Loading…
Machine Learning Approach on High Risk Treadmill Exercise Test to Predict Obstructive Coronary Artery Disease by using P, QRS, and T waves’ Features
Treadmill Exercise Test (TET) results and patients' clinical symptoms influence cardiologists' decision to perform Coronary Angiography (CAG) which is an invasive procedure. Since TET has high false positive rates, it can cause an unnecessary invasive CAG. Our primary objective was to deve...
Saved in:
Published in: | Current problems in cardiology 2023-02, Vol.48 (2), p.101482-101482, Article 101482 |
---|---|
Main Authors: | , , , , , , , , , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c301t-afc55833f9851e6515dddec5a03a0628c222b2578a1cb0ed7813639a918245b93 |
---|---|
cites | cdi_FETCH-LOGICAL-c301t-afc55833f9851e6515dddec5a03a0628c222b2578a1cb0ed7813639a918245b93 |
container_end_page | 101482 |
container_issue | 2 |
container_start_page | 101482 |
container_title | Current problems in cardiology |
container_volume | 48 |
creator | Yilmaz, Abdurrahim Hayıroğlu, Mert İlker Salturk, Serkan Pay, Levent Demircali, Ali Anil Coşkun, Cahit Varol, Rahmetullah Tezen, Ozan Eren, Semih Çetin, Tuğba Tekkeşin, Ahmet İlker Uvet, Huseyin |
description | Treadmill Exercise Test (TET) results and patients' clinical symptoms influence cardiologists' decision to perform Coronary Angiography (CAG) which is an invasive procedure. Since TET has high false positive rates, it can cause an unnecessary invasive CAG. Our primary objective was to develop a machine learning model capable of optimizing TET performance based on electrocardiography (ECG) waves characteristics and signals. TET reports from 294 patients who underwent CAG following high risk TET were collected and categorized into those with critical CAD and others. The signal was converted to time series format. A dataset containing the P, QRS, and T wave times and amplitudes was created. Using this dataset, 5 machine learning algorithms were trained with 5-fold cross validation. All these models were then compared to the performance of cardiologists on V5 signal. The results from 5 machine learning models were clearly superior to the cardiologists' V5 signal performance (P < 0.0001). In addition, the XGBoost model, with an accuracy of 80.92±6.42% and an area under the curve (AUC) of 0.78±0.06, was the most successful model. Machine learning models can produce high-performance diagnoses using the V5 signal markers only as it does not require any clinical markers obtained from TET reports. This can lead to significant contributions to improving clinical prediction in non-invasive methods. |
doi_str_mv | 10.1016/j.cpcardiol.2022.101482 |
format | article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2733203829</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0146280622003796</els_id><sourcerecordid>2733203829</sourcerecordid><originalsourceid>FETCH-LOGICAL-c301t-afc55833f9851e6515dddec5a03a0628c222b2578a1cb0ed7813639a918245b93</originalsourceid><addsrcrecordid>eNqFUctuFDEQtBARWQK_AH3kkNn4Ec_juFoSgrQoISxny2P3Jl5mxxvbs5AbX4HE7_EleLRJrjl1q1TVpeoi5D2jU0ZZebKemq3RwTrfTTnlfERPa_6CTJgUsih5TV-SScbKIq_lIXkd45pSxhtWviKHohSiZKyakD9ftLl1PcICdehdfwOz7Tb4DILv4cLd3MK1iz9gGVDbjes6OPuFwbiIsMSYIHm4CmidSXDZxhQGk9wOYe6D73W4h1lImMfHLNBZ097DEEeXq2P4ev3tGHRvYQk_9Q7jv99_4Rx1GgLGN-RgpbuIbx_mEfl-fracXxSLy0-f57NFYQRlqdArI2UtxKqpJcNSMmmtRSM1FZrmJxjOectlVWtmWoq2qlmO3uiG1fxUto04Ih_2d3PmuyEHUhsXDXad7tEPUfFKCE5FzUdqtaea4GMMuFLb4DY5o2JUjaWotXoqRY2lqH0pWfnuwWRoN2ifdI8tZMJsT8AcdecwqGgc9ib_NaBJynr3rMl_26CirA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2733203829</pqid></control><display><type>article</type><title>Machine Learning Approach on High Risk Treadmill Exercise Test to Predict Obstructive Coronary Artery Disease by using P, QRS, and T waves’ Features</title><source>ScienceDirect Freedom Collection 2022-2024</source><creator>Yilmaz, Abdurrahim ; Hayıroğlu, Mert İlker ; Salturk, Serkan ; Pay, Levent ; Demircali, Ali Anil ; Coşkun, Cahit ; Varol, Rahmetullah ; Tezen, Ozan ; Eren, Semih ; Çetin, Tuğba ; Tekkeşin, Ahmet İlker ; Uvet, Huseyin</creator><creatorcontrib>Yilmaz, Abdurrahim ; Hayıroğlu, Mert İlker ; Salturk, Serkan ; Pay, Levent ; Demircali, Ali Anil ; Coşkun, Cahit ; Varol, Rahmetullah ; Tezen, Ozan ; Eren, Semih ; Çetin, Tuğba ; Tekkeşin, Ahmet İlker ; Uvet, Huseyin</creatorcontrib><description>Treadmill Exercise Test (TET) results and patients' clinical symptoms influence cardiologists' decision to perform Coronary Angiography (CAG) which is an invasive procedure. Since TET has high false positive rates, it can cause an unnecessary invasive CAG. Our primary objective was to develop a machine learning model capable of optimizing TET performance based on electrocardiography (ECG) waves characteristics and signals. TET reports from 294 patients who underwent CAG following high risk TET were collected and categorized into those with critical CAD and others. The signal was converted to time series format. A dataset containing the P, QRS, and T wave times and amplitudes was created. Using this dataset, 5 machine learning algorithms were trained with 5-fold cross validation. All these models were then compared to the performance of cardiologists on V5 signal. The results from 5 machine learning models were clearly superior to the cardiologists' V5 signal performance (P < 0.0001). In addition, the XGBoost model, with an accuracy of 80.92±6.42% and an area under the curve (AUC) of 0.78±0.06, was the most successful model. Machine learning models can produce high-performance diagnoses using the V5 signal markers only as it does not require any clinical markers obtained from TET reports. This can lead to significant contributions to improving clinical prediction in non-invasive methods.</description><identifier>ISSN: 0146-2806</identifier><identifier>EISSN: 1535-6280</identifier><identifier>DOI: 10.1016/j.cpcardiol.2022.101482</identifier><identifier>PMID: 36336117</identifier><language>eng</language><publisher>United States: Elsevier Inc</publisher><subject>Coronary Angiography ; Coronary Artery Disease - diagnosis ; Electrocardiography ; Exercise Test - methods ; Humans ; Machine Learning</subject><ispartof>Current problems in cardiology, 2023-02, Vol.48 (2), p.101482-101482, Article 101482</ispartof><rights>2022 Elsevier Inc.</rights><rights>Copyright © 2022 Elsevier Inc. All rights reserved.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c301t-afc55833f9851e6515dddec5a03a0628c222b2578a1cb0ed7813639a918245b93</citedby><cites>FETCH-LOGICAL-c301t-afc55833f9851e6515dddec5a03a0628c222b2578a1cb0ed7813639a918245b93</cites><orcidid>0000-0002-4922-7391</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>315,786,790,27957,27958</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/36336117$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Yilmaz, Abdurrahim</creatorcontrib><creatorcontrib>Hayıroğlu, Mert İlker</creatorcontrib><creatorcontrib>Salturk, Serkan</creatorcontrib><creatorcontrib>Pay, Levent</creatorcontrib><creatorcontrib>Demircali, Ali Anil</creatorcontrib><creatorcontrib>Coşkun, Cahit</creatorcontrib><creatorcontrib>Varol, Rahmetullah</creatorcontrib><creatorcontrib>Tezen, Ozan</creatorcontrib><creatorcontrib>Eren, Semih</creatorcontrib><creatorcontrib>Çetin, Tuğba</creatorcontrib><creatorcontrib>Tekkeşin, Ahmet İlker</creatorcontrib><creatorcontrib>Uvet, Huseyin</creatorcontrib><title>Machine Learning Approach on High Risk Treadmill Exercise Test to Predict Obstructive Coronary Artery Disease by using P, QRS, and T waves’ Features</title><title>Current problems in cardiology</title><addtitle>Curr Probl Cardiol</addtitle><description>Treadmill Exercise Test (TET) results and patients' clinical symptoms influence cardiologists' decision to perform Coronary Angiography (CAG) which is an invasive procedure. Since TET has high false positive rates, it can cause an unnecessary invasive CAG. Our primary objective was to develop a machine learning model capable of optimizing TET performance based on electrocardiography (ECG) waves characteristics and signals. TET reports from 294 patients who underwent CAG following high risk TET were collected and categorized into those with critical CAD and others. The signal was converted to time series format. A dataset containing the P, QRS, and T wave times and amplitudes was created. Using this dataset, 5 machine learning algorithms were trained with 5-fold cross validation. All these models were then compared to the performance of cardiologists on V5 signal. The results from 5 machine learning models were clearly superior to the cardiologists' V5 signal performance (P < 0.0001). In addition, the XGBoost model, with an accuracy of 80.92±6.42% and an area under the curve (AUC) of 0.78±0.06, was the most successful model. Machine learning models can produce high-performance diagnoses using the V5 signal markers only as it does not require any clinical markers obtained from TET reports. This can lead to significant contributions to improving clinical prediction in non-invasive methods.</description><subject>Coronary Angiography</subject><subject>Coronary Artery Disease - diagnosis</subject><subject>Electrocardiography</subject><subject>Exercise Test - methods</subject><subject>Humans</subject><subject>Machine Learning</subject><issn>0146-2806</issn><issn>1535-6280</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNqFUctuFDEQtBARWQK_AH3kkNn4Ec_juFoSgrQoISxny2P3Jl5mxxvbs5AbX4HE7_EleLRJrjl1q1TVpeoi5D2jU0ZZebKemq3RwTrfTTnlfERPa_6CTJgUsih5TV-SScbKIq_lIXkd45pSxhtWviKHohSiZKyakD9ftLl1PcICdehdfwOz7Tb4DILv4cLd3MK1iz9gGVDbjes6OPuFwbiIsMSYIHm4CmidSXDZxhQGk9wOYe6D73W4h1lImMfHLNBZ097DEEeXq2P4ev3tGHRvYQk_9Q7jv99_4Rx1GgLGN-RgpbuIbx_mEfl-fracXxSLy0-f57NFYQRlqdArI2UtxKqpJcNSMmmtRSM1FZrmJxjOectlVWtmWoq2qlmO3uiG1fxUto04Ih_2d3PmuyEHUhsXDXad7tEPUfFKCE5FzUdqtaea4GMMuFLb4DY5o2JUjaWotXoqRY2lqH0pWfnuwWRoN2ifdI8tZMJsT8AcdecwqGgc9ib_NaBJynr3rMl_26CirA</recordid><startdate>202302</startdate><enddate>202302</enddate><creator>Yilmaz, Abdurrahim</creator><creator>Hayıroğlu, Mert İlker</creator><creator>Salturk, Serkan</creator><creator>Pay, Levent</creator><creator>Demircali, Ali Anil</creator><creator>Coşkun, Cahit</creator><creator>Varol, Rahmetullah</creator><creator>Tezen, Ozan</creator><creator>Eren, Semih</creator><creator>Çetin, Tuğba</creator><creator>Tekkeşin, Ahmet İlker</creator><creator>Uvet, Huseyin</creator><general>Elsevier Inc</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-4922-7391</orcidid></search><sort><creationdate>202302</creationdate><title>Machine Learning Approach on High Risk Treadmill Exercise Test to Predict Obstructive Coronary Artery Disease by using P, QRS, and T waves’ Features</title><author>Yilmaz, Abdurrahim ; Hayıroğlu, Mert İlker ; Salturk, Serkan ; Pay, Levent ; Demircali, Ali Anil ; Coşkun, Cahit ; Varol, Rahmetullah ; Tezen, Ozan ; Eren, Semih ; Çetin, Tuğba ; Tekkeşin, Ahmet İlker ; Uvet, Huseyin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c301t-afc55833f9851e6515dddec5a03a0628c222b2578a1cb0ed7813639a918245b93</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Coronary Angiography</topic><topic>Coronary Artery Disease - diagnosis</topic><topic>Electrocardiography</topic><topic>Exercise Test - methods</topic><topic>Humans</topic><topic>Machine Learning</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yilmaz, Abdurrahim</creatorcontrib><creatorcontrib>Hayıroğlu, Mert İlker</creatorcontrib><creatorcontrib>Salturk, Serkan</creatorcontrib><creatorcontrib>Pay, Levent</creatorcontrib><creatorcontrib>Demircali, Ali Anil</creatorcontrib><creatorcontrib>Coşkun, Cahit</creatorcontrib><creatorcontrib>Varol, Rahmetullah</creatorcontrib><creatorcontrib>Tezen, Ozan</creatorcontrib><creatorcontrib>Eren, Semih</creatorcontrib><creatorcontrib>Çetin, Tuğba</creatorcontrib><creatorcontrib>Tekkeşin, Ahmet İlker</creatorcontrib><creatorcontrib>Uvet, Huseyin</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Current problems in cardiology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yilmaz, Abdurrahim</au><au>Hayıroğlu, Mert İlker</au><au>Salturk, Serkan</au><au>Pay, Levent</au><au>Demircali, Ali Anil</au><au>Coşkun, Cahit</au><au>Varol, Rahmetullah</au><au>Tezen, Ozan</au><au>Eren, Semih</au><au>Çetin, Tuğba</au><au>Tekkeşin, Ahmet İlker</au><au>Uvet, Huseyin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Machine Learning Approach on High Risk Treadmill Exercise Test to Predict Obstructive Coronary Artery Disease by using P, QRS, and T waves’ Features</atitle><jtitle>Current problems in cardiology</jtitle><addtitle>Curr Probl Cardiol</addtitle><date>2023-02</date><risdate>2023</risdate><volume>48</volume><issue>2</issue><spage>101482</spage><epage>101482</epage><pages>101482-101482</pages><artnum>101482</artnum><issn>0146-2806</issn><eissn>1535-6280</eissn><notes>ObjectType-Article-2</notes><notes>SourceType-Scholarly Journals-1</notes><notes>ObjectType-Feature-3</notes><notes>content type line 23</notes><notes>ObjectType-Review-1</notes><abstract>Treadmill Exercise Test (TET) results and patients' clinical symptoms influence cardiologists' decision to perform Coronary Angiography (CAG) which is an invasive procedure. Since TET has high false positive rates, it can cause an unnecessary invasive CAG. Our primary objective was to develop a machine learning model capable of optimizing TET performance based on electrocardiography (ECG) waves characteristics and signals. TET reports from 294 patients who underwent CAG following high risk TET were collected and categorized into those with critical CAD and others. The signal was converted to time series format. A dataset containing the P, QRS, and T wave times and amplitudes was created. Using this dataset, 5 machine learning algorithms were trained with 5-fold cross validation. All these models were then compared to the performance of cardiologists on V5 signal. The results from 5 machine learning models were clearly superior to the cardiologists' V5 signal performance (P < 0.0001). In addition, the XGBoost model, with an accuracy of 80.92±6.42% and an area under the curve (AUC) of 0.78±0.06, was the most successful model. Machine learning models can produce high-performance diagnoses using the V5 signal markers only as it does not require any clinical markers obtained from TET reports. This can lead to significant contributions to improving clinical prediction in non-invasive methods.</abstract><cop>United States</cop><pub>Elsevier Inc</pub><pmid>36336117</pmid><doi>10.1016/j.cpcardiol.2022.101482</doi><tpages>1</tpages><orcidid>https://orcid.org/0000-0002-4922-7391</orcidid></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0146-2806 |
ispartof | Current problems in cardiology, 2023-02, Vol.48 (2), p.101482-101482, Article 101482 |
issn | 0146-2806 1535-6280 |
language | eng |
recordid | cdi_proquest_miscellaneous_2733203829 |
source | ScienceDirect Freedom Collection 2022-2024 |
subjects | Coronary Angiography Coronary Artery Disease - diagnosis Electrocardiography Exercise Test - methods Humans Machine Learning |
title | Machine Learning Approach on High Risk Treadmill Exercise Test to Predict Obstructive Coronary Artery Disease by using P, QRS, and T waves’ Features |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-22T15%3A26%3A38IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Machine%20Learning%20Approach%20on%20High%20Risk%20Treadmill%20Exercise%20Test%20to%20Predict%20Obstructive%20Coronary%20Artery%20Disease%20by%20using%20P,%20QRS,%20and%20T%20waves%E2%80%99%20Features&rft.jtitle=Current%20problems%20in%20cardiology&rft.au=Yilmaz,%20Abdurrahim&rft.date=2023-02&rft.volume=48&rft.issue=2&rft.spage=101482&rft.epage=101482&rft.pages=101482-101482&rft.artnum=101482&rft.issn=0146-2806&rft.eissn=1535-6280&rft_id=info:doi/10.1016/j.cpcardiol.2022.101482&rft_dat=%3Cproquest_cross%3E2733203829%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c301t-afc55833f9851e6515dddec5a03a0628c222b2578a1cb0ed7813639a918245b93%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2733203829&rft_id=info:pmid/36336117&rfr_iscdi=true |