Heart attack mortality prediction: an application of machine learning methods

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21340%2F19%3A00332898" target="_blank" >RIV/68407700:21340/19:00332898 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.3906/elk-1811-4" target="_blank" >https://doi.org/10.3906/elk-1811-4</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.3906/elk-1811-4" target="_blank" >10.3906/elk-1811-4</a>

Result language
angličtina
Original language name
Heart attack mortality prediction: an application of machine learning methods
Original language description
The heart is an important organ in the human body, and Acute Myocardial Infarction (AMI) is the leading 5 cause of death in most countries. Researchers are diverting a lot of data analysis work to assist doctors in predicting 6 the heart problem. An analysis of the data related to dierent health problems and its functions can help in predicting 7 with a degree of certainty the wellness of this organ. Our research reported in this paper is twofold. In the rst part 8 of the paper, we compare dierent predictive models of hospital mortality for patients with AMI. All results presented 9 in this part are based on real data of about 603 patients from a hospital in Czechia and about 184 patients from two 10 hospitals in Syria. Although the learned models may be specic to the data, we also draw more general conclusions 11 that we believe are generally valid. In the second part of the paper, because the data is incomplete and imbalanced 12 we develop the Chow-Liu and tree-augmented naive Bayesian (TAN) to deal with that data in better conditions, and 13 measure the quality of these algorithms with other algorithms.
Czech name
—
Czech description
—

Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical
Turkish Journal of Electrical Engineering & Computer Sciences
ISSN
1300-0632
e-ISSN
1303-6203
Volume of the periodical
27
Issue of the periodical within the volume
6
Country of publishing house
TR - TURKEY
Number of pages
12
Pages from-to
4378-4389
UT code for WoS article
000506165400025
EID of the result in the Scopus database
2-s2.0-85076636366

Similar results(10)