Search PubMed⌕ Search

Biomedical subjects

K A Spackman

Publications and source records attributed to K A Spackman.

15 recordsLinked to original sources
PubMed1997

SNOMED RT: a reference terminology for health care.

We describe the framework for SNOMED RT (Reference Terminology), designed to complement the broad coverage of medical concepts in SNOMED with a set of enhanced features that significantly increases its value as a reference terminology for representing clinical data. We describe what is meant by a reference terminology, and differentiate SNOMED RT from specialized terminologies that enable user interfaces, electronic messaging, or natural language processing, as well as from other specialized reference terminologies whose primary purpose is for representing data that is not primarily clinical in nature. We then describe how SNOMED RT represents multiple hierarchies and incorporates description logic. We believe that such a comprehensive set of concepts at multiple levels of granularity, with multiple logic-based subsumption hierarchies can meet the requirements of a reference terminology for health care.

Terminology as Topic↗
PubMed1996

An expert system to diagnose anemia and report results directly on hematology forms.

An attempt was made to create an expert system with sufficient accuracy to diagnose classes of anemia and report presumptive diagnoses directly on the hematology form. The system should simulate the processes of human experts who can reliably achieve diagnostic separability by pattern analysis. A hybrid expert system combining rule-based and artificial neural network (ANN) models was constructed to evaluate microcytic anemia in a 3-layered program using hematocrit (HCT), mean corpuscular volume (MCV), and coefficient of variation of cell distribution width (RDWcv) as inputs. These measurements are available as standard output on most hematology analyzers. Three categories of microcytic anemia were considered, iron deficiency (IDA), hemoglobinopathy (HEM), and anemia of chronic disease (ACD). A novel feature of the model is its construction and training using human expert input alone. Model construction is described in detail. The model's performance was evaluated with actual case data. It was successful in correctly classifying 96.5% of 473 documented cases of microcytic anemia and anemia of chronic disease. It thus exhibits sufficient accuracy for it to be considered for use in reporting microcytic anemia diagnoses on hematology forms.

Anemia↗
PubMed1996

Recognizing noun phrases in medical discharge summaries: an evaluation of two natural language parsers.

We evaluated the ability of two natural language parsers, CLARIT and the Xerox Tagger, to identify simple, noun phrases in medical discharge summaries. In twenty randomly selected discharge summaries, there were 1909 unique simple noun phrases. CLARIT and the Xerox Tagger exactly identified 77.0% and 68.7% of the phrases, respectively, and partially identified 85.7% and 80.8% of the phrases. Neither system had been specially modified or tuned to the medical domain. These results suggest that it is possible to apply existing natural language processing (NLP) techniques to large bodies of medical text, in order to empirically identify the terminology used in medicine. Virtually all the noun phrases could be regarded as having special medical connotation and would be candidates for entry into a controlled medical vocabulary.

Medical Records↗
PubMed1993

The CIO and the medical informaticist: alliance for progress.

To achieve the full potential of information technology, health care institutions must overcome organizational and political barriers that often overshadow scientific and technical barriers. The time has come for an alliance between the Chief Information Officer (CIO) and medical informatics specialists, or informaticists. Organizations that successfully accomplish this alliance will position themselves to take advantage of the enormous potential of information technology to manage today's cost-quality pressures. This article first reviews some of the recent developments in the way health care organizations manage information technology. It then describes the traditional, perhaps the natural state of affairs, in which there may be tension and conflict between medical informaticists and line managers of information systems (IS). Finally, the article makes a case for closer collaboration and cooperation between these groups, and provides a case study that illustrates one example of such an alliance.

Academic Medical Centers↗
PubMed1992

Combining logistic regression and neural networks to create predictive models.

Neural networks are being used widely in medicine and other areas to create predictive models from data. The statistical method that most closely parallels neural networks is logistic regression. This paper outlines some ways in which neural networks and logistic regression are similar, shows how a small modification of logistic regression can be used in the training of neural network models, and illustrates the use of this modification for variable selection and predictive model building with neural networks.

Algorithms↗
PubMed1991

Maximum likelihood training of connectionist models: comparison with least squares back-propagation and logistic regression.

This paper presents maximum likelihood back-propagation (ML-BP), an approach to training neural networks. The widely reported original approach uses least squares back-propagation (LS-BP), minimizing the sum of squared errors (SSE). Unfortunately, least squares estimation does not give a maximum likelihood (ML) estimate of the weights in the network. Logistic regression, on the other hand, gives ML estimates for single layer linear models only. This report describes how to obtain ML estimates of the weights in a multi-layer model, and compares LS-BP to ML-BP using several examples. It shows that in many neural networks, least squares estimation gives inferior results and should be abandoned in favor of maximum likelihood estimation. Questions remain about the potential uses of multi-level connectionist models in such areas as diagnostic systems and risk-stratification in outcomes research.

Diagnosis, Computer-Assisted↗
PubMed1991

Information workstations in clinical pathology.

Multitasking operating systems and expanding networks now permit smooth access to remote computers, peripherals, data, and information resources. Graphic user interfaces and productivity-enhancing software packages reduce the need for training and memorization of commands. New models of desktop computers based on "data-centered" software architecture can enhance workstation usefulness even more. Pathologists need to consider how these tools might improve access to and management of information and knowledge.

Computer Systems↗
PubMed1990

A knowledge-based system for transfusion advice.

A knowledge-based system has been designed for evaluating the appropriateness of transfusion of non-red blood cell blood components. The goal of the system is to assist the blood bank physician in quality assurance efforts by automatically identifying cases of inappropriate transfusion before the blood is issued. Evaluation of a working prototype system shows that it is indeed capable of serving this function. The system identifies and summarizes cases, but it leaves consultation, education, and decision making to the blood bank physician. Small "expert systems" such as this may find use in quality assurance activities throughout the laboratory.

Blood Transfusion↗
PubMed1987

Knowledge-based systems in laboratory medicine and pathology. A review and survey of the field.

Knowledge-based systems are computer systems designed to handle knowledge-intensive tasks, usually involving reasoning and inference. They are increasingly being applied to problems in laboratory medicine and pathology. In this article we provide a brief introduction to the basic concepts of knowledge-based systems, review some of their published applications, and report on an informal survey of specialists in laboratory medicine and pathology. The survey, sent to 102 individuals, indicated that 24% were involved in developing knowledge-based systems, with most systems at an early stage of development. Recent advances in knowledge-based systems research as well as survey responses suggest that this technology will have increasing value in laboratory medicine and pathology.

Artificial Intelligence↗
PubMed1985

A program for machine learning of counting criteria: empirical induction of logic-based classification rules.

A program has been developed which derives classification rules from empirical observations and expresses these rules in a knowledge representation format called 'counting criteria'. Decision rules derived in this format are often more comprehensible than rules derived by existing machine learning programs such as AQ11. Use of the program is illustrated by the inference of discrimination criteria for certain types of bacteria based upon their biochemical characteristics. The program may be useful for the conceptual analysis of data and for the automatic generation of prototype knowledge bases for expert systems.

Artificial Intelligence↗
PubMedDate not supplied

Evaluation of a "lexically assign, logically refine" strategy for semi-automated integration of overlapping terminologies.

OBJECTIVE: To evaluate a "lexically assign, logically refine" (LALR) strategy for merging overlapping healthcare terminologies. This strategy combines description logic classification with lexical techniques that propose initial term definitions. The lexically suggested initial definitions are manually refined by domain experts to yield description logic definitions for each term in the overlapping terminologies of interest. Logic-based techniques are then used to merge defined terms. METHODS: A LALR strategy was applied to 7,763 LOINC and 2,050 SNOMED procedure terms using a common set of defining relationships taken from the LOINC data model. Candidate value restrictions were derived by lexically comparing the procedure's name with other terms contained in the reference SNOMED topography, living organism, function, and chemical axes. These candidate restrictions were reviewed by a domain expert, transformed into terminologic definitions for each of the terms, and then algorithmically classified. RESULTS: The authors successfully defined 5,724 (73%) LOINC and 1,151 (56%) SNOMED procedure terms using a LALR strategy. Algorithmic classification of the defined concepts resulted in an organization mirroring that of the reference hierarchies. The classification techniques appropriately placed more detailed LOINC terms underneath the corresponding SNOMED terms, thus forming a complementary relationship between the LOINC and SNOMED terms. DISCUSSION: LALR is a successful strategy for merging overlapping terminologies in a test case where both terminologies can be defined using the same defining relationships, and where value restrictions can be drawn from a single reference hierarchy. Those concepts not having lexically suggested value restrictions frequently indicate gaps in the reference hierarchy.

Algorithms↗