Haimowitz, I. J., and Kohane, I. S. (1996) "Managing temporal worlds for medical trend diagnosis," Artificial Intelligence in Medicine, Vol. 8, pp. 299-321.  Home/Search   Document Not in Database   Summary   Related Articles   Check

.... 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, 53], oncology [45, 44, 8, 41, 35] psychiatry [26] internal medicine [54, 43, 34, 13, 46] intensive care [55, 45, 37, 56, 57] cardiac surgery [10] orthopedics [6] urology [34] infectious diseases [35] anesthesiology [38, 58, 56] pediatrics [52] endocrinology [59] Various clinical tasks are ....

.... areas: cardiology [49, 50, 11, 30, 51, 47, 52, 53] oncology [45, 44, 8, 41, 35] psychiatry [26] internal medicine [54, 43, 34, 13, 46] intensive care [55, 45, 37, 56, 57] cardiac surgery [10] orthopedics [6] urology [34] infectious diseases [35] anesthesiology [38, 58, 56] pediatrics [52], endocrinology [59] Various clinical tasks are supported by the systems proposed in literature: diagnosis [6, 60, 26] therapy administration and monitoring [40, 36, 53] protocol and guideline based therapy [44, 35, 13, 48] and patient management [27, 61, 62, 34, 29, 30] In the paper, ....

[Article contains additional citation context not shown here]

Haimowitz IJ, Kohane IS. Managing temporal worlds for medical trend diagnosis. In [16]: 299322.

....than a single pathological value at the time of observation. The online detection of qualitative patterns such as artifacts, level changes and trends is important for assessing the patient s state. Several approaches for qualitative data abstraction have been suggested. Haimowitz and Kohane [10] [11] fit trend templates to the data, which are predefined functional forms of relevant patterns. Miksch et al. 12] 1996) propose to measure deviations of measurements from a given target range. Makivirta [1] suggests to preprocess the data by a median filter, which is common practice in signal ....

....have been developed and applied to clinical problems, the most obvious being the first order approximation with a straight line. Although higher order polynomials have also been used, their applications are limited to cases where such a relation is assumed to exist. Haimowitz and coworkers [10] [11] developed TrenDx using the concept of trend templates for diagnosing pediatric growth disorders and detecting clinically significant trends in hemodynamics and blood gases in intensive care units. A trend template denotes a time varying pattern in multiple variables common to a diagnostic ....

Haimowitz, I.J., and Kohane, I.S. (1996), "Managing temporal worlds for medical trend diagnosis," Art. Intel. Med., vol. 8, pp. 299-321.

....are called temporal abstractions. For example temporal reasoning is central in establishing the existence of some delay or prematurity in the unfolding of some ossification process, or the existence of some trend. Temporal data abstraction is presently attracting considerable research interest [54, 63, 70, 90, 110, 118, 142, 150, 151], as a fundamental intermediate reasoning process for the intelligent interpretation of temporal data in support of tasks such as diagnosis, monitoring, etc. Background domain knowledge [74] can be e#ectively utilized in the context of temporal data abstraction. 2.1 The need for data abstraction ....

....proposal has been demonstrated through its application to a number of medical domains (therapy for insulin dependent diabetes, protocol based care of AIDS and of chronic GVHD, and monitoring of children s growth) with promising results. 2.4. 2 Haimowitz and Kohane s approach Haimowitz and Kohane [54] have developed a system, TrenDx, with the specific focus of medical trend diagnosis. Generic trends are defined through the notion of a trend template that gives great power of expression. This is both the strength and the limitation of this approach. Strength because of the higher power of ....

Haimowitz, I.J. and Kohane, I.S., "Managing temporal worlds for medical trend diagnosis." Artificial Intelligence in Medicine, 8(3): 299--321 (1996).

.... low level numerical measurements (the level of the equipment) and high level qualitative principles (the level of medical reasoning) While knowledge based systems have mostly been applied for diagnosis and therapy planning (e.g. 28] 19] some systems also aim at on line patient monitoring [7, 21, 26]. Morik et al.: Knowledge Discovery and Knowledge Validation in Intensive Care 3 of 32 Methods that have proved their value in handling low frequency patient data are not applicable for on line monitoring [21] Quantitative measurements and qualitative reasoning have to be integrated in a system ....

....system required more than 25 person years. It is a propositional rule base without a mechanism for consistency checking or matching rules and data. All validation efforts started only after the knowledge base had been completed. Temporal reasoning is taken seriously in other developments [4, 7, 21, 28]. The Stanford approach uses an explicit time ontology for low frequency data [28] This approach is not feasable for our application. The VIE VENT system is comparable with our approach in that it combines numerical data and a knowledge base [21] Qualitative abstractions are derived for ....

[Article contains additional citation context not shown here]

I. J. Haimowitz, and I. S. Kohane, Managing temporal worlds for medical trend diagnosis, Artificial Intelligence in Medicine 8 (1996), 299-321.

No context found.

Haimowitz, I. J., and Kohane, I. S. (1996) "Managing temporal worlds for medical trend diagnosis," Artificial Intelligence in Medicine, Vol. 8, pp. 299-321.

No context found.

Haimowitz, I. J., and Kohane, I. S. (1996) "Managing temporal worlds for medical trend diagnosis," Artificial Intelligence in Medicine, Vol. 8, pp. 299-321.

No context found.

Haimowitz, I. J., and Kohane, I. S. (1996) "Managing temporal worlds for medical trend diagnosis," Artificial Intelligence in Medicine, Vol. 8, pp. 299-321.

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