Search PubMed⌕ Search

Biomedical subjects

M A Musen

Publications and source records attributed to M A Musen.

At least 19 recordsLinked to original sources
PubMed1997

Sequential versus standard neural networks for pattern recognition: an example using the domain of coronary heart disease.

The goal of this study was to compare standard and sequential neural network models for recognition of patterns of disease progression. Medical researchers who perform prognostic modeling usually oversimplify the problem by choosing a single point in time to predict outcomes (e.g. death in 5 years). This approach not only fails to differentiate patterns of disease progression, but also wastes important information that is usually available in time-oriented research data bases. The adequate use of sequential neural networks can improve the performance of prognostic systems if the interdependencies among prognoses at different intervals of time are explicitly modeled. In such models, predictions for a certain interval of time (e.g. death within 1 year) are influenced by predictions made for other intervals, and prognostic survival curves that provide consistent estimates for several points in time can be produced. We developed a system of neural network models that makes use of time-oriented data to predict development of coronary heart disease (CHD), using a set of 2594 patients. The output of the neural network system was a prognostic curve representing survival without CHD, and the inputs were the values of demographic, clinical, and laboratory variables. The system of neural networks was trained by backpropagation and its results were evaluated in test sets of previously unseen cases. We showed that, by explicitly modeling time in the neural network architecture, the performance of the prognostic index, measured by the area under the receiver operating characteristic (ROC) curve, was significantly improved (p < 0.05).

Adult↗
PubMed1997

A foundational model of time for heterogeneous clinical databases.

Differences among the database representations of clinical data are a major barrier to the integration of databases and to the sharing of decision-support applications across databases. Prior research on resolving data heterogeneity has not addressed specifically the types of mismatches found in various timestamping approaches for clinical data. Such temporal mismatches, which include time-unit differences among timestamps, must be overcome before many applications can use these data to reason about diagnosis, therapy, or prognosis. In this paper, we present an analysis of the types of temporal mismatches that exist in databases. To formalize these various approaches to timestamping, we provide a foundational model of time. This model gives us the semantics necessary to encode the temporal dimensions of clinical data in legacy databases and to transform such heterogeneous data into a uniform temporal representation suitable for decision support. We have implemented this foundational model as an extension to our Chronus system, which provides clinical decision-support applications the ability to match temporal patterns in clinical databases. We discuss the uniqueness of our approach in comparison with other research on representing and querying clinical data with varying timestamp representations.

Databases as Topic↗
PubMed1997

A temporal database mediator for protocol-based decision support.

To meet the data-processing requirements for protocol-based decision support, a clinical data-management system must be capable of creating high-level summaries of time-oriented patient data, and of retrieving those summaries in a temporally meaningful fashion. We previously described a temporal-abstraction module (RESUME) and a temporal-querying module (Chronus) that can be used together to perform these tasks. These modules had to be coordinated by individual applications, however, to resolve the temporal queries of protocol planners. In this paper, we present a new module that integrates the previous two modules and that provides for their coordination automatically. The new module can be used as a standalone system for retrieving both primitive and abstracted time-oriented data, or can be embedded in a larger computational framework for protocol-based reasoning.

Artificial Intelligence↗
PubMed1996

Knowledge-based temporal abstraction in clinical domains.

We have defined a knowledge-based framework for the creation of abstract, interval-based concepts from time-stamped clinical data, the knowledge-based temporal-abstraction (KBTA) method. The KBTA method decomposes its task into five subtasks; for each subtask we propose a formal solving mechanism. Our framework emphasizes explicit representation of knowledge required for abstraction of time-oriented clinical data, and facilitates its acquisition, maintenance, reuse and sharing. The RESUME system implements the KBTA method. We tested RESUME in several clinical-monitoring domains, including the domain of monitoring patients who have insulin-dependent diabetes. We acquired from a diabetes-therapy expert diabetes-therapy temporal-abstraction knowledge. Two diabetes-therapy experts (including the first one) created temporal abstractions from about 800 points of diabetic-patients' data. RESUME generated about 80% of the abstractions agreed by both experts; about 97% of the generated abstractions were valid. We discuss the advantages and limitations of the current architecture.

Artificial Intelligence↗
PubMed1996

Toward reusable software components at the point of care.

An architecture built from five software components -a Router, Parser, Matcher, Mapper, and Server -fulfills key requirements common to several point-of-care information and knowledge processing tasks. The requirements include problem-list creation, exploiting the contents of the Electronic Medical Record for the patient at hand, knowledge access, and support for semantic visualization and software agents. The components use the National Library of Medicine Unified Medical Language System to create and exploit lexical closure-a state in which terms, text and reference models are represented explicitly and consistently. Preliminary versions of the components are in use in an oncology knowledge server.

Computer Systems↗
PubMed1996

Knowledge acquisition for temporal abstraction.

Temporal abstraction is the task of detecting relevant patterns in data over time. The knowledge-based temporal-abstraction method uses knowledge about a clinical domain's contexts, external events, and parameters to create meaningful interval-based abstractions from raw time-stamped clinical data. In this paper, we describe the acquisition and maintenance of domain-specific temporal-abstraction knowledge. Using the PROTEGE-II framework, we have designed a graphical tool for acquiring temporal knowledge directly from expert physicians, maintaining the knowledge in a sharable form, and converting the knowledge into a suitable format for use by an appropriate problem-solving method. In initial tests, the tool offered significant gains in our ability to rapidly acquire temporal knowledge and to use that knowledge to perform automated temporal reasoning.

Artificial Intelligence↗
PubMed1996

The EON model of intervention protocols and guidelines.

We present a computational model of treatment protocols abstracted from implemented systems that we have developed previously. In our framework, a protocol is modeled as a hierarchical plan where high-level protocol steps are decomposed into descriptions of more specific actions. The clinical algorithms embodied in a protocol are represented by procedures that encode the sequencing, looping, and synchronization of protocol steps. The representation allows concurrent and optional protocol steps. We define the semantics of a procedure in terms of an execution model that specifies how the procedure should be interpreted. We show that the model can be applied to an asthma guideline different from the protocols for which the model was originally constructed.

Adult↗
PubMed1996

Making generic guidelines site-specific.

Health care providers are more likely to follow a clinical guideline if the guideline's recommendations are consistent with the way in which their organization does its work. Unfortunately, developing guidelines that are specific to an organization is expensive, and limits the ability to share guidelines among different institutions. We describe a methodology that separates the site-independent information of guidelines from site-specific information, and that facilitates the development of site-specific guidelines from generic guidelines. We have used this methodology in a prototype system that assists developers in creating generic guidelines that are sharable across different sites. When combined with site information, generic guidelines can be used to generate site-specific guidelines that are responsive to organizational change and that can be implemented at a level of detail that makes site-specific computer-based workflow management and simulation possible.

Artificial Intelligence↗
PubMed1995

Computer-based screening of patients with HIV/AIDS for clinical-trial eligibility.

OBJECTIVE: To assess the potential effect of a computer-based system on accrual to clinical trials, we have developed methodology to identify retrospectively and prospectively patients who are eligible or potentially eligible for protocols. DESIGN: Retrospective chart abstraction with computer screening of data for potential protocol eligibility. SETTING: A county-operated clinic serving human immunodeficiency virus (HIV) positive patients with or without acquired immune deficiency syndrome (AIDS). PATIENTS: A randomly selected group of 60 patients who were HIV-infected, 30 of whom had an AIDS-defining diagnosis. DESIGN: Using a computer-based eligibility screening system, for each clinic visit and hospitalization, patients were categorized as eligible, potentially eligible, or ineligible for each of the 17 protocols active during the 7-month study period. Reasons for ineligibility were categorized. RESULTS: None of the patients was enrolled on a clinical trial during the 7-month period. Thirteen patients were identified as eligible for protocol; three patients were eligible for two different protocols; and one patient was eligible for the same protocol during two different time intervals. Fifty-four patients were identified as potentially eligible for a total of 165 accrual opportunities, but important information, such as the result of a required laboratory test, was missing, so that eligibility could not be determined unequivocally. Ineligibility for protocol was determined in 414 (35%) potential opportunities based only on conditions that were amenable to modification, such as the use of concurrent medications; 194 (17%) failed only laboratory tests or subjective determinations not routinely performed; and 346 (29%) failed only routine laboratory tests. CONCLUSIONS: There are substantial numbers of eligible and potentially eligible patients who are not enrolled or evaluated for enrollment in prospective clinical trials. Computer-based eligibility screening when coupled with a computer-based medical record offers the potential to identify patients eligible or potentially eligible for clinical trial, to assist in the selection of protocol eligibility criteria, and to make accrual estimates.

Acquired Immunodeficiency Syndrome↗
PubMed1995

Ontology-based configuration of problem-solving methods and generation of knowledge-acquisition tools: application of PROTEGE-II to protocol-based decision support.

PROTEGE-II is a suite of tools and a methodology for building knowledge-based systems and domain-specific knowledge-acquisition tools. In this paper, we show how PROTEGE-II can be applied to the task of providing protocol-based decision support in the domain of treating HIV-infected patients. To apply PROTEGE-II, (1) we construct a decomposable problem-solving method called episodic skeletal-plan refinement, (2) we build an application ontology that consists of the terms and relations in the domain, and of method-specific distinctions not already captured in the domain terms, and (3) we specify mapping relations that link terms from the application ontology to the domain-independent terms used in the problem-solving method. From the application ontology, we automatically generate a domain-specific knowledge-acquisition tool that is custom-tailored for the application. The knowledge-acquisition tool is used for the creation and maintenance of domain knowledge used by the problem-solving method. The general goal of the PROTEGE-II approach is to produce systems and components that are reusable and easily maintained. This is the rationale for constructing ontologies and problem-solving methods that can be composed from a set of smaller-grained methods and mechanisms. This is also why we tightly couple the knowledge-acquisition tools to the application ontology that specifies the domain terms used in the problem-solving systems. Although our evaluation is still preliminary, for the application task of providing protocol-based decision support, we show that these goals of reusability and easy maintenance can be achieved. We discuss design decisions and the tradeoffs that have to be made in the development of the system.

Artificial Intelligence↗
PubMed1995

Support for information management in critical care: a new approach to identify needs.

Managing information is necessary to support clinical decision making and action in critical care. By understanding the nature of information management and its relationship to sound clinical practice, we should come to use technology more wisely. We demonstrated that a new approach inspired by ethnographic research methods could identify useful and unexpected findings about clinical information management. In this approach, a clinician experienced in a specific domain (critical care), with advice from a medical anthropologist, made short-term observations of information management in that domain. We identified 8 areas in a critical care Unit in which information management was seriously in need of better support. We also found interesting differences in how these needs were viewed by nurses and physicians. Our interest in this approach was at two levels: 1. Identify and describe representative instances of sub-optimal information management in a critical care Unit. 2. Investigate the effectiveness of such short-term observations by clinicians. Our long-range goal is to explore the use of this approach and the information it reveals to optimize the process of developing and selecting new information support tools, preparing for their introduction, and optimizing clinical outcomes.

Critical Care↗
PubMed1995

A web-based architecture for a medical vocabulary server.

For health care providers to share computing resources and medical application programs across different sites, those applications must share a common medical vocabulary. To construct a common vocabulary, researchers must have an architecture that supports collaborative, networked development. In this paper, we present a web-based server architecture for the collaborative development of a medical vocabulary: a system that provides network services in support of medical applications that need a common, controlled medical terminology. The server supports vocabulary browsing and editing and can respond to direct programmatic queries about vocabulary terms. We have tested the programmatic query-response capability of the vocabulary server with a medical application that determines when patients who have HIV infection may be eligible for certain clinical trials. Our emphasis in this paper is not on the content of the vocabulary, but rather on the communication protocol and the tools that enable collaborative improvement of the vocabulary by any network-connected user.

Computer Communication Networks↗
PubMed1995

A rational reconstruction of INTERNIST-I using PROTEGE-II.

PROTEGE-II is a methodology and a suite of tools that allow developers to build and maintain knowledge-based systems in a principled manner. We used PROTEGE-II to reconstruct the well-known INTERNIST-I system, demonstrating the role of a domain ontology (a framework for specification of a model of an application area), a reusable problem-solving method, and declarative mapping relations in creating a new, working program. PROTEGE-II generates automatically a domain-specific knowledge-acquisition tool, which, in the case of the INTERNIST-I reconstruction, has much of the functionality of the QMR-KAT knowledge-acquisition tool. This study provides a means to understand better both the PROTEGE-II methodology and the models that underlie INTERNIST-I.

Artificial Intelligence↗
PubMed1995

A comparison of the temporal expressiveness of three database query methods.

Time is a multifaceted phenomenon that developers of clinical decision-support systems can model at various levels of complexity. An unresolved issue for the design of clinical databases is whether the underlying data model should support interval semantics. In this paper, we examine whether interval-based operations are required for querying protocol-based conditions. We report on an analysis of a set of 256 eligibility criteria that the T-HELPER system uses to screen patients for enrollment in eight clinical-trial protocols for HIV disease. We consider three data-manipulation methods for temporal querying: the consensus query representation Arden Syntax, the commercial standard query language SQL, and the temporal query language TimeLineSQL (TLSQL). We compare the ability of these three query methods to express the eligibility criteria. Seventy nine percent of the 256 criteria require operations on time stamps. These temporal conditions comprise four distinct patterns, two of which use interval-based data. Our analysis indicates that the Arden Syntax can query the two non-interval patterns, which represent 54% of the temporal conditions. Timepoint comparisons formulated in SQL can instantiate the two non-interval patterns and one interval pattern, which encompass 96% of the temporal conditions. TLSQL, which supports an interval-based model of time, can express all four types of temporal patterns. Our results demonstrate that the T-HELPER system requires simple temporal operations for most protocol-based queries. Of the three approaches tested, TLSQL is the only query method that is sufficiently expressive for the temporal conditions in this system.

Decision Making, Computer-Assisted↗
PubMed1995

A comparison of two computer-based prognostic systems for AIDS.

We compare the performances of a Cox model and a neural network model that are used as prognostic tools for a cohort of people living with AIDS. We modeled disease progression for patients who had AIDS (according to the 1993 CDC definition) in a cohort of 588 patients in California, using data from the ATHOS project. We divided the study population into 10 training and 10 test sets and evaluated the prognostic accuracy of a Cox proportional hazards model and of a neural network model by determining the number of predicted deaths, the sensitivities, specificities, positive predictive values, and negative predictive values for intervals of one year following the diagnosis of AIDS. For the Cox model, we further tested the agreement between a series of binary observations, representing death in one, two, and three years, and a set of estimates which define the probability of survival for those intervals. Both models were able to provide accurate numbers on how many patients were likely to die at each interval, and reasonable individualized estimates for the two- and three-year survival of a given patient, but failed to provide reliable predictions for the first year after diagnosis. There was no evidence that the Cox model performed better than did the neural network model or vice-versa, but the former method had the advantage of providing some insight on which variables were most influential for prognosis. Nevertheless, it is likely that the assumptions required by the Cox model may not be satisfied in all data sets, justifying the use of neural networks in certain cases.

Acquired Immunodeficiency Syndrome↗
PubMed1995

The development of a controlled medical terminology: identification, collaboration, and customization.

An increasing focus in health care is the development and use of electronic medical record systems to capture and store patient information. T-HELPER is an electronic medical record system that health care providers use to record ambulatory-care patient progress notes. These data are stored in an on-line database and analyzed by T-HELPER to provide users with decision support regarding patient eligibility for clinical trial protocols and assistance with continued protocol-based care. Our goal is to provide a system that enhances the process of identifying patients who are potentially eligible for clinical trials of experimental therapies in a clinic that is limited by the existence of a singular clinical trial coordinator. Effective implementation of such a system requires the development of a meaningful controlled medical terminology that satisfies the needs of a diverse community of providers all of who contribute to the health care process. The development of a controlled medical terminology is a process of identification, collaboration, and customization. We enlisted the help of collaborators familiar with the proposed work environment to identify user needs, to collaborate with our development team to construct the preliminary terminology, and to customize the controlled medical terminology to make it meaningful and acceptable to the clinic users.

Ambulatory Care↗