Kohane, I.S. (1987). Temporal reasoning in medical expert systems. Technical Report 389, Laboratory of Computer Science, Massachusetts Institute of Technology, Cambridge, MA.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....temporal abstraction, information visualization, and knowledge acquisition. Several approaches have been applied to the task of abstraction of time oriented data into higher level concepts, especially in medical domains, in which both large amounts of data and considerable knowledge are available [9, 10, 13, 15, 16, 19, 28]. None of these approaches, however, emphasized the need for a formal representation that facilitates acquisition, maintenance, sharing, and reuse of the required temporal abstraction knowledge; this emphasis is the focus of our previous and current research. Furthermore, previous ....

Kohane, I.S. (1987). Temporal reasoning in medical expert systems. Technical Report 389, Laboratory of Computer Science, Massachusetts Institute of Technology, Cambridge, MA.

.... features of the represented real world [3] and when reasoning about time oriented data [4] Researchers in the medical informatics field investigated temporal data modeling, temporal maintenance and temporal reasoning, to support both electronic medical records and medical expert systems [5, 6, 7, 8, 9, 10, 11, 12, 13, 14]. One indication of the significance of research on timeoriented systems in medicine is that the level and the amount of scientific works in this area motivated two different special issues of the journal ################################### [15, 16] Another indication is that research focusing on ....

Kohane IS. Temporal reasoning in medical expert systems. Technical Report 389, Laboratory of Computer Science, Massachusetts Institute of technology, Cambridge, MA, 1987.

....parameter propositions are sharable, for all parameter values. This phenomenon was enabled by the fact that all contexts in VM had the same vocabulary, in particular with respect to the parameters domain of values and its meaning. The TrenDx system of Haimowitz and Kohane [24] builds on Kohanes [25] constraint satisfaction temporal utilities package, and defines domain specific patterns called trend templates (TTs) TrenDx is useful in detecting that the data is consistent with one or more TTs, including TTs of which only a part is observed. Like RSUM, TrenDx assumes implicitly an ....

I.S. Kohane, Temporal reasoning in medical expert systems. Technical Report 389, Laboratory of Computer Science, Massachusetts Institute of Technology, Cambridge, MA, (1987).

....are described in terms of various standard types of curves, and we are expanding the original representation to include statistical information as well. The representation is supported by a temporal utility package (TUP) that propagates temporal bound inferences among related points and intervals [17, 16]. The value component characterizes constraints on individual data values and propositions and on computed trends in time ordered data, and specifies constraints that must hold among different data streams. In matching a trend template to data, two tasks are carried out simultaneously. First, the ....

I. S. Kohane. Temporal reasoning in medical expert systems. TR 389, Massachusetts Institute of Technology, Laboratory for Computer Science, 545 Technology Square, Cambridge, MA, 02139, Apr. 1987.

....are described in terms of various standard types of curves, and we are expanding the original representation to include statistical information as well. The representation is supported by a temporal utility package (TUP) that propagates temporal bound inferences among related points and intervals [17, 16]. The value component characterizes constraints on individual data values and propositions and on computed trends in time ordered data, and specifies constraints that must hold among different data streams. In matching a trend template to data, two tasks are carried out simultaneously. First, the ....

I. S. Kohane. Temporal reasoning in medical expert systems. In R. Salamon, B. Blum, and M. Jrgensen, editors, MEDINFO 86: Proceedings of the Fifth Conference on Medical Informatics, pages 170--174, Washington, Oct. 1986. North-Holland.

.... performing a TA task that were implemented mainly for clinical domains include Fagans ventilation management (VM) system [10] Blums Rx system for knowledge discovery from time oriented clinical databases [3] Downs summarization program for medical records [8] Kohanes temporal utilities package [18]; de Zegher Geets IDEFIX system for summarizing patient visits [7] Russ temporal control structure system [27] Kahns TOPAZ system [17] the Guardian project [14] Haimovitz and Kohanes TrenDx system [13] and Larizzas TA module in the M HTP project [21] Several of the systems mentioned above ....

....of temporal properties of the domain. In contrast, the RSUM domain independent TA mechanisms perform all of the TA, given a (declarative) representation of the domains TA ontology. The TrenDx system of Haimowitz and Kohane [13] builds on Kohanes constraint satisfaction temporalutilities package [18], and defines domain specific patterns called trend templates (TTs) TrenDx is useful in detecting that the data is consistent with one or more TTs, including TTs of which only a part is observed. The goal of TrenDx is different from that of RSUM. TrenDx does not create any intermediate ....

I.S. Kohane, Temporal reasoning in medical expert systems. Technical Report 389, Laboratory of Computer Science, Massachusetts Institute of technology, Cambridge, MA, 1987.

....plays a crucial role in many areas of reasoning such as program verification, scheduling, planning and natural language understanding. Since the provocative paper on The Naive Physics manifesto by Pat Hayes [8] a great deal of research has been done in the area of qualitative temporal reasoning [2, 3, 4, 5, 9, 15, 1, 7, 11, 14]. Two well understood approaches for representing temporal information (as qualitative relations between interval and time points) are interval algebra by Allen [2] and point algebra by Vilain and Kautz [15] Motivated by computational advantages, Peter van Beek proposed a restricted algebra ....

I.S. Kohane. Temporal Reasoning in Medical Expert Systems. MIT Laboratory for Computer Science, Technical Report TR-389, Cambridge, 1987.

....in real world applications [15] Both IA and PA consider events as unique occurrences and are not concerned with events that occur repeatedly. However, the repeated occurrence of events is a common phenomena in many applications such as electronic recording of cardiac cycles in medical diagnosis [4], reasoning with patient medical histories [2] and personal scheduling [13] Ladkin [5] and Morris, Shoaff and Khatib [10, 3] proposed to deal with such temporal information in terms of sets of interval events that occur more than once, called non convex intervals (NCIs) In this formalism, an ....

....Implementations of Temporal Reasoning While there have been extensive studies on the theoretical foundations of representation and reasoning with time dependent information, very few attempts have been made to develop practical temporal reasoning systems. 14 Temporal Utility Package (TUP) [4] includes the implementation of IA relations as conjunctions of end point relations and an applies these in a time varying medical domain. In TUP, information about events is stored as relations between the absolute times of the start and end points. However, the system can only handle atomic IA ....

I.S. Kohane. Temporal Reasoning in Medical Expert Systems. PhD thesis, MIT Laboratory for Computer Science, Technical Report TR-389, Cambridge, 1987.

....plays a crucial role in many areas of reasoning such as program verification, scheduling, planning and natural language understanding. Since the provocative paper on The Naive Physics manifesto by Pat Hayes [7] a great deal of research has been done in the area of qualitative temporal reasoning [1, 2, 3, 4, 9, 15, 8, 6, 11, 14]. Two well understood approaches for representing temporal information (as qualitative relations between interval and time points) are interval algebra by Allen [1] and point algebra by Vilain and Kautz [15] Motivated by computational advantages, Peter van Beek proposed a restricted algebra ....

I.S. Kohane. Temporal Reasoning in Medical Expert Systems. MIT Laboratory for Computer Science, Technical Report TR-389, Cambridge, 1987.

....have been used either embodied within an application system or as the basis for a temporal reasoner in charge of providing temporal functionalities to an application system. TR has been applied in planning systems [8, 106, 92, 5] natural language understanding [120, 15, 17, 44] or expert systems [59, 31, 11, 88, 58, 94, 95], to cite few of them. A set of ontological and representational issues has to be considered in defining a TR system. The rest of this article is devoted to presenting and analysing them. For each I discuss the advantages and problems of the different choices that one can make 1 . Therefore, in ....

I. S. Kohane, editor. Temporal Reasoning in Medical Expert Systems. Massachussetts Institute of Technology, 1987.

....2. 3 Relation to Other Work Major work in AI has focused on defining relationships between differing time intervals and creating a calculus for the manipulation of these relations [1, 2, 3, 14, 15] the use of constraint propagation techniques to narrow ambiguous bounds on temporal statements [13, 17]. Tcs does not examine these issues. Instead, it assumes that the time data is available and the extent of any periods of validity can be calculated exactly. Medical applications have included using a time oriented database to search for causal relationships [4] the interpretation of clinical ....

Isaac S. Kohane. Temporal reasoning in medical expert systems. In Salamon et al. [21], pages 170--174.

....led unexpectedly to a simple but reasonable prognostic ability, as PIP could use current data to predict future instances of disease. Our interest in temporal reasoning has continued through the doctoral Guardian Angel Patient Centered Health Information Systems 30 work of Kohane [Koha86, Koha87] exploring temporal constraints in diagnostic reasoning; Russ [Russ90, Russ91] who designed a control structure that supports reasoning about unreliable streams of time oriented data and applied it to diabetic ketoacidosis; and Haimowitz [Haim93, Haim93a] who studies trend detection in ....

....in 1985. He joined the Harvard Medical School faculty and the staff of Children s Hospital in July, 1992. He holds a medical degree and practices pediatric endocrinology. His PhD was awarded for his research in artificial intelligence in medicine and for his work on the Temporal Utility Package [Koha87] and its application to medical diagnosis. Dr. Kohane currently spends 80 of his time on work in medical informatics. In 1991 he completed the implementation of an on line medical chart (the Clinician s Workstation CWS) Koha90] for the Division of Endocrinology. This system has now been in ....

. Kohane, I. S. Temporal Reasoning in Medical Expert Systems. MIT-LCS TR-389, 1987.

....the (approximate) time boundary between these two conditions. Its best estimate will minimize deviations from the constraints. Second, the matcher computes an overall measure of the quality of fit from the deviations. The trend matching algorithms rely on the Temporal Utility Package (TUP) 8] [9] that propagates temporal bound inferences among related points and intervals. III. Some comparisons The preceding examples illustrate some of the limitations that current attack recognition languages appear to su#er, but di#erent extant languages exhibit di#erent limitations. In this section, ....

Isaac S. Kohane, "Temporal reasoning in medical expert systems, " in MEDINFO 86: Proceedings of the Fifth Conference on Medical Informatics, R. Salamon, B. Blum, and M. Jrgensen, Eds., Washington, Oct. 1986, pp. 170--174, North-Holland.

....find the (approximate) time boundary between these two conditions. Its best estimate will minimize deviations from the constraints. Second, the matcher computes an overall measure of the quality of fit from the deviations. The trend matching algorithms rely on the Temporal Utility Package (TUP) [8], 9] that propagates temporal bound inferences among related points and intervals. III. Some comparisons The preceding examples illustrate some of the limitations that current attack recognition languages appear to su#er, but di#erent extant languages exhibit di#erent limitations. In this ....

Isaac S. Kohane, "Temporal reasoning in medical expert systems, " TR 389, Massachusetts Institute of Technology, Laboratory for Computer Science, 545 Technology Square, Cambridge, MA, 02139, Apr. 1987.

....nd the (approximate) time boundary between these two conditions. Its best estimate will minimize deviations from the constraints. Second, the matcher computes an overall measure of the quality of t from the deviations. The trend matching algorithms rely on the Temporal Utility Package (TUP) 8] [9] that propagates temporal bound inferences among related points and intervals. III. Some comparisons The preceding examples illustrate some of the limitations that current attack recognition languages appear to su er, but di erent extant languages exhibit di erent limitations. In this section, ....

Isaac S. Kohane, \Temporal reasoning in medical expert systems, " in MEDINFO 86: Proceedings of the Fifth Conference on Medical Informatics, R. Salamon, B. Blum, and M. Jrgensen, Eds., Washington, Oct. 1986, pp. 170-174, North-Holland.

....nd the (approximate) time boundary between these two conditions. Its best estimate will minimize deviations from the constraints. Second, the matcher computes an overall measure of the quality of t from the deviations. The trend matching algorithms rely on the Temporal Utility Package (TUP) [8], 9] that propagates temporal bound inferences among related points and intervals. III. Some comparisons The preceding examples illustrate some of the limitations that current attack recognition languages appear to su er, but di erent extant languages exhibit di erent limitations. In this ....

Isaac S. Kohane, \Temporal reasoning in medical expert systems, " TR 389, Massachusetts Institute of Technology, Laboratory for Computer Science, 545 Technology Square, Cambridge, MA, 02139, Apr. 1987.

....either as offsets of the form (min max) from a landmark point, or offsets of the form (min max) from another interval s begin or end point. The temporal representation is supported by a temporal utility package (TUP) that propagates temporal bound inferences among related points and intervals [17, 16]. The value component characterizes constraints on individual data values and propositions and on computed trends in time ordered data, and specifies constraints that must hold among different data streams. To illustrate the representation, Figure 4 presents portions of a simplified trend ....

I. S. Kohane. Temporal reasoning in medical expert systems. TR 389, Massachusetts Institute of Technology, Laboratory for Computer Science, 545 Technology Square, Cambridge, MA, 02139, Apr. 1987.

....either as offsets of the form (min max) from a landmark point, or offsets of the form (min max) from another interval s begin or end point. The temporal representation is supported by a temporal utility package (TUP) that propagates temporal bound inferences among related points and intervals [17, 16]. The value component characterizes constraints on individual data values and propositions and on computed trends in time ordered data, and specifies constraints that must hold among different data streams. To illustrate the representation, Figure 4 presents portions of a simplified trend ....

I. S. Kohane. Temporal reasoning in medical expert systems. In R. Salamon, B. Blum, and M. Jrgensen, editors, MEDINFO 86: Proceedings of the Fifth Conference on Medical Informatics, pages 170--174, Washington, Oct. 1986. NorthHolland.

....are declared either as: offsets of the form (min max) from a landmark point, or offsets of the form (min max) from another interval s begin or end point. The representation is supported by a temporal utility package (TUP) that propagates temporal bound inferences among related points and intervals [27, 26]. The value component characterizes constraints on individual data values and propositions and on computed trends in timeordered data, and specifies constraints that must hold among different data streams. In matching a trend template to data, two tasks are carried out simultaneously. First, the ....

....discrepant information arose. Later versions introduced a simple model of time, categorizing both patient data and a hypothesis oriented time line along the dimension: past, recent past, now, near future, future. Our interest in temporal reasoning has continued through the doctoral work of Kohane [27, 26], exploring temporal constraints in diagnostic reason25 ing and Temporal Utility Package (TUP) Russ [42, 43, 44, 45] who designed a control structure that supports reasoning about unreliable streams of time oriented data and applied it to diabetic ketoacidosis; and Haimowitz [21, 20] who ....

I. S. Kohane. Temporal reasoning in medical expert systems. TR 389, Massachusetts Institute of Technology, Laboratory for Computer Science, 545 Technology Square, Cambridge, MA, 02139, Apr. 1987.

....are declared either as: offsets of the form (min max) from a landmark point, or offsets of the form (min max) from another interval s begin or end point. The representation is supported by a temporal utility package (TUP) that propagates temporal bound inferences among related points and intervals [27, 26]. The value component characterizes constraints on individual data values and propositions and on computed trends in timeordered data, and specifies constraints that must hold among different data streams. In matching a trend template to data, two tasks are carried out simultaneously. First, the ....

....discrepant information arose. Later versions introduced a simple model of time, categorizing both patient data and a hypothesis oriented time line along the dimension: past, recent past, now, near future, future. Our interest in temporal reasoning has continued through the doctoral work of Kohane [27, 26], exploring temporal constraints in diagnostic reason25 ing and Temporal Utility Package (TUP) Russ [42, 43, 44, 45] who designed a control structure that supports reasoning about unreliable streams of time oriented data and applied it to diabetic ketoacidosis; and Haimowitz [21, 20] who ....

I. S. Kohane. Temporal reasoning in medical expert systems. In R. Salamon, B. Blum, and M. Jørgensen, editors, MEDINFO 86: Proceedings of the Fifth Conference on Medical Informatics, pages 170--174, Washington, Oct. 1986. North-Holland.

No context found.

Kohane, I.S.: Temporal reasoning in medical expert systems. Technical Report 389, Laboratory of Computer Science, Massachusetts Institute of technology, Cambridge, MA, 1987.

No context found.

Kohane IS. Temporal reasoning in medical expert systems. Technical Report: Massachusetts Institute of Technology; 1987 May 1987. Report No.: TR-389.

No context found.

Kohane IS. Temporal reasoning in medical expert systems. In: Salamon R, Blum B, Jorgensen M (eds). MEDINFO '86: Proceedings of the Fifth Conference on Medical Informatics. Amsterdam: North-Holland. 1984:170--74.

No context found.

I.S. Kohane. Temporal reasoning in medical expert systems. Technical Report 389, Laboratory of Computer Science, Massachusetts Institute of Technology, Cambridge, MA, 1987.

No context found.

Kohane, I.S.: Temporal Reasoning in Medical Expert Systems. MIT Laboratory for Computer Science, Technical Report TR-389, Cambridge. 1987

First 50 documents

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