Studies in health technology and informatics
-
Stud Health Technol Inform · Jan 2013
Engineering natural language processing solutions for structured information from clinical text: extracting sentinel events from palliative care consult letters.
Despite a trend to formalize and codify medical information, natural language communications still play a prominent role in health care workflows, in particular when it comes to hand-overs between providers. Natural language processing (NLP) attempts to bridge the gap between informal, natural language information and coded, machine-interpretable data. This paper reports on a study that applies an advanced NLP method for the extraction of sentinel events in palliative care consult letters. ⋯ A random selection of 215 anonymized consult letters was used for the study. The results of the NLP extraction were evaluated by comparison with coded sentinel event data captured independently by clinicians. The average accuracy of the automated extraction was 73.6%.
-
Stud Health Technol Inform · Jan 2013
Understanding how clinical judgement and communicative practices interact with the use of an electronic clinical handover system.
Clinical handover is a high risk scenario involving the transfer of information, responsibility and accountability for patient care. Many strategies have been proposed to improve clinical handover and reduce risks it can pose to the safety and quality of patient care. ⋯ This research examines these issues based on evidence generated from a user-centred approach involving clinicians in the development and implementation of an electronic clinical handover system. The paper highlights how clinical judgements and communicative practices interact with an electronic clinical handover system, and discusses their potential implications for patient safety as part of a broader clinical handover improvement project.
-
This paper is concerned with the development of an Emergency Medical Services (EMS) system which interfaces with a Holistic Emergency Care Record (HECR) that aims at managing emergency care holistically by supporting EMS processes and is accessible by Android-enabled mobile devices.
-
Stud Health Technol Inform · Jan 2013
Observational StudyWhiteboard icons to support the blood-test process in an emergency department: an observational study of temporal patterns.
The competent treatment of emergency department (ED) patients requires an effective and efficient process for handling laboratory tests such as blood tests. This study investigates how ED clinicians go about the process, from ordering blood tests to acknowledging their results and, specifically, assesses the use of whiteboard icons to support this process. ⋯ The whiteboard icons, which indicate four temporally distinct steps in the blood-test process, support the nurses in maintaining the flow of patients through the ED and the physicians in assessing test results at timeouts. The main results of this study are, however, that the blood-test process is temporally and collaboratively complex, that the whiteboard icons pass by most of this complexity, that attending to the icons is yet another temporally sensitive activity to remember, and that whereas the assessment of test results is integral to patient treatment, the acknowledgement of having seen the results is a formal add-on, the responsibility for which is sometimes unclear.
-
Stud Health Technol Inform · Jan 2013
Architecture of a prehospital emergency patient care report system (PEPRS).
In recent years, prehospital emergency care adapted to the technology shift towards tablet computers and mobile computing. In particular, electronic patient care report (e-PCR) systems gained considerable attention and adoption in prehospital emergency medicine [1]. On the other hand, hospital information systems are already widely adopted. ⋯ Aim of this project is to describe a generic architecture which can be used to implement data transfer and integration of pre hospital emergency care reports to hospital information systems. In summary, the prototype was able to integrate data in a standardized manner. The devised methods can be used design generic software for prehospital to hospital data integration.