Shahar, Y. and Musen, M. (1996) "Knowledge-Based Temporal Abstraction in Clinical Domains," Artificial Intelligence in Medicine, Vol. 8, pp. 267-298  Home/Search   Document Details and Download   Summary   Related Articles   Check

....is linguistical description about primtive patterns occurred in channel FSGR . Channel name: FSGR (Linguistic format) Very big downward spike at 21:50:08, 21:51:36, 21:53:36, and 22:36:05. Big erratic spike at 23:56:17. 3.3 High Level Abstraction. This function is mainly based on KBTA method [4] [5] Currently it carries out vertical and horizontal aggregation. Vertical aggregation is based on simultaneous check and horizontal aggregation involves joining nearby patterns to form a main set of patterns. The following is the results of high level abstracton on the sample data set. ....

....by SumTime Turbine. Another is let experts write summary about the same scenario and then compares the two summaries to score it . 5 Related Work There are a number of systems, which are related with summarised time series data, of which are RESUME, GoalGetter, and SumTime Mousam. RESUME [4] uses KBTA method to create temporal abstractions from medical data. The KBTA framework provides the most comprehensive starting point for generating summaries of temporal data, however, doesn t produce textual summaries. GoalGetter [7] is a data to speech system, which generates Dutch spoken ....

Y. Shahar, M. A. Musen (1996) " Knowledge-Based Temporal Abstraction in Clinical Domains" Artificial intelligence in Medicine 1996 8(3): 267-298

....information, by using a piecewise model combined with segmentation and agglomerative clustering. In Oates et al. OJC98] a system is applied to extracting patterns from network failures, by looking at all possible sequences of events and keeping tabs on the frequency of these events. Shahar [SM95] suggests an expert system architecture for knowledge based temporal abstraction and also suggests that this system could be used for learning, though he does not actually do so. He then applies the techniques to clinical domains. Paliouras [Pal97] discusses refinement of temporal parameters in ....

Yuval Shahar and Mark A. Musen. Knowledge-based temporal abstraction in clinical domains. Technical report, Stanford University, 1995.

....tables (# =6.25, p 0.025) 7. Medical application based on Paint Strips We employed Paint Strips in a system for the visual definition and use of temporal clinical abstractions. A temporal abstraction provides a concise and high level description of a collection of time stamped raw data [18]. In medical informatics, temporal abstraction plays a central role in supplying care providers with data at a suitable level for supporting decision making. Temporal abstraction on clinical data has thus been investigated in some depth in recent years. In this context, Shahar and Musen [18] ....

....data [18] In medical informatics, temporal abstraction plays a central role in supplying care providers with data at a suitable level for supporting decision making. Temporal abstraction on clinical data has thus been investigated in some depth in recent years. In this context, Shahar and Musen [18] proposed a general framework for abstraction of time stamped data, called the Knowledge Based Temporal Abstraction (KBTA) Method. The output of KBTA includes the basic abstractions of type state, gradient, rate (e.g. LOW, DECREASING, and FAST are some abstractions of the three types for values ....

[Article contains additional citation context not shown here]

Y. Shahar and M.A. Musen, Knowledge-based temporal abstraction in clinical domains, Artificial Intelligence in Medicine 8 (1996) 267-298.

....description about primitive patterns occurring in channel FSGR in Figure 2. Channel name: FSGR (Linguistic format) Very big downward spike at 21:50:08, 21:51:36, 21:53:36, and 22:36:05. Big erratic spike at 23:56:17. 3.3 High Level Abstraction. This function is mainly based on KBTA method [4] [5] Currently it carries out vertical and horizontal aggregation. Vertical aggregation is based on simultaneous check and horizontal aggregation involves joining nearby patterns to form a main set of patterns. The following is the results of high level abstracton on the sample data set. ....

....Another is let experts write summaries about the same scenario and then compares the computer generated and human writers summaries. 5 Related Work There are a number of systems, which are related with summarised time series data, of which are RESUME, GoalGetter, and SumTime Mousam. RESUME [4] uses KBTA method to create temporal abstractions from medical data. The KBTA framework provides the most comprehensive starting point for generating summaries of temporal data. However, it doesn t produce textual summaries. GoalGetter [7] is a data to speech system, which generates Dutch spoken ....

Y. Shahar, M. A. Musen (1996), Knowledge-Based Temporal Abstraction in Clinical Domains, Artificial Intelligence in Medicine 1996 8(3): 267-298

....to extract from huge amount of temporal information its most relevant features. In the medical domain, TAs are successfully used to describe patients states holding over time periods like hypoglycemia at dinner for a week or hyperglycemia associated to presence of glycosuria at breakfast [15]. In our application we resort to TAs to summarize in an abstracted and comprehensible form for the physicians the results of the TS structural analysis. The problem solving method underlying TAs is based on an explicit ontology and a model of time adapted from [4] and described in detail in ....

Shahar, Y., Musen, M.A.: Knowledge-Based Temporal Abstraction in Clinical Domains. Artificial Intelligence in Medicine. 8 (1996) 267-298.

....and by a periodic (with period equal to one day) course of BGL. The characteristic daily BGL pattern that summarizes the typical patient s response to the therapy is called Modal Day and is usually derived by the frequency histograms of BGL measurements in the different times of the day (see [4, 12, 20, 28] for a detailed discussion) Looking for modal days and trends can be viewed as a search for a prototypical structure in the data, and can be faced with a TS technique known as structural analysis. Structural filtering has been proposed in the Diabetes field by Deutsch et al. 12] and their ....

....high number of approaches have been presented for the analysis of data coming from Diabetic patients home monitoring. A number of such approaches have been devoted to the prediction of BGL time series [24, 22, 2] while few of them were oriented to an overall interpretation of the patient behavior [20, 31, 28], including 18 some commercial products, like Camit Pro TM or Eurotouch TM. While the difference of our approach with respect to the former class of such system is quite clear, a brief comment should be given to highlight the differences and similarities of our approach with respect to the ....

[Article contains additional citation context not shown here]

Y. Shahar, and M.A. Musen, Knowledge-Based Temporal Abstraction in Clinical Do- mains. Artificial Intelligence in Medicine 8 (1996) 267-298.

....analysis are timeseries analysis, control theory, and probabilistic or fuzzy classifiers [2] These approaches have a lot of shortcomings, which lead to applying knowledge based techniques to derive qualitative values or patterns of current and past situations of a patient. The R ESUM E project [18] performs temporal abstraction of timestamped data without predefined trends. The system is based on a knowledge based temporal abstraction method. Larizza et al. 8] have developed methods to 2 detect predefined courses in a time series. Complex abstraction allows to detect specific temporal ....

Y. Shahar and M. A. Musen, `Knowledge-based temporal abstraction in clinical domains', Artificial Intelligence in Medicine, 8(3), 267--298, (1996).

No context found.

Shahar Y, Musen, MA. Knowledge-based temporal abstraction in clinical domains. Artif Int Med, 1996; 8(3): 267--298.

....very different domain, monitoring of traffic control actions. The method we reused is the knowledge based temporal abstraction method [1] which solves the task of abstraction of high level concepts and patterns from time oriented data, and which was applied previously mainly to clinical domains [2]. We first show how we have applied that method to solve both the temporal and spatial abstraction tasks in the traffic control domain. We then generalize our results by showing how, using an existing methodology for construction of knowledge based systems, a spatiotemporal abstraction method ....

....functions (e.g. the meaning of the value LOW of the hemoglobin state abstraction depends on the context) 0 400 200 100 50 . 1000 2000 D ( D ( Granulocyte counts . Time (days) Platelet counts PAZ protocol M[0] M[1]M[2]M[3] M[0] M[0] BMT Expected CGVHD Figure 1: Abstraction of platelet and granulocyte values during administration of the PAZ clinical protocol for treating patients who have chronic graft versus host disease (CGVHD) The time line starts with a bone marrow transplantation (BMT) event. The ....

[Article contains additional citation context not shown here]

Shahar Y and Musen MA. Knowledge-based temporal abstraction in clinical domains. Artif Intell Med 1996; 8(3): 267-298.

....of domain specific properties of the particular data, such as meaningful classifications into more abstract patterns, knowledge of whether similar patterns can be joined or should be considered as separate episodes, and an indication of how data should be displayed. We have previously shown [29, 34] that such temporal abstraction knowledge can be acquired and represented formally within knowledge bases specific to each clinical domain. Thus, knowledge based summarization, visualization, and exploration of time oriented clinical data and their abstractions requires an integrated solution to ....

....e.g. monitoring of diabetes therapy) and their IS A relations; and (5) all relations between inducing propositions and induced contexts. 2.2. RSUM: an implementation of knowledgebased temporal abstraction We have implemented the knowledge based temporalabstraction method as the RSUM system [33, 34]. RSUM generates temporal abstractions, given timestamped data and events, and the domain s temporalabstraction ontology. We tested the RSUM system in several different clinical and engineering domains: protocol based care (experimental therapy of AIDS patients, therapy of chronic ....

[Article contains additional citation context not shown here]

Shahar, Y., and Musen, M.A. (1996). Knowledge-based temporal abstraction in clinical domains. Artificial Intelligence in Medicine 8 (3), 267--298.

....developed for the protocol based therapy planning task. Separating the temporal abstraction subtask from the monolithic formulation of the ESPR method in PROTG I allowed us to develop a temporalabstraction subsystem that has been used in several medical subspecialties outside the AIDS domain [20] [34] . Recently, we applied the skeletal plan refinement method to configuration tasks outside medicine, such as the problem of selecting equipment from a rental center. In this domain, classes of rental equipment such as trucks and trailers are analogous to the medication hierarchy; formulas for ....

Y. Shahar, A.K. Das, S.W. Tu, and M.A. Musen, Knowledge-based temporal abstraction in clinical management tasks, in: Spring Symposium on Artificial Intelligence in Medicine (Stanford, CA, 1994) in press.

No context found.

Shahar Y, Musen MA. Knowledge-based temporal abstraction in clinical domains. Artif Intell Med. 1996;8:267-98.

.... 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 ....

.... clinical data, such as: management of time oriented data stored in medical records of ambulatory or hospitalized patients [27, 28, 29, 11, 12, 30, 31, 32, 33, 34, 35, 36] prediction of future values of clinical data, given past trends [37, 38, 39] abstraction of time oriented clinical data [8, 40, 41, 13, 42] time oriented knowledge based decision support systems, such as systems supporting diagnosis, monitoring, or therapy planning [43, 26, 6, 44, 45, 46, 47, 14, 40, 48] Studies of time oriented applications have been performed in multiple clinical areas: cardiology [49, 50, 11, 30, 51, 47, 52, ....

[Article contains additional citation context not shown here]

Shahar Y, Musen MA. Knowledge-based temporal abstraction in clinical domains. In [16]: 267-298.

....in which they were created. 3. Input data should be used and incorporated in the interpretation even if they arrive out of temporal order (e.g. a laboratory result from last Tuesday arrives today) Thus, the past can change our view of the present. This phenomenon has been called a view update [7]. Furthermore, new data should enable us to reflect on the past; thus, the present (or future) can change our interpretation of the past, a property referred to as hindsight [8] 4. Several possible interpretations of the data might be reasonable, each depending on additional factors that are ....

....maintenance, reuse, and sharing. The KBTA method has been implemented by the RSUM system and evaluated in several clinical domains, such as guideline based care of oncology and AIDS patients, monitoring of children s growth, and management of patients who have insulin dependent diabetes [7]. The KBTA method proposes particular ontology (a theory of concepts and relations among them) of time, time oriented objects, and temporal reasoning knowledge. Another example of such a general ontology is Keravnou s time object ontology for medical tasks [10] Other approaches have been ....

Shahar, Y. and Musen, M.A.: Knowledge-based temporal abstraction in clinical domains. Artificial Intelligence in Medicine 8(3) (1996) 267--298.

No context found.

Shahar Y, Musen MA. Knowledge-based temporal abstraction in clinical domains. Artificial Intelligence in Medicine, 1996; 8:267-298.

....should enable reusing its domain independent knowledge for solving the TA task in other domains, and enable sharing of domainspecific knowledge with other tasks in the same domain. The framework that we are using for solving the TA task is based on our work on temporal abstraction mechanisms [1, 2, 3, 4, 5]. We have defined a general problem solving method [6] for interpreting data in time oriented domains, with clear semantics for both the method and its domain specific knowledge requirements: the knowledge based temporal abstraction (KBTA) method. The KBTA method comprises a knowledge level ....

....and task. We have implemented the KBTA method as the RSUM system [2] and applied it with encouraging results to several clinical domains such as chronic graft versus host disease [2] monitoring of childrens growth [8] therapy of AIDS patients [3] and therapy of patients who have diabetes [4]. We also have used the KBTA method and the RSUM system to model and solve a spatiotemporal traffic monitoring task [9, 10] The RSUM system is currently used within the Tzolkin temporal mediator server, a part of the EON architecture for support of clinical guidelinebased therapy [11] 3. THE ....

[Article contains additional citation context not shown here]

Y. Shahar and M.A. Musen, Knowledge-based temporal abstraction in clinical domains, Artificial Intelligence in Medicine 8(3) (1996) 267298.

No context found.

Shahar, Y. and Musen, M. (1996) "Knowledge-Based Temporal Abstraction in Clinical Domains," Artificial Intelligence in Medicine, Vol. 8, pp. 267-298

No context found.

Shahar, Y. and Musen, M. (1996) "Knowledge-Based Temporal Abstraction in Clinical Domains," Artificial Intelligence in Medicine, Vol. 8, pp. 267-298

No context found.

Shahar, Y., Musen, M.A.: Knowledge-Based Temporal Abstraction in Clinical Domains. Artificial Intelligence in Medicine 8, (1996) 267-298

No context found.

Shahar, Y., Musen, MA.: Knowledge-Based Temporal Abstraction in Clinical Domains. Artificial Intelligence in Medicine 8, (1996) 267-298

No context found.

Shahar, Y. and Musen, M. (1996) "Knowledge-Based Temporal Abstraction in Clinical Domains," Artificial Intelligence in Medicine, Vol. 8, pp. 267-298

No context found.

Shahar, Y. and Musen, M. A. (1996). Knowledge-based temporal abstraction in clinical domains. Artificial Intelligence in Medicine, 8:267--298.

No context found.

Shahar Y, Musen MA. Knowledge-based temporal abstraction in clinical domains. Artificial Intelligence in Medicine 1996;8:267-298.

No context found.

Shahar Y, Musen MA. Knowledge-Based Temporal Abstraction in Clinical Domains. Artificial Intelligence in Medicine. 1996; 8: 267-298.

No context found.

Shahar Y, Musen MA. Knowledge-based temporal abstraction in clinical domains. Artif Intell Med. 1996;8(3):267-98.

First 50 documents  Next 50

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