Development and validation of an artificial neural network algorithm to predict mortality and admission to hospital for heart failure after myocardial infarction: a nationwide population-based study
Patients have an estimated mortality of 15–20% within the first year following myocardial infarction and one in four patients who survive myocardial infarction will develop heart failure, severely reducing quality of life and increasing the risk of long-term mortality. We aimed to establish the accu...
Gespeichert in:
| Veröffentlicht in: | LANCET DIGITAL HEALTH 2022-01, Vol.4 (1), p.e37-e45 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | e45 |
|---|---|
| container_issue | 1 |
| container_start_page | e37 |
| container_title | LANCET DIGITAL HEALTH |
| container_volume | 4 |
| creator | Mohammad, Moman A Olesen, Kevin K W Koul, Sasha Gale, Chris P Rylance, Rebecca Jernberg, Tomas Baron, Tomasz Spaak, Jonas James, Stefan Lindahl, Bertil Maeng, Michael Erlinge, David |
| description | Patients have an estimated mortality of 15–20% within the first year following myocardial infarction and one in four patients who survive myocardial infarction will develop heart failure, severely reducing quality of life and increasing the risk of long-term mortality. We aimed to establish the accuracy of an artificial neural network (ANN) algorithm in predicting 1-year mortality and admission to hospital for heart failure after myocardial infarction.
In this nationwide population-based study, we used data for all patients admitted to hospital for myocardial infarction and discharged alive from a coronary care unit in Sweden (n=139 288) between Jan 1, 2008, and April 1, 2017, from the Swedish Web system for Enhancement and Development of Evidence-based care in Heart disease Evaluated According to Recommended Therapies (SWEDEHEART) nationwide registry; these patients were randomly divided into training (80%) and testing (20%) datasets. We developed an ANN using 21 variables (including age, sex, medical history, previous medications, in-hospital characteristics, and discharge medications) associated with the outcomes of interest with a back-propagation algorithm in the training dataset and tested it in the testing dataset. The ANN algorithm was then validated in patients with incident myocardial infarction enrolled in the Western Denmark Heart Registry (external validation cohort) between Jan 1, 2008, and Dec 31, 2016. The predictive ability of the model was evaluated using area under the receiver operating characteristic curve (AUROC) and Youden's index was established as a means of identifying an empirical dichotomous cutoff, allowing further evaluation of model performance.
139 288 patients who were admitted to hospital for myocardial infarction in the SWEDEHEART registry were randomly divided into a training dataset of 111 558 (80%) patients and a testing dataset of 27 730 (20%) patients. 30 971 patients with myocardial infarction who were enrolled in the Western Denmark Heart Registry were included in the external validation cohort. A first event, either all-cause mortality or admission to hospital for heart failure 1 year after myocardial infarction, occurred in 32 308 (23·2%) patients in the testing and training cohorts only. For 1-year all-cause mortality, the ANN had an AUROC of 0·85 (95% CI 0·84–0·85) in the testing dataset and 0·84 (0·83–0·84) in the external validation cohort. The AUROC for admission to hospital for heart failure within 1 year w |
| doi_str_mv | 10.1016/S2589-7500(21)00228-4 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_swepu</sourceid><recordid>TN_cdi_swepub_primary_oai_swepub_ki_se_456685</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S2589750021002284</els_id><sourcerecordid>2614233948</sourcerecordid><originalsourceid>FETCH-LOGICAL-c622t-a2c2462c627d5fe5999696d7b4f51ce72669423e310ee73b2062e12e810a89293</originalsourceid><addsrcrecordid>eNqFkstu1DAUhiMEolXpI4C8LFIDieM4DhtUtdykkVhw2VqOfdIxTeLgy4zmBXkuTmamFZuKhWX7-Dv_fyT_WfayLN6URcnffqO1aPOmLooLWr4uCkpFzp5kpw_lp_-cT7LzEH4VC1VWTdM8z04q1taUN-w0-3MDGxjcPMIUiZoM2ajBGhWtm4jrsUKUj7a32qqBTJD8fotb5--IGm6dt3E9kujI7MFYHcnofESJuNurKTPaEBYxRNYuzBYfSe88WQMKk17ZIXkgqo_gybhzWnmzWNmpV14vY7wjikz7gbbWAJndnIb9Ne9UAENCTGb3InvWqyHA-XE_y358_PD9-nO--vrpy_XVKtec0pgrqinjFC-NqXuo27blLTdNx_q61NBQzltGK6jKAqCpOlpwCiUFURZKtLStzrL8oBu2MKdOzt6Oyu-kU1YeS3d4AslqzkWN_OpRfkgzrg7X0tBBI3TLOol2vWSiZ7JDW6kEFctMXFBAuctH5W7szyvp_K1MSTJeFw1D_OKAz979ThCixN_QMAxqApeCpLxE5aplAtH6gGrvQvA4wr02zrBkTu4zJ5dASVrKfebkYvHqaJG6EcxD133CEHh_AAC_ZWPBy6AtTBrT4kFHaZz9j8VfJjnrJA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2614233948</pqid></control><display><type>article</type><title>Development and validation of an artificial neural network algorithm to predict mortality and admission to hospital for heart failure after myocardial infarction: a nationwide population-based study</title><source>MEDLINE</source><source>DOAJ Directory of Open Access Journals</source><source>SWEPUB Freely available online</source><source>EZB-FREE-00999 freely available EZB journals</source><source>Alma/SFX Local Collection</source><creator>Mohammad, Moman A ; Olesen, Kevin K W ; Koul, Sasha ; Gale, Chris P ; Rylance, Rebecca ; Jernberg, Tomas ; Baron, Tomasz ; Spaak, Jonas ; James, Stefan ; Lindahl, Bertil ; Maeng, Michael ; Erlinge, David</creator><creatorcontrib>Mohammad, Moman A ; Olesen, Kevin K W ; Koul, Sasha ; Gale, Chris P ; Rylance, Rebecca ; Jernberg, Tomas ; Baron, Tomasz ; Spaak, Jonas ; James, Stefan ; Lindahl, Bertil ; Maeng, Michael ; Erlinge, David</creatorcontrib><description>Patients have an estimated mortality of 15–20% within the first year following myocardial infarction and one in four patients who survive myocardial infarction will develop heart failure, severely reducing quality of life and increasing the risk of long-term mortality. We aimed to establish the accuracy of an artificial neural network (ANN) algorithm in predicting 1-year mortality and admission to hospital for heart failure after myocardial infarction.
In this nationwide population-based study, we used data for all patients admitted to hospital for myocardial infarction and discharged alive from a coronary care unit in Sweden (n=139 288) between Jan 1, 2008, and April 1, 2017, from the Swedish Web system for Enhancement and Development of Evidence-based care in Heart disease Evaluated According to Recommended Therapies (SWEDEHEART) nationwide registry; these patients were randomly divided into training (80%) and testing (20%) datasets. We developed an ANN using 21 variables (including age, sex, medical history, previous medications, in-hospital characteristics, and discharge medications) associated with the outcomes of interest with a back-propagation algorithm in the training dataset and tested it in the testing dataset. The ANN algorithm was then validated in patients with incident myocardial infarction enrolled in the Western Denmark Heart Registry (external validation cohort) between Jan 1, 2008, and Dec 31, 2016. The predictive ability of the model was evaluated using area under the receiver operating characteristic curve (AUROC) and Youden's index was established as a means of identifying an empirical dichotomous cutoff, allowing further evaluation of model performance.
139 288 patients who were admitted to hospital for myocardial infarction in the SWEDEHEART registry were randomly divided into a training dataset of 111 558 (80%) patients and a testing dataset of 27 730 (20%) patients. 30 971 patients with myocardial infarction who were enrolled in the Western Denmark Heart Registry were included in the external validation cohort. A first event, either all-cause mortality or admission to hospital for heart failure 1 year after myocardial infarction, occurred in 32 308 (23·2%) patients in the testing and training cohorts only. For 1-year all-cause mortality, the ANN had an AUROC of 0·85 (95% CI 0·84–0·85) in the testing dataset and 0·84 (0·83–0·84) in the external validation cohort. The AUROC for admission to hospital for heart failure within 1 year was 0·82 (0·81–0·82) in the testing dataset and 0·78 (0·77–0·79) in the external validation dataset. With an empirical cutoff the ANN algorithm correctly classified 73·6% of patients with regard to all-cause mortality and 61·5% of patients with regard to admission to hospital for heart failure in the external validation cohort, ruling out adverse outcomes with 97·1–98·7% probability in the external validation cohort.
Identifying patients at a high risk of developing heart failure or death after myocardial infarction could result in tailored therapies and monitoring by the allocation of resources to those at greatest risk.
The Swedish Heart and Lung Foundation, Swedish Scientific Research Council, Swedish Foundation for Strategic Research, Knut and Alice Wallenberg Foundation, ALF Agreement on Medical Education and Research, Skane University Hospital, The Bundy Academy, the Märta Winkler Foundation, the Anna-Lisa and Sven-Eric Lundgren Foundation for Medical Research.</description><identifier>ISSN: 2589-7500</identifier><identifier>EISSN: 2589-7500</identifier><identifier>DOI: 10.1016/S2589-7500(21)00228-4</identifier><identifier>PMID: 34952674</identifier><language>eng</language><publisher>England: Elsevier Ltd</publisher><subject>Aged ; Aged, 80 and over ; Cardiac and Cardiovascular Systems ; Clinical Medicine ; Female ; Heart Failure - etiology ; Heart Failure - mortality ; Hospitalization - statistics & numerical data ; Humans ; Kardiologi ; Klinisk medicin ; Male ; Medical and Health Sciences ; Medicin och hälsovetenskap ; Middle Aged ; Myocardial Infarction - complications ; Neural Networks, Computer ; Predictive Value of Tests ; Quality of Life ; Registries ; Risk Factors</subject><ispartof>LANCET DIGITAL HEALTH, 2022-01, Vol.4 (1), p.e37-e45</ispartof><rights>2022 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license</rights><rights>Copyright © 2022 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license. Published by Elsevier Ltd.. All rights reserved.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c622t-a2c2462c627d5fe5999696d7b4f51ce72669423e310ee73b2062e12e810a89293</citedby><cites>FETCH-LOGICAL-c622t-a2c2462c627d5fe5999696d7b4f51ce72669423e310ee73b2062e12e810a89293</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,314,550,776,780,860,881,4009,27902,27903,27904</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/34952674$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink><backlink>$$Uhttps://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-465074$$DView record from Swedish Publication Index$$Hfree_for_read</backlink><backlink>$$Uhttps://lup.lub.lu.se/record/be78c94b-12ef-48f4-b810-a8289423682e$$DView record from Swedish Publication Index$$Hfree_for_read</backlink><backlink>$$Uhttp://kipublications.ki.se/Default.aspx?queryparsed=id:148453621$$DView record from Swedish Publication Index$$Hfree_for_read</backlink></links><search><creatorcontrib>Mohammad, Moman A</creatorcontrib><creatorcontrib>Olesen, Kevin K W</creatorcontrib><creatorcontrib>Koul, Sasha</creatorcontrib><creatorcontrib>Gale, Chris P</creatorcontrib><creatorcontrib>Rylance, Rebecca</creatorcontrib><creatorcontrib>Jernberg, Tomas</creatorcontrib><creatorcontrib>Baron, Tomasz</creatorcontrib><creatorcontrib>Spaak, Jonas</creatorcontrib><creatorcontrib>James, Stefan</creatorcontrib><creatorcontrib>Lindahl, Bertil</creatorcontrib><creatorcontrib>Maeng, Michael</creatorcontrib><creatorcontrib>Erlinge, David</creatorcontrib><title>Development and validation of an artificial neural network algorithm to predict mortality and admission to hospital for heart failure after myocardial infarction: a nationwide population-based study</title><title>LANCET DIGITAL HEALTH</title><addtitle>Lancet Digit Health</addtitle><description>Patients have an estimated mortality of 15–20% within the first year following myocardial infarction and one in four patients who survive myocardial infarction will develop heart failure, severely reducing quality of life and increasing the risk of long-term mortality. We aimed to establish the accuracy of an artificial neural network (ANN) algorithm in predicting 1-year mortality and admission to hospital for heart failure after myocardial infarction.
In this nationwide population-based study, we used data for all patients admitted to hospital for myocardial infarction and discharged alive from a coronary care unit in Sweden (n=139 288) between Jan 1, 2008, and April 1, 2017, from the Swedish Web system for Enhancement and Development of Evidence-based care in Heart disease Evaluated According to Recommended Therapies (SWEDEHEART) nationwide registry; these patients were randomly divided into training (80%) and testing (20%) datasets. We developed an ANN using 21 variables (including age, sex, medical history, previous medications, in-hospital characteristics, and discharge medications) associated with the outcomes of interest with a back-propagation algorithm in the training dataset and tested it in the testing dataset. The ANN algorithm was then validated in patients with incident myocardial infarction enrolled in the Western Denmark Heart Registry (external validation cohort) between Jan 1, 2008, and Dec 31, 2016. The predictive ability of the model was evaluated using area under the receiver operating characteristic curve (AUROC) and Youden's index was established as a means of identifying an empirical dichotomous cutoff, allowing further evaluation of model performance.
139 288 patients who were admitted to hospital for myocardial infarction in the SWEDEHEART registry were randomly divided into a training dataset of 111 558 (80%) patients and a testing dataset of 27 730 (20%) patients. 30 971 patients with myocardial infarction who were enrolled in the Western Denmark Heart Registry were included in the external validation cohort. A first event, either all-cause mortality or admission to hospital for heart failure 1 year after myocardial infarction, occurred in 32 308 (23·2%) patients in the testing and training cohorts only. For 1-year all-cause mortality, the ANN had an AUROC of 0·85 (95% CI 0·84–0·85) in the testing dataset and 0·84 (0·83–0·84) in the external validation cohort. The AUROC for admission to hospital for heart failure within 1 year was 0·82 (0·81–0·82) in the testing dataset and 0·78 (0·77–0·79) in the external validation dataset. With an empirical cutoff the ANN algorithm correctly classified 73·6% of patients with regard to all-cause mortality and 61·5% of patients with regard to admission to hospital for heart failure in the external validation cohort, ruling out adverse outcomes with 97·1–98·7% probability in the external validation cohort.
Identifying patients at a high risk of developing heart failure or death after myocardial infarction could result in tailored therapies and monitoring by the allocation of resources to those at greatest risk.
The Swedish Heart and Lung Foundation, Swedish Scientific Research Council, Swedish Foundation for Strategic Research, Knut and Alice Wallenberg Foundation, ALF Agreement on Medical Education and Research, Skane University Hospital, The Bundy Academy, the Märta Winkler Foundation, the Anna-Lisa and Sven-Eric Lundgren Foundation for Medical Research.</description><subject>Aged</subject><subject>Aged, 80 and over</subject><subject>Cardiac and Cardiovascular Systems</subject><subject>Clinical Medicine</subject><subject>Female</subject><subject>Heart Failure - etiology</subject><subject>Heart Failure - mortality</subject><subject>Hospitalization - statistics & numerical data</subject><subject>Humans</subject><subject>Kardiologi</subject><subject>Klinisk medicin</subject><subject>Male</subject><subject>Medical and Health Sciences</subject><subject>Medicin och hälsovetenskap</subject><subject>Middle Aged</subject><subject>Myocardial Infarction - complications</subject><subject>Neural Networks, Computer</subject><subject>Predictive Value of Tests</subject><subject>Quality of Life</subject><subject>Registries</subject><subject>Risk Factors</subject><issn>2589-7500</issn><issn>2589-7500</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><sourceid>D8T</sourceid><recordid>eNqFkstu1DAUhiMEolXpI4C8LFIDieM4DhtUtdykkVhw2VqOfdIxTeLgy4zmBXkuTmamFZuKhWX7-Dv_fyT_WfayLN6URcnffqO1aPOmLooLWr4uCkpFzp5kpw_lp_-cT7LzEH4VC1VWTdM8z04q1taUN-w0-3MDGxjcPMIUiZoM2ajBGhWtm4jrsUKUj7a32qqBTJD8fotb5--IGm6dt3E9kujI7MFYHcnofESJuNurKTPaEBYxRNYuzBYfSe88WQMKk17ZIXkgqo_gybhzWnmzWNmpV14vY7wjikz7gbbWAJndnIb9Ne9UAENCTGb3InvWqyHA-XE_y358_PD9-nO--vrpy_XVKtec0pgrqinjFC-NqXuo27blLTdNx_q61NBQzltGK6jKAqCpOlpwCiUFURZKtLStzrL8oBu2MKdOzt6Oyu-kU1YeS3d4AslqzkWN_OpRfkgzrg7X0tBBI3TLOol2vWSiZ7JDW6kEFctMXFBAuctH5W7szyvp_K1MSTJeFw1D_OKAz979ThCixN_QMAxqApeCpLxE5aplAtH6gGrvQvA4wr02zrBkTu4zJ5dASVrKfebkYvHqaJG6EcxD133CEHh_AAC_ZWPBy6AtTBrT4kFHaZz9j8VfJjnrJA</recordid><startdate>202201</startdate><enddate>202201</enddate><creator>Mohammad, Moman A</creator><creator>Olesen, Kevin K W</creator><creator>Koul, Sasha</creator><creator>Gale, Chris P</creator><creator>Rylance, Rebecca</creator><creator>Jernberg, Tomas</creator><creator>Baron, Tomasz</creator><creator>Spaak, Jonas</creator><creator>James, Stefan</creator><creator>Lindahl, Bertil</creator><creator>Maeng, Michael</creator><creator>Erlinge, David</creator><general>Elsevier Ltd</general><scope>6I.</scope><scope>AAFTH</scope><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><scope>ACNBI</scope><scope>ADTPV</scope><scope>AOWAS</scope><scope>D8T</scope><scope>DF2</scope><scope>ZZAVC</scope><scope>AGCHP</scope><scope>D95</scope></search><sort><creationdate>202201</creationdate><title>Development and validation of an artificial neural network algorithm to predict mortality and admission to hospital for heart failure after myocardial infarction: a nationwide population-based study</title><author>Mohammad, Moman A ; Olesen, Kevin K W ; Koul, Sasha ; Gale, Chris P ; Rylance, Rebecca ; Jernberg, Tomas ; Baron, Tomasz ; Spaak, Jonas ; James, Stefan ; Lindahl, Bertil ; Maeng, Michael ; Erlinge, David</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c622t-a2c2462c627d5fe5999696d7b4f51ce72669423e310ee73b2062e12e810a89293</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Aged</topic><topic>Aged, 80 and over</topic><topic>Cardiac and Cardiovascular Systems</topic><topic>Clinical Medicine</topic><topic>Female</topic><topic>Heart Failure - etiology</topic><topic>Heart Failure - mortality</topic><topic>Hospitalization - statistics & numerical data</topic><topic>Humans</topic><topic>Kardiologi</topic><topic>Klinisk medicin</topic><topic>Male</topic><topic>Medical and Health Sciences</topic><topic>Medicin och hälsovetenskap</topic><topic>Middle Aged</topic><topic>Myocardial Infarction - complications</topic><topic>Neural Networks, Computer</topic><topic>Predictive Value of Tests</topic><topic>Quality of Life</topic><topic>Registries</topic><topic>Risk Factors</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Mohammad, Moman A</creatorcontrib><creatorcontrib>Olesen, Kevin K W</creatorcontrib><creatorcontrib>Koul, Sasha</creatorcontrib><creatorcontrib>Gale, Chris P</creatorcontrib><creatorcontrib>Rylance, Rebecca</creatorcontrib><creatorcontrib>Jernberg, Tomas</creatorcontrib><creatorcontrib>Baron, Tomasz</creatorcontrib><creatorcontrib>Spaak, Jonas</creatorcontrib><creatorcontrib>James, Stefan</creatorcontrib><creatorcontrib>Lindahl, Bertil</creatorcontrib><creatorcontrib>Maeng, Michael</creatorcontrib><creatorcontrib>Erlinge, David</creatorcontrib><collection>ScienceDirect Open Access Titles</collection><collection>Elsevier:ScienceDirect:Open Access</collection><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><collection>SWEPUB Uppsala universitet full text</collection><collection>SwePub</collection><collection>SwePub Articles</collection><collection>SWEPUB Freely available online</collection><collection>SWEPUB Uppsala universitet</collection><collection>SwePub Articles full text</collection><collection>SWEPUB Lunds universitet full text</collection><collection>SWEPUB Lunds universitet</collection><jtitle>LANCET DIGITAL HEALTH</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Mohammad, Moman A</au><au>Olesen, Kevin K W</au><au>Koul, Sasha</au><au>Gale, Chris P</au><au>Rylance, Rebecca</au><au>Jernberg, Tomas</au><au>Baron, Tomasz</au><au>Spaak, Jonas</au><au>James, Stefan</au><au>Lindahl, Bertil</au><au>Maeng, Michael</au><au>Erlinge, David</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Development and validation of an artificial neural network algorithm to predict mortality and admission to hospital for heart failure after myocardial infarction: a nationwide population-based study</atitle><jtitle>LANCET DIGITAL HEALTH</jtitle><addtitle>Lancet Digit Health</addtitle><date>2022-01</date><risdate>2022</risdate><volume>4</volume><issue>1</issue><spage>e37</spage><epage>e45</epage><pages>e37-e45</pages><issn>2589-7500</issn><eissn>2589-7500</eissn><abstract>Patients have an estimated mortality of 15–20% within the first year following myocardial infarction and one in four patients who survive myocardial infarction will develop heart failure, severely reducing quality of life and increasing the risk of long-term mortality. We aimed to establish the accuracy of an artificial neural network (ANN) algorithm in predicting 1-year mortality and admission to hospital for heart failure after myocardial infarction.
In this nationwide population-based study, we used data for all patients admitted to hospital for myocardial infarction and discharged alive from a coronary care unit in Sweden (n=139 288) between Jan 1, 2008, and April 1, 2017, from the Swedish Web system for Enhancement and Development of Evidence-based care in Heart disease Evaluated According to Recommended Therapies (SWEDEHEART) nationwide registry; these patients were randomly divided into training (80%) and testing (20%) datasets. We developed an ANN using 21 variables (including age, sex, medical history, previous medications, in-hospital characteristics, and discharge medications) associated with the outcomes of interest with a back-propagation algorithm in the training dataset and tested it in the testing dataset. The ANN algorithm was then validated in patients with incident myocardial infarction enrolled in the Western Denmark Heart Registry (external validation cohort) between Jan 1, 2008, and Dec 31, 2016. The predictive ability of the model was evaluated using area under the receiver operating characteristic curve (AUROC) and Youden's index was established as a means of identifying an empirical dichotomous cutoff, allowing further evaluation of model performance.
139 288 patients who were admitted to hospital for myocardial infarction in the SWEDEHEART registry were randomly divided into a training dataset of 111 558 (80%) patients and a testing dataset of 27 730 (20%) patients. 30 971 patients with myocardial infarction who were enrolled in the Western Denmark Heart Registry were included in the external validation cohort. A first event, either all-cause mortality or admission to hospital for heart failure 1 year after myocardial infarction, occurred in 32 308 (23·2%) patients in the testing and training cohorts only. For 1-year all-cause mortality, the ANN had an AUROC of 0·85 (95% CI 0·84–0·85) in the testing dataset and 0·84 (0·83–0·84) in the external validation cohort. The AUROC for admission to hospital for heart failure within 1 year was 0·82 (0·81–0·82) in the testing dataset and 0·78 (0·77–0·79) in the external validation dataset. With an empirical cutoff the ANN algorithm correctly classified 73·6% of patients with regard to all-cause mortality and 61·5% of patients with regard to admission to hospital for heart failure in the external validation cohort, ruling out adverse outcomes with 97·1–98·7% probability in the external validation cohort.
Identifying patients at a high risk of developing heart failure or death after myocardial infarction could result in tailored therapies and monitoring by the allocation of resources to those at greatest risk.
The Swedish Heart and Lung Foundation, Swedish Scientific Research Council, Swedish Foundation for Strategic Research, Knut and Alice Wallenberg Foundation, ALF Agreement on Medical Education and Research, Skane University Hospital, The Bundy Academy, the Märta Winkler Foundation, the Anna-Lisa and Sven-Eric Lundgren Foundation for Medical Research.</abstract><cop>England</cop><pub>Elsevier Ltd</pub><pmid>34952674</pmid><doi>10.1016/S2589-7500(21)00228-4</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2589-7500 |
| ispartof | LANCET DIGITAL HEALTH, 2022-01, Vol.4 (1), p.e37-e45 |
| issn | 2589-7500 2589-7500 |
| language | eng |
| recordid | cdi_swepub_primary_oai_swepub_ki_se_456685 |
| source | MEDLINE; DOAJ Directory of Open Access Journals; SWEPUB Freely available online; EZB-FREE-00999 freely available EZB journals; Alma/SFX Local Collection |
| subjects | Aged Aged, 80 and over Cardiac and Cardiovascular Systems Clinical Medicine Female Heart Failure - etiology Heart Failure - mortality Hospitalization - statistics & numerical data Humans Kardiologi Klinisk medicin Male Medical and Health Sciences Medicin och hälsovetenskap Middle Aged Myocardial Infarction - complications Neural Networks, Computer Predictive Value of Tests Quality of Life Registries Risk Factors |
| title | Development and validation of an artificial neural network algorithm to predict mortality and admission to hospital for heart failure after myocardial infarction: a nationwide population-based study |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-24T12%3A33%3A16IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_swepu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Development%20and%20validation%20of%20an%20artificial%20neural%20network%20algorithm%20to%20predict%20mortality%20and%20admission%20to%20hospital%20for%20heart%20failure%20after%20myocardial%20infarction:%20a%20nationwide%20population-based%20study&rft.jtitle=LANCET%20DIGITAL%20HEALTH&rft.au=Mohammad,%20Moman%20A&rft.date=2022-01&rft.volume=4&rft.issue=1&rft.spage=e37&rft.epage=e45&rft.pages=e37-e45&rft.issn=2589-7500&rft.eissn=2589-7500&rft_id=info:doi/10.1016/S2589-7500(21)00228-4&rft_dat=%3Cproquest_swepu%3E2614233948%3C/proquest_swepu%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2614233948&rft_id=info:pmid/34952674&rft_els_id=S2589750021002284&rfr_iscdi=true |