Search

Background: Identifying implausible clinical observations (e.g., laboratory test and vital sign values) in Electronic Health Record (EHR) data using rule-based procedures is challenging. Anomaly/outlier detection methods can be applied as an alternative algorithmic approach to flagging such implausible values in EHRs., Methods: The primary objectives of this research were to develop and test an unsupervised clustering-based anomaly/outlier detection approach for detecting implausible observations in EHR data as an alternative algorithmic solution to the existing procedures. Our approach is built upon two underlying hypotheses that, (i) when there are large number of observations, implausible records should be sparse, and therefore (ii) if these data are clustered properly, clusters with sparse populations should represent implausible observations. To test these hypotheses, we applied an unsupervised clustering algorithm to EHR observation data on 50 laboratory tests from Partners HealthCare. We tested different specifications of the clustering approach and computed confusion matrix indices against a set of silver-standard plausibility thresholds. We compared the results from the proposed approach with conventional anomaly detection (CAD) approaches, including standard deviation and Mahalanobis distance., Results: We found that the clustering approach produced results with exceptional specificity and high sensitivity. Compared with the conventional anomaly detection approaches, our proposed clustering approach resulted in significantly smaller number of false positive cases., Conclusion: Our contributions include (i) a clustering approach for identifying implausible EHR observations, (ii) evidence that implausible observations are sparse in EHR laboratory test results, (iii) a parallel implementation of the clustering approach on i2b2 star schema, and (3) a set of silver-standard plausibility thresholds for 50 laboratory tests that can be used in other studies for validation. The proposed algorithmic solution can augment human decisions to improve data quality. Therefore, a workflow is needed to complement the algorithm's job and initiate necessary actions that need to be taken in order to improve the quality of data.

Background: Interoperable phenotyping algorithms, needed to identify patient cohorts meeting eligibility criteria for observational studies or clinical trials, require medical data in a consistent structured, coded format. Data heterogeneity limits such algorithms' applicability. Existing approaches are often: not widely interoperable; or, have low sensitivity due to reliance on the lowest common denominator (ICD-9 diagnoses). In the Scalable Collaborative Infrastructure for a Learning Healthcare System (SCILHS) we endeavor to use the widely-available Current Procedural Terminology (CPT) procedure codes with ICD-9. Unfortunately, CPT changes drastically year-to-year - codes are retired/replaced. Longitudinal analysis requires grouping retired and current codes. BioPortal provides a navigable CPT hierarchy, which we imported into the Informatics for Integrating Biology and the Bedside (i2b2) data warehouse and analytics platform. However, this hierarchy does not include retired codes., Methods: We compared BioPortal's 2014AA CPT hierarchy with Partners Healthcare's SCILHS datamart, comprising three-million patients' data over 15 years. 573 CPT codes were not present in 2014AA (6.5 million occurrences). No existing terminology provided hierarchical linkages for these missing codes, so we developed a method that automatically places missing codes in the most specific "grouper" category, using the numerical similarity of CPT codes. Two informaticians reviewed the results. We incorporated the final table into our i2b2 SCILHS/PCORnet ontology, deployed it at seven sites, and performed a gap analysis and an evaluation against several phenotyping algorithms., Results: The reviewers found the method placed the code correctly with 97 % precision when considering only miscategorizations ("correctness precision") and 52 % precision using a gold-standard of optimal placement ("optimality precision"). High correctness precision meant that codes were placed in a reasonable hierarchal position that a reviewer can quickly validate. Lower optimality precision meant that codes were not often placed in the optimal hierarchical subfolder. The seven sites encountered few occurrences of codes outside our ontology, 93 % of which comprised just four codes. Our hierarchical approach correctly grouped retired and non-retired codes in most cases and extended the temporal reach of several important phenotyping algorithms., Conclusions: We developed a simple, easily-validated, automated method to place retired CPT codes into the BioPortal CPT hierarchy. This complements existing hierarchical terminologies, which do not include retired codes. The approach's utility is confirmed by the high correctness precision and successful grouping of retired with non-retired codes.

Background: Capturing accurate and machine-interpretable primary data from clinical encounters is a challenging task, yet critical to the integrity of the practice of medicine. We explore the intriguing possibility that technology can help accurately capture structured data from the clinical encounter using a combination of automated speech recognition (ASR) systems and tools for extraction of clinical meaning from narrative medical text. Our goal is to produce a displayed evolving encounter note, visible and editable (using speech) during the encounter., Results: This is very ambitious, and so far we have taken only the most preliminary steps. We report a simple proof-of-concept system and the design of the more comprehensive one we are building, discussing both the engineering design and challenges encountered. Without a formal evaluation, we were encouraged by our initial results. The proof-of-concept, despite a few false positives, correctly recognized the proper category of single-and multi-word phrases in uncorrected ASR output. The more comprehensive system captures and transcribes speech and stores alternative phrase interpretations in an XML-based format used by a text-engineering framework. It does not yet use the framework to perform the language processing present in the proof-of-concept., Conclusion: The work here encouraged us that the goal is reachable, so we conclude with proposed next steps.Some challenging steps include acquiring a corpus of doctor-patient conversations, exploring a workable microphone setup, performing user interface research, and developing a multi-speaker version of our tools.