Search

Intermountain Healthcare has designed and implemented a publish-subscribe (PubSub) infrastructure to support essential event processing workflows across our organization. A recent implementation of a commercial EMR highlighted the need to provide this capability on top of the EMR to support external applications and services that require access to triggering events within the EMR. A description of the PubSub architecture is presented. Use cases for health information exchange, public health reporting, and pulmonary embolism diagnosis that utilize PubSub are described, along with benefits of using the paradigm. Besides providing support for these external applications, the PubSub infrastructure allows additional event handling functionality not available in the commercial EMR. The open, standards-based nature of the design should allow other organizations to implement the system in their information systems environment.

During the last decade, software supporting healthcare delivery has proliferated. This software can be divided into electronic medical record (EHR) systems and applications that treat EHRs as platforms. These collect, manage, and interpret medical data, thereby adding value to associated EHRs. To reduce the burden of developing for multiple EHR platforms, a group of standards has evolved that allow software written for one vendor's EHR to be introduced into settings supported by other vendors. The Health Services Platform Consortium (HSPC) is a collaborative effort to advocate for standards that will make healthcare applications truly interoperable. In this document, we discuss the approach adopted by the consortium and the standards central to this approach. We discriminate between interoperability standards that support the plug-and-play transfer of applications from one vendor's EHR to another and knowledge portability standards that allow knowledge artifacts used in one software environment to be introduced effectively in others.

Objective: Natural language processing (NLP) tasks are commonly decomposed into subtasks, chained together to form processing pipelines. The residual error produced in these subtasks propagates, adversely affecting the end objectives. Limited availability of annotated clinical data remains a barrier to reaching state-of-the-art operating characteristics using statistically based NLP tools in the clinical domain. Here we explore the unique linguistic constructions of clinical texts and demonstrate the loss in operating characteristics when out-of-the-box part-of-speech (POS) tagging tools are applied to the clinical domain. We test a domain adaptation approach integrating a novel lexical-generation probability rule used in a transformation-based learner to boost POS performance on clinical narratives., Methods: Two target corpora from independent healthcare institutions were constructed from high frequency clinical narratives. Four leading POS taggers with their out-of-the-box models trained from general English and biomedical abstracts were evaluated against these clinical corpora. A high performing domain adaptation method, Easy Adapt, was compared to our newly proposed method ClinAdapt., Results: The evaluated POS taggers drop in accuracy by 8.5-15% when tested on clinical narratives. The highest performing tagger reports an accuracy of 88.6%. Domain adaptation with Easy Adapt reports accuracies of 88.3-91.0% on clinical texts. ClinAdapt reports 93.2-93.9%., Conclusions: ClinAdapt successfully boosts POS tagging performance through domain adaptation requiring a modest amount of annotated clinical data. Improving the performance of critical NLP subtasks is expected to reduce pipeline error propagation leading to better overall results on complex processing tasks.

Family history (FH) is an important risk factor for many diseases and its assessment can be a powerful tool for identifying and stratifying patients at risk. As part of an initiative to improve FH collection and decision support at Intermountain Healthcare we conducted a literature review on FH data collection and reviewed a number of current Web-based tools. An ideal list of features was produced to help implement goals of the initiative.

In critically ill patients control of blood sugar levels with IV insulin has been shown to improve clinical outcomes in the intensive care units. We have developed an analytical framework with which to evaluate and compare IV insulin-treatment models and protocols. Performance of the analytical framework is demonstrated using protocols published by others and new protocols under development by our group.

Constantly changing diabetes care standards makes it challenging to deliver care adapted to the unique condition of the individual patient. The availability of large amounts of data from patient's electronic medical records makes it possible to individualize diabetes management. Initial design of a "patient-specific" hybrid system (physiological-causal probabilistic) of adaptive diabetes models and insulin treatment algorithms will be presented. The system is uniquely derived and tested using a diabetes data mart of about 33,000 patients.

When machine learning algorithms are applied to data collected during the course of clinical care, it is generally accepted that the data has not been consistently collected. The absence of expected data elements is common and the mechanism through which a data element is missing often involves the clinical relevance of that data element in a specific patient. Therefore, the absence of data may have information value of its own. In the process of designing an application intended to support a medical problem list, we have studied whether the "missingness" of clinical data can provide useful information in building prediction models. In this study, we experimented with four methods of treating missing values in a clinical data set-two of them explicitly model the absence or "missingness" of data. Each of these data sets were used to build four different kinds of Bayesian classifiers-a naive Bayes structure, a human-composed network structure, and two networks based on structural learning algorithms. We compared the performance between groups with and without explicit models of missingness using the area under the ROC curve. The results showed that in most cases the classifiers trained using the explicit missing value treatments performed better. The result suggests that information may exist in "missingness" itself. Thus, when designing a decision support system, we suggest one consider explicitly representing the presence/absence of data in the underlying logic.

PTXT Finder was developed to reduce the manual efforts necessary to map from clinical variables in a decision support system to data elements in an EHR. The descriptions in a data dictionary may be inadequate for pinpointing data elements that represent a clinical variable. Semantics implied in taxonomy and real usage of the element are two important supporting information sources. PTXT Finder provides description, hierarchy, and statistics displays so users can cross-reference among these views.

In the third stage of electronic medical record development, key features of EMR systems have converged, making them more difficult to differentiate from a cost/benefit standpoint. Fourth stage EMR systems are likely to introduce new, more effective decision support capabilities, offering a competitive advantage to hospitals that use them. Intermountain Health Care's HELP systems, which developed along different paths than other early EMR systems, offer unique decision-support capabilities that provide significant additional benefits. This paper quantifies and compare the benefits of Third Stage EMR systems, and the possible Fourth Stage capabilities of the HELP.

In this study, we evaluate the performance of a Natural Language Processing (NLP) application designed to extract medical problems from narrative text clinical documents. The documents come from a patient's electronic medical record and medical problems are proposed for inclusion in the patient's electronic problem list. This application has been developed to help maintain the problem list and make it more accurate, complete, and up-to-date. The NLP part of this system-analyzed in this study-uses the UMLS MetaMap Transfer (MMTx) application and a negation detection algorithm called NegEx to extract 80 different medical problems selected for their frequency of use in our institution. When using MMTx with its default data set, we measured a recall of 0.74 and a precision of 0.756. A custom data subset for MMTx was created, making it faster and significantly improving the recall to 0.896 with a non-significant reduction in precision.

Electronic health records are designed to provide online transactional data recording and reporting services that support the health care process. The characteristics of clinical data as it originates during the process of clinical documentation, including issues of data availability and complex representation models can make data mining applications challenging. Data preprocessing and transformation are required before one can apply data mining to clinical data. In this article, an approach to data preparation that utilizes information from the data, metadata and sources of medical knowledge is described. Heuristic rules and policies are defined for these three types of supporting information. Compared with an entirely manual process for data preparation, this approach can potentially reduce manual work by achieving a degree of automation in the rule creation and execution. A pilot experiment demonstrates that data sets created through this approach lead to a better model learning results than a fully manual process.

Background: The medical problem list is an important part of the electronic medical record in development in our institution. To serve the functions it is designed for, the problem list has to be as accurate and timely as possible. However, the current problem list is usually incomplete and inaccurate, and is often totally unused. To alleviate this issue, we are building an environment where the problem list can be easily and effectively maintained., Methods: For this project, 80 medical problems were selected for their frequency of use in our future clinical field of evaluation (cardiovascular). We have developed an Automated Problem List system composed of two main components: a background and a foreground application. The background application uses Natural Language Processing (NLP) to harvest potential problem list entries from the list of 80 targeted problems detected in the multiple free-text electronic documents available in our electronic medical record. These proposed medical problems drive the foreground application designed for management of the problem list. Within this application, the extracted problems are proposed to the physicians for addition to the official problem list., Results: The set of 80 targeted medical problems selected for this project covered about 5% of all possible diagnoses coded in ICD-9-CM in our study population (cardiovascular adult inpatients), but about 64% of all instances of these coded diagnoses. The system contains algorithms to detect first document sections, then sentences within these sections, and finally potential problems within the sentences. The initial evaluation of the section and sentence detection algorithms demonstrated a sensitivity and positive predictive value of 100% when detecting sections, and a sensitivity of 89% and a positive predictive value of 94% when detecting sentences., Conclusion: The global aim of our project is to automate the process of creating and maintaining a problem list for hospitalized patients and thereby help to guarantee the timeliness, accuracy and completeness of this information.

To help maintain a complete, accurate and timely Problem List, we are developing a system to automatically retrieve medical problems from free-text documents. This system uses Natural Language Processing to analyze all electronic narrative text documents in a patient's record. Here we evaluate and compare 3 different applications of NLP technology in our system: the first using MMTx (MetaMap Transfer) with a negation detection algorithm (NegEx), the second using an alpha version of a locally developed NLP application called MPLUS2, and the third using keyword searching. They were adapted and trained to extract medical problems from a set of 80 problems of diagnosis type. The version using MMTx and NegEx was improved by adding some disambiguation and modifying the negation detection algorithm, and these modifications significantly improved recall and precision. The different versions of the NLP module were compared, and showed the following recall / precision results: standard MMTx with NegEx version 0.775 / 0.398; improved MMTx with NegEx version 0.892 / 0.753; MPLUS2 version 0.693 / 0.402; and keyword searching version 0.575 / 0.807. Average results for the reviewers were a recall of 0.788 and a precision of 0.912.

Objective: Do-not-resuscitate (DNR) orders and advance directives are increasingly prevalent and may affect medical interventions and outcomes. Simple, automated techniques to identify patients with DNR orders do not currently exist but could help avoid costly and time-consuming chart review. This study hypothesized that a decision to withhold cardiopulmonary resuscitation would be included in a patient's dictated reports. The authors developed and validated a simple computerized search method, which screens dictated reports to detect patients with DNR status., Methods: A list of concepts related to DNR order documentation was developed using emergency department, hospital admission, consult, and hospital discharge reports of 665 consecutive, hospitalized pneumonia patients during a four-year period (1995-1999). The list was validated in an independent group of 190 consecutive inpatients with pneumonia during a five-month period (1999-2000). The reference standard for the presence of DNR orders was manual chart review of all study patients. Sensitivity, specificity, predictive values, and nonerror rates were calculated for individual and combined concepts., Results: The list of concepts included: DNR, Do Not Attempt to Resuscitate (DNAR), DNI, NCR, advanced directive, living will, power of attorney, Cardiopulmonary Resuscitation (CPR), defibrillation, arrest, resuscitate, code, and comfort care. As determined by manual chart review, a DNR order was written for 32.6% of patients in the derivation and for 31.6% in the validation group. Dictated reports included DNR order-related information for 74.5% of patients in the derivation and 73% in the validation group. If mentioned in the dictated report, the combined keyword search had a sensitivity of 74.2% in the derivation group (70.0% in the validation group), a specificity of 91.5% (81.5%), a positive predictive value of 80.9% (63.6%), a negative predictive value of 88.0% (85.5%), and a nonerror rate of 85.9% (77.9%). DNR and resuscitate were the most frequently used and power of attorney and advanced directives the least frequently used terms., Conclusion: Dictated hospital reports frequently contained DNR order-related information for patients with a written DNR order. Using an uncomplicated keyword search, electronic screening of dictated reports yielded good accuracy for identifying patients with DNR order information.

We are developing tools to help maintain a complete, accurate and timely problem list within a general purpose Electronic Medical Record system. As a part of this project, we have designed a system to automatically retrieve medical problems from free-text documents. Here we describe an information model based on XML (eXtensible Markup Language) and compliant with the CDA (Clinical Document Architecture). This model is used to ease the exchange of clinical data between the Natural Language Understanding application that retrieves potential problems from narrative document, and the problem list management application.

Objective: This study examined whether clinical data routinely available in a computerized patient record (CPR) can be used to drive a complex guideline that supports physicians in real time and at the point of care in assessing the risk of mortality for patients with community-acquired pneumonia., Setting: Emergency department of a tertiary-care hospital., Design: Retrospective analysis with medical chart review., Patients: All 241 inpatients during a 17-month period (Jun 1995 to Nov 1996) who presented to the emergency department and had a primary discharge diagnosis of community-acquired pneumonia. METHODS/MAIN OUTCOME MEASURES: The 20 guideline variables were extracted from the CPR (HELP System) and the paper chart. The risk score and the risk class of the Pneumonia Severity Index were computed using data from the CPR alone and from a reference standard of all data available in the paper chart and the CPR at the time of the emergency department encounters. Availability and concordance were quantified to determine data quality. The type and cause of errors were analyzed depending on the source and format of the clinical variables., Results: Of the 20 guideline variables, 12 variables were required to be present for every computer-charted emergency department patient, seven variables were required for selected patients only, and one variable was not typically available in the HELP System during a patient's encounter. The risk class was identical for 86.7 percent of the patients. The majority of patients with different risk classes were assigned too low a risk class. The risk scores were identical for 72.1 percent of the patients. The average availability was 0.99 for the data elements that were required to be present and 0.79 for the data elements that were not required to be present. The average concordance was 0.98 when all a patient's variables were taken into account. The cause of error was attributed to the nurse charting in 77 percent of the cases and to the computerized evaluation in 23 percent. The type of error originated from the free-text fields in 64 percent, from coded fields in 21 percent, from vital signs in 14 percent, and from laboratory results in 1 percent., Conclusion: From a clinical perspective, the current level of data quality in the HELP System supports the automation and the prospective evaluation of the Pneumonia Severity Index as a computerized decision support tool.

Free-text or natural language documents make up an increasing part of the computerized medical record. While they do provide accessible clinical information to health care personnel, they fail to support processes that require clinical data coded according to a shared lexicon and data structure. We have developed a natural language parser that converts free-text admitting diagnoses into a coded form. This application has proven acceptably accurate in the experimental laboratory to warrant a test in the target clinical environment. Here we describe an approach to moving this research application into a production environment where it can contribute to the efforts of the Health Information Services Department. This transition is essential if the products of natural language understanding research are to contribute to patient care in a routine and sustainable way.

Objective: To report lessons learned from evaluation of an automated interface between a hospital clinical information system and a severity of illness index., Design: A system was developed to convert coded electronic patient findings from the HELP System at LDS Hospital into the attributes used by the Computerized Severity Index (CSI) to calculate a severity of illness score. Performance was assessed by comparing the automated CSI score with the manual CSI score (from paper chart review) and by evaluating changes introduced by augmenting the manual CSI score with verified patient data discovered by the automated CSI method., Measurements: The strengths and weaknesses of each method are presented., Results: The automated CSI score matched the manual CSI score in 61% of the cases. Sources of errors were analyzed. When the automated score was in error, two-thirds of the time it was due to the lack of codes in the HELP system representing CSI concepts; one-third of the time it was due to nurses not using established HELP system codes. Surprisingly, significant problems were also discovered in the manual system, making it difficult to define a "gold standard"., Conclusions: Automated computerized severity indices have great potential for future applicability once their performance exceeds that of the time-consuming manual chart review method. Neither automated nor manual methods are adequate at the present time. This area remains a fertile ground for future research.

The value of the computerized medical record is derived in part from the availability of medical information in a coded form accessible to manipulation by processes designed for automated decision support, medical research, and computer assistance in the management of health care delivery. To meet these needs medical reports captured and stored as natural language documents must be encoded. Below we discuss an ongoing formative process aimed at developing a natural language understanding system for chest x-ray reports. Comparative data showing the progress of this process is presented.

Virtually there. Natural language or textual data in the patient record plays a critical role in medicine. Read about the innovative system LDS Hospital has implemented to integrate textual data into the computerized patient record.

The Computerized Severity Index (CSI) is a commercially available scoring system for hospital inpatients. Trained abstractors review the patient's paper medical record and enter the diagnoses and relevant physiological attributes. The HELP (Health Evaluation through Logical Processing) System at LDS Hospital stores patient data in discrete codes. This paper describes the development of an automatic interface between the standalone, personal-computer-based severity system and the mainframe-based hospital information system. The interface scores patient severity without the need for manual chart review. Severity scores from the automated and manual methods were identical for 70% of 222 general medical patients scored retrospectively. An evaluation of the causes for differing scores between the two methods is presented.