Steven H. Brown

Integrating computerized clinical decision support systems into clinical work: A meta-synthesis of qualitative research

PURPOSEnComputerized clinical decision support systems (CDSS) are an emerging means for improving healthcare safety, quality and efficiency, but meta-analyses findings are mixed. This meta-synthesis aggregates qualitative research findings as possible explanations for variable quantitative research outcomes.nnnINCLUSION CRITERIAnQualitative studies published between 2000 and 2013 in English, involving physicians, registered and advanced practice nurses experience of CDSS use in clinical practice were included.nnnSEARCH STRATEGYnPubMed and CINAHL databases were searched. Study titles and abstracts were screened against inclusion criteria. Retained studies were appraised against quality criteria. Findings were extracted iteratively from studies in the 4th quartile of quality scores. Two reviewers constructed themes inductively. A third reviewer applied the defined themes deductively achieving 92% agreement.nnnRESULTSn3798 unique records were returned; 56 met inclusion criteria and were reviewed against quality criteria. 9 studies were of sufficiently high quality for synthetic analysis. Five major themes (clinician-patient-system integration; user interface usability; the need for better algorithms; system maturity; patient safety) were defined.nnnCONCLUSIONSnDespite ongoing development, CDSS remains an emerging technology. Lack of understanding about and lack of consideration for the interaction between human decision makers and CDSS is a major reason for poor system adoption and use. Further high-quality qualitative research is needed to better understand human-system interaction issues. These issues may continue to confound quantitative study results if not addressed.

Detection of infectious symptoms from VA emergency department and primary care clinical documentation

OBJECTIVEnThe majority of clinical symptoms are stored as free text in the clinical record, and this information can inform clinical decision support and automated surveillance efforts if it can be accurately processed into computer interpretable data.nnnMETHODSnWe developed rule-based algorithms and evaluated a natural language processing (NLP) system for infectious symptom detection using clinical narratives. Training (60) and testing (444) documents were randomly selected from VA emergency department, urgent care, and primary care records. Each document was processed with NLP and independently manually reviewed by two clinicians with adjudication by referee. Infectious symptom detection rules were developed in the training set using keywords and SNOMED-CT concepts, and subsequently evaluated using the testing set.nnnRESULTSnOverall symptom detection performance was measured with a precision of 0.91, a recall of 0.84, and an F measure of 0.87. Overall symptom detection with assertion performance was measured with a precision of 0.67, a recall of 0.62, and an F measure of 0.64. Among those instances in which the automated system matched the reference set determination for symptom, the system correctly detected 84.7% of positive assertions, 75.1% of negative assertions, and 0.7% of uncertain assertions.nnnCONCLUSIONnThis work demonstrates how processed text could enable detection of non-specific symptom clusters for use in automated surveillance activities.

A formal representation for messages containing compositional expressions

Clinically useful controlled vocabularies should represent healthcare concepts completely and with high reliability. Anticipating and pre-coordinating all possible expressions (e.g. fracture of the left femur and fracture of the right femur) is not feasible. Variation in practice styles, requirements for the granularity of content, the exponential growth of terminology size, and increased cost of maintaining pre-coordinated terminologies lead us to conclude that no enumerated terminology can ever be truly comprehensive. Compositional terminologies are one potential solution to the problem of content completeness, but carry a risk of generating expressions whose equivalency cannot be easily determined. In order for post-coordinated expressions to be comparable, a sufficiently detailed formal mechanism for information representation is necessary. Comparable data for post-coordinated expressions requires normalization of both the contents and the semantics of the contents of the terminology with the information captured in post-coordinated expressions. In addition, comparable data requires a storage and messaging paradigm robust enough to faithfully represent the information contained within arbitrarily complex compositional expressions. We present a formalism for storing, and sending messages containing compositional expressions using a large-scale reference terminology. It is our intent that this formalism be used to algorithmically determine whether or not messages contain comparable data. In addition, we advocate transmitting the upward transitive closure of subsumption of all concepts, to improve comparability of data and to decrease reliance on locally stored versions of the underlying reference terminology.

Guideline for Health Informatics: Controlled Health Vocabularies - Vocabulary Structure and High-level Indicators

Developers and purchasers of controlled health terminologies require valid mechanisms for comparing terminological systems. By Controlled Health Vocabularies we refer to terminologies and terminological systems designed to represent clinical data at a granularity consistent with the practice of todays healthcare delivery. Comprehensive criterion for the evaluation of such systems are lacking and the known criteria are inconsistently applied. Although there are many papers, which describe specific desirable features of a controlled health vocabulary, to date there is not a consistent guide for evaluators of terminologies to reference, which will help them compare implementations of terminological systems on an equal footing 1,2 This guideline serves to fill the gap between academic enumeration of desirable terminological characteristics and the practical implementation or rigorous evaluations which will yield comparable data regarding the quality of one or more controlled health vocabularies.