kth.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
Logistic regression modelling for STHR analysis
KTH, School of Engineering Sciences (SCI), Mathematics (Dept.), Mathematical Statistics.
2014 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Logistisk regression för STHR-analys (Swedish)
Abstract [en]

Coronary artery heart disease (CAD) is a common condition which can impair the quality of life and lead to cardiac infarctions. Traditional criteria during exercise tests are good but far from perfect. A lot of patients with inconclusive tests are referred to radiological examinations. By finding better evaluation criteria during the exercise test we can save a lot of money and let the patients avoid unnecessary examinations.

Computers record amounts of numerical data during the exercise test. In this retrospective study 267 patients with inconclusive exercise test and performed radiological examinations were included. The purpose was to use clinical considerations as-well as mathematical statistics to be able to find new diagnostic criteria.

We created a few new parameters and evaluated them together with previously used parameters. For women we found some interesting univariable results where new parameters discriminated better than the formerly used. However, the number of females with observed CAD was small (14) which made it impossible to obtain strong significance. For men we computed a multivariable model, using logistic regression, which discriminates way better than the traditional parameters for these patients. The area under the ROC curve was 0:90 (95 % CI: 0.83-0.97) which is excellent to outstanding discrimination in a group initially included due to their inconclusive results.

If the model can be proved to hold for another population it could contribute a lot to the diagnostics of this common medical conditions

Place, publisher, year, edition, pages
2014.
Series
TRITA-MAT-E ; 2014:44
National Category
Probability Theory and Statistics
Identifiers
URN: urn:nbn:se:kth:diva-148971OAI: oai:DiVA.org:kth-148971DiVA, id: diva2:742118
Subject / course
Mathematical Statistics
Educational program
Master of Science in Engineering -Engineering Physics
Supervisors
Examiners
Available from: 2014-08-31 Created: 2014-08-16 Last updated: 2022-06-23Bibliographically approved

Open Access in DiVA

fulltext(626 kB)297 downloads
File information
File name FULLTEXT01.pdfFile size 626 kBChecksum SHA-512
2dd2619976d452e4adb76bd06e639dc905f7eb24b32e5df91f0c4ddffa42ff61e68b9db85026697cf4ae6c8fae0e0a98e1ded9a2861db7c50bfc946874ee2b89
Type fulltextMimetype application/pdf

By organisation
Mathematical Statistics
Probability Theory and Statistics

Search outside of DiVA

GoogleGoogle Scholar
Total: 297 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 155 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