Who Is Your Doctor? Analysis of Patient-Reported and EHR-Imputed Primary Care Physician.

Significant efforts have been made to improve physician-to-physician communication and care coordination during transition of care in order to reduce adverse events and readmissions. As electronic health records (EHRs) become widely available, many hospitals have implemented physician collaboration and hand-off tools to automatically send admission notifications, discharge summaries, and pending laboratory results to a patient's primary care physician (PCP). However, the effectiveness of such tools depends on a fundamental question that remains unstudied: who is the patient's PCP? Missing or outdated PCP information may become the bottleneck to effective patient-centered care coordination regardless of existing efforts on promoting interoperability among healthcare providers. In this paper, we characterized patient-reported PCPs and experimented with an imputation algorithm that automatically infers a patient's primary provider based on patient-provider encounter data. We compared the imputation results with patient-reported PCPs and suggested practical uses of our findings.

Characterizing the Structure of a Patient's Care Team through Electronic Encounter Data Analysis.

As the field of medicine grows more complicated and doctors become more specialized in a particular field, the number of healthcare providers involved in healing an individual patient increases. This is particularly true of patients with multiple chronic conditions. Establishing effective communications among the care providers becomes critical to facilitate care coordination and more efficient resource use, which will ultimately result in health outcome improvement. The first step for care coordination is to understand who have been involved in a patient's care and their relationships with the patient. The widespread adoption of Electronic Health Records provides us an opportunity to explore solutions to well-coordinated care. This paper presents the concept of a patient's care team and demonstrates the feasibility of identifying relevant healthcare providers for an individual patient by leveraging electronic patient encounter data. Combined with network analysis techniques, we further visualize the care team structure with quantified strength of patient-provider relationships. Our work is foundational to the larger goal of patient-centered, coordinated care in the digital age of healthcare.

Improving Clinical Data Integrity by using Data Adjudication Techniques for Data Received through a Health Information Exchange (HIE).

Growing participation in Healthcare Information Exchange (HIE) has created opportunities for the seamless integration of external data into an organization's own EHR and clinical workflows. The process of integrating external data has the potential to detect data integrity issues. Lack of critiquing external data before its incorporation can lead to data unfit for use in the clinical setting. HIE data adjudication, by detecting inconsistencies, physiological and temporal incompatibilities, data completeness and timeliness issues in HIE data, facilitates corrective actions and improves clinical data integrity.

Patient-level analysis of outcomes using structured labor and delivery data.

This paper presents methods for identifying and analyzing associations among nursing care processes, patient attributes, and patient outcomes using unit-level and patient-level representations of care derived from computerized nurse documentation. The retrospective, descriptive analysis included documented nursing events for 900 Labor and Delivery patients at three hospitals over the 2-month period of January and February 2006. Two models were used to produce quantified measurements of nursing care received by each patient. The first model considered only the hourly census of nurses and patients. The second model considered the size of nurses' patient loads as represented by computerized nurse-entered documentation. Significant relationships were identified between durations of labor and nursing care scores generated by the second model. In addition to the clinical associations identified, the study demonstrated an approach with global application for representing the amount of nursing care received at the individual patient level in analyses of patient outcomes.

Physician use of outpatient electronic health records to improve care.

We applied a model of usage categories of electronic health records for outpatient physicians to a large population of physicians, using an established electronic health record. This model categorizes physician users according to how extensively they adopt the various capabilities of electronic health records. We identified representative indicators from usage statistics for outpatient physician use of the HELP-2 outpatient electronic medical record, in use at Intermountain Healthcare. Using these indicators, we calculated the relative proportion of users in each category. These proportions are useful for predicting the expected benefits of electronic health record adoption.

Generating nurse profiles from computerized labor and delivery documentation.

This paper presents methods for generating nurse profiles using computerized documentation. NuProGen (Nurse Profile Generator), a custom-built knowledge discovery tool, enabled profile generation by calculating the numbers of various complicated patient cases (including high body mass index, bleeding, and multiple gestation) managed by each of 91 Labor and Delivery nurses at a single Intermountain Healthcare facility during the 3-month study period of January through March 2007. The tool identified patterns of documentation recorded by each nurse, as well as nursing care patterns associated with each of the three patient conditions examined in the study. Individual nurse profiles supported identification of expert and novice nurses corresponding to the management of specific conditions. A discussion of the benefits provided by available nurse profile data is also presented.

Modeling the distribution of Nursing Effort using structured Labor and Delivery documentation.

Our study objectives included the development and evaluation of models for representing the distribution of shared unit-wide nursing care resources among individual Labor and Delivery patients using quantified measurements of nursing care, referred to as Nursing Effort. The models were intended to enable discrimination between the amounts of care delivered to patient subsets defined by attributes such as patient acuity. For each of five proposed models, scores were generated using an analysis set of 686,402 computerized nurse-documented events associated with 1093 patients at three hospitals during January and February 2006. Significant differences were detected in Nursing Effort scores according to patient acuity, care facility, and in scores generated during shift change versus non-shift change hours. The development of nursing care quantification strategies proposed in this study supports outcomes analysis by establishing a foundation for measuring the effect of patient-level nursing care on individual patient outcomes.

Neonatal bilirubin management as an implementation example of interdisciplinary continuum of care tools.

Management of newborn bilirubin spans the inpatient and outpatient continuum of care. Intermountain Healthcare has developed and implemented a web-based tool for managing bilirubin that follows newborn patients across care settings and providers with a consistent plan of care. The underlying model for the tool is derived from published guidelines. The model divides the time-sensitive data into risk zones and associates each zone with the appropriate order set for follow-up care. The tool integrates Intermountain's Help2 infrastructure for authoring terms, guidelines, and order sets, with alerts, results, and data entry within the context of the care model. Implementation of the bilirubin management tool is shown to improve communication, ease workflow, and improve guideline compliance. Lessons learned from the implementation include recommendations for handling point-of-care laboratory data and managing archival views, which are insightful to health networks managing longitudinal data.

Feasibility of linking external valuation sources to bedside-caregiver activities in interdisciplinary patient care standards.

Establishing accurate and standardized values for bedside-care activities is crucial to the development of resource utilization prediction and management systems. We describe our experience of associating a representative sample of activities extracted from interdisciplinary patient care standards developed at Intermountain Healthcare with an external database of time & motion valued actions. The association exercise revealed important considerations for the development of a standard methodology for linking activities to future national or international standardized value units.

Extracting nursing practice patterns from structured labor and delivery data sets.

This study was designed to demonstrate the feasibility of a computerized care process model that provides real-time case profiling and outcome forecasting. A methodology was defined for extracting nursing practice patterns from structured point-of-care data collected using the labor and delivery information system at Intermountain Healthcare. Data collected during January 2006 were retrieved from Intermountain Healthcare's enterprise data warehouse for use in the study. The knowledge discovery in databases process provided a framework for data analysis including data selection, preprocessing, data-mining, and evaluation. Development of an interactive data-mining tool and construction of a data model for stratification of patient records into profiles supported the goals of the study. Five benefits of the practice pattern extraction capability, which extend to other clinical domains, are listed with supporting examples.

Architectural strategies and issues with health information exchange.

We present a model for architectural strategies and issues regarding health information exchange (HIE). This model is a continuum of options, between separated systems and a monolithic approach. We discuss characteristics, examples and potential impacts of each approach, based on generalized observations of practical implementations. The continuum model allows for approaches that mature from an initial implementation to a long-term strategy.

Physician use of electronic medical records: issues and successes with direct data entry and physician productivity.

At Intermountain Health Care, we evaluated whether physicians in an ambulatory setting will voluntarily choose to enter data directly into an electronic health record (EHR). In this paper we describe the benefits of an EHR, as they exist in the current IHC application and the ways in which we have sought to minimize obstacles to physician data entry. Currently, of 472 IHC employed physicians, 321 (68%) routinely enter some data directly into the EHR without coercion. Twenty-five percent (80/321) of the physicians use voice recognition for some data entry. Twelve of our 95 ambulatory clinics have voluntarily adopted measures to eliminate paper charts. Of the 212 physicians who entered data in 2004, sixty-nine physicians (22%) increased their level of data entry, while 12 (6%) decreased. We conclude that physicians will voluntarily adopt an EHR system, and will continue and even increase use after implementation barriers are addressed.

Use and impact of a computer-generated patient summary worksheet for primary care.

Advanced clinical information systems have been proposed to improve patient care in terms of safety, effectiveness, and efficiency. In order to be effective, such systems require detailed patient-specific clinical information in a form easily reviewed by clinicians. We have developed a patient summary worksheet for use in outpatient clinics, which presents a structured overview of patient health information. The worksheet provides patient demographic information, specific problems and conditions, the patient's current medication profile, laboratory test results pertinent to patient problems, and disease-specific or preventive care actionable advisories. Usage has grown from a few hundred to over 25,000 unique patients per month during a two-year period. Diabetic patients for whom the worksheet is accessed are significantly more likely to be in compliance with accepted testing regimens for glycosolated hemoglobin (OR 1.47, 95% CI 1.28, 1.61).

Aiding clinicians through summarization of perinatal data.

Exploratory analysis has focused on developing summarized views of monitor-captured perinatal data to support adherence to established clinical protocols. In addition to facilitating rapid access to significant clinical trends and reducing subjective interpretation of monitor-captured data, combining data summaries with traditional monitor review may assist in the anticipation of complications.

Reducing duplicate patient creation using a probabilistic matching algorithm in an open-access community data sharing environment.

In an open-access community data sharing environment, Intermountain Health Care (IHC) is managing the creation of duplicate patient records through a probabilistic matching algorithm that allows the threshold limits for the returned set to be dynamically assigned to the source system. For internal hospital systems, the rate of duplicate creation was cut 30% in the first 6 months. For IHC's first community data sharing partner, the rate of duplicate creation has been maintained below the acceptable range for the internal Health Plans rate.

Integration challenges of clinical information systems developed without a shared data dictionary.

Legacy systems have proven to be long-term integration challenges for Intermountain Health Care (IHC) despite commitment and attention to share clinical information across settings and among clinicians. This study measures the extent of the disparity of data elements across three independent data systems in current use. A sample of relevant data elements was selected across systems covering prenatal, labor and delivery, and newborn intensive care units (NICU). The findings revealed only 17% of these sample data elements had compatible structure across all three systems. The implications from differences in granularity, missing data, and duplicate data entry, include diminished data quality, greater risk for medical error, increased costs of integration and inefficient use of clinician time. Retrospective guidelines for managing conceptual context and granularity are given to assist in designing an integrated longitudinal patient electronic medical record.

Using point of service clinical documentation to reduce variability in charge capture.

Data collected at bedside to document patient care can also be used to generate an itemized summary of charges including activity-based clinician charges. This approach becomes advantageous when the charge capture operation is transparent to the clinician who would otherwise have to review the care documentation, recall the appropriate charging rules, and exercise discretion in capturing charges. Documented procedures and supplies convert directly into patient charge rules. Documented patient care is more difficult to translate into activity-based charges because nursing care can vary in intensity and duration depending on the patient's needs. The problem can be overcome by embedding time or data-driven logic into the charging rules. Using this approach in the labor and delivery units of 7 IHC hospitals (114 beds), we generated consistent charge summaries. We improved the accuracy of patient charges from 65% to over 98% of our charge summaries having no missed charges.