Grace O’Mahony, Christopher Hawthorne, Karl McQuaid, Guillermo H. Lopez-Campos
1195 - 1196
Sepsis results in various patient complications and is due to a heightened inflammatory response against infection. This condition requires further exploration of biomarkers. We employed an “in silico” method comprised of text-mining and additionally clinical validation through the Medical Information Mart for Intensive Care. We highlight that Factor VIII shows potential as a pertinent septic shock biomarker.
Maria Patte, Joseph Liaskos, Parisis Gallos, John Mantas
1197 - 1198
The information of the general population regarding the prevention of eye diseases is crucial. This work presents the design and development of an online prevention tool for the information and education of the general population about ophthalmological diseases. A literature review was conducted for the collection of all necessary and up-to-date information regarding the diseases selected. The phases of requirement analysis, design, development and evaluation were followed. The online tool developed, proved to accomplish the aims of usability and usefulness in the prevention of eye diseases and their complications.
Saly Abouelenein, Tremaine Williams, Jaime Baldner, Meredith Nahm Zozus
1199 - 1200
This job analysis was conducted to compare, assess and refine the competencies of the clinical research data management profession.
Materials and Methods:
Two questionnaires were administered in 2015 and 2018 to collect information from data managers on professional competencies, types of data managed, types of studies supported, and necessary foundational knowledge.
In 2018 survey, 67 professional competencies were identified. Job tasks differed between early- to mid-career and mid- to late-career practitioners. A large variation in the types of studies conducted and variation in the data managed by the participants was observed.
Clinical research data managers managed different types of data with variety of research settings, which indicated a need for training in methods and concepts that could be applied across therapeutic areas and types of data.
The competency survey reported here serves as the foundation for the upcoming revision of the Certified Clinical Data Manager (CCDMTM) exam.
Giacomo Derchi, Marco Visentin, Vincenzo Marchio, Lisa Lardani, Antonio Barone, Marco Prenassi, Sara Marceglia
1201 - 1202
Literature reviews are crucial in the choice of the best personalized material type and restauration type in restorative dentistry. We developed an IBM-Watson based system to support literature search for restorative dentistry, and compared its results to a literature search performed by a trained professional. We found that our system could assist the researcher in performing a literature review, but the grounding semantic model needs to be refined in order to provide more extensive results.
Austin Springer, Donna Chachere, Awaad Alsarkhi, Meredith Zozus
1203 - 1204
One of the biggest challenges facing biomedical research today is the lack of reproducibility in findings. In response, a growing body of literature has emerged to address this. However, much of this focuses on bias and methods, while little addresses the issue of information quality. The purpose of this poster is to determine the role of information quality for retracted bioinformatics literature.
Sapan Mandloi, Zackary Falls, Rong Deng, Ram Samudrala, Peter L. Elkin
1205 - 1206
RNA-editing is an important post-transcriptional RNA sequence modification performed by two catalytic enzymes, “ADAR”(A>I) and “APOBEC”(C>U). Although APOBEC-mediated C>U editing has been associated with a number of human cancers, the extent of C>U editing in human disease remains unclear. Here, we performed an association study and found that at least 1293 human disease variants occur at sites predicted by sequence motif analysis (RNASee protocol) to undergo APOBEC3A/G C>U editing. These variants were associated with a wide array of human disease conditions ranging from cancer, metabolic disorders, retinopathies, cardiomyopathies, neurodegenerative disorders and immunodeficiencies. These results indicate that APOBEC mediated C>U RNA editing may have widespread and previously unreported contributions to human disease conditions.
Michał Kopka, Wiktor Paskal, Adriana M. Paskal, Piotr Pietruski, Ryszard Kopka, Pawel K. Wlodarski
1209 - 1210
Analyses of nerve histology are core assays in basic and applied research and even in clinical setting. Detailed report on nerve morphology may unbiasedly indicate the current state of a peripheral nerve. Manual method requires trained technician and is a time-consuming procedure. Available plugins to well known image processors are limited in use and data outcomes. Thus, the aim of the study was to create a. tool for for fast and repeatable analysis of a nerve section image. As a results we get very high precision of analysis in shorter time.
The determination of vital signs is a fundamental aspect of patient care. Electronic health records have a structured format for their registration. It is known that the frequency with which this data is recollected is not representative of reality. To complement the missing data we have created a tool that extract the information regarding blood pressure, heart rate, respiratory rate, height, weight and pain level recorded in free text in the clinical notes of outpatients.
Thomas Engelsma, Monique W.M. Jaspers, Anne M. Turner
1213 - 1214
the aim of this scoping review is to 1) identify guidelines, frameworks, issues, and recommendations regarding the development of a discrete choice experiment (DCE), 2) look at potential design considerations regarding the development of a DCE for older adults with dementia, and 3) summarize knowledge about the current inclusion of and experiences with older adults with cognitive impairment in DCE studies.
Two literature searches divided into two topics were performed in PubMed, CINAHL, and PsycINFO.
Topic 1 found 19 articles regarding frameworks, guidelines and design considerations for DCEs in healthcare. Topic 2 found eight articles regarding the effect of cognitive impairment on DCE results and/or discussing the inclusion of cognitive impaired older adults in these DCE studies.
There is minimal literature available regarding the effect of cognitive impairment on DCE results. In future studies we will explore if DCEs can be used to involve older adults with dementia in decisions regarding transitions in care.
Pierre Gillois, Lionel Di Marco, Josep M. Nicolàs, Alexandre Moreau-Gaudry, Anne Ego, Sandra David-Tchouda, Donald K. Martin, Jean-Luc Bosson
1215 - 1216
Biostatistics is one of the transversal subjects that all future doctors must acquire and master. Nonetheless, it is a subject that has the reputation of being difficult, which has not been able to be corrected even with the application of new pedagogical methods such as blended learning. We address this problem with our acculturative and disruptive approach in the form of a serious game scenario in clinical research that integrates biostatistics with our R4Web adapted tools. Our approach was launched in 2008 for the second year of medical school. Here we describe this LOE scenario for serious game including the biostatistics disruptive acculturation task and present its new international version.
Hospital Italiano de Buenos Aires (HIBA) is an academic tertiary care hospital highly specialized that has started the process of informatization of chemotherapy protocols. The objective is to describe the development of a computerized physician order entry (CPOE) oriented to the oncology adult patient and the members of the healthcare team that works with him (physicians, pharmacists, nurses and administrative staf) to improve the process and prevent errors at a critical point in the patient’s health care: during prescription, preparation and / or administration. The development of this system consisted of several stages: inquiries about the usual work and perception of needs of the potential users; user-centered design; interoperability with the electronic health record (EHR) and development of a final prototype
In this, study, an attempt is made to differentiate muscle nonfatigue and fatigue condition using signal complexity metrics derived from phase space network features. A total of 55 healthy adult volunteers performed dynamic contraction of the biceps brachii muscle. The first and last curl are segmented and are considered as nonfatigue and fatigue condition respectively. A weighted phase space network is constructed and reduced to a binary network based on various radii. The mean and median degree centrality features are extracted from these networks and are used for classification. The results of the classification indicate that these features are capable of differentiating nonfatigue and fatigue condition with 91% accuracy. This method of analysis can be extended to applications such as diagnosis of neuromuscular disorder where fatigue is a symptom.
This work explores the design and implementation of an algorithm for the classification of magnetic resonance imaging data for computer-aided diagnosis of schizophrenia. Features for classification were first extracted using two morphometric methods: voxel-based morphometry (VBM) and deformation-based morphometry (DBM). These features were then transformed into a wavelet domain using the discrete wavelet transform with various numbers of decomposition levels. The number of features was then reduced by thresholding and subsequent selection by: Fisher’s Discrimination Ratio (FDR), Bhattacharyya Distance, and Variances (Var.). A Support Vector Machine with a linear kernel was used for classification. The evaluation strategy was based on leave-one-out cross-validation.
The automated analysis of digitized immunohistochemistry microscope slides is usually a challenging task, because markers should be analysed on the tumor area only. Tumor areas could be recognized on a different slide, stained with Haematoxylin-Eosin. The basic idea of the present poster is to evaluate how well deep learning methods perform on the single haematoxylin component of staining, with the prospective possibility of developing a classifier able to recognize tumor areas on IHC slides on their haematoxylin component only. In a preliminary experiment, single stain images obtained by H-E color deconvolution showed an accuracy of 0.808 and 0.812 for Hematoxilyn and Eosin components, respectively.
In this study, an attempt has been made to differentiate normal and cardiomegaly using cardio-mediastinal ratiometric features and machine learning approaches. A total of 60 chest radiographs including normal and cardiomegaly subjects are considered from a public dataset. The images are preprocessed using edge aware contrast enhancement technique to improve the edge contrast of lung boundaries. The mediastinal, cardiac and thoracic widths and their ratiometric indices are computed to characterize the morphological variations. The features are fed to three different classifiers for the differentiation of normal and cardiomegaly. Results show that the Linear discriminant analysis classifier is found to perform better with average values of recall 88.7%, precision 88.8%, and area under the curve 91.9%. Hence, the proposed computer aided diagnostic approach appears to be clinically significant to distinguish normal and cardiomegaly especially in remote and resource – poor settings.
Raphaël Chauvet, Cédric Bousquet, Agnès Lillo-Lelouet, Ilan Zana, Ilan Ben Kimoun, Marie-Christine Jaulent
1227 - 1228
This poster presents a non-exhaustive study of machine learning classification algorithms on pharmacovigilance data. In this study, we have taken into account the patient’s clinical data such as medical history, medications taken and their indications for prescriptions, and the observed side effects. From these elements we determine whether the patient case is considered serious or not. We show the performances of the different algorithms by their precision, recall and accuracy as well as their learning curves.
Downtime of information systems is a universal challenge faced by health care institutions. In this poster, we present the findings of a scoping review of how hospital organizations and their staff deal with downtime, and how coping can be grouped into three strategies; 1) Increasing communication, 2) Analog fallback, and 3) Restricted redundant systems. Our findings point to the importance of customizing coping mechanisms for individual healthcare institutions, and designing systems that empower users to deal with downtime.
Mariano Aizpurua, Tomás Galluzzi, Santiago Esteban
1231 - 1232
The implementation of an Electronic Medical Record (EMR) in the public healthcare system of Buenos Aires City began in June 2016. AGISE is a government department that assists in health decision-making processes by providing timely and quality data. In this study we designed a professional development program to improve organizational capacities for health analytics.
To perform a cross-mapping study between nursing documentation from a Electronic Health Record (EHR) of a Brazilian hospital and four nursing terminology systems.
Descriptive, quantitative and retrospective study.
The EHR presents a total of 247 anamnesis / physical examination terms, 75 nursing diagnoses, and 205 nursing interventions terms to nurses make their choice.
Authors strongly recommend that attempts in building more usable and friendly EHRs for clínical care practice documentation consider classification systems structures in their development, to ensure complete, safe, evidence-based and comparable registries.
The aim of this study was to examine existing methods for sharing results of stem cell research via online data repositories. To identify the relevant repositories, a PubMed search was conducted using standard MeSH terms which was followed by a web-based search of relevant databases. The search yielded 16 databases created between 2010 and 2019. The review of databases identified 35 major rubrics and their sub-rubrics organized in a five-module system. Data integration approaches were characterized by three domains (common data elements, data visualization and analysis tools, and ontology mapping) which varied widely across the databases. Current state of stem cell data integration lacks reproducibility and standardization. Standardization of data integration approaches for representing stem cell studies is necessary to facilitate data sharing.
This article reviews the main characteristics of five widely used data provenance models and recommendations. We suggest a set of six provenance properties that should be satisfied by any provenance model as a basis for further implementation of provenance mechanisms, supporting the findable, accessible, interoperable and reusable (FAIR) principles for both, research and health data.
Bridget J. Daley, Evangelia Kyrimi, Kudakwashe Dube, Norman E. Fenton, Graham A. Hitman, Scott McLachlan
1239 - 1240
Information visualisation is transforming data into visual representations to convey information hidden within large datasets. Information visualisation in medicine is underdeveloped. In midwifery, the impact of different graphs on clinicians’ and patients’ understanding is not well understood. We investigate this gap and its potential consequences.
We developed a deep learning approach for accurate prediction of PCA patients one year earlier with minimal features from electronic health records. The area under the receiver operating curve for prediction of PCA was 0.94. Moreover, the sensitivity and specificity of CNN were 0.87 and 0.88, respectively.
Miguel Pedrera, Pablo Serrano, Ana Terriza, Jaime Cruz, Carolina Varela, Ana Salamanca, Noelia Garcia, Carmen Salgado, Consuelo Sanz, Lucía Hernández, Montse Alemany, Adolfo Muñoz
1243 - 1244
This work aims to define a standardized information model for representation of multiple data sources in breast cancer. A set of data elements has been identified using ICHOM Breast Cancer as the minimum data set and adapting it to the needs of Hospital Universitario 12 de Octubre. With this, an information model has been defined according to ISO 13606 and SNOMED CT standards.