Frances P. Morrison

An Electronic Health Record Based on Structured Narrative

OBJECTIVE To develop an electronic health record that facilitates rapid capture of detailed narrative observations from clinicians, with partial structuring of narrative information for integration and reuse. DESIGN We propose a design in which unstructured text and coded data are fused into a single model called structured narrative. Each major clinical event (e.g., encounter or procedure) is represented as a document that is marked up to identify gross structure (sections, fields, paragraphs, lists) as well as fine structure within sentences (concepts, modifiers, relationships). Marked up items are associated with standardized codes that enable linkage to other events, as well as efficient reuse of information, which can speed up data entry by clinicians. Natural language processing is used to identify fine structure, which can reduce the need for form-based entry. VALIDATION The model is validated through an example of use by a clinician, with discussion of relevant aspects of the user interface, data structures and processing rules. DISCUSSION The proposed model represents all patient information as documents with standardized gross structure (templates). Clinicians enter their data as free text, which is coded by natural language processing in real time making it immediately usable for other computation, such as alerts or critiques. In addition, the narrative data annotates and augments structured data with temporal relations, severity and degree modifiers, causal connections, clinical explanations and rationale. CONCLUSION Structured narrative has potential to facilitate capture of data directly from clinicians by allowing freedom of expression, giving immediate feedback, supporting reuse of clinical information and structuring data for subsequent processing, such as quality assurance and clinical research.

Syndromic Surveillance Using Ambulatory Electronic Health Records

OBJECTIVE To assess the performance of electronic health record data for syndromic surveillance and to assess the feasibility of broadly distributed surveillance. DESIGN Two systems were developed to identify influenza-like illness and gastrointestinal infectious disease in ambulatory electronic health record data from a network of community health centers. The first system used queries on structured data and was designed for this specific electronic health record. The second used natural language processing of narrative data, but its queries were developed independently from this health record. Both were compared to influenza isolates and to a verified emergency department chief complaint surveillance system. MEASUREMENTS Lagged cross-correlation and graphs of the three time series. RESULTS For influenza-like illness, both the structured and narrative data correlated well with the influenza isolates and with the emergency department data, achieving cross-correlations of 0.89 (structured) and 0.84 (narrative) for isolates and 0.93 and 0.89 for emergency department data, and having similar peaks during influenza season. For gastrointestinal infectious disease, the structured data correlated fairly well with the emergency department data (0.81) with a similar peak, but the narrative data correlated less well (0.47). CONCLUSIONS It is feasible to use electronic health records for syndromic surveillance. The structured data performed best but required knowledge engineering to match the health record data to the queries. The narrative data illustrated the potential performance of a broadly disseminated system and achieved mixed results.

Preliminary Development of the Physician Documentation Quality Instrument

OBJECTIVES This study sought to design and validate a reliable instrument to assess the quality of physician documentation. DESIGN Adjectives describing clinician attitudes about high-quality clinical documentation were gathered through literature review, assessed by clinical experts, and transformed into a semantic differential scale. Using the scale, physicians and nurse practitioners scored the importance of the adjectives for describing quality in three note types: admission, progress, and discharge notes. Psychometric methods including exploratory factor analysis were applied to provide preliminary evidence for the construct validity and internal consistency reliability. RESULTS A 22-item Physician Documentation Quality Instrument (PDQI) was developed. Exploratory factor analysis (n = 67 clinician respondents) on three note types resulted in solutions ranging from four (discharge) to six (admission and progress) factors, and explained 65.8% (discharge) to 73% (admission and progress) of the variance. Each factor solution was unique. However, four sets of items consistently factored together across all note types: (1) up-to-date and current; (2) brief, concise, succinct; (3) organized and structured; and (4) correct, comprehensible, consistent. Internal consistency reliabilities were: admission note (factor scales = 0.52-88, overall = 0.86), progress note (factor scales = 0.59-0.84, overall = 0.87), and discharge summary (factor scales = 0.76-0.85, overall = 0.88). CONCLUSION The exploratory factor analyses and reliability analyses provide preliminary evidence for the construct validity and internal consistency reliability of the PDQI. Two novel dimensions of the construct for document quality were developed related to form (Well-formed, Compact). Additional work is needed to assess intrarater and interrater reliability of applying of the proposed instrument and to examine the reproducibility of the factors in other samples.

Using electronic health record alerts to provide public health situational awareness to clinicians.

Alerting providers to public health situations requires timeliness and context-relevance, both lacking in current systems. Incorporating decision support tools into electronic health records may provide a way to deploy public health alerts to clinicians at the point of care. A timely process for responding to Health Alert Network messages sent by the New York City Department of Health and Mental Hygiene was developed by a network of community health centers. Alerts with order sets and recommended actions were created to notify primary care providers of local disease outbreaks. The process, effect, and lessons learned from alerts for Legionella, toxogenic E coli, and measles outbreaks are described. Electronic alerts have the potential to improve management of diseases during an outbreak, including appropriate laboratory testing, management guidance, and diagnostic assistance as well as to enhance bi-directional data exchange between clinical and public health organizations.

Repurposing the Clinical Record: Can an Existing Natural Language Processing System De-identify Clinical Notes?

Electronic clinical documentation can be useful for activities such as public health surveillance, quality improvement, and research, but existing methods of de-identification may not provide sufficient protection of patient data. The general-purpose natural language processor MedLEE retains medical concepts while excluding the remaining text so, in addition to processing text into structured data, it may be able provide a secondary benefit of de-identification. Without modifying the system, the authors tested the ability of MedLEE to remove protected health information (PHI) by comparing 100 outpatient clinical notes with the corresponding XML-tagged output. Of 809 instances of PHI, 26 (3.2%) were detected in output as a result of processing and identification errors. However, PHI in the output was highly transformed, much appearing as normalized terms for medical concepts, potentially making re-identification more difficult. The MedLEE processor may be a good enhancement to other de-identification systems, both removing PHI and providing coded data from clinical text.

Impact of integrating public health clinical decision support alerts into electronic health records on testing for gastrointestinal illness.

Laboratory testing by clinicians is essential to outbreak investigations. Electronic health records may increase testing through clinical decision support that alerts providers about existing outbreaks and facilitates laboratory ordering. The impact on laboratory testing was evaluated for foodborne disease outbreaks between 2006 and 2009. After controlling for standard public health messaging and season, decision support resulted in a significant increase in laboratory testing and may be useful in enhancing public health messaging and provider action.