Artificial Intelligence in Medicine

Name: Artificial Intelligence in Medicine | 16th Conference on Artificial Intelligence in Medicine, AIME 2017, Vienna, Austria, June 21-24, 2017, Proceedings
Brand: Springer
Price: 69.54 EUR
Availability: OnlineOnly

16th Conference on Artificial Intelligence in Medicine, AIME 2017, Vienna, Austria, June 21-24, 2017, Proceedings

Annette ten Teije Christian Popow John H. Holmes Lucia Sacchi(Herausgeber*in)

Springer (Verlag)

Erschienen am 12. Juni 2017

XXV, 369 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-319-59758-4 (ISBN)

69,54 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Intro
Preface
Organization
Invited Talks
SNOMED CT: The Thorny Way Towards Interoperability of Clinical Routine Data
Collaborative, Exploratory Question Answering Against Medical Literature
Contents
Ontologies and Knowledge Representation
Studying the Reuse of Content in Biomedical Ontologies: An Axiom-Based Approach
1 Introduction
2 Methods
2.1 Types of Term Reuse in Biomedical Ontologies
2.2 Characterisation of Ontologies Based on Reuse
2.3 Identification of Hidden Axioms
2.4 A Modular Strategy for Increasing the Amount of Knowledge that is Already Being Reused
3 Results
3.1 Experimental Setup
3.2 Analysis of the Reused Terms URIs
3.3 Analysis by the Type of Reuse
3.4 Analysis of Hidden Axioms and Terms Already Reused
4 Discussion and Conclusions
References
Ontological Representation of Laboratory Test Observables: Challenges and Perspectives in the SNOMED CT Observable Entity Model Adoption
Abstract
1 Introduction
2 Materials and Methods
2.1 Terminologies and Ontologies
2.2 Lab Test Observable Classification
3 Results
3.1 ELK Classification Metrics
3.2 Lab Test Classification Issue
3.3 Representation of Observation Using BTL2
4 Conclusion
References
CAREDAS: Context and Activity Recognition Enabling Detection of Anomalous Situation
1 Introduction
2 Related Work
2.1 Anomaly Detection
2.2 Markov Logic Network (MLN)
3 Contributions
4 CAREDAS Knowledge Base
4.1 Data Structure Definition
4.2 The MLN Model for Anomalous Situation Detection
5 CAREDAS Inference Engine
5.1 Situation Construction
5.2 Dynamic Ground MLN Creation
5.3 Rules Weights Calculus
5.4 Computation of the Weight of Probabilistic Hidden Predicates
6 Experimental Evaluation
7 Conclusion and Future Work
References
Using Constraint Logic Programming for the Verification of Customized Decision Models for Clinical Guidelines
Abstract
1 Introduction
2 Related Work
2.1 Customization of CPGs
2.2 Automatic Verification and Evaluation of CIGs
3 Methods
3.1 Two-Layered Contextual Decision Model
3.2 Constraint Logic Programming and MiniZinc
3.3 Using CLP to Check Properties of Two-Layered Decision Models
3.4 Analysis of Property Violations and Revisions of the PROforma Model
4 Case Study Example
5 Results
5.1 A Decision Model for Asthma with the Secondary Personal Domains
5.2 Verification and Revision of the Decision Model for Asthma
6 Discussion and Conclusions
References
Constructing Disease-Centric Knowledge Graphs: A Case Study for Depression (short Version)
1 Introduction
2 Challenges
3 Knowledge Resources and Integration
4 Use Cases
5 Implementation, Discussion and Conclusion
References
Bayesian Methods
Implementing Guidelines for Causality Assessment of Adverse Drug Reaction Reports: A Bayesian Network Approach
1 Introduction
2 Materials and Methods
2.1 Bayesian Network Model Definition
2.2 Evaluation Strategy and Software Used
3 Results
4 Discussion
5 Concluding Remarks
References
Bayesian Gaussian Process Classification from Event-Related Brain Potentials in Alzheimer's Disease
Abstract
1 Introduction
2 Materials and Methods
2.1 Subjects
2.2 Assessment of Cognitive Decline and Apolipoprotein E Genotyping
2.3 Recording and Pre-processing of Event-Related Potentials
2.4 Spatial Synchrony Measures
2.5 Spatiotemporal Synchrony Measures
2.6 Machine Learning Classifiers
3 Results
3.1 Prediction of Rapid Cognitive Decline
3.2 Apolipoprotein E e4 Classification
4 Summary and Discussion
Acknowledgment
References
Data Fusion Approach for Learning Transcriptional Bayesian Networks
Abstract
1 Introduction
2 Methods
2.1 Reconstruction of CML Transcriptional Regulatory Network
2.2 Hybrid Bayesian Network Structure Learning Algorithm
3 Results and Discussion
References
A Prognostic Model of Glioblastoma Multiforme Using Survival Bayesian Networks
1 Introduction
2 Conditional Survival Bayesian Networks
2.1 Modelling Survival in Bayesian Networks
2.2 Learning and Inference
3 Experimental Work
3.1 Experimental Setup
3.2 Results
4 Conclusions
References
Accurate Bayesian Prediction of Cardiovascular-Related Mortality Using Ambulatory Blood Pressure Measurements
1 Introduction
2 Related Research
3 Experimental Methodology
4 Results
4.1 Bayesian Classification
5 Conclusion
References
Temporal Methods
Modelling Time-Series of Glucose Measurements from Diabetes Patients Using Predictive Clustering Trees
1 Introduction
2 Predictive Clustering Trees for Time Series Modelling
3 Data Description and Experimental Design
4 Results
5 Conclusions
References
Estimation of Sleep Quality by Using Microstructure Profiles
1 Introduction
2 Data Set Description
3 Sleep Features
3.1 Hypnogram Features
3.2 PSM Based Sleep Features
4 Methodology
4.1 Feature Selection
5 Results and Discussion
6 Conclusion
References
Combining Multitask Learning and Short Time Series Analysis in Parkinson's Disease Patients Stratification
1 Introduction
2 Background and Motivation
3 The Parkinson's Disease Data Set
3.1 PPMI Symptoms Data Sets
3.2 PPMI Concomitant Medications Log
3.3 Experimental Data Set
4 Methodology
5 Data Analysis
5.1 Results
6 Conclusions
References
Change-Point Detection Method for Clinical Decision Support System Rule Monitoring
1 Introduction
2 Method
2.1 Data Transformation to Stabilize Variance
2.2 Seasonal-Trend Decomposition
2.3 Likelihood Ratio Statistics
2.4 Further Improvements
3 Experiments
3.1 Experiment Design
3.2 Results on Data with Known Change-Points
3.3 Results on Data with Simulated Change-Points
4 Related Work and Discussion
5 Conclusion
References
Discovering Discriminative and Interpretable Patterns for Surgical Motion Analysis
1 Introduction
2 Background
3 Method
3.1 Symbolic Aggregate ApproXimation (SAX)
3.2 Bag of Words Representation of Kinematic Data
3.3 Vector Space Model (VSM)
3.4 Training and Classifying Kinematic Data
4 Experimental Evaluation
4.1 Gesture Classification
4.2 Skills Classification
4.3 Interpretable Patterns Visualization
5 Conclusion
References
Natural Language Processing
Automatic Classification of Radiological Reports for Clinical Care
1 Introduction
2 Background and Related Work
3 Data Representation and Annotation
3.1 Classification Schema
3.2 Data
4 Report Classification
4.1 Text Processing
4.2 Automatic Annotation
4.3 Classification
4.4 Machine Learning Algorithms
5 Evaluation and Discussion
6 Conclusion
References
Learning Concept-Driven Document Embeddings for Medical Information Search
1 Introduction
2 On the Semantic Gap Problem in Medical Search
3 Model
3.1 Problem Formulation
3.2 Learning the Concept-Based Representation of Documents
3.3 Solving the Optimization Problem
4 Experiments
4.1 Experimental Setup
4.2 Results
5 Conclusion and Future Work
References
Automatic Identification of Substance Abuse from Social History in Clinical Text
Abstract
1 Introduction
2 Related Work
3 Dataset
3.1 Annotation Process
3.2 Annotation Statistics
4 Methods
4.1 Step 1 - Identification of Sentences with Substance Abuse Events
4.2 Step 2 - Extraction of Entities for Substance Abuse Events
4.3 Step 3 - Event Template Creation
5 Results
5.1 Performance of Sentence and Entity Extraction Steps on the Training Set
5.2 Performance of the Event Extraction Pipeline on the Test Set
5.3 Error Analysis
6 Conclusion
References
Analyzing Perceived Intentions of Public Health-Related Communication on Twitter
1 Introduction
2 Related Work
3 Research Design
4 An Intention Taxonomy for Public Tweets
5 Discourse Features for Intention Discovery
6 Results and Discussion
7 Conclusion and Future Work
References
Exploring IBM Watson to Extract Meaningful Information from the List of References of a Clinical Practice Guideline
Abstract
1 Introduction
2 Methods
3 Results
4 Discussion and Conclusion
References
Recurrent Neural Network Architectures for Event Extraction from Italian Medical Reports
Abstract
1 Introduction
2 Materials and Methods
2.1 Dataset
2.2 The Model
2.3 Evaluation Metrics
3 Results
4 Discussion and Conclusion
References
Numerical Eligibility Criteria in Clinical Protocols: Annotation, Automatic Detection and Interpretation
1 Introduction
2 Material
3 Methods
4 Results and Discussion
5 Conclusion and Future Work
References
Enhancing Speech-Based Depression Detection Through Gender Dependent Vowel-Level Formant Features
1 Introduction
2 Vowel-Level Formant Analysis
3 Classification Experiments
3.1 Set-Up
3.2 Results
4 Conclusions
References
A Co-occurrence Based MedDRA Terminology Generation: Some Preliminary Results
1 Introduction
2 Background and Related Work
3 Methods and Experiments
4 Conclusions
References
Health Care Processes
Towards Dynamic Duration Constraints for Therapy and Monitoring Tasks
1 Introduction
2 Background and Related Work
3 Motivating Clinical Scenarios
4 Modeling and Managing Shifted Durations in BPMN
4.1 Shifted Duration Specification and Detection of Violations
4.2 Management of Violated Shifted Duration Constraints
5 Conclusions
References
Discriminant Chronicles Mining
1 Introduction
2 Discriminant Chronicles
2.1 Sequences and Chronicles
2.2 Chronicle Support
2.3 Discriminant Chronicles Mining
3 DCM Algorithm
3.1 Temporal Constraints Mining
4 Case Study
4.1 Dataset
4.2 Results
5 Conclusion
References
Is Crowdsourcing Patient-Reported Outcomes the Future of Evidence-Based Medicine? A Case Study of Back Pain
Abstract
1 Introduction
2 Background
2.1 Statistically-Controlled Methods to Collect Evidence Prospectively
2.2 Provider Systems for Collecting PROM
2.3 Using Crowdsourcing to Find Clinical Evidence for Treatment Effectiveness
3 Methods
3.1 Data Collection and Data Set
3.2 Data Analysis
4 Results
4.1 Data Characterization
4.2 Consistency of Relationships with Those Described in the Literature
4.3 Comparing Treatment Effectiveness
5 Discussion
5.1 Regression vs. Propensity Score Matching
5.2 Limitations and Future Research
5.3 Future Work
Acknowledgement
References
Multi-level Interactive Medical Process Mining
1 Introduction
2 Process Mining Approach
3 An Interactive Session of Work
4 Conclusions
References
Declarative Sequential Pattern Mining of Care Pathways
1 Introduction
2 Context, Data and Pharmaco-Epidemiological Question
3 Sequential Pattern Mining with ASP
4 Declarative Care Pathway Mining
5 Conclusion
References
Knowledge-Based Trace Abstraction for Semantic Process Mining
1 Introduction
2 Knowledge-Based Trace Abstraction
3 Experimental Results
4 Concluding Remarks and Future Work
References
The Spanish Kidney Exchange Model: Study of Computation-Based Alternatives to the Current Procedure
1 Introduction and Previous Work
2 Problem Definition and Formulation
3 Description of both Approaches
4 Simulation Description and Results
5 Conclusions and Future Work
References
A Similarity Measure Based on Care Trajectories as Sequences of Sets
Abstract
1 Introduction
2 Materials and Methods
2.1 Representing Trajectories as Sequences of Sets
2.2 Comparing Sequences of Sets
2.3 Experimentations
3 Results
4 Discussion and Conclusion
References
Machine Learning
Influence of Data Distribution in Missing Data Imputation
1 Introduction
2 Related Work
3 Methodology
3.1 Data Collection
3.2 Missing Data Generation
3.3 Data Imputation
3.4 Evaluation Metrics for Missing Data Imputation
4 Experimental Results and Discussion
5 Conclusions and Future Work
References
Detecting Mental Fatigue from Eye-Tracking Data Gathered While Watching Video
1 Introduction
2 Data Collection
2.1 Participants
2.2 Experimental Design and Procedure
2.3 Stimuli and Eye-Tracking Data Acquisition
3 Mental Fatigue Detection Model
3.1 Data Preprocessing and Features
3.2 Classification and Feature Selection
4 Results
4.1 Mental Fatigue After the Cognitive Tasks
4.2 Model Performance
5 Conclusion
References
Automatic Identification of Intraretinal Cystoid Regions in Optical Coherence Tomography
1 Introduction and Previous Work
2 Methodology
2.1 Retinal Layer Segmentation
2.2 Feature Measurement
2.3 Feature Selection and Classification
3 Results and Discussion
4 Conclusions
References
Convolutional Neural Networks for the Identification of Regions of Interest in PET Scans: A Study of Representation Learning for Diagnosing Alzheimer's Disease
1 Introduction
2 Methodology
2.1 Data Acquisition and Preprocessing
2.2 Generation of Binary Classifiers
2.3 ROI Discovery and Ranking
3 Experiments and Results
4 Conclusions and Future Work
References
Skin Hair Removal in Dermoscopic Images Using Soft Color Morphology
1 Introduction
2 Soft Color Morphology
3 Hair Removal Algorithm
4 Experiments and Conclusions
References
Risk Mediation in Association Rules
Abstract
1 Introduction
2 Background
2.1 Recommender Systems in Precarious Domains
2.2 Risk as a Post-mining Metric
3 Risk Model Formulation
4 Implementation
4.1 Health Records' Risk
4.2 Health Records' Severity
4.3 Drug Severity
5 Validation
6 Conclusion
References
Identifying Parkinson's Patients: A Functional Gradient Boosting Approach
1 Introduction
2 Background
3 Proposed Approach
4 Experiments
5 Conclusion
References
Echo State Networks as Novel Approach for Low-Cost Myoelectric Control
1 Introduction
2 Methods
2.1 From Linear Regression to Echo State Networks
2.2 Experimental Protocol
3 Results
4 Discussion and Conclusion
References
Demo's
Semi-automated Ontology Development and Management System Applied to Medically Unexplained Syndromes in the U.S. Veterans Population
Abstract
1 Introduction and Background
2 Methods
3 Results
4 Discussion
Acknowledgments
References
pMineR: An Innovative R Library for Performing Process Mining in Medicine
1 Introduction
2 The pMineR Library
2.1 Process Discovery
2.2 Conformance Checking
3 Conclusion
References
Advanced Algorithms for Medical Decision Analysis. Implementation in OpenMarkov
1 Introduction
2 OpenMarkov
3 Problems and Solutions
3.1 Explanation of Reasoning
3.2 Modelling and Solving Asymmetric Problems
3.3 Strategy Trees
3.4 Cost-Effectiveness Analysis
3.5 Temporal Reasoning Was Not Possible with IDs
4 Conclusion
References
A Platform for Targeting Cost-Utility Analyses to Specific Populations
Abstract
1 Introduction
2 Methods
3 Results
4 Discussion and Conclusion
References
Author Index

Systemvoraussetzungen

Als PDF speichern Als Link merken