Managing temporal worlds for medical trend diagnosis

The medical trend diagnosis system TrenDx has been applied as a prototype for diagnosing pediatric growth disorders, and as a proof of concept in detecting clinically significant trends in hemodynamics and blood gases in intensive care unit patients. TrenDx diagnoses trends by matching patient data to patterns of normal and abnormal trends called trend templates that define disorders as typical patterns of relevant variables. These patterns consist of a partially ordered set of temporal intervals with uncertain endpoints. Bound to each temporal interval are value constraints on real-valued functions of measurable parameters. The temporal uncertainty in trend templates allows TrenDx to conclude both what trend pattern best matches the data and also when significant landmarks and phase transitions have occurred within the best matching trend. The temporal uncertainty in trend templates requires that TrenDx consider alternate temporal worlds in monitoring patient data. The number of temporal worlds grows worst case polynomially in the number of time slices of data. To manage the competing temporal worlds, TrenDx employs two techniques: beam search based on regression scores, and temporal granularity in the trend template definitions. These two techniques, described here in detail, allow TrenDx to choose different points in the trade-off between accuracy of trend detection and algorithm efficiency.

[1]  Henry A. Kautz,et al.  Constraint Propagation Algorithms for Temporal Reasoning , 1986, AAAI.

[2]  Haimowitz Ij.  Intelligent diagnostic monitoring using trend templates. , 1994 .

[3]  Benjamin Kuipers,et al.  Commonsense Reasoning about Causality: Deriving Behavior from Structure , 1984, Artif. Intell..

[4]  Drew McDermott,et al.  Temporal Data Base Management , 1987, Artif. Intell..

[5]  Mark S. Boddy,et al.  Incremental Causal Reasoning , 1987, AAAI.

[6]  Yuval Shahar,et al.  Knowledge acquisition for temporal-abstraction mechanisms , 1992 .

[7]  Isaac S. Kohane.  TEMPORAL REASONING IN MEDICAL EXPERT SYSTEMS , 1987 .

[8]  G. Stephanopoulos,et al.  Representation of process trends—Part I. A formal representation framework , 1990 .

[9]  R. Willoughby,et al.  Textbook of Pediatric Intensive Care , 1996 .

[10]  Ira J. Haimowitz,et al.  Clinical monitoring using regression-based trend templates , 1995, Artif. Intell. Medicine.

[11]  Michael G. Kahn,et al.  The visual display of temporal information , 1991, Artif. Intell. Medicine.

[12]  Enrico W. Coiera,et al.  Monitoring diseases with empirical and model-generated histories , 1990, Artif. Intell. Medicine.

[13]  Ira J. Haimowitz,et al.  Knowledge-based trend detection and diagnosis , 1994 .

[14]  P. Schönemann.  On artificial intelligence , 1985, Behavioral and Brain Sciences.

[15]  Friedrich Steimann,et al.  Clinical monitoring with fuzzy automata , 1994 .

[16]  M A Musen,et al.  Knowledge reuse: temporal-abstraction mechanisms for the assessment of children's growth. , 1993, Proceedings. Symposium on Computer Applications in Medical Care.

[17]  Toshiomi Yoshida,et al.  Real-time qualitative analysis of the temporal shapes of (bio) process variables , 1992 .

[18]  Herbert B. Enderton,et al.  A mathematical introduction to logic , 1972 .

[19]  Peter Szolovits,et al.  Reasoning with time-dependent data , 1991 .

[20]  Steve Hanks,et al.  Exploiting Domain structure to Achieve Efficient Temporal Reasoning , 1993, IJCAI.

[21]  Elpida T. Keravnou,et al.  A temporal reasoning framework used in the diagnosis of skeletal dysplasias , 1990, Artif. Intell. Medicine.