PubMed Health⌕ Search

Biomedical subjects

G Hripcsak

Publications and source records attributed to G Hripcsak.

53 records · Page 3Linked to original sources
PubMed1993

Monitoring the monitor: automated statistical tracking of a clinical event monitor.

At Columbia-Presbyterian Medical Center, a clinical event monitor processes a set of rules called Medical Logic Modules (MLMs), which generate messages (interpretations, warnings, suggestions) for health care providers. The automated statistical tracker (AST) monitors the operation of the clinical event monitor for the purpose of detecting malfunctions in MLMs or in the clinical event monitor itself. The AST follows the number of messages generated by each MLM each day and issues an alert to a system administrator if the current count of messages seems unusual compared to the MLM's past activity. The AST is based upon a combination of Poisson and normal distributions. The AST was implemented using Unix shell scripts and put into operation. Of two malfunctions that occurred during a prospective study of 12 MLMs over 85 days, the AST automatically detected one that might otherwise have gone undetected, and the system administrator detected the other during routine review of the AST's daily report. The AST's performance was compared to that of five human subjects, and it was found to rank third among the six total subjects. The AST generated eight false-positive alerts during the study period (false-positive rate = 0.009 alerts/MLM day); seven of these were also picked by the human subjects. Subsequent experience has proven the AST to be useful and efficient for a system with 20 to 60 MLMs.

Algorithms↗
PubMed1993

The Arden syntax for medical logic modules.

The Arden Syntax for sharing medical knowledge bases is described. Its current focus is on knowledge that is represented as a set of independent modules that can provide therapeutic suggestions, alerts, diagnosis scores, etc. The syntax is based largely upon HELP and the Regenstrief Medical Record System. Each module, called a Medical Logic Module or MLM, is made of slots grouped into maintenance, library, and knowledge categories. The syntax has provisions for querying a clinical database and representing time. Several clinical information systems were analyzed and appear to be compatible with the syntax. The syntax has been tested for syntactic ambiguities using the tools lex and yacc. Seventeen institutions are currently in the process of adopting the Arden Syntax for their decision-support systems. A subcommittee of ASTM has been formed to develop standards for sharing medical knowledge bases. The Arden Syntax has been published by ASTM as a initial standard for sharing medical knowledge.

Artificial Intelligence↗
PubMed1993

ASTM E31.15 on health knowledge representation: the Arden Syntax.

ASTM subcommittee E31.15 on Health Knowledge Representation was formed to promote standards for defining and sharing health knowledge bases. Its first standard, the Ardan Syntax, is focused on knowledge bases that can be represented as a set of independent modules called Medical Logic Modules (MLMs). The standard is in clinical use and has generated significant interest in industry and academics. The Extensions task group plans to extend the syntax where appropriate, to expand to other types of knowledge bases. The Validation/Verification task group is approaching the enormous problem of evaluating knowledge bases and the process of sharing them.

Artificial Intelligence↗
PubMed1993

Sharing MLM's: an experiment between Columbia-Presbyterian and LDS Hospital.

The use of Arden syntax for development of shareable medical logic modules (MLM's) has developed as an ASTM standard. To test the feasibility of sharing MLM's between institutions a study was conducted between Columbia-Presbyterian Medical Center and LDS Hospital. In this study seven MLM's clinically executing at Columbia-Presbyterian were used to test the sharing potential of the Arden syntax. The study was limited to measuring the modifications necessary to make executable at LDS Hospital the shared MLM's. Because of the site specific nature of the data variables, multiple modifications were required. Three classes of modifications were necessary. The simplest involved only data variable mappings. The other classes required either minor modifications to the logic or relatively major modifications. Over 50% of the modifications were in the minor or major classes. While the sharing of decision logic was possible and facilitated by the use of the MLM's at the two sites, the absence of standard medical vocabularies limited the utility of the MLM as a mechanism for directly sharing medical knowledge.

Hospital Information Systems↗
PubMed1993

Desperately seeking data: knowledge base-database links.

Linking a knowledge-based system (KBS) to a clinical database is a difficult task, but critical if such systems are to achieve widespread use. The Columbia-Presbyterian Medical Center's clinical event monitor provides alerts, interpretations, research screening, and quality assurance functions for the center. Its knowledge base consists of Arden Syntax Medical Logic Modules (MLMs). The knowledge base was analyzed in order to quantify the use and impact of KBS-database links. The MLM data slot, which contains the definition of these links, had almost as many statements (5.8 vs. 8.8, ns with p = 0.15) and more tokens (122 vs. 76, p = 0.037) than the logic slot, which contains the actual medical knowledge. The data slot underwent about twice as many modifications over time as the logic slot (3.0 vs. 1.6 modifications/version, p = 0.010). Database queries and updates accounted for 97.2% of the MLM's total elapsed execution time. Thus, KBS-database links consume substantial resources in an MLM knowledge base, in terms of coding, maintenance, and performance.

Academic Medical Centers↗
PubMed1993

Evaluating consensus among physicians in medical knowledge base construction.

This study evaluates inter-author variability in knowledge base construction. Seven board-certified internists independently profiled "acute perinephric abscess", using as reference material a set of 109 peer-reviewed articles. Each participant created a list of findings associated with the disease, estimated the predictive value and sensitivity of each finding, and assessed the pertinence of each article for making each judgment. Agreement in finding selection was significantly different from chance: seven, six, and five participants selected the same finding 78.6, 9.8, and 1.6 times more often than predicted by chance. Findings with the highest sensitivity were most likely to be included by all participants. The selection of supporting evidence from the medical literature was significantly related to each physician's agreement with the majority. The study shows that, with appropriate guidance, physicians can reproducibly extract information from the medical literature, and thus established a foundation for multi-author knowledge base construction.

Abscess↗
PubMed1991

The Columbia-Presbyterian Medical Center decision-support system as a model for implementing the Arden Syntax.

Columbia-Presbyterian Medical Center is implementing a decision-support system based on the Arden Syntax for Medical Logic Modules (MLM's). The system uses a compiler-interpreter pair. MLM's are first compiled into pseudo-codes, which are instructions for a virtual machine. The MLM's are then executed using an interpreter that emulates the virtual machine. This design has resulted in increased portability, easier debugging and verification, and more compact compiled MLM's. The time spent interpreting the MLM pseudo-codes has been found to be insignificant compared to database accesses. The compiler, which is written using the tools "lex" and "yacc," optimizes MLM's by minimizing the number of database accesses. The interpreter emulates a stack-oriented machine. A phased implementation of the syntax was used to speed the development of the system.

Artificial Intelligence↗
PubMed1991

Conceptual data model for a central patient database.

This paper presents methods used to develop a conceptual model for a patient database forming the centerpiece of a clinical information system under development. Various modeling techniques are discussed using a simplified fragment of the model. A method for mapping the model onto a relational design optimized for single patient retrievals is described. The results section discusses a number of issues pertaining to the flexibility and usability of this architecture.

Databases, Factual↗
PubMed1990

Using connectionist modules for decision support.

A connectionist model for decision support was constructed out of several back-propagation modules. Manifestations serve as input to the model; they may be real-valued, and the confidence in their measurement may be specified. The model produces as its output the posterior probability of disease. The model was trained on 1,000 cases taken from a simulated underlying population with three conditionally independent manifestations. The first manifestation had a linear relationship between value and posterior probability of disease, the second had a stepped relationship, and the third was normally distributed. An independent test set of 30,000 cases showed that the model was better able to estimate the posterior probability of disease (the standard deviation of residuals was 0.046, with a 95% confidence interval of 0.046-0.047) than a model constructed using logistic regression (with a standard deviation of residuals of 0.062, with a 95% confidence interval of 0.062-0.063). The model fitted the normal and stepped manifestations better than the linear one. It accommodated intermediate levels of confidence well.

Computer Communication Networks↗
PubMedDate not supplied

Knowledge-based approaches to the maintenance of a large controlled medical terminology.

OBJECTIVE: Develop a knowledge-based representation for a controlled terminology of clinical information to facilitate creation, maintenance, and use of the terminology. DESIGN: The Medical Entities Dictionary (MED) is a semantic network, based on the Unified Medical Language System (UMLS), with a directed acyclic graph to represent multiple hierarchies. Terms from four hospital systems (laboratory, electrocardiography, medical records coding, and pharmacy) were added as nodes in the network. Additional knowledge about terms, added as semantic links, was used to assist in integration, harmonization, and automated classification of disparate terminologies. RESULTS: The MED contains 32,767 terms and is in active clinical use. Automated classification was successfully applied to terms for laboratory specimens, laboratory tests, and medications. One benefit of the approach has been the automated inclusion of medications into multiple pharmacologic and allergenic classes that were not present in the pharmacy system. Another benefit has been the reduction of maintenance efforts by 90%. CONCLUSION: The MED is a hybrid of terminology and knowledge. It provides domain coverage, synonymy, consistency of views, explicit relationships, and multiple classification while preventing redundancy, ambiguity (homonymy) and misclassification.

Computer Simulation↗
PubMedDate not supplied

Access to data: comparing AccessMed with Query by Review.

OBJECTIVE: To evaluate the performance of tools for authoring patient database queries. DESIGN: Query by Review, a tool that exploits the training that users have undergone to master a result review system, was compared with AccessMed, a vocabulary browser that supports lexical matching and the traversal of hierarchical and semantic links. Seven subjects (Medical Logic Module authors) were asked to use both tools to gather the vocabulary terms necessary to perform each of eight laboratory queries. MEASUREMENTS: The proportion of queries that were correct; intersubject agreement. RESULTS: Query by Review had better performance than AccessMed (38% correct queries versus 18%, p = 0.002), but both figures were low. Poor intersubject agreement (28% for Query by Review and 21% for AccessMed) corroborated the relatively low performance. Subjects appeared to have trouble distinguishing laboratory tests from laboratory batteries, picking terms relevant to the particular data type required, and using classes in the vocabulary's hierarchy. CONCLUSION: Query by Review, with its more constrained user interface, performed somewhat better than AccessMed, a more general tool. Neither tool achieved adequate performance, however, which points to the difficulty of formulating a query for a clinical database and the need for further work.

Artificial Intelligence↗
PubMedDate not supplied

Automated tuberculosis detection.

OBJECTIVE: To measure the accuracy of automated tuberculosis case detection. SETTING: An inner-city medical center. INTERVENTION: An electronic medical record and a clinical event monitor with a natural language processor were used to detect tuberculosis cases according to Centers for Disease Control criteria. MEASUREMENT: Cases identified by the automated system were compared to the local health department's tuberculosis registry, and positive predictive value and sensitivity were calculated. RESULTS: The best automated rule was based on tuberculosis cultures; it had a sensitivity of .89 (95% CI.75-.96) and a positive predictive value of .96 (.89-.99). All other rules had a positive predictive value less than .20. A rule based on chest radiographs had a sensitivity of .41 (.26-.57) and a positive predictive value of .03 (.02-.05), and rule the represented the overall Centers for Disease Control criteria had a sensitivity of .91 (.78-.97) and a positive predictive value of .15 (.12-.18). The culture-based rule was the most useful rule for automated case reporting to the health department, and the chest radiograph-based rule was the most useful rule for improving tuberculosis respiratory isolation compliance. CONCLUSIONS: Automated tuberculosis case detection is feasible and useful, although the predictive value of most of the clinical rules was low. The usefulness of an individual rule depends on the context in which it is used. The major challenge facing automated detection is the availability and accuracy of electronic clinical data.

Diagnosis, Computer-Assisted↗
PubMedDate not supplied

Representing information in patient reports using natural language processing and the extensible markup language.

OBJECTIVE: To design a document model that provides reliable and efficient access to clinical information in patient reports for a broad range of clinical applications, and to implement an automated method using natural language processing that maps textual reports to a form consistent with the model. METHODS: A document model that encodes structured clinical information in patient reports while retaining the original contents was designed using the extensible markup language (XML), and a document type definition (DTD) was created. An existing natural language processor (NLP) was modified to generate output consistent with the model. Two hundred reports were processed using the modified NLP system, and the XML output that was generated was validated using an XML validating parser. RESULTS: The modified NLP system successfully processed all 200 reports. The output of one report was invalid, and 199 reports were valid XML forms consistent with the DTD. CONCLUSIONS: Natural language processing can be used to automatically create an enriched document that contains a structured component whose elements are linked to portions of the original textual report. This integrated document model provides a representation where documents containing specific information can be accurately and efficiently retrieved by querying the structured components. If manual review of the documents is desired, the salient information in the original reports can also be identified and highlighted. Using an XML model of tagging provides an additional benefit in that software tools that manipulate XML documents are readily available.

Humans↗
PubMedDate not supplied

A reliability study for evaluating information extraction from radiology reports.

GOAL: To assess the reliability of a reference standard for an information extraction task. SETTING: Twenty-four physician raters from two sites and two specialties judged whether clinical conditions were present based on reading chest radiograph reports. METHODS: Variance components, generalizability (reliability) coefficients, and the number of expert raters needed to generate a reliable reference standard were estimated. RESULTS: Per-rater reliability averaged across conditions was 0.80 (95% CI, 0.79-0.81). Reliability for the nine individual conditions varied from 0.67 to 0.97, with central line presence and pneumothorax the most reliable, and pleural effusion (excluding CHF) and pneumonia the least reliable. One to two raters were needed to achieve a reliability of 0.70, and six raters, on average, were required to achieve a reliability of 0.95. This was far more reliable than a previously published per-rater reliability of 0.19 for a more complex task. Differences between sites were attributable to changes to the condition definitions. CONCLUSION: In these evaluations, physician raters were able to judge very reliably the presence of clinical conditions based on text reports. Once the reliability of a specific rater is confirmed, it would be possible for that rater to create a reference standard reliable enough to assess aggregate measures on a system. Six raters would be needed to create a reference standard sufficient to assess a system on a case-by-case basis. These results should help evaluators design future information extraction studies for natural language processors and other knowledge-based systems.

Evaluation Studies as Topic↗
PubMedDate not supplied

IAIMS architecture.

An information system architecture defines the components of a system and the interfaces among the components. A good architecture is essential for creating an Integrated Advanced Information Management System (IAIMS) that works as an integrated whole yet is flexible enough to accommodate many users and roles, multiple applications, changing vendors, evolving user needs, and advancing technology. Modularity and layering promote flexibility by reducing the complexity of a system and by restricting the ways in which components may interact. Enterprise-wide mediation promotes integration by providing message routing, support for standards, dictionary-based code translation, a centralized conceptual data schema, business rule implementation, and consistent access to databases. Several IAIMS sites have adopted a client-server architecture, and some have adopted a three-tiered approach, separating user interface functions, application logic, and repositories.

Computer Systems↗