mdh.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Retrieve and Classify
Mälardalen University, Department of Computer Science and Electronics.
2005 (English)Doctoral thesis, comprehensive summary (Other scientific)
Abstract [sv]

Diagnoshjälp för läkare

Markus Nilsson har vid Institutionen för Datavetenskap och Elektronik (IDE) forskat fram ett beslutsstödssytem för kliniker, läkare och psykologer. Systemet använder sig av artificiell intelligens (AI) för att resonera sig fram till nya diagnoser och tolkningar av mätvärden med hjälp av tidigare erfarenheter och kunskap. Systemet fungerar som en nyutexaminerad läkare, det lär och förbättrar sig av sin erfarenhet. Ju mer det används, desto mer lär den sig, desto bättre blir den på att ställa diagnoser. Systemet har vid uppstarten samma kunskapsnivå som en ledande expert inom ämnet psykofysiologisk medicin. Expertens kunskap har lärts in av systemet under översyn. Därefter blir varje individuellt system unikt beroende på sina erfarenheter.

Psykofysiologi är interaktionen mellan de psykologiska och fysiologiska aspekterna i kroppen. Hjärnan, hjärtat, lungorna och magen är sammankopplade genom Vagusnerven. Stressrelaterade problem så som utbrändhet kan ofta upptäckas och även förhindras om man analyserar interaktionen mellan dessa delar av kroppen. En viktig faktor är respiratorisk sinus arrhytmi (RSA). RSA är andningens påverkan på hjärtfrekvensen, pulsen. En andning hos en normal och frisk människa påverkar hjärtat på sådant sätt att pulsen ökar vid inandning, och vid en utandning minskar pulsen igen. En lugn och fin våg av hjärtfrekvensen bildas, en sinusvåg. Vissa psykiska eller fysiologiska dysfunktioner kan störa denna interaktion och det är just dessa som är intressanta vid stressprevention och behandling.

AI är en del inom datavetenskapen och sägs ofta vara en blandning av psykologi, biologi, filosofi, matematik och lingvistik. Det finns många inriktningar inom AI. Markus har valt att inrikta sig på en paradigm baserad från psykologin som säger att människor resonerar fram nya lösningar från tidigare explicita händelser med hjälp av inlärd kunskap. Man ställer sig frågan, hur gjorde jag när jag senast ställdes inför det här problemet?, och hur löste jag det?

Paradigmen som Markus arbetar efter kallas case-based reasoning (CBR). CBR har en dynamisk minnesarktitektur där ny kunskap kan läggas till, tas bort eller ändras lokalt. Hela minnet behöver inte påverkas när kunskapen förändras.

Abstract [en]

Diagnostics based on time series are sometimes difficult to perform, particularly when the time series is continuous and non-stationary, i.e. they seldom contain recurring patterns which makes it difficult to identify similarities with other time series. This doctoral thesis presents an artificial intelligence approach to the analysis of continuous non-stationary signals for diagnostic purposes. One way to solve this kind of problem is to break down the series into new forms that are more easily interpreted, and to identify familiar patterns within them. The newly formed series is analysed, using the Case-Based Reasoning paradigm. Known problemsolution pairs are stored in memory and reused for solving problems by classifying new patterns occurring in time series obtained subsequently. Reasoning is conducted on the basis of the knowledge available and a best-guess solution obtained using the available knowledge is presented. The memory need not therefore contain a problem, which has been solved previously and is identical with the problem which is to be solved. This approach to problem solving has been applied to physiological time series as a clinical decision support system. The system provides decision support by classifying patterns of respiratory sinus arrhythmia from heart rate and capnography time series.

Place, publisher, year, edition, pages
2005. , 32 p.
Series
Mälardalen University Press Dissertations, ISSN 1651-4238 ; 14
National Category
Computer Science
Research subject
Datavetenskap
Identifiers
URN: urn:nbn:se:mdh:diva-65ISBN: 91-88834-63-8 (print)OAI: oai:DiVA.org:mdh-65DiVA: diva2:121259
Public defence
2005-08-16, Gamma, Västerås, 10:00
Opponent
Supervisors
Available from: 2005-11-24 Created: 2005-11-24
List of papers
1. Clinical decision support for diagnosing stress related disorders by applying psychophysiological medical knowledge to an instance based learning system
Open this publication in new window or tab >>Clinical decision support for diagnosing stress related disorders by applying psychophysiological medical knowledge to an instance based learning system
Show others...
2006 (English)In: Artificial Intelligence in Medicine, ISSN 0933-3657, E-ISSN 1873-2860, Vol. 36, no 2, 159-176 p.Article in journal (Refereed) Published
Abstract [en]

Objective: An important procedure in diagnosing stress-related disorders caused by dysfunction in the interaction of the heart with breathing, i.e., respiratory sinus arrhythmia (RSA), is to analyse the breathing first and then the heart rate. Analysing these measurements is a time-consuming task for the diagnosing clinician. A decision-support system in this area would reduce the analysis task of the clinician and enable him/her to give more attention to the patient. We have created a decision-support system which contains a signal classifier and a pattern identifier. The system performs an analysis of the physiological time series concerned which would otherwise be performed manually by the clinician. Methods: The signal-classifier, HR3Modul, classifies heart-rate patterns by analysing both cardio- and pulmonary signals, i.e., physiological time series. HR3Modul uses case-basedreasoning (CBR), using a wavelet-based method for retrieving features from the signals. The system searches for familiar shapes in the signals by comparing them with shapes already stored. We have applied a best fit scheme for handling signals of different lengths, as the length of a breath is highly dynamic. We also apply automatic weighting to the features to obtain a more autonomous system. The classified heart signals indicate if a patient may be suffering from a stress-related disorder and the nature of the disorder. These classified signals are thereafter sent to the second subsystem, the pattern-identifier. The pattern-identifier analyses the classified signals and searches for familiar patterns by identifying sequences in the classified signals. The identified sequences give clinicians a more complete analysis of the measurements, providing them with a better basis for diagnosis. Results and conclusion: We have shown that a case-based classifier with a wavelet feature extractor and automatic weighting is a viable option for building a decision-support system for the psychophysiological domain, as it is at par, or even outperforms other retrieval techniques and is less complex.

National Category
Engineering and Technology
Identifiers
urn:nbn:se:mdh:diva-4215 (URN)10.1016/j.artmed.2005.04.004 (DOI)000236113700004 ()2-s2.0-32644460132 (Scopus ID)
Available from: 2005-11-24 Created: 2005-11-24 Last updated: 2013-12-03Bibliographically approved
2. Advancement and Trends in Medical Case-Based Reasoning: An Overview of Systems and System Development
Open this publication in new window or tab >>Advancement and Trends in Medical Case-Based Reasoning: An Overview of Systems and System Development
2004 (English)In: Proceedings of the Seventeenth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2004, 2004, 178-183 p.Conference paper, Published paper (Other academic)
Abstract [en]

Case-Based Reasoning (CBR) is a recognised and well established method for building medical systems. In this paper, we identify strengths and weaknesses of CBR in medicine. System properties, divided into construction-oriented and purpose-oriented, are used as the basis for a survey of recent publications and research projects. The survey is used to find current trends in present medical CBR research.

National Category
Computer Systems
Identifiers
urn:nbn:se:mdh:diva-4216 (URN)2-s2.0-10044221017 (Scopus ID)
Conference
Seventeenth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2004; Miami Beach, FL; United States; 17 May 2004 through 19 May 2004
Available from: 2005-11-24 Created: 2005-11-24 Last updated: 2015-07-29Bibliographically approved
3. Complex Measurement Classification in Medical Applications Using A Case-Based Approach
Open this publication in new window or tab >>Complex Measurement Classification in Medical Applications Using A Case-Based Approach
2003 (English)In: Workshop proceedings of the fifth international conference on case-based reasoning, NTNU, Trondheim, Norway, 2003, 63-72 p.Conference paper, Published paper (Other academic)
National Category
Computer Systems
Identifiers
urn:nbn:se:mdh:diva-4217 (URN)
Conference
Fifth international conference on case-based reasoning, NTNU, Trondheim, Norway
Available from: 2005-11-24 Created: 2005-11-24 Last updated: 2015-07-29Bibliographically approved
4. A Case-Based Classification of Respiratory Sinus Arrhythmia
Open this publication in new window or tab >>A Case-Based Classification of Respiratory Sinus Arrhythmia
2004 (English)In: Advances in Case-Based Reasoning, 2004, 673-685 p.Conference paper, Published paper (Other academic)
Abstract [en]

Respiratory Sinus Arrhythmia has until now been analysed manually by reviewing long time series of heart rate measurements. Patterns are identified in the analysis of the measurements. We propose a design for a classification system of Respiratory Sinus Arrhythmia by time series analysis of heart and respiration measurements. The classification uses Case-Based Reasoning and Rule-Based Reasoning in a Multi-Modal architecture. The system is in use as a research tool in psychophysiological medicine, and will be available as a decision support system for treatment personnel.

Series
Lecture Notes in Computer Science, ISSN 0302-9743 ; 3155
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:mdh:diva-4218 (URN)10.1007/978-3-540-28631-8_49 (DOI)2-s2.0-35048820539 (Scopus ID)978-3-540-22882-0 (ISBN)
Conference
7th European Conference, ECCBR 2004, Madrid, Spain, August 30 - September 2, 2004
Available from: 2005-11-24 Created: 2005-11-24 Last updated: 2015-07-28Bibliographically approved

Open Access in DiVA

No full text

By organisation
Department of Computer Science and Electronics
Computer Science

Search outside of DiVA

GoogleGoogle Scholar

Total: 159 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf