No description available.

No description available.

Class of 2016 Abstract / Objectives: To evaluate the level of accuracy of medical information presented in the seventh season of the medical drama, House M.D. To assess the accuracy of the presentation, diagnostic procedures and treatment presented in season seven. Methods: A descriptive, retrospective assessment of the accuracy of all the episodes of the seventh season of House M.D. Three reviewers independently rated the accuracy (on a scale of one to four) for the presenting signs and symptoms, diagnostic procedures, and treatment in each episode. A rating of one meant a correct and usual representation while a rating of two indicated a correct but somewhat unusual representation. A three was given for a correct but extremely unusual representation and a rating of four indicated an incorrect representation. Each researcher independently rated the episodes, and an average for each rating was used for analysis. Results: Results of the ANOVA test demonstrated no statistically significance differences between the three dependent variables (p=0.0782), therefore the Tukey HSD post-hoc test was unnecessary. The average rating for the treatment variable was 2.17 (±1.19), whereas the average ratings for the signs and symptoms and diagnosis variables were 2.74 (±0.92), and 2.87 (±1.14), respectively. The ratings for the treatment variable were more accurate compared to the other two variables. Conclusions: All three dependent variables observed in season seven of House, MD were similar in regards to accuracy falling between a rating of 2.0-3.0 representing a correct but somewhat unusual to a correct and extremely unusual representation.

The use of medical information systems is now prevailing in the whole healthcare environment where the focus is on reducing clinical errors and supporting healthcare professionals in their routine tasks. Hospitals adopt medical information systems to facilitate their healthcare staff in providing efficient services to patients. Studies show that most of the time these systems cannot deliver according to their functional capacities due to certain implementation problems. In this research, we have indicated different implementation problems, their root causes and suggested proper approaches for solving these issues. In the textual analysis, we examined different technical, psychological and social problems that may arise during the implementation process. These theoretical findings have been validated through questionnaires and interviews with doctors, nurses, technicians and people involved in the development of medical information systems. The companies that are providing implementation services are also consulted to validate the theoretical facts. The results show that implementation problems are social and psychological rather than technical, so these problems should be solved with interpersonal, psychological and social skills. The focus of the implementation process should be on the social, psychological and technical effects to avoid any conflict. Reasonable user involvement in the decision making process, motivation and proper training reduces many implementation issues automatically. It is concluded from empirical results that development and implementation teams should have reasonable medical domain knowledge to diminish future implementation and maintenance hazards. The theoretical and empirical results show that data security issues are psychological as well as technical and should be dealt with by high priority.

Medical Information Visualization makes optimized use of digitized data of medical records, e.g. Electronic Medical Record. This thesis is an extended work of Pictorial Information Visualization System (PIVS) developed by Yongji Jin (Jin, 2016) Jiaren Suo (Suo, 2017) which is a graphical visualization system by picturizing patient’s medical history summary depicting patients’ medical information in order to help patients and doctors to easily capture patients’ past and present conditions. The summary information has been manually entered into the interface where the information can be taken from clinical notes. This study proposes a methodology of automatically extracting medical information from patients’ clinical notes by using the techniques of Natural Language Processing in order to produce medical history summarization from past medical records. We develop a Named Entities Recognition system to extract the information of the medical imaging procedure (performance date, human body location, imaging results and so on) and medications (medication names, frequency and quantities) by applying the model of conditional random fields with three main features and others: word-based, part-of-speech, Metamap semantic features. Adding Metamap semantic features is a novel idea which raised the accuracy compared to previous studies. Our evaluation shows that our model has higher accuracy than others on medication extraction as a case study. For enhancing the accuracy of entities extraction, we also propose a methodology of Topic Segmentation to clinical notes using boundary detection by determining the difference of classification probabilities of subsequence sequences, which is different from the traditional Topic Segmentation approaches such as TextTiling, TopicTiling and Beeferman Statistical Model. With Topic Segmentation combined for Named Entities Extraction, we observed higher accuracy for medication extraction compared to the case without the segmentation. Finally, we also present a prototype of integrating our information extraction system with PIVS by simply building the database of interface coordinates and the terms of human body parts.

Τα πληροφοριακά συστήματα υγείας είναι μια πραγματικότητα που έχει εφαρμοστεί στο χώρο της υγείας των περισσότερων κρατών της ευρωπαϊκής ένωσης εδώ και αρκετά χρόνια. Στην Ελλάδα ο τομέας αυτός άρχισε να αναπτύσσεται τα τελευταία χρόνια μέσω των έργων των Ολοκληρωμένων Περιφερειακών Συστημάτων Υγείας (ΟΠΣΥ). Το σύνολο αυτών των έργων στοχεύει σε πρώτη φάση στη δημιουργία βασικών υποδομών στις Μονάδες Υγείας (Νοσοκομεία, Κέντρα Υγείας κ.λ.π.) και σε δεύτερη φάση στην καθιέρωση σύγχρονων ηλεκτρονικών υπηρεσιών. Η αποτελεσματική αντιμετώπιση των επειγόντων περιστατικών είναι ζήτημα υψίστης σημασίας για την αξιοπιστία ενός συστήματος υγείας. Στην Ελλάδα, η λειτουργία αυτή πάσχει σημαντικά, γεγονός που δεν οφείλεται στην ποιότητα παροχής ιατρικών υπηρεσιών, αλλά στην οργάνωση του συστήματος καθώς και σε διοικητικές και υλικοτεχνικές ανεπάρκειες, οι οποίες οδήγησαν στη σημερινή εικόνα. Κατά γενική αποδοχή, η ποιότητα στις υπηρεσίες υγείας εξαρτάται, εκτός των άλλων, από την ταχύτητα με την οποία το ιατρικό και παραϊατρικό προσωπικό μπορεί να έχει στη διάθεσή του τα ιατρικά δεδομένα κάθε ασθενή. Ειδικά στα τμήματα επειγόντων περιστατικών (ΤΕΠ), τα κρίσιμα αυτά δεδομένα μπορούν να κρίνουν ακόμα και την έκβαση ενός περιστατικού. Προς αυτή την κατεύθυνση η παρούσα διπλωματική εργασία αφορά την κατασκευή μιας βάσης δεδομένων για την παρακολούθηση και αντιμετώπιση ασθενών που εξετάζονται στο ΤΕΠ. Είναι εμπλουτισμένη με πραγματικά στοιχεία από την περίθαλψη ασθενών στο ΤΕΠ του Π.Γ.Ν.Πατρών στο χρονικό διάστημα Σεπτέμβριος-Δεκέμβριος 2008. Ο σκοπός της είναι να διευκολύνει το έργο του ιατρικού προσωπικού μέσω της άμεσης παροχής πληροφορίας για τους ασθενείς (όπως π.χ. ιστορικό ασθενούς, προηγούμενες εξετάσεις στο ΤΕΠ, εργαστηριακός έλεγχος κ.λ.π.), αλλά και να βελτιώσει την ποιότητα παροχής υπηρεσιών προς όφελος των ασθενών που εξετάζονται στο ΤΕΠ. Στα κεφάλαια που ακολουθούν αναλύονται τα εξής θέματα: Στο 1ο κεφάλαιο γίνεται μια εισαγωγή στις Βάσεις Δεδομένων και περιγράφονται οι βασικές τους έννοιες όπως τα μοντέλα τους, τα Συστήματα Διαχείρισης Βάσεων Δεδομένων (ΣΔΒΔ-DBMS) και η αρχι-τεκτονική τους, το Διάγραμμα Οντοτήτων Συσχετίσεων κ.λ.π. Στο 2ο κεφάλαιο γίνεται μια σύντομη περιγραφή στο DBMS Microsoft Access με το οποίο κατασκευάστηκε η βάση δεδομένων της διπλωματικής εργασίας. Στο 3ο κεφάλαιο γίνεται αναφορά στα πληροφοριακά συστήματα Υγείας στην Ελλάδα και στο εξωτερικό καθώς και σε έρευνες που έχουν γίνει για την επέκταση και τη βελτίωση τους. Στο 4ο κεφάλαιο περιγράφεται η σχεδίαση της βάσης δεδομένων για την παρακολούθηση και αντιμετώπιση ασθενών που εξετάστηκαν στο ΤΕΠ του Π.Γ.Ν. Πατρών και παρουσιάζονται όλα τα εργαλεία που προσφέρει όπως π.χ. ένα γραφικό και φιλικό προς το χρήστη περιβάλλον για καταχώριση και διαχείριση ασθενών, στατιστικά στοιχεία και γραφήματα που τα αναπαριστάνουν, ερωτήματα για επιλογή πληροφορίας, μακροεντολές που διευκολύνουν το χειρισμό της κ.λ.π. Στο 5ο κεφάλαιο παρουσιάζονται τα συμπεράσματα από το πλη-ροφοριακό σύστημα που κατασκευάστηκε, αναλύεται η χρησιμότητα του και προτείνονται τρόποι για τη μελλοντική επέκταση και βελτίωση του. / Medical information systems have been applied in the field of health of most states of European Union for many years. In Greece this sector started to evolve the last years through the Completed Regional System of Health. The total of these projects aims, firstly, to the creation of the basic infractions to the Health Units (Hospitals, Health Centres etc), and secondly, to the establishment of modern electronic services. The effective treatment of urgent incidents is a matter of the utmost importance for the credibility of a health system. In Greece this function suffers considerably, which is not due to the quality of the provision of medical services, but to the organization of the system, as well as to administrative and logistic deficiencies, which led to the current situation. At general acceptance, the quality of the health services depends on the rapidity with which the medical and paramedical personnel can have at his disposal the medical data of each patient. Specifically, in the Emergency Unit, these critical data can even predicate the outcome of an incident. To this direction, this diplomatic essay concerns the construction of a new database system that follows up and treats patients who are examined in the Emergency Units. It is enriched with actual data from the nursing in the Emergency Unit of the General University Hospital of Patras during September-December 2008. Its aim is to facilitate the work of the medical personnel through the direct provision of information for the patients (such as the medical records, previous examinations in the Emergency Unit, laboratory tests, etc), but also to improve the quality of the provision of information for the benefit of the patients who are examined in the Emergency Unit. The following chapters will analyze the following issues: 1st Chapter: Introduction to Database Systems and presentation of their main definitions such as database models, Database Management Systems (DBMS) and their architecture, Entity-Relationship diagram etc. 2nd Chapter: A quick reference to Microsoft Access DBMS, which has been used for the database construction of this diplomatic essay. 3rd Chapter: A presentation about the medical information systems in Greece and abroad, as well as researches that have been taken place concerning their extension and improvement. 4th Chapter: A detailed reference of the construction of the data-base system that follows up and treats patients who are examined in the Emergency Unit of the General University Hospital of Patras and represents all the tools that are used, such as a graphic and user-friendly interface for the registration and management of the patients, statistics and charts that reconstruct them, questions about the choice of the information, macros that facilitate its control, etc. 5th Chapter: The conclusions of the information system that have been constructed, analysis of its utility and proposals about its future extension and improvement.

One of the challenges in medical information retrieval is the terminology gap between the documents (commonly written by medical professional, using medical jargons), and the queries (commonly composed by non professional, using layman terms). In this thesis, we investigate the effect of query expansion, using domain-specific knowledge resource, to deal with this challenge. We use the Unified Medical Language System (UMLS), a repository of biomedical vocabularies, and utilize two of its resources: the Metathesaurus and the Semantic Network. We use the query set and document set provided by CLEF eHealth organizer. The query sets, provided for the medical information retrieval shared task, represent two different use cases of medical information retrieval. We experiment with query expansion using synonymous terms and non-synonymous concepts, blind relevance feedback, field weighting, and linear interpolation of different systems. Powered by TCPDF (www.tcpdf.org)

En dépit de la production standardisée de millions d'enregistrements décrivant année après année l'activité d'hospitalisation complète en France, aucune étude globale, aucun suivi précis et répété dans le temps, n'a pu être mené à partir de ces données.Si ces données sont exploitées dans une grande variété d'études spécifiques, elles peinent à trouver une utilisation significative dans l'analyse de l'activité et du recrutement des établissements de santé, ou dans celle des besoins de la population. Tout un pan d'analyse de l'efficience du système de santé reste ainsi inaccessible.Nous nous fixons comme objectif de contribuer à développer un cadre précis d'exploitation de ces données. Cette démarche se fera en trois temps :- Définition d'une méthode de consolidation des données ;- Construction de référentiels d'analyse des données ;- Elaboration de méthodes d'analyse sur deux thématiques générales : la caractérisation de l'activité des établissements et l'étude de leur recrutement, avec exemple d'application de ces méthodes. / Millions of computerized records describing inpatient hospitalization activity are produced year after year in France.In spite of the availability of this massive amount of data, no global, iterative and well calibrated related study on health system efficiency has been possible.There are of course many specific studies partially or totally relying on these data, but their systematic use for assessing hospital activity, catchment areas or population health needs remains to be implented.Our work aims to contribute to create a methodological framework for analyzing these data through a three step approach :- Definition of data consolidation methods ;- Creation of adequate data repositories ;- Determination of analysis methods for two general topics : hospital activity characterization and study, with example applications.

The thesis is aimed at the quality of health care in the specificmedical facility. The goal of the thesis is to characterize actualsituation of services, which are provided and to find out whether the present information system contribute to increase quality in the medical facility or not. In the first part is defined theoretical knowledge of the quality of medical care and the quality of information systems. This theoretical base is applied in the second part. On the base of data from information system, the indicators by which the quality was evaluated were defined. Used indicators were analysed, compared and consequently evaluated. In the case of ineffective system, which does not contribute to increase the quality of medical facility, there are some recommendation and changes which leads the system to be more effective.

В диссертации был проведен анализ литературы и нормативно-справочной документации по теме диссертации, по результатам исследования была сформирована таблица сравнений медицинских информационных систем. Разработаны требования к медицинским системам. В ходе работы были построены модели исследуемых бизнес-процессов и разработан новый блок медицинской информационной системы для клиники «Геном-Волга». / The analysis of literature and normative-reference documentation on the subject of the thesis was carried out in the thesis, the table of comparisons of medical information systems was formed based on the results of the research. Requirements to medical systems are developed. In the course of the work, models of the studied business processes were built and a new block of medical information system for Genom-Volga clinic was developed.