Background: Enrollment of large cohorts of syncope patients from administrative data is crucial for proper risk stratification but is limited by the enormous amount of time required for manual revision of medical records. Aim: To develop a Natural Language Processing (NLP) algorithm to automatically identify syncope from Emergency Department (ED) electronic medical records (EMRs). Methods: De-identified EMRs of all consecutive patients evaluated at Humanitas Research Hospital ED from 1 December 2013 to 31 March 2014 and from 1 December 2015 to 31 March 2016 were manually annotated to identify syncope. Records were combined in a single dataset and classified. The performance of combined multiple NLP feature selectors and classifiers was tested. Primary Outcomes: NLP algorithms’ accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F3 score. Results: 15,098 and 15,222 records from 2013 and 2015 datasets were analyzed. Syncope was present in 571 records. Normalized Gini Index feature selector combined with Support Vector Machines classifier obtained the best F3 value (84.0%), with 92.2% sensitivity and 47.4% positive predictive value. A 96% analysis time reduction was computed, compared with EMRs manual review. Conclusions: This artificial intelligence algorithm enabled the automatic identification of a large population of syncope patients using EMRs.
Human Tissue Banks are key for Oncological research and practice. Biobanking processes cross many care departments and have a number of stakeholders, often carrying different objectives: quality assurance and process efficiency are hard to garrison. Key issues in a biobanking project are: dedicated organization, process control, completeness of clinical information on samples, integrated Information and Communication Technologies. Fondazione IRCCS Istituto Nazionale dei Tumori is an oncologic research and treatment institution in Milan (Italy). Our project started in October 2007 aiming at revising the whole tissue collection process (from Surgery to Anatomical pathology assessment, to analysis and storage in the Biobank), developing a clinical biobank management system collecting structured data on cases, and designing an RFId-based system able to track the time-and temperature-sensitive specimens' flow. Now that go-live has begun, technological and-above all-organizational challenges of the project can be discussed in detail. We hope other organizations will appreciate our efforts and are willing to apply a biobanking network as soon as possible.
Traceability and quality assurance of bedside processes are often still manual, without the appropriate support of information systems. Automatic Identification and Data Capture (AIDC) solutions integrated with Mobile&Wireless devices are key solutions to meet the needs of secure identification of persons and items and of traceability of processes in healthcare organizations. These technologies can fit a variety of processes, like enterprise-wide person/item identification, blood transfusions, surgical samples identification, therapy management. The challenge is to extend the use of these solutions also to other processes like biobanking, where stem cellular products require strict procedures of collection and manipulation, even in critical environmental conditions. Fondazione IRCCS Istituto Nazionale dei Tumori in Milan (Italy) has a wide experience in RFId projects and is starting to lead a project aimed to design, develop and implement a set of organizational models, acknowledged procedures and ICT tools in order to improve actual support to collection and transplantation of Human Stem Cells. In this paper we present a literature overview of cases of implementation of AIDC technology solution and of how its character of ubiquity and versatility could fit well with process requirements, discussing the Istituto's business case.
305
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.