International journal of medical informatics
-
Electronic health record (EHR) systems contain structured data (such as diagnostic codes) and unstructured data (clinical documentation). Clinical insights can be derived from analyzing both. The use of natural language processing (NLP) algorithms to effectively analyze unstructured data has been well demonstrated. Here we examine the utility of NLP for the identification of patients with non-alcoholic fatty liver disease, assess patterns of disease progression, and identify gaps in care related to breakdown in communication among providers. ⋯ For identification of NAFLD, NLP performed better than alternative selection modalities. It then facilitated analysis of knowledge flow between physician and enabled the identification of breakdowns where key information was lost that could have slowed or prevented later disease progression.
-
Review
A review of electronic medical record keeping on mobile medical service trips in austere settings.
Electronic medical records (EMRs) may address the need for decision and language support for Western clinicians on mobile medical service trips (MSTs) in low resource settings abroad, while providing improved access to records and data management. However, there has yet to be a review of this emerging technology used by MSTs in low-resource settings. The aim of this study is to describe EMR systems designed specifically for use by mobile MSTs in remote settings, and accordingly, determine new opportunities for this technology to improve quality of healthcare provided by MSTs. ⋯ There have been limited attempts to tailor EMRs to mobile MSTs. Only Open MRS has a broad user base, and other EMR systems should consider interoperability and data sharing with larger systems as a priority. Several systems include tablet compatibility, or are specifically designed for smartphone, which may be helpful given the environment and low resource context. Results from this review may be useful to non-government organizations (NGOs) considering modernization of their medical records practices as EMR use facilitates research, decreases paper administration costs, and improves perceptions of professionalism; however, most MST-specific EMRs remain in their early stages, and further development and research is required before reaching the stage of widespread adoption.
-
Nursing triage documentation is the first free-form text data created at the start of an emergency department (ED) visit. These 1-3 unstructured sentences reflect the clinical impression of an experienced nurse and are key in gauging a patient's illness. We aimed to predict final ED disposition using three commonly-employed natural language processing (NLP) techniques of nursing triage notes in isolation from other data. ⋯ Nursing triage notes can be used to predict final ED patient disposition, even when used separately from other clinical information. These findings have substantial implications for future studies, suggesting that free text from medical records may be considered as a critical predictor in research of patient outcomes.
-
Comparative Study
Criterion validity of a computer-assisted instrument of self-triage (ca-ISET) compared to the validity of regular triage in an ophthalmic emergency department.
The computer-assisted version of a self-triage tool (ca-ISET) for an ophthalmic emergency department (ED) was developed to increase the validity of the triage procedure when trained ED staff is absent. ⋯ The sensitivity, PPV and NPV of the ca-ISET does not differ from the sensitivity of the regular triage, while the ca-ISET retained a reasonable level of specificity. Therefore the ca-ISET can be recommended as a tool for ophthalmic emergency departments, and could be used when trained ED staff is absent.
-
Self-management can optimize health outcomes for individuals with chronic pain (CP), an increasing fiscal and social burden in Canada. However, self-management is rarely integrated into the regular care (team activities and medical treatment) patients receive. Health information technology offers an opportunity to provide regular monitoring and exchange of information between patient and care team. ⋯ Internet-based programs contain automated, communication and decision support features that can address information and care gaps reported by patients and clinicians. However, focus groups identified functionalities not reported in the literature, non-medical and condition- and context-specific information, integration of personal health records, and the role of the different health professionals in chronic pain management were not identified. These gaps need to be considered in the future development of Internet-based programs. While the association between the mechanisms of Internet-based programs' features and outcomes is not clearly established, the results of this study indicate that interactivity, personalization and tailored messages, combined with therapist contact will maximize the effectiveness of an Internet-based chronic pain program in enhancing self-management.