No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Fuzzy Medical Diagnostic Decision Support with Semiautomatic Knowledge Acquisition: A Case Study in Infectious Diseases.
Abstract
Research in the modeling of uncertainties using soft computing techniques, has an important role in the development of computational systems to aid medical decision-making. The present work revisits the fuzzy relations based approach for medical diagnosis, described by Wagholikar, Sutar and Deshpande [1], and investigates the use of semi-automatic method to implement the algorithm. In the case study, a medical diagnostic decision support (MDDS) system is developed with the semiautomatic method, and evaluated on a database of 57 patients diagnosed with infectious diseases. Jackknifing gives an accuracy of 94 percent, for the outcome of presence of correct diagnosis (as made by the physician) within the first two diagnoses suggested by the system. The study demonstrates the utility of the semi-automatic method and fuzzy relations based approach, and the need for further research.
ResearchGate has not been able to resolve any citations for this publication.
Fuzzy set theory has a number of properties that make it suitable for formalizing the uncertain information upon which medical diagnosis and treatment is usually based. Firstly, it defines inexact medical entities as fuzzy sets. Secondly, it provides a linguistic approach with an excellent approximation to texts. Finally, fuzzy logic offers reasoning methods capable of drawing approximate inferences. These facts suggest that fuzzy set theory might be a suitable basis for the development of a computerized diagnosis system. This is verified by trials performed with the medical expert system CADIAG-2, which uses fuzzy set theory to formalize medical relationships and fuzzy logic to model the diagnostic process.
Most mathematical models of physician decision processes offered to date, especially those relative to diagnosis and patient treatment, suffer from the inability to incorporate all useful data on the patient. Pertinent information so neglected or poorly modelled relate to variables that are intrinsically fuzzy but which describe the patient's health status. We present mathematical models based on fuzzy set theory for physician aided evaluation of a complete representation of information emanating from the initial interview including patient past history, present symptoms, signs observed upon physical examination, and results of clinical and diagnostic tests.
Our concern is with the development of a more accurate mathematical model of physician diagnosis decision processes. Using the complete information net of matrices outputed from Part I, the various diagnoses processes—medical hypothesis, initial preliminary diagnoses, other preliminary diagnosis and final diagnoses, are modelled as fuzzy matrices. A general fuzzy decision model which could be particularized to each of the foregoing cases is then developed. Our general technique is based on fuzzy clustering theory with the criterion function being a modified form of the minimum Minkowski metric.
In this paper we define and explore the properties of lower and upper inverses of fuzzy relations which extend multi-valued mappings. With the notion of degree of inclusion of non fuzzy sets, we then relate the preceeding notions to possibility distributions in natural languages and to problems of medical diagnosis.
Classical mathematical models for medical diagnosis which have been computerized are known to perform very poorly when compared to diagnoses made by the physician. Factors which contribute to their poor performance relate to the omission by these models of important information on the patient such as symptoms of past undiagnosed diseases which can only be vaguely recalled by the patient. Other deficiencies include failure to model the stage of development of the disease, and certain intrinsically fuzzy aspects of the pertinent information nets that are needed to develop a medical hypothesis. Models which attempted to remedy these shortcomings were developed and presented by the authors elsewhere.In this effort, we describe a study in which our fuzzy diagnosis models were computerized, validated and compared with a mock physician hypothesis as well as existing mathematical models. The example involved a medical hypothesis concerning a medical condition of valvular heart disease. The fuzzy sets together with their membership functions were measured using a distance criterion measure similar to the one employed by Kochen to quantify fuzzy adjectives in psychology. The results show that while there were discrepancies between the fuzzy model's and the physician's hypotheses, the model's performance was vastly superior to that of existing mathematical models. While the fuzzy models did well in naming the diseases, they performed less satisfactorily in the specification of the disease stage development, a factor completely ignored by classical models. Improvement in measurement aspects and the choice of diseases possessing discriminant attributes will greatly increase the accuracy of these models. It is however shown that a fuzzy systems approach is not only practical but results in models of greater validity than those based on classical set theoretic approaches.
Medicine is one field in which efforts were initiated in mid- 70' s on modeling of uncertainties using soft computing techniques. The descriptions of disease entities often use linguistic terms that are inherently vague. The uncertainty found in the process of diagnosis prompted the use of fuzzy set theory. We have revisited max- min fuzzy operations used in medical diagnosis with a case study of cardiovascular diseases identified by a team of experts (cardiologists) and compared the accuracy of the algorithm for 42 diagnostic records. Vagueness in the perception of the experts in describing the symptoms in linguistic terms for the diseases has been the primary focus of the analysis. The study demonstrates the utility of fuzzy modeling and need for further research.
CADIAG-1 and CADIAG-2 (Computer-Assisted DIAGnosis) are medical expert systems especially designed for ill-defined areas such as internal medicine. Both systems are being tested in the setting of a medical information system. With respect to their knowledge representation, CADIAG-1 has obvious advantages in totally ill-defined areas such as syndromes in internal medicine, whereas CADIAG-2 seems more suited for domains with basic laboratory programs, e.g., hepatology or gall bladder and bile duct diseases. The formalization of relationships between medical entities led to first-order predicate calculus formulas in the case of CADIAG-1 and to a model based on fuzzy set theory in the case of CADIAG-2. In both systems two kinds of relationships between medical entities are considered: (1) necessity of occurrence and (2) sufficiency of occurrence. Statistical interpretations using the 2 X 2 table paradigm yield a way to calculate these relationships automatically from samples of patient data. Results obtained by exploiting 3530 patient records from a rheumatological hospital are presented. The described application is a machine-learning program that allows inductive learning from examples under statistical uncertainty.
CADIAG-2 is a data-driven fuzzy medical expert system built for computer-based consultation in internal medicine. It has been integrated into the medical information system WAMIS of the Vienna General Hospital. Through the integration, CADIAG-2 is able to access patient data and laboratory test results already collected in the central patient database of WAMIS. CADIAG-2 operates in two subsequent phases: (1) as an automatic screening procedure for detecting pathological states in the patient, for generating diagnostic hypotheses, and for proposing further useful examinations; and (2) as an on-line consultation system for the clinician to assist him in clarifying patients' disorders completely and in great detail. At present, CADIAG-2 is subject to extended clinical trials. There are four application areas: rheumatic diseases, pancreatic diseases, gall bladder and bile duct diseases and colon diseases. First results on the performance of CADIAG-2 based on the evaluation of about 500 cases were obtained. In this paper, the principal goals, main components and concepts of CADIAG-2, and the experience gained until now are discussed.
Uncertainty of knowledge about the patient and about medical relationships is generally accepted and considered to be an inherent concept in medicine. The physician, however, is quite capable of drawing conclusions from this information. Naturally, these conclusions are approximate rather than precise.
Fuzzy set theory provides the possibility of defining imprecise medical entities as fuzzy sets. It offers a linguistic concept with excellent approximation to medical texts. In addition, fuzzy logic presents powerful reasoning methods that can handle approximate inferences. These facts make fuzzy set theory highly suitable for the development of computer-based medical diagnostic systems.
The medical expert system CADIAG-2 provides evidence that fuzzy set theory is a suitable mathematical tool for formalizing medical processes.
CADIAG-2/RHEUMA is being extensively tested on cases from a rheumatological hospital. Results from 327 cases are presented. In 265 cases, i.e. 81%, the clinical diagnosis could be either confirmed (223 cases, i.e. 68.2%) or established as a diagnostic hypothesis (42 cases, i.e. 12.8%).
CADIAG-2/PANCREAS was tested on 47 cases of pancreatic diseases. In 43 cases, i.e. 91.5%, the clinical diagnosis was either confirmed by CADIAG-2 or established as one of the hypotheses with the highest or second highest number of points in a ranked list of hypotheses.
Indeed, the complexity of biological systems may force us to alter in radical ways our traditional approaches to the analysis of such systems. Thus, we may have to accept as unavoidable a substantial degree of fuzziness in the description of the behavior of biological systems as well as in their characterization. This fuzziness, distasteful though it may be, is the price we have to pay for the ineffectiveness of precise mathematical techniques in dealing with systems comprising a very large number of interacting elements or involving a large number of variables in their decision trees.
The aim of the project is to introduce and implement in medical practice a fuzzy expert system specialized in the non-invasive diagnosis of myocardial ischemia. The system is able to embed and process medical knowledge independently of the way it is expressed (quantitatively or qualitatively, numerically or linguistically). It implements a novel medical diagnostic technique, has minimal computational requirements, performs an accurate diagnosis, is flexible and user-friendly. It is currently being tested in health care institutions and is used as a tool for different analyses and studies.
Accurate and reliable decision making in oncological prognosis can help in the planning of suitable surgery and therapy, and generally, improve patient management through the different stages of the disease. In recent years, several prognostic markers have been used as indicators of disease progression in oncology. However, the rapid increase in the discovery of novel prognostic markers resulting from the development in medical technology, has dictated the need for developing reliable methods for extracting clinically significant markers where complex and nonlinear interactions between these markers naturally exist. The aim of this paper is to investigate the fuzzy k-nearest neighbor (FK-NN) classifier as a fuzzy logic method that provides a certainty degree for prognostic decision and assessment of the markers, and to compare it with: 1) logistic regression as a statistical method and 2) multilayer feedforward backpropagation neural networks an artificial neural-network tool, the latter two techniques having been widely used for oncological prognosis. In order to achieve this aim, breast and prostate cancer data sets are considered as benchmarks for this analysis. The overall results obtained indicate that the FK-NN-based method yields the highest predictive accuracy, and that it has produced a more reliable prognostic marker model than the statistical and artificial neural-network-based methods.
Early prediction of infection following surgery for gastric cancer may permit earlier intervention.
The aim was to develop an early diagnostic system for postoperative infection.
Clinical and laboratory data were analyzed in 180 patients who had surgery for gastric cancer at the Wakayama Medical University Hospital (January 1992 to December 1994). Of these, 60 patients developed a postoperative infection. A predictive system was then devised using fuzzy theory and evaluated in a second set of 137 patients who underwent surgery for gastric cancer at Wakayama Medical University and 10 other associated hospitals (August 1995 to January 1997).
The system identified seven parameters grouped into six rules and entered into a fuzzy logic system to predict either infection or non-infection. (1) Blood loss, and extent of resection; (2) the febrile pattern during days 2 to 4; (3) differential leukocyte count on day 4; (4) C-reactive protein level on day 4; (5) time sequential vectors during days 1-4 for the band cell neutrophil count, and (6) leukocyte count. The sensitivity was 86% (24/28), the specificity was 90% (98/109), the negative predictive value was 96% (98/102), the positive predictive value was 69% (24/35) and the overall accuracy was 80% (122/137).
Fuzzy theory can provide early prediction of postoperative infection using standard clinical and biochemical parameters. The clinical utility of this system needs to be determined in future studies.
This paper describes the fuzzy knowledge representation framework of the medical computer consultation system MedFrame/CADIAG-IV as well as the specific knowledge acquisition techniques that have been developed to support the definition of knowledge concepts and inference rules. As in its predecessor system CADIAG-II, fuzzy medical knowledge bases are used to model the uncertainty and the vagueness of medical concepts and fuzzy logic reasoning mechanisms provide the basic inference processes. The elicitation and acquisition of medical knowledge from domain experts has often been described as the most difficult and time-consuming task in knowledge-based system development in medicine. It comes as no surprise that this is even more so when unfamiliar representations like fuzzy membership functions are to be acquired. From previous projects we have learned that a user-centered approach is mandatory in complex and ill-defined knowledge domains such as internal medicine. This paper describes the knowledge acquisition framework that has been developed in order to make easier and more accessible the three main tasks of: (a) defining medical concepts; (b) providing appropriate interpretations for patient data; and (c) constructing inferential knowledge in a fuzzy knowledge representation framework. Special emphasis is laid on the motivations for some system design and data modeling decisions. The theoretical framework has been implemented in a software package, the Knowledge Base Builder Toolkit. The conception and the design of this system reflect the need for a user-centered, intuitive, and easy-to-handle tool. First results gained from pilot studies have shown that our approach can be successfully implemented in the context of a complex fuzzy theoretical framework. As a result, this critical aspect of knowledge-based system development can be accomplished more easily.
Park's Textbook of Preventive and Social Medicine. 15 edn
- K Park
Park, K., ed.: Park's Textbook of Preventive and Social Medicine. 15 edn. Banarsidas
Bhanot Publishers (1997)
Fuzzy Expert System with Semi-automatic Knowledge Acquisition for Medical Decision Support
- K B Wagholikar
Wagholikar, K.B.: Fuzzy Expert System with Semi-automatic Knowledge Acquisition
for Medical Decision Support. [Thesis for Advanced Diploma Bioinformatics].
Fuzzy Sets and Fuzzy Logic -Theory and Applications Upper Saddle River Biological applications of the theory of fuzzy sets and systems
- G Klir
- B Yuan
- L A Zadeh
Klir, G., Yuan, B.: Fuzzy Sets and Fuzzy Logic -Theory and Applications. Prentice
Hall, Upper Saddle River, NJ (1995)
[21]
Zadeh, L.A.: Biological applications of the theory of fuzzy sets and systems. In: The
Proceedings of an International Symposium on Biocybernetics of Central Nervous
System, Boston, Little, Brown and Company (1969) 199-206
Applications of fuzzy set theory to the evaluation of cardiac function
- H Joly
- E Sanchez
- J Gouvernet
- J Valty
Joly, H., Sanchez, E., Gouvernet, J., Valty, J.: Applications of fuzzy set theory to the
evaluation of cardiac function. In Lindberg, D., Kaihara, S., eds.: Proceedings of the
MedInfo'80, North Holland Amsterdam (1980) 91-95
Application of fuzzy relations to medical decision making
- G Soula
- J Gouvernet
- A Barre
- J S Marco
Soula, G., Gouvernet, J., Barre, A., Marco, J.S.: Application of fuzzy relations to
medical decision making. In: Mediinfo 80. (1980)
Fuzzy sets. Information and Control
- L A Zadeh
Zadeh, L.A.: Fuzzy sets. Information and Control. 8 (1965) 338-353
Biological applications of the theory of fuzzy sets and systems
- L A Zadeh
Zadeh, L.A.: Biological applications of the theory of fuzzy sets and systems. In: The
Proceedings of an International Symposium on Biocybernetics of Central Nervous
System, Boston, Little, Brown and Company (1969) 199-206