an effective, efficient and fast health care service to patients at risk, even if the doctors or relatives are not near the patients.

Gesture Classification for a Hand Controller Device Using Neural Networks.

This paper presents a convolutional neural network-based classification of the hand flexion and extension gestures used in wrist recovery after injury. The hand gesture recognition device used in our study is the Leap Motion controller. The Leap Motion device's inability to accurately differentiate the left hand from the right hand when performing hand rotation gestures was eliminated by introducing hand and thumb direction vectors into the database used to train the neural network. A 3D environment was created for the introduction of the data describing the gesture into the database. A classification accuracy of 95% was achieved for the hand flexion and extension gesture divided into three levels for each hand. The populated database may also be used to classify other gestures involving hand rotation.