Journal of biomedical informatics
-
Structured data on mammographic findings are difficult to obtain without manual review. We developed and evaluated a rule-based natural language processing (NLP) system to extract mammographic findings from free-text mammography reports. ⋯ Our NLP system successfully extracts clinically useful information from mammography reports. Moreover, SAS is a feasible platform for implementing NLP algorithms.
-
The workflow models of the patient journey in a Pediatric Emergency Department (PED) seems to be an effective approach to develop an accurate and complete representation of the PED processes. This model can drive the collection of comprehensive quantitative and qualitative service delivery and patient treatment data as an evidence base for the PED service planning. Our objective in this study is to identify crowded situation indicators and bottlenecks that contribute to over-crowding. ⋯ This modeling, which has to represent most faithfully possible the reality of the PED of CHRU of Lille, is necessary. It must be detailed enough to produce an analysis allowing to identify the dysfunctions of the PED and also to propose and to estimate prevention indicators of crowded situations. Our survey is integrated into the French National Research Agency (ANR) project, titled: "Hospital: Optimization, Simulation and avoidance of strain" (HOST).
-
The focus of this paper is on the challenges and opportunities presented by developing scenarios of use for interactive medical devices. Scenarios are integral to the international standard for usability engineering of medical devices (IEC 62366:2007), and are also applied to the development of health software (draft standard IEC 82304-1). The 62366 standard lays out a process for mitigating risk during normal use (i.e. use as per the instructions, or accepted medical practice). ⋯ Challenges include: integrating scenario-based design with usability engineering practice; covering the breadth of uses of infusion devices; and managing contradictory evidence. Opportunities included scenario use beyond design to guide marketing, to inform purchasing and as resources for training staff. This study exemplifies one empirically grounded approach to communicating and negotiating the realities of practice.
-
Integrating monitor alarms with laboratory test results to enhance patient deterioration prediction.
Patient monitors in modern hospitals have become ubiquitous but they generate an excessive number of false alarms causing alarm fatigue. Our previous work showed that combinations of frequently co-occurring monitor alarms, called SuperAlarm patterns, were capable of predicting in-hospital code blue events at a lower alarm frequency. In the present study, we extend the conceptual domain of a SuperAlarm to incorporate laboratory test results along with monitor alarms so as to build an integrated data set to mine SuperAlarm patterns. ⋯ For a given FPRmax threshold, the SuperAlarm set generated from the integrated data set has higher sensitivity and lower WDR than the SuperAlarm set generated from the regular monitor alarm data set. In addition, the McNemar's test also shows that the performance of the SuperAlarm set from the integrated data set is significantly different from that of the SuperAlarm set from the regular monitor alarm data set. We therefore conclude that the SuperAlarm patterns generated from the integrated data set are better at predicting code blue events.
-
Physicians' adoption seems to be a significant issue when comprehensive implementation of Electronic Medical Records (EMR) is considered. This study was conducted to determine the organizational contextual factors affecting physicians' adoption of EMR. ⋯ The present study acknowledged that considerable part of physicians' attitude toward EMRs' adoption is controlled by organizational contextual factors. These factors should be subsequently the major concern of health organizations and health policy makers.