R.S. Patil, P. Szolovits and W.B. Schwartz (1982). Modeling knowledge of the patient in acid-base and electrolyte disorders. In Artificial Intelligence in Medicine (P. Szolovits, ed.). Boulder, CO: Westview Press.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....are generated in order to explain the given observations. In a second step, we define a quality measure for ranking competing hypotheses. Abductive reasoning with set covering models has got a long tradition in diagnostic reasoning: One of the earliest approaches might be Patil s system ABEL [2], which describes abnormal behavior models with multi level nets. Edges between the state nodes can describe causal, associative or grouping knowledge. However, ABEL cannot represent uncertain information about causal relationships. The assessment of a diagnosis is defined by the completeness with ....

Ramesh S. Patil, Peter Szolovits, and William B. Schwartz. Modeling knowledge of the patient in acid-base and electrolyte disorders. In: Szolovits, P. (Ed.). Artificial Intelligence in Medicine, Westview Press, Boulder, Colorado, 1982.

....we propose an abductive reasoning step: Firstly, hypotheses are generated in order to explain the given observations. Secondly competing hypotheses are ranked using a quality measure. Reasoning with set covering models has got a long tradition in diagnostic reasoning: Early work was done by Patil [3] with his system ABEL, which implemented a comprehensive set covering representation including causal, associational and grouping relations. Reggia et al. 1] contributed a formal approach to set covering models and addressed the problem of hypothesis generation with a pre University of W ....

Ramesh S. Patil, Peter Szolovits, and William B. Schwartz. Modeling Knowledge of the Patient in Acid-Base and Electrolyte Disorders. In: Szolovits, P. (Ed.). Artificial Intelligence in Medicine, Westview Press, Boulder, Colorado, 1982.

.... for the diagnosis and treatment of eye disease; MYCIN [6] a rule based program for diagnosis and therapy selection for infectious diseases; the Digitalis Therapy Advisor [7] which aids the physician in prescribing the right dose of the drug digitalis and also explains its actions; and ABEL [8], a program that uses multi level pathophysiologic models for diagnosis of acid base and electrolyte disorders. A very popular expert system for ophthalmology is VIBES (Visual Impairments and Blindness Expert System) 9] VIBES consists of categories and was developed to help answer questions and ....

Patil RS, Szolovits P, and Schwartz WB. Modeling Knowledge of the Patient in Acid-Base and Electrolyte Disorders. in [1].

....domain. For example, such models describe the structural and functional interactions among components of a physical system, or the causal interactions among elements in a domain. Model based diagnosis was, in fact, already explored in the early systems INTER [17] SOPHIE [3] CASNET [43] and ABEL [27]. Although the introduction of the model based approach to building diagnostic applications had a significant impact on the field of diagnosis, it did not immediately provide deep insight into the process of diagnosis. Real fundamental understanding of the nature of the diagnostic process was ....

R.S. Patil, P. Szolovits, W.B. Schwartz, Modeling knowledge of the patient in acid-base and electrolyte disorders, in: P. Szolovits (Ed.), Artificial Intelligence in Medicine, Westview Press, Boulder, CO, 1982.

.... the broad domain of internal medicine [Miller et al. 1982; Bankowitz et al. 1989] CASNET, an expert system for the diagnosis and treatment of glaucoma [Kulikowski Weis, 1982; Weiss et al. 1978] ABEL, an expert system for the management of electrolyte and acid base derangements [Patil, 1981; Patil et al. 1982] and the well known MYCIN system, an expert system for the diagnosis and treatment of septicaemia and meningitis [Buchanan Shortliffe, 1984; Shortliffe, 1976] Many diagnostic systems have also been developed in technical fields, solving a wide variety of diagnostic problems. Early examples of ....

R.S. Patil, P. Szolovits and W.B. Schwartz (1982). Modeling knowledge of the patient in acid-base and electrolyte disorders. In Artificial Intelligence in Medicine (P. Szolovits, ed.). Boulder, CO: Westview Press.

....domain. For example, such models describe the structural and functional interactions among components of a physical system, or the causal interactions among elements in a domain. Model based diagnosis was, in fact, already explored in the early systems INTER [17] SOPHIE [3] CASNET [43] and ABEL [27]. Although the introduction of the model based approach to building diagnostic applications had a signi cant impact on the eld of diagnosis, it did not immediately provide deep insight into the process of diagnosis. Real fundamental understanding of the nature of the diagnostic process was ....

R.S. Patil, P. Szolovits and W.B. Schwartz, Modeling knowledge of the patient in acid-base and electrolyte disorders, in: P. Szolovits, ed., Articial Intelligence in Medicine (Westview Press, Boulder, CO, 1982).

....that is, one hypothesis must not have a subtractive effect on another. This is common in medicine, though. For example, in the domain of acid base disorders, one disease might explain an increased blood pH, and another might explain a decreased pH, but together the result might be a normal pH ([Patil et al. 1982] as cited in [Bylander et al. 1991] Although excluding interactions between hypotheses is a strong restriction, we may choose to do so, because it enables us to simplify the representation of the framework for abductive reasoning. In an independent abductive problem the relation e can be ....

R. S. Patil, P. Szolovits and W. B. Schwartz. Modeling knowledge of the patient in acid-base and electrolyte disorders. In: P. Szolovits, ed. Artifical Intelligence in Medicine, pp. 191--226. Westview Press, Boulder, CO, 1982.

.... the broad domain of internal medicine [Miller et al. 1982; Bankowitz et al. 1989] CASNET, an expert system for the diagnosis and treatment of glaucoma [Kulikowski Weis, 1982; Weiss et al. 1978] ABEL, an expert system for the management of electrolyte and acid base derangements [Patil, 1981; Patil et al. 1982] and the well known MYCIN system, an expert system for the diagnosis and treatment of septicaemia and meningitis [Buchanan Shortli e, 1984; Shortli e, 1976] Many diagnostic systems have also been developed in technical elds, solving a wide variety of diagnostic problems. Early examples of ....

R.S. Patil, P. Szolovits and W.B. Schwartz (1982). Modeling knowledge of the patient in acid-base and electrolyte disorders. In Articial Intelligence in Medicine (P. Szolovits, ed.). Boulder, CO: Westview Press.

....due to known causality. In this case we enter the area of causal modeling. The inference process follows the pathways of the causal net during problem solving. The causal net approach has its foundations in early medical (AIM )systems (CASNET [Weiss et al. 1978] CADUCEUS [Pople 1982] ABEL [Patil et al. 1982]) It supports the trace of known pathophysiological relations. In addition, it is a convenient way to model the basic constituents of the medical domain: anatomy [Horn 1989] physiology, pathophysiology, etiology and nosology [Senyk et al. 1989] thus providing a basis for AIM systems with the ....

....previously mentioned, there are different forms of abstraction: ffl There is abstraction of factual knowledge. Knowledge is represented at different levels of abstraction supporting the inference steps to be performed at different levels of detail. An early example is the ABEL system [Patil 1981, Patil et al. 1982]. The importance of abstraction steps for diagnosis was also recognized early in the CADUCEUS system for internal medicine [Pople 1982] by introducing planning links associating manifestations with abstract involvement structures. The use of abstractions during diagnosis helps to focus the ....

Patil R.S., Szolovits P., Schwartz W.B. (1982): Modeling Knowledge of the Patient in Acid-Base and Electrolyte Disorders, in Szolovits P.(ed.), Artificial Intelligence in Medicine, Westview Press, Boulder, CO.

....Cancellation can occur when one hypothesis can have a subtractive effect on another. This is common in medicine, e.g. in the domain of acid base disorders, one disease might explain an increased blood pH, and another might explain a decreased pH, but together the result might be a normal pH [17]. Different faults in different components can result in cancellation, e.g. a stuck at 1 input into an AND gate might account for an output of 1, but not if the other input is stuck at 0. Cancellation commonly occurs in the physical world. Newton s second law implies that forces can cancel each ....

R. S. Patil, P. Szolovits, and W. B. Schwartz. Modeling knowledge of the patient in acid-base and electrolyte disorders. In P. Szolovits, editor, Artificial Intelligence in Medicine, pages 191--226. Westview Press, Boulder, CO, 1982.

....generalization rules are explicitly written, as above. Specialization 1 works in the opposite direction and may require additional information. In the above example, if the problem is believed to be of a mechanical nature, 1 The specialization strategy is also referred to as refinement, e.g. [113]. then the following rules can be used to further specialize: Mechanical causes Acute back pain ) Prolapsed intervertebral disc Prolapsed intervertebral disc Abnormal Sensation ) Prolapsed intervertebral disc between L5 and S1 vertebrae For these rules to be applicable, additional ....

....is probably simpler to write a rule of the form: Chest Wound (Side=S) Survey Chest X Ray 2 Alpay [5] separates such strategies as problem refinement strategies, but that terminology may be confusing given that refinement was previously referring to any specialization. The explore strategy [113] can be viewed as a special case of a symptom based specialization strategy. In that strategy, more information is gathered when there is not enough information in the patient s case to generate hypotheses. 7.2.3 Confirmation and Elimination During the course of diagnosis, a variety of competing ....

Patil, R. S., Szolovits, P., and Schwartz, W. B., Modeling Knowledge of the Patient in Acid-Base and Electrolyte Disorders. in Artificial Intelligence in Medicine, P. Szolovits ed., Westview Press, 1982.

No context found.

R.S. Patil, P. Szolovits and W.B. Schwartz (1982). Modeling knowledge of the patient in acid-base and electrolyte disorders. In Artificial Intelligence in Medicine (P. Szolovits, ed.). Boulder, CO: Westview Press.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC