Integrating consultation and semi-automatic knowledge acquisition in a prototype-based architecture: Experiences with dysmorphic syndromes

doi:10.1016/0933-3657(94)90056-6

Artificial Intelligence in Medicine

Volume 6, Issue 1, February 1994, Pages 29-49

https://doi.org/10.1016/0933-3657(94)90056-6 Get rights and content

Abstract

The paper describes an application of cognitive theories of Tversky and Rosch to prototype similarity of dysmorphic syndromes cases. The knowledge-based system supports diagnostic consultation and research in dysmophic syndromes. It has been used routinely for many years. The knowledge base is semi-automatically generated from known cases of an outpatient clinic. Some results of the evaluation process of the system's achievements are shown. General conclusions based on the experience with this successful system are discussed.

References (40)

W.J. Clancey
Heuristic classification
Artificial Intelligence
(1985)
M. de la Maza
A prototype based symbolic concept learning system
J.L. Kolodner
Extending problem solver capabilities through case-based inference
E. Rosch et al.
Family resemblance: Studies in the internal structures of categories
Cognitive Psychol.
(1975)
R.C. Schank et al.
Creativity and learning in a case-based explainer
Artificial Intelligence
(1989)
R. Bareis
Exemplar-Based Knowledge Acquisition
(1989)
A. Berchtold et al.
A. Dempster
Upper and lower probabilities induced by a multivalued mapping
Amer. Math. Statist.
(1967)
M. Derenbach et al.
ExTra - Expert system for complications after kidney transplantation
G. Eckert
Die Methode der Bildstatistik und vergleichbare bildstatistisch-anthropometrische Untersuchungen beim Down-Syndrom

S. Fertig et al.

FGP: A virtual machine for acquiring knowledge from cases

A. Ghezal

Automatic human face recognition using an artificial neural network

L. Gierl et al.

Knowledge acquisition for scheme-based medical expert systems: The dysmorphic syndrome example

J. Gouvernet et al.

GENDIAG: A computer-assited facility in medical genetics based on belief function

Meth. Inf. Med.

(1985)

J.A. Hupp

DXplain — A computer-based diagnostic knowledge base

J.L. Kolodner et al.

Problem solving and dynamic memory

M. Lebowitz

Lerning concepts in a rich input domain

R.A. Miller

INTERNIST-1/CADUCEUS: Problems facing expert consultant programs

Meth. Inf. Med.

(1984)

R.A. Miller et al.

The demise of the “Greek Oracle” model for medical diagnostic systems

Meth. Inf. Med.

(1990)

H. Müller et al.

Rechnerunterstütztes Ebenenmodell zur Analyse und Prädiktion von Makromolekülen

Cited by (48)

How to use contextual knowledge in medical case-based reasoning systems: A survey on very recent trends
2011, Artificial Intelligence in Medicine
Citation Excerpt :
However, at the same time, the need to properly manage contextual knowledge in order to preserve recency and to continuously verify validity clearly makes the acquisition, adaptation and reuse activities more challenging. These challenges are approached e.g. in [30], by resorting to the definition and exploitation of prototypes [31]. Prototypes are a generalization from single to clustered typical cases.
This paper aims at systematizing the ways in which the contextual knowledge embedded in the case library can support decision making, within case-based reasoning (CBR) systems. In particular, CBR applications to the medical domain are considered.
After a quick survey on the definition and on the role of context in artificial intelligence research, we have focused on CBR, with a particular emphasis on medical applications. In this field, we have identified a number of very recent contributions, which strongly recognize context per se as a major knowledge source. These contributions propose to maintain and to rely on contextual information, in order to support human reasoning in different fashions.
We have distinguished three main directions in which contextual knowledge can be resorted to, in order to optimize physicians’ decision making. Such directions can be summarized as follows: (1) to reduce the search space in the case retrieval step; (2) to maintain the overall knowledge content always valid and up to date, and (3) to adapt knowledge application and reasoning to local/personal constraints. We have also properly categorized the surveyed works within these three clusters, and identified the most significant ones, able to exploit contextual knowledge along more than one direction.
Innovative applications of the contextual knowledge recorded in the case library, described and systematized in this paper, can trace promising research directions for the future.
Constructing a personalized e-learning system based on genetic algorithm and case-based reasoning approach
2007, Expert Systems with Applications
The Internet and the World Wide Web in particular provide a unique platform to connect learners with educational resources. Educational material in hypermedia form in a Web-based educational system makes learning a task-driven process. It motivates learners to explore alternative navigational paths through the domain knowledge and from different resources around the globe. Consequently, many researchers have focused on developing e-learning systems with personalized learning mechanisms to assist on-line Web-based learning and to adaptively provide learning paths. However, although most personalized systems consider learner preferences, interests and browsing behaviors when providing personalized curriculum sequencing services, these systems usually neglect to consider whether learner ability and the difficulty level of the recommended curriculums are matched to each other.
Therefore, our proposed approach is based on the evolvement technique through computerized adaptive testing (CAT). Then the genetic algorithm (GA) and case-based reasoning (CBR) are employed to construct an optimal learning path for each learner. This paper makes three critical contributions: (1) it presents a genetic-based curriculum sequencing approach that will generate a personalized curriculum sequencing; (2) it illustrates the case-based reasoning to develop a summative examination or assessment analysis; and (3) it uses empirical research to indicate that the proposed approach can generate the appropriate course materials for learners, based on individual learner requirements, to help them to learn more effectively in a Web-based environment.
Integrating data mining with case-based reasoning for chronic diseases prognosis and diagnosis
2007, Expert Systems with Applications
The threats to people’s health from chronic diseases are always exist and increasing gradually. How to decrease these threats is an important issue in medical treatment. Thus, this paper suggests a model of a chronic diseases prognosis and diagnosis system integrating data mining (DM) and case-based reasoning (CBR). The main processes of the system include: (1) adopting data mining techniques to discover the implicit meaningful rules from health examination data, (2) using the extracted rules for the specific chronic diseases prognosis, (3) employing CBR to support the chronic diseases diagnosis and treatments, and (4) expanding these processes to work within a system for the convenience of chronic diseases knowledge creating, organizing, refining, and sharing. The experiment data are collected from a professional health examination center, MJ health screening center, and implemented through the system for analysis. The findings are considered as helpful references for doctors and patients in chronic diseases treatments.
A prognostic model for temporal courses that combines temporal abstraction and case-based reasoning
2005, International Journal of Medical Informatics
Since clinical management of patients and clinical research are essentially time-oriented endeavours, reasoning about time has become a hot topic in medical informatics. Here we present a method for prognosis of temporal courses, which combines temporal abstractions with case-based reasoning. It is useful for application domains where neither well-known standards, nor known periodicity, nor a complete domain theory exist. We have used our method in two prognostic applications. The first one deals with prognosis of the kidney function for intensive care patients. The idea is to elicit impairments on time, especially to warn against threatening kidney failures. Our second application deals with a completely different domain, namely geographical medicine. Its intention is to compute early warnings against approaching infectious diseases, which are characterised by irregular cyclic occurrences. So far, we have applied our program on influenza and bronchitis. In this paper, we focus on influenza forecast and show first experimental results.
Conducting feasibility studies for knowledge based systems
2004, Knowledge-Based Systems
Genetic counselling in carriers of reciprocal chromosomal translocations involving short arm of chromosome X
2004, Annales de Genetique
Citation Excerpt :
Her height was 92 cm (25th–50th centile), her weight 13.5 kg (10th–25th centile) and OTC 47.5 cm (10th–25th centile). Morphological studies were performed at 3 years (Fig. 3e,f) according to Gierl and Stengel-Rutkowski [10], Stengel-Rutkowski et al. [32]. Anthropological features were described according to Stengel-Rutkowski et al. [32].
A central concept in genetic counselling is the estimation of the probability of occurrence of unbalanced progeny at birth and other unfavourable outcomes of pregnancy (miscarriages, stillbirths and early death). The estimation of the occurrence probability for individual carriers of four different X-autosome translocations with breakpoints at Xp, namely t(X;5)(p22.2;q32), t(X;6)(p11.2;q21), t(X;7)(p22.2;p11.1), and t(X;22)(p22.1;p11.1), is presented. The breakpoint positions of chromosomal translocations were interpreted using GTG, RBG and FISH-wcp. Most of these translocations were detected in women with normal phenotype, karyotyped because of repeated miscarriages and/or malformed progeny. A girl with very rare pure trisomy Xp22.1→pter and a functional Xp disomy was ascertained in one family and her clinical picture has been described in details. It has been suggested that not fully skewed X chromosome inactivation of X-autosome translocation with breakpoint positions at Xp22 (critical segment) could influence the phenotype and risk value. Therefore, the X inactivation status was additionally evaluated by analysis of replication banding patterns using RBG technique after incorporation of BrdU. In two carriers of translocations: t(X;5)(p22.2;q32) and t(X;7)(p22.2;p11.1), late replication state of der(X) was observed in 5/100 and 10/180 analysed cells, respectively. In these both cases the breakpoint positions were clustered at the critical segment Xp22.2. In two other cases, one with the breakpoint position within [t(X;22)(p22.1;p11.1)] and one outside the critical region [t(X;6)(p11.2;q21)], fully skewed inactivation was seen. Therefore, we suggest that neither the distribution of the breakpoint positions nor fully skewed inactivation influenced the phenotype of observed t(X;A) carriers. The occurrence probabilities of the unbalanced progeny were calculated according to Stene and Stengel-Rutkowski along with application of updated available empirical data. In the studied group the values of occurrence probability for unbalanced offspring at birth ranged from 2.1% to 17%. Information on the magnitude of the individual figures may be important for women carrying a reciprocal X;A translocation when deciding upon further family planning.

View all citing articles on Scopus

View full text

PaperIntegrating consultation and semi-automatic knowledge acquisition in a prototype-based architecture: Experiences with dysmorphic syndromes

Abstract

Artificial Intelligence

Cognitive Psychol.

Artificial Intelligence

Exemplar-Based Knowledge Acquisition

Upper and lower probabilities induced by a multivalued mapping

Amer. Math. Statist.

ExTra - Expert system for complications after kidney transplantation

Die Methode der Bildstatistik und vergleichbare bildstatistisch-anthropometrische Untersuchungen beim Down-Syndrom

FGP: A virtual machine for acquiring knowledge from cases

Automatic human face recognition using an artificial neural network

Knowledge acquisition for scheme-based medical expert systems: The dysmorphic syndrome example

GENDIAG: A computer-assited facility in medical genetics based on belief function

Meth. Inf. Med.

DXplain — A computer-based diagnostic knowledge base

Problem solving and dynamic memory

Lerning concepts in a rich input domain

INTERNIST-1/CADUCEUS: Problems facing expert consultant programs

Meth. Inf. Med.

The demise of the “Greek Oracle” model for medical diagnostic systems

Meth. Inf. Med.

Rechnerunterstütztes Ebenenmodell zur Analyse und Prädiktion von Makromolekülen

Paper
Integrating consultation and semi-automatic knowledge acquisition in a prototype-based architecture: Experiences with dysmorphic syndromes