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.

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.

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.

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%.

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.

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.

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.

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.

The EFMI Working Group "Healthcare Informatics for Interregional Cooperation": An Evolving Strategy for Building Cooperation Bridges

The Working Group "Health Informatics for Interregional Cooperation" (WG HIIC) of the European Federation for Medical Informatics (EFMI) is dedicated to develop, to implement and to disseminate a strategy for promoting exchange of information, knowledge and experiences all around the world and more particularly, between Health Informatics arena players in the different European continent regions.

Improving the Prescription Process Information Support with Structured Medical Prospectuses Using Neural Networks

To provide the best treatment, a physician needs information about both the patient and the medicines matching the patient status and improving it. In this article, we present three methods for structuring the sections of medical prospectuses using neural networks. To structure the information from a medical prospectus we use 3 web sources with structured data from sections (with names sections from prospectuses and with uniformized names of sections) to train as input for neural networks. The tests were conducted on Romanian prospectuses. After running the three algorithms, the prospectuses were compared in terms of accuracy and execution time for each source. It was concluded that the accuracy is higher in convolutional networks and in the case of uniform name sections. The output data is used in applications with decision support for the treatment, matching best treatment with the patient's status.

Named Entity Recognition and Classification for Medical Prospectuses

Structuring and processing natural language is a growing challenge in the medical field. Researchers are looking for new ways to extract knowledge to create databases and applications to help doctors treat patients and minimize medical errors. A very important part in treating a patient is to provide a fair and effective treatment for diseases. In this article we present a method of extracting important information from medical prospectuses, such as a drug-treated condition, a medicine name, a drug type, etc. To extract these entities, we use Stanford NER Tagger trained for prospectuses in Romanian language. The model was trained and tested with 3 types of medication. For each test, the accuracy of the extracted data was calculated. The extracted medical information is used to create databases with structured information that are useful for decision-support applications to check for or find suggestions for the best treatments.

A Multi-Lingual Dictionary for Health Informatics as an International Cooperation Pillar

Even if, English is generally used for international communication, it is essential to keep in mind that research is running at the local level by local teams generally communicating in their local/national language. Bearing these in mind, the "European Federation for Medical Informatics Working Group on Health Informatics for Inter-regional Cooperation" has as one of its objectives, to develop a multilingual dictionary focusing on Health Informatics as a collaboration tool allowing improving international and more particularly European cooperation. This dictionary is implemented as a part of HeTOP (Health Terminology/Ontology Portal) which is currently integrating more than 70 terminologies and ontologies in 32 languages. The EFMI Dictionary main aims are helping medical librarians, translators, academic and industrial researchers understanding better one another and supporting students self-learning.

Alternative Medicine Patient Records Moving to a Digital Environment

As technology immerses in daily life, all types of clinical practices migrate more on storing medical records on electronically media. The issue is up for debate on several fronts, as both paper and electronic records offer strengths and weaknesses. This paper presents the process of changing from paper medical records to a digital environment in the case of an alternative medicine clinic, having years of stored paper records, with its benefits and challenges. Focusing on quality criteria, the current study shows how beneficial an electronic medical record could be, while arguing how the diagnosis coding from the paper-based patient record resulted in major qualitative disadvantages.

Harnessing Ontologies to Improve Prescription in Pediatric Medicine

There are many drug databases, but sometimes the data quality may result in wrong medication for patients. Results that it is very important to provide a good quality drug information, supply structured information and build useful relations between the drugs related information and the patient status in terms of particularities. Children are the most sensitive to drug dosage or certain substances that is why pediatrics was our first choice for the research. To support this, we propose an ontology starting from on-line drug prospectuses. We start extracting the prospectuses information from the web pages, investigate the sections of the prospectuses structure (indications, contraindications, dosage, etc.) and use the information in an ontology that we integrate into a pediatric application. In the background of the application this solution provides the correct matching between the patient and the treatment, extracting for the physician only the best prescription options for the current case. The application allows the physician to select the appropriate drug and decide the best treatment in terms of correct substances and dosage for a certain child. We use the prospectuses solution because the application is in Romanian and other resources are not very well provided. For the future the solution will be adapted to other languages and other databases. This model can be generalized in different languages. The application is improved with the new ontology module and helps physicians to give a good treatment considering all relationships, constraints or antagonistic situations that may occur in providing a treatment.

Supporting Prescriptions with Synonym Matching of Section Names in Prospectuses

The field of medicine still reports errors because of insufficient knowledge or resources, work load or data not available at the right time and place, and this may be fatal for a patient. To improve the healthcare quality, a doctor needs accurate and complex information processing when accessing drug information. Our work builds on improvement of accessing drug information for a better treatment through homogenization of sections in a prospectus. The sections names in a prospectus may be different for one source to another, and in this article, we propose a method to homogenize the content of all drug prospectuses. Once a correct homogenization of the sections has been established, the prospectuses can be used in clinical decision applications to provide the necessary data for physicians. Classification of the section names is using the Cousine similarity method and the Scikit-learn machine learning software. The best results were obtained with the Scikit-learn software.

VR Medical Gamification for Training and Education

The new virtual reality based medical applications is providing a better understanding of healthcare related subjects for both medical students and physicians. The work presented in this paper underlines gamification as a concept and uses VR as a new modality to study the human skeleton. The team proposes a mobile Android platform application based on Unity 5.4 editor and Google VR SDK. The results confirmed that the approach provides a more intuitive user experience during the learning process, concluding that the gamification of classical medical software provides an increased interactivity level for medical students during the study of the human skeleton.

DNA Encoding Training Using 3D Gesture Interaction

The work described in this paper summarizes the development process and presents the results of a human genetics training application, studying the 20 amino acids formed by the combination of the 3 nucleotides of DNA targeting mainly medical and bioinformatics students. Currently, the domain applications using recognized human gestures of the Leap Motion sensor are used in molecules controlling and learning from Mendeleev table or in visualizing the animated reactions of specific molecules with water. The novelty in the current application consists in using the Leap Motion sensor creating new gestures for the application control and creating a tag based algorithm corresponding to each amino acid, depending on the position in the 3D virtual space of the 4 nucleotides of DNA and their type. The team proposes a 3D application based on Unity editor and on Leap Motion sensor where the user has the liberty of forming different combinations of the 20 amino acids. The results confirm that this new type of study of medicine/biochemistry using the Leap Motion sensor for handling amino acids is suitable for students. The application is original and interactive and the users can create their own amino acid structures in a 3D-like environment which they could not do otherwise using traditional pen-and-paper.

Gesture Interaction Browser-Based 3D Molecular Viewer

The paper presents an open source system that allows the user to interact with a 3D molecular viewer using associated hand gestures for rotating, scaling and panning the rendered model. The novelty of this approach is that the entire application is browser-based and doesn't require installation of third party plug-ins or additional software components in order to visualize the supported chemical file formats. This kind of solution is suitable for instruction of users in less IT oriented environments, like medicine or chemistry. For rendering various molecular geometries our team used GLmol (a molecular viewer written in JavaScript). The interaction with the 3D models is made with Leap Motion controller that allows real-time tracking of the user's hand gestures. The first results confirmed that the resulting application leads to a better way of understanding various types of translational bioinformatics related problems in both biomedical research and education.

Integrated System for Monitoring and Prevention in Obstetrics-Gynaecology

A better monitoring of pregnant women, mainly during the third trimester of pregnancy and an easy communication between physician and patients are very important for the prevention and good health of baby and mother. The paper presents an integrated system as support for the Obstetrics - Gynaecology domain consisting in two modules: a mobile application, ObGynCare, dedicated to the pregnant women and a new component of the Obstetrics-Gynaecology Department Information System dedicated to the physicians for a better monitoring of the pregnant women. The mobile application informs the pregnant women about their status, permits them to introduce glycaemia and weight values and has as option pulse and blood pressure acquisition from a smart sensor and provides results in a graphic format. It also provides support for easy patient-doctor communication related to any health problems. ObGyn Care offers nutrition recommendations and gives the pregnant women the possibility to enter a social space of common interests using social networks (Facebook) to exchange useful and practical information. Data collected from patients and from sensor are stored on the cloud and the physician may access the information and analyse it. The extended module of the Obstetrics-Gynaecology Department Information System already developed supports the physicians to visualize weekly, monthly, or on a trimester, the patient data and to discuss with her through the chat module. The mobile application is in test by pregnant women and medical personnel.

Client-side Medical Image Colorization in a Collaborative Environment

The paper presents an application related to collaborative medicine using a browser based medical visualization system with focus on the medical image colorization process and the underlying open source web development technologies involved. Browser based systems allow physicians to share medical data with their remotely located counterparts or medical students, assisting them during patient diagnosis, treatment monitoring, surgery planning or for educational purposes. This approach brings forth the advantage of ubiquity. The system can be accessed from a any device, in order to process the images, assuring the independence towards having a specific proprietary operating system. The current work starts with processing of DICOM (Digital Imaging and Communications in Medicine) files and ends with the rendering of the resulting bitmap images on a HTML5 (fifth revision of the HyperText Markup Language) canvas element. The application improves the image visualization emphasizing different tissue densities.

Integrated wireless sensor network for monitoring pregnant women

The paper presents an integrated monitoring system for pregnant women in the third trimester using a mobile cardiotocograph and body sensors. The medical staff has a useful tool to detect abnormalities and prevent unfortunate events in time. The mobile cardiotocograph sends data in real time to a Smartphone that communicates the information in a cloud. The physician accesses the data using the hospital ObgGyn application. The advantage of using this system is that the pregnant woman can follow her pregnancy status evolution from home, and the physician receives alarms from the system if the data is not in normal range and has available information about the health status at any time and location.

Comparing video and avatar technology for a health education application for deaf people

The article describes the steps and results of a parallel research investigating e-health systems design and implementation for deaf people both in avatar and video technology. The application translates medical knowledge and concepts in deaf sign language for impaired users through an avatar. Two types of avatar technologies are taken into consideration: Video Avatar with recorded humans interface and Animated Avatar with animated figure interface. The comparative study investigates the data collection, design, implementation and the impact study. The comparative analysis of video and animated technology for data collection shows that the video format editing requires fewer skills and results are obtained easier, quicker and less expensive. The video technology supports an easier to design and implement architecture. The impact study for 2 deaf students communities is under development and for the time being the video avatar is better perceived.

User experience integrated life-style cloud-based medical application

Having a modern application capable to automatically collect and process data from users, based on information and lifestyle answers is one of current challenges for researchers and medical science. The purpose of the current study is to integrate user experience design (UXD) in a cloud-based medical application to improve patient safety, quality of care and organizational efficiency. The process consists of collecting traditional and new data from patients and users using online questionnaires. A questionnaire dynamically asks questions about the user's current diet and lifestyle. After the user will introduce the data, the application will formulate a presumptive nutritional plan and will suggest different medical recommendations regarding a healthy lifestyle, and calculates a risk factor for diseases. This software application, by design and usability will be an efficient tool dedicated for fitness, nutrition and health professionals.

Supporting diagnosis and treatment in medical care based on Big Data processing

With information and data in all domains growing every day, it is difficult to manage and extract useful knowledge for specific situations. This paper presents an integrated system architecture to support the activity in the Ob-Gin departments with further developments in using new technology to manage Big Data processing - using Google BigQuery - in the medical domain. The data collected and processed with Google BigQuery results from different sources: two Obstetrics & Gynaecology Departments, the TreatSuggest application - an application for suggesting treatments, and a home foetal surveillance system. Data is uploaded in Google BigQuery from Bega Hospital Timişoara, Romania. The analysed data is useful for the medical staff, researchers and statisticians from public health domain. The current work describes the technological architecture and its processing possibilities that in the future will be proved based on quality criteria to lead to a better decision process in diagnosis and public health.

Increasing information accessibility for patients in obstetrics-gynecology domain

It is important for the patient to have access to personal medical information in order to manage information for increased quality of medical care and life. The paper presents a module added to an Obstetrics-Gynaecology Department information system (OGD IS) supporting patient empowerment. The patient is accessing the system easily using laptops or mobile devices. The application accessed by the patient is web-based, implemented in Visual Studio. NET, using ASP.NET pages and C# language, and the application is published in the Windows Azure cloud. The solution is user friendly using familiar devices and is ubiquitous using the cloud solution. A module for translating medical terms in colloquial ones is integrated in the system. For certain situations the patient will get information related to life style influencing health status as how and what to eat or what type of exercise it is recommended.

Data and knowledge in medical distributed applications

Building a clinical decision support system (CDSS) capable to collect process and diagnose data from the patients automatically, based on information, symptoms and investigations is one of the current challenges for researchers and medical science. The purpose of the current study is to design a cloud-based CDSS to improve patient safety, quality of care and organizational efficiency. It presents the design of a cloud-based application system using a medical based approach, which covers different diseases to diagnosis, differentiated on most important pathologies. Using online questionnaires, traditional and new data will be collected from patients. After data input, the application will formulate a presumptive diagnosis and will direct patients to the correspondent department. A questionnaire will dynamically ask questions about the interface, and functionality improvements. Based on the answers, the functionality of the system and the user interface will be improved considering the real needs expressed by the end-users. The cloud-based CDSS, as a useful tool for patients, physicians and healthcare providers involves the computer support in the diagnosis of different pathologies and an accurate automatic differential diagnostic system.

Pediatrics prescriptions with ontologies and treatment suggestions

Diagnosis and treatment for children healthcare are very sensitive activities. The present work presents an ontology based model for a future information system to support these activities. The input data contains children health status, and drug characteristics. During clinical practice a database with what specialists mark as successful treatments is created. This database is gradually growing bigger and is built by physicians based on their good results related to a treatment for a certain health condition. The new ontology system proposed in this paper is supporting the e-prescription process. The relations are managed using the open source application Protégé and for suggesting treatments, using the database with successful treatments, we developed a special module that offers to physicians a selection from which they can chose the best treatment for their current case.

Interoperability evaluation case study: an Obstetrics-Gynecology Department and related Information Systems

The paper presents the steps and metrics for evaluating the interoperability of an Obstetrics-Gynecology Department Information System applied on Bega Clinic Timisoara regarding its readiness for interoperability in relation with similar systems. The developed OGD IS was modeled starting from the Generic Component Model and sends information to other medical units using the HL7 Clinical Document Architecture and Continuity of Care Document standards. The data for evaluation are real, collected between 2009 and 2010 from Bega Clinic Timisoara. The results were relatively good for the investigated data and structure.

Cloud computing technology applied in healthcare for developing large scale flexible solutions

An extremely important area in which there is also vital information needed in different locations is the healthcare domain. In the areas of healthcare there is an important exchange of information since there are many departments where a patient can be sent for investigation. In this regard cloud computing is a technology that could really help supporting flexibility, seamless care and financial cuts.

Flexible solution for interoperable cloud healthcare systems

It is extremely important for the healthcare domain to have a standardized communication because will improve the quality of information and in the end the resulting benefits will improve the quality of patients' life. The standards proposed to be used are: HL7 CDA and CCD. For a better access to the medical data a solution based on cloud computing (CC) is investigated. CC is a technology that supports flexibility, seamless care, and reduced costs of the medical act. To ensure interoperability between healthcare information systems a solution creating a Web Custom Control is presented. The control shows the database tables and fields used to configure the two standards. This control will facilitate the work of the medical staff and hospital administrators, because they can configure the local system easily and prepare it for communication with other systems. The resulted information will have a higher quality and will provide knowledge that will support better patient management and diagnosis.

Extracting clinical information to support medical decision based on standards

The paper presents a method connecting medical databases to a medical decision system, and describes a service created to extract the necessary information that is transferred based on standards. The medical decision can be improved based on many inputs from different medical locations. The developed solution is described for a concrete case concerning the management for chronic pelvic pain, based on the information retrieved from diverse healthcare databases.

Tele-assistance for discharged patients supporting continuity of care

The paper describes a tele-assistance / tele-monitoring system that assist discharged patients at their home. The system consists of units located at the homes of the monitored persons collecting and sending medical and environmental data from sensors and a call centre with a server for recording and monitoring the data. Here, specialized staff will support tele-surveillance and tele-assistance services. The algorithm that describes the alarm processing related to the threshold conditions of the values read from the sensors is presented as one important part of the system functionalities. During the project an important activity was related to the integration of the devices used in the monitoring process. There were different devices and equipments from different companies and the integration was almost impossible. The solution was to create complex software that can make the things work together.