Andriana Prentza

Machine Learning in Medical Applications

Machine Learning (ML) provides methods, techniques, and tools that can help solving diagnostic and prognostic problems in a variety of medical domains. ML is being used for the analysis of the importance of clinical parameters and their combinations for prognosis, e.g. prediction of disease progression, extraction of medical knowledge for outcome research, therapy planning and support, and for the overall patient management. ML is also being used for data analysis, such as detection of regularities in the data by appropriately dealing with imperfect data, interpretation of continuous data used in the Intensive Care Unit, and intelligent alarming resulting in effective and efficient monitoring. It is argued that the successful implementation of ML methods can help the integration of computer-based systems in the healthcare environment providing opportunities to facilitate and enhance the work of medical experts and ultimately to improve the efficiency and quality of medical care. Below, we summarize some major ML applications in medicine.

Medical support system for continuation of care based on XML web technology

In this paper, the implementation of an Internet-based telematic service for medical support is presented, which was developed and operated in pilot form within the INTRANET HEALTH CLINIC project--a 2-year project supported by the European Commission under the Health Telematics Programme. The aim of the application is to offer high quality care to users of health services over inexpensive communication pathways, using Internet-based, interactive communication tools, like remote access to medical records and transmission of multimedia information. The XML technology was employed to achieve customised views on patient data, according to the access rights of different user profiles. Strict security and access control policy were implemented to ensure secure transmission of medical data through the Internet. The system was designed to collaborate with existing clinical patient record systems and to be adjustable to different medical applications. Current implementations include the fields of Oncology, Lupus Erythrematosis, Obstetrics and Chronic Obstructive Pulmonary disease. The results of the pilot operation with oncological patients in Greece were encouraging, so that the refining of the system and its expansion to a large number of patients is already in progress.

An Android-Enabled Mobile Framework for Ubiquitous Access to Cloud Emergency Medical Services

Recently, there has been a remarkable upsurge in activity surrounding the adoption of Personal Health Records (PHRs). Since PHRs contain global patient information and not certain pieces collected by individual healthcare providers, they can be used as basic infrastructures for building and operating several important systems for both healthcare and the tax payers. Emergency medical systems (EMS) are among the most crucial ones as they involve a variety of activities which are performed from the time of a call to an ambulance service till the time of patients discharge from the emergency department of a hospital and are closely interrelated so that collaboration and coordination becomes a vital issue for patients and for emergency healthcare service performance. The integration of leading-edge technologies, such as cloud-based services and mobile technology, with Personal Health Records (PHRs) can prove important in emergency care delivery as it can facilitate authorized access to comprehensive and unified health information at any point of care or decision making through familiar environments such as Googles Android. This paper is concerned with the development of a PHR-based EMS in a cloud computing environment. The proposed EMS is accessible by Android-enabled mobile devices and incorporates a customized asynchronous notification feature whereby caregivers are notified on critical data updates in a way that efficient utilization of mobile device resources is achieved. This feature draws upon a cloud-based push messaging mechanism, namely Google Cloud Messaging, a lightweight mechanism which enables servers to communicate asynchronously with mobile applications running on Android Operating System.

Delivery of healthcare services over mobile phones: e-Vital and CHS paradigms.

Health delivery practices are shifting towards home care, since there are better possibilities for managing chronic care, controlling health delivery costs, increasing quality of life and quality of health services and the distinct possibility of predicting and thus avoiding serious complications. Mobility brings a totally new dimension to the healthcare domain and to the whole interdisciplinary provision of regional healthcare. Healthcare services can be provided in virtually any location, where access to a mobile communications system is available. Mobile tele-health systems apply mobility as a potential means in order to bring significant improvements to emergency, treatment, routine check-ups and medical consultation, e-Vital project (eTen) and CHS project (IST) worked towards m-health applications

Evaluating the effect of various background correction methods regarding noise reduction, in two-channel microarray data

In this work, two novel background correction (BC) methods, along with several commonly used ones, are evaluated regarding noise reduction in eleven two-channel self-versus-self (SVS) hybridizations. The evaluation of each BC method is investigated under the use of four statistical criteria combined into a single measure, the polygon area measure. Overall, our proposed BC approaches perform very well in terms of the proposed measure for most of the cases and provide an improved effect regarding technical noise reduction.

A Web-based interactive communication environment for the continuation in health care

Abstract Intranet health clinic is a two-year project supported by the European Commission (Telematics Applications Programme of DGXIII – Health Care Sector). Its goal is to cover the gaps experienced in the continuation and coordination of care all the way from the initial delivery of primary health care up to the delivery of highly specialized, tertiary health services and vice versa, where transfer of any type of relevant health data is needed, namely, among health care professionals and between them and the patients. Different health-related application domains are addressed covering the needs of treating chronic patients with frequent acute periods of exacerbation, chronic and even terminal patients with less “acute” aspects, and in principle healthy persons with an acute need of intensive information during pregnancy. In this paper, the proposed solution concerning the specification of a common shell and the access procedures to the service will be presented.

Elucidating the identity of resistance mechanisms to prednisolone exposure in acute lymphoblastic leukemia cells through transcriptomic analysis: A computational approach

BackgroundIt has been shown previously that glucocorticoids exert a dual mechanism of action, entailing cytotoxic, mitogenic as well as cell proliferative and anti-apoptotic responses, in a dose-dependent manner on CCRF-CEM cells at 72 h. Early gene expression response implies a dose-dependent dual mechanism of action of prednisolone too, something reflected on cell state upon 72 h of treatment.MethodsIn this work, a generic, computational microarray data analysis framework is proposed, in order to examine the hypothesis, whether CCRF-CEM cells exhibit an intrinsic or acquired mechanism of resistance and investigate the molecular imprint of this, upon prednisolone treatment. The experimental design enables the examination of both the dose (0 nM, 10 nM, 22 uM, 700 uM) effect of glucocorticoid exposure and the dynamics (early and late, namely 4 h, 72 h) of the molecular response of the cells at the transcriptomic layer.ResultsIn this work, we demonstrated that CCRF-CEM cells may attain a mixed mechanism of response to glucocorticoids, however, with a clear preference towards an intrinsic mechanism of resistance. Specifically, at 4 h, prednisolone appeared to down-regulate apoptotic genes. Also, low and high prednisolone concentrations up-regulates genes related to metabolism and signal-transduction in both time points, thus favoring cell proliferative actions. In addition, regulation of NF-κB-related genes implies an inherent mechanism of resistance through the established link of NF-κB inflammatory role and GC-induced resistance. The analysis framework applied here highlights prednisolone-activated regulatory mechanisms through identification of early responding sets of genes. On the other hand, study of the prolonged exposure to glucocorticoids (72 h exposure) highlights the effect of homeostatic feedback mechanisms of the treated cells.ConclusionsOverall, it appears that CCRF-CEM cells in this study exhibit a diversified, combined pattern of intrinsic and acquired resistance to prednisolone, with a tendency towards inherent resistant characteristics, through activation of different molecular courses of action.

Research note: A European ehealth space for moving cross-border eprescription and patient summary services forward

Purpose The purpose of the paper is to present a framework for moving cross-border ePrescription (eP) and Patient Summary (PS) services forward, bearing in mind the needs and requirements of the European e-health space for cross-border eP and PS services, the limitations of the already developed solutions, as well as outcomes available from other domains. Design/methodology/approach The outcomes of previous and current large-scale pilot projects, aiming toward the delivery of electronic cross-border services, are examined. Integration of generic building blocks (BBs) is considered for the further development of cross-border eP and PS, in line with the European Directive on patients’ rights in cross-border health care. Findings The e-health domain is expected to greatly benefit from mitigating non-domain concerns such as those for electronic identification, end point detection, non-repudiation and the use of electronic signatures and trust establishments for basic cross-border public services in Europe. Research limitations/implications Research limitations are related to the fact that electronic identification, electronic signature and semantic issues have not been fully addressed yet at a European level to support cross-border services. Practical implications Practical implications are related to the cooperation, European level compatibility and sustainability of the underlying national infrastructures required to support reliable and secure exchange of medical data, as well as the readiness to address continuously evolving interoperability, legal and security requirements in a cross-border setting. Originality/value The need for consolidating the existing outcomes of non-health specific BBs is examined for two high-priority e-health services. Ongoing progress is presented, together with related issues that need to be resolved for improving technical certainty and making it easier to use health-care services abroad in cases of emergency.

A Context-Aware, Capability-Based, Role-Centric Access Control Model for IoMT

The Internet of Medical Things (IoMT) can be described as connecting everyday devices and wearables to the Internet in order to intelligently link them together, thus enabling new forms of communication between things (medical devices) and people (patients) and between things themselves. This paper describes a context-aware access control model that hinges on the role-based and attribute-based access control (RABAC) and the capability-based access control (CapBAC) models. A prototype access control mechanism based on the model is intended to be incorporated into a personal health record (PHR) platform.

Comparative computational methods for identification of inherent or acquired mechanisms of resistance to prednisolone in Acute Lymphoblastic Leukemia cells

It has been shown previously that glucocorticoids exert a dual mechanism of action, meaning cytotoxic and mitogenic as well as mitogenic and anti-apoptotic, in a dose-dependent manner on CCRF-CEM cells at 72h. Early gene expression response suggested also a dose-dependent dual mechanism of action of prednisolone which is apparently reflected on cell state upon 72 h of treatment. The present work applies different computational methods on microarray data in order to examine the hypothesis whether these cells have an intrinsic or acquired mechanism of resistance. Early onset gene expression at 4h was compared to 72h gene expression. Early gene expression allowed identification of genes initiating pivotal, early onset regulatory mechanisms activated by prednisolone. Late, 72h exposure, microarray analysis allowed the relative identification of feedback mechanisms. From these results, it appears that CCRF-CEM cells used in this study exhibited a combined pattern of intrinsic and acquired resistance to prednisolone.