PubMed Health⌕ Search

Biomedical subjects

E H Shortliffe

Publications and source records attributed to E H Shortliffe.

At least 55 records · Page 3Linked to original sources
PubMed1991

Thomas: building Bayesian statistical expert systems to aid in clinical decision making.

Knowledge-based system for classical statistical analysis must separate the task of analyzing data from that of using the results of the analysis. In contrast, a Bayesian framework for building biostatistical expert system allows for the integration of the data-analytic and decision-making tasks. The architecture of such a framework entails enabling the system (1) to make its recommendations on decision-analytic grounds; (2) to construct statistical models dynamically; (3) to update a statistical model based on the user's prior beliefs and on data from, the methodological concerns evinced by, the study. This architecture permits the knowledge engineer to represent a variety of types of statistical and domain knowledge. Construction of such systems requires that the knowledge engineer reinterpret traditional statistical concerns, such as by replacing the notion of statistical significance with that of a pragmatic clinical threshold. The clinical user of such a system can interact with the system at a semantic level appropriate to her fund of methodological knowledge, rather than at the level of statistical details. We demonstrate these issues with a prototype system called THOMAS which helps a physician decision maker interpret the results of a published randomized clinical trial.

Artificial Intelligence↗
PubMed1991

Developing trends in clinical computing.

With the emergence of personal computers and graphical interfaces during the 1980s, advanced computational power has at last become accessible and affordable for practising clinicians in both inpatient and outpatient settings. Many observers have accordingly noted the relatively low level of direct computer use by physicians in their practices. This paper summarises developing trends in clinical computing, emphasising the role of local and wide-access networks, the revolutionary potential of optical storage techniques, and the notion of integrated workstations that will bring a critical mass of diverse functions to the physician. An important lesson of this review is the current availability of most of the technologies needed for high-quality and acceptable clinical computing tools. The barriers to successful implementation tend to be logistical, financial, and political. Despite these obstacles, new technologies, coupled with educational efforts, should allow the computer to emerge as a crucial aid to clinicians in the decade ahead.

Attitude to Computers↗
PubMed1990

Medical informatics. An emerging academic discipline and institutional priority.

Information management constitutes a major activity of the health care professional. Currently, a number of forces are focusing attention on this function. After many years of development of information systems to support the infrastructure of medicine, greater focus on the needs of physicians and other health care managers and professionals is occurring--to support education, decision making, communication, and many other aspects of professional activity. Medical informatics is the field that concerns itself with the cognitive, information processing, and communication tasks of medical practice, education, and research, including the information science and the technology to support these tasks. An intrinsically interdisciplinary field, medical informatics has a highly applied focus, but also addresses a number of fundamental research problems as well as planning and policy issues. Medical informatics is now emerging as a distinct academic entity. Health care institutions are considering, and a few are making, large-scale commitments to information systems and services that will affect every aspect of their organizations' function. While academic units of medical informatics are presently established at only a few medical institutions in the United States, increasing numbers of schools are considering this activity and many traditional departments are seeking and attracting individuals with medical informatics skills.

Career Choice↗
PubMed1990

Temporal representation of clinical algorithms using expert-system and database tools.

The HyperLipid Advisory System combines a rule-based implementation of a clinical algorithm (the NIH Cholesterol Education Program Expert Panel recommendations) with a temporal representation that facilitates reasoning over time while maintaining efficient storage in a standard database. The temporal representation consists of objects that model point events such as visits and interval events such as specific therapies. These objects are combined into abstractions called phases, which correspond to higher level clinical concepts such as a diet or drug treatment. The time-oriented data objects are referenced in the rules using a custom-tailored operator query language. Between user sessions relevant clinical data are stored in external files. When the advisory system is reconsulted, this information is retrieved and mapped back into an object-oriented format. Use of a commercially available expert-system shell for such tasks allows algorithm implementation in standard personal computing environments.

Algorithms↗
PubMed1987

Computer programs to support clinical decision making.

Computer programs to assist with medical decision making have long been anticipated by physicians with both curiosity and concern. This article summarizes the current status of computer-based medical decision support, the goals of system developers, the reasons for slow progress since the field began almost 30 years ago, and the logistical and scientific challenges that lie ahead. It emphasizes in particular that decision-support programs are intended to serve as tools for trained practitioners who retain ultimate responsibility for determining diagnostic and therapeutic strategies.

Artificial Intelligence↗
PubMed1987

A therapy planning architecture that combines decision theory and artificial intelligence techniques.

Through our experience with the ONCOCIN cancer therapy consultation system, we have identified a set of medical planning problems to which no single existing computer-based reasoning technique readily applies. In response to the need for automated assistance with this class of problems, we have devised a computer program called ONYX that combines decision-theoretic and artificial intelligence approaches to planning. We discuss our rationale for devising a new planning architecture and describe in detail how that architecture is implemented. The program's planning process consists of three steps: (i) the use of rules derived from therapy planning strategies to generate a small set of plausible plans, (ii) the use of knowledge about the structure and behavior of the human body to create simulations that predict possible consequences of each plan for the patient, and (iii) the use of decision theory to rank the plans according to how well the results of each simulation meet the treatment goals. This architecture explicitly manages the uncertainty inherent in many planning tasks, introduces a possible mechanism for the dissemination of decision-theoretic therapy advice, and potentially increases the number of problem solving domains in which expert system techniques can be effectively applied.

Artificial Intelligence↗
PubMed1987

A computational model of reasoning from the clinical literature.

This paper explores the premise that a formalized representation of empirical studies can play a central role in computer-based decision support. The specific motivations underlying this research include the following propositions: Reasoning from experimental evidence contained in the clinical literature is central to the decisions physicians make in patient care. A computational model, based upon a declarative representation for published reports of clinical studies, can drive a computer program that selectively tailors knowledge of the clinical literature as it is applied to a particular case. The development of such a computational model is an important first step toward filling a void in computer-based decision support systems. Furthermore, the model may help us better understand the general principles of reasoning from experimental evidence both in medicine and other domains. Roundsman is a developmental computer system which draws upon structured representations of the clinical literature in order to critique plans for the management of primary breast cancer. Roundsman is able to produce patient-specific analyses of breast cancer management options based on the 24 clinical studies currently encoded in its knowledge base. The Roundsman system is a first step in exploring how the computer can help to bring a critical analysis of the relevant literature to the physician, structured around a particular patient and treatment decision.

Artificial Intelligence↗
PubMed1987

Reasoning from the clinical literature: a "distance" metric.

There has been little or no integration of specific studies from the clinical literature with computer-based medical advice systems. This paper reports preliminary results of a research project designed to model reasoning from the clinical literature. The program, named "Roundsman", draws upon structured representations of the clinical literature in order to critique plans for medical management. This paper discusses the need for a clinical "distance" metric to use in mapping from studies to treatment choices. The design of one such metric is outlined, and the results of its incorporation in Roundsman are shown in a sample output from the program. The application domain for this program is the management of primary breast cancer, but the research goals are to identify general issues which arise in diverse medical management domains.

Breast Neoplasms↗
PubMed1987

Knowledge engineering for a clinical trial advice system: uncovering errors in protocol specification.

ONCOCIN is an expert system that provides advice to physicians who are treating cancer patients enrolled in clinical trials. The process of encoding oncology protocol knowledge for the system has revealed serious omissions and unintentional ambiguities in the protocol documents. We have also discovered that many protocols allow for significant latitude in treating patients and that even when protocol guidelines are explicit, physicians often choose to apply their own judgment on the assumption that the specifications are incomplete. Computer-based tools offer the possibility of insuring completeness and reproducibility in the definition of new protocols. One goal of our automated protocol authoring environment, called OPAL, is to help physicians develop protocols that are free of ambiguity and thus to assure better compliance and standardization of care.

Clinical Trials as Topic↗
PubMed1986

Medical expert systems--knowledge tools for physicians.

Recent advances in the field of artificial intelligence have led to the emergence of expert systems, computational tools designed to capture and make available the knowledge of experts in a field. Although much of the underlying technology available today is derived from basic research on biomedical advice systems during the 1970s, medical application packages are thus far generally unavailable from the young artificial intelligence industry. Medical expert systems will begin to appear, however, as researchers in medical artificial intelligence continue to make progress in key areas such as knowledge acquisition, model-based reasoning and system integration for clinical environments. It is accordingly important for physicians to understand the current state of such research and the theoretic and logistic barriers that remain before useful systems can be made available. One experimental system, ONCOCIN, provides a glimpse of the kinds of knowledge-based tools that will someday be available to physicians.

Drug Therapy, Computer-Assisted↗
PubMed1985

Improvements in data collection through physician use of a computer-based chemotherapy treatment consultant.

The impact of a computer-based data management system on the completeness of clinical trial data was studied before and after the system's introduction in an oncology clinic. Physicians use the system, termed ONCOCIN, to record data during patient visits and to receive advice about treatment and tests required by experimental cancer protocols. Although ONCOCIN does not force the user to enter all data expected by the protocol, after its introduction there was improvement in the recording frequency of such data. The percentage of expected physical findings recorded increased from 74% to 91% (P less than .05), toxicity history from less than 1% to 45% (P less than .01), general chemistry results from 36% to 82% (P less than .01), x-ray results from 44% to 73% (P less than .01), and physicians' assessments of overall disease activity and Karnofsky performance status from 73% to 91% (P less than .05). Analysis of the steps in data collection and their contribution to loss of data suggests that observations or test ordering which are dependent on the physician are most improved by the system. Furthermore, analysis of post-ONCOCIN visits when the system was unavailable suggests that the recording of physician-dependent data (physical findings and assessments of disease activity and performance status) is likely to revert to pre-ONCOCIN levels if the system is not used routinely. The results show that ONCOCIN can greatly enhance recovery of those data expected for chemotherapy protocol patients. The program's interaction with the physician is central to its effectiveness in data collection, especially for data that arise directly from the patient-physician encounter.

Antineoplastic Agents↗
PubMed1985

The treatment advice of a computer-based cancer chemotherapy protocol advisor.

ONCOCIN is a chemotherapy protocol advisor used experimentally in a university oncology clinic. The program combines formal protocol guidelines with judgments of oncologists who have experience adjusting therapy in complex clinical situations. We compared the chemotherapy administered by clinic physicians with the treatment that would have been recommended by ONCOCIN in 415 visits for 39 patients with lymphoma seen before the program's introduction. In 189 visits the program agreed with the therapy actually administered. In a blinded evaluation, four experts on lymphoma failed to find a significant difference between the treatments selected by physicians and those proposed by ONCOCIN. Further analyses showed that ONCOCIN tended to attenuate drug doses or delay treatment more than the experts recommended, whereas the physicians were less likely to attenuate doses to the extent the experts suggested. Our results show that ONCOCIN provides advice on lymphoma treatment similar to the treatment provided in a university oncology clinic.

Adult↗