Artificial Intelligence in Medicine: 10th Conference on Artificial Intelligence in Medicine, AIME 2005, Aberdeen, UK, July 23-27, 2005, ProceedingsSilvia Miksch, Jim Hunter, Elpida Keravnou This book constitutes the refereed proceedings of the 10th Conference on Artificial Intelligence in Medicine in Europe, AIME 2005, held in Aberdeen, UK in July 2005. The 35 revised full papers and 34 revised short papers presented together with 2 invited contributions were carefully reviewed and selected from 148 submissions. The papers are organized in topical sections on temporal representation and reasoning, decision support systems, clinical guidelines and protocols, ontology and terminology, case-based reasoning, signal interpretation, visual mining, computer vision and imaging, knowledge management, machine learning, knowledge discovery, and data mining. |
From inside the book
Results 6-10 of 86
Page 14
... Temporal Patterns. Several methods of extraction of temporal patterns from physiological signals can be found in existing literature. We will only mention here methods which have been used on signals acquired in ICU. Avent and Charlton ...
... Temporal Patterns. Several methods of extraction of temporal patterns from physiological signals can be found in existing literature. We will only mention here methods which have been used on signals acquired in ICU. Avent and Charlton ...
Page 15
... temporal pattern, it is possible to describe and recognize a certain number of specific clinical situations by pattern templates. A pattern template is a finite set of temporal patterns pre-established from medical knowledge and from ...
... temporal pattern, it is possible to describe and recognize a certain number of specific clinical situations by pattern templates. A pattern template is a finite set of temporal patterns pre-established from medical knowledge and from ...
Page 16
... temporal pattern can only be established from the data themselves, taking into account their anteriority [13]. Our method uses adaptive thresholds which depend on the distribution of values to qualify signals. 4. Last, the level of temporal ...
... temporal pattern can only be established from the data themselves, taking into account their anteriority [13]. Our method uses adaptive thresholds which depend on the distribution of values to qualify signals. 4. Last, the level of temporal ...
Page 17
... temporal evolution of regression coefficients thresholds : plain line for negative threshold, dashed for positive one. Right bottom panel : temporal evolution of standard deviation threshold kurtosis or flattening-coefficient K1 which ...
... temporal evolution of regression coefficients thresholds : plain line for negative threshold, dashed for positive one. Right bottom panel : temporal evolution of standard deviation threshold kurtosis or flattening-coefficient K1 which ...
Page 19
... temporal structures composed of words. At each point t, a word concatenates symbols from an alphabet of four letters ... temporal order of the symbols forming the words, the number of occurrences of each word in the sequence, and the ...
... temporal structures composed of words. At each point t, a word concatenates symbols from an alphabet of four letters ... temporal order of the symbols forming the words, the number of occurrences of each word in the sequence, and the ...
Contents
3 | |
23 | |
43 | |
Decision Support Systems | 56 |
Extending Temporal Databases to Deal with TelicAtelic Medical Data | 58 |
An Expert System for Atherosclerosis Risk Assessment | 78 |
A Rehabilitation Expert System for Poststroke Patients | 94 |
A Collaborative Activities Representation for Building | 111 |
The Use of Verbal Classification in Determining the Course of Medical | 276 |
Interactive Knowledge Validation in CBR for Decision Support | 287 |
Adaptation and Medical CaseBased Reasoning Focusing on Endocrine | 300 |
Towards Information Visualization and Clustering Techniques for | 315 |
Automatic Landmarking of Cephalograms by Cellular Neural Networks | 333 |
Morphometry of the Hippocampus Based on a Deformable Model | 353 |
Multiagent Patient Representation in Primary Care | 375 |
Clinical Reasoning Learning with Simulated Patients | 385 |
Improving Clinical Guideline Implementation Through Prototypical | 126 |
Helping Physicians to Organize Guidelines Within Conceptual | 141 |
MHB A ManyHeaded Bridge Between Informal and Formal | 146 |
A HistoryBased Algebra for QualityChecking Medical Guidelines | 161 |
Gaining Process Information from Clinical Practice Guidelines Using | 181 |
Formalising Medical Quality Indicators to Improve Guidelines | 201 |
OntologyMediated Distributed Decision Support for Breast Cancer | 221 |
Building Medical Ontologies Based on Terminology Extraction from | 231 |
Using Lexical and Logical Methods for the Alignment of Medical | 241 |
A Benchmark Evaluation of the French MeSH Indexers | 251 |
Ontology of Time and Situoids in Medical Conceptual Modeling | 266 |
Which Kind of Knowledge Is Suitable for Redesigning Hospital Logistic | 400 |
An Evolutionary Divide and Conquer Method for LongTerm Dietary | 419 |
A Data Preprocessing Method to Increase Efficiency and Accuracy | 434 |
Subgroup Mining for Interactive Knowledge Refinement | 453 |
On Understanding and Assessing Feature Selection Bias | 468 |
Learning Rules from Multisource Data for Cardiac Monitoring | 484 |
Signature Recognition Methods for Identifying Influenza Sequences | 504 |
An Algorithm to Learn Causal Relations Between Genes from Steady | 524 |
Author Index | 545 |
Other editions - View all
Common terms and phrases
Abstract accuracy actions AIME algorithm allergen analysis annotation application approach Artificial Intelligence Asbru automatically Bayesian network Berlin Heidelberg 2005 biomedical cancer Case-Based Reasoning classification clinical guidelines complex Computer concepts constraints corpus CPGs data mining database dataset decision support decision tree defined described detection developed diabetes diagnosis disease domain evaluation example expert extraction feature FiO2 formal function gene graph Heidelberg identified implemented indicators interaction keratoconus knowledge base language machine learning Medical Informatics Medicine method Miksch multi-agent systems multisource n-gram neural network node obtained ontology paper parameters patient patterns performance problem Proc proposed query region predictions relations relevant represent representation rules score selection semantic sequences sketch specific Springer-Verlag Berlin Heidelberg step structure subgroup Support Vector Machines task TeachMed techniques templates temporal therapy threshold tion topological ordering treatment values variables visualization