Dynamic evaluation of a COVID-19 death prediction model using Extreme Gradient Boosting Predictive Model/Modelo preditivo de avaliaçao dinâmica de morte por COVID-19 usando Extreme Gradient Boosting/Evaluacion dinámica de un modelo de prediccion de muertes por COVID-19 utilizando modelo Extreme Gradient Boosting
The COVID-19 pandemic has evolved dynamically with the emergence of new variants and an increase in vaccination coverage. Given the high fatality rate of severe COVID-19, disease severity prediction models must incorporate these temporal variations. In this light, the present study seeks to develop...
Uložené v:
| Vydané v: | Ciência & saude coletiva Ročník 30; číslo 7; s. 1 - 15 |
|---|---|
| Hlavní autori: | , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Associacao Brasileira de Pos-Graduacao em Saude Coletiva - ABRASCO
01.07.2025
|
| Predmet: | |
| ISSN: | 1413-8123 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | The COVID-19 pandemic has evolved dynamically with the emergence of new variants and an increase in vaccination coverage. Given the high fatality rate of severe COVID-19, disease severity prediction models must incorporate these temporal variations. In this light, the present study seeks to develop a model to predict COVID-19 mortality in hospitalized patients. The Extreme Gradient Boost model was used to predict COVID-19 mortality upon hospital admission, and the results were correlated with laboratory test results, vaccination status, comorbidities, and clinical signs and symptoms at the time of admission. Clinical data from electronic medical records, vaccination databases, and severe acute respiratory syndrome (SARS) reports were used. The XGBoost model performed best, with an area under the curve (AUC) of 96.4% at epidemiological week 53 of 2020. The most significant variables for the model were body temperature, blood pressure, respiratory rate, heart rate, urea, magnesium, sodium, and C reactive protein levels. Our study identified key clinical and laboratory variables for predicting COVID-19 mortality. |
|---|---|
| AbstractList | The COVID-19 pandemic has evolved dynamically with the emergence of new variants and an increase in vaccination coverage. Given the high fatality rate of severe COVID-19, disease severity prediction models must incorporate these temporal variations. In this light, the present study seeks to develop a model to predict COVID-19 mortality in hospitalized patients. The Extreme Gradient Boost model was used to predict COVID-19 mortality upon hospital admission, and the results were correlated with laboratory test results, vaccination status, comorbidities, and clinical signs and symptoms at the time of admission. Clinical data from electronic medical records, vaccination databases, and severe acute respiratory syndrome (SARS) reports were used. The XGBoost model performed best, with an area under the curve (AUC) of 96.4% at epidemiological week 53 of 2020. The most significant variables for the model were body temperature, blood pressure, respiratory rate, heart rate, urea, magnesium, sodium, and C reactive protein levels. Our study identified key clinical and laboratory variables for predicting COVID-19 mortality. Key words Predictive modeling, COVID-19, Mortality, Machine learning, XGBoost algorithm Resumo A pandemia de COVID-19 evoluiu de forma dinâmica com o surgimento de novas variantes e o aumento da cobertura vacinal. Dada a alta taxa de mortalidade da COVID-19 grave, os modelos de previsao de gravidade da doença precisam incorporar essas variações temporais. Este estudo teve como objetivo desenvolver um modelo para prever a mortalidade por COVID-19 em pacientes hospitalizados. O modelo Extreme Gradient Boost (XGBoost) foi utilizado para prever a mortalidade por COVID-19 na admissao hospitalar, e os resultados foram correlacionados com os resultados de exames laboratoriais, status vacinal, comorbidades e sinais e sintomas clínicos no momento da admissao. Dados clínicos de prontuários eletrônicos, bancos de dados de vacinaçao e notificações de síndrome respiratoria aguda grave foram utilizados. O modelo XGBoost obteve o melhor desempenho, com uma área sob a curva (AUC) de 96,4% na semana epidemiologica 53 de 2020. As variáveis mais significativas para o modelo foram temperatura corporal, pressao arterial, taxa respiratoria, frequência cardíaca, ureia, magnesio, níveis de sodio e proteína C reativa. Nosso estudo identificou variáveis clínicas e laboratoriais chave para a previsao de mortalidade por COVID-19. Palavras-chave Modelagem preditiva, COVID-19, Mortalidade, Aprendizado de máquina, Algoritmo XGBoost La pandemia de COVID-19 ha evolucionado dinámicamente con la aparicion de nuevas variantes y la progresion de la cobertura de vacunacion. Dada la alta tasa de mortalidad de la COVID-19 grave, los modelos de prediccion de la gravedad de la enfermedad deben incorporar estas variaciones temporales. En este estudio pretendemos entrenar un modelo para predecir la muerte de pacientes hospitalizados por COVID-19. Se utilizaron modelos predictivos de aprendizaje automático para predecir las muertes por COVID-19 al momento del ingreso hospitalario, y los resultados se correlacionaron con los resultados de las pruebas de laboratorio, el estado de vacunacion, las comorbilidades y los signos y síntomas en el momento del ingreso. Se utilizaron datos clínicos de historias clínicas electronicas, bases de datos de vacunacion y notificaciones de síndrome respiratorio agudo severo. El modelo predictivo XGBoost tuvo el mejor rendimiento, con un área bajo la curva (AUC) del 96,4% en la semana epidemiologica 53 de 2020. Las variables más significativas para el modelo fueron la temperatura, la presion arterial, la frecuencia respiratoria, la frecuencia cardíaca, y niveles de urea, magnesio, sodio y proteína C reactiva. Nuestro estudio identifico variables clínicas y de laboratorio clave para predecir la mortalidad por COVID-19. Palabras clave Modelado predictivo, COVID-19, Mortalidad, Aprendizaje automático, Modelo XGBoost The COVID-19 pandemic has evolved dynamically with the emergence of new variants and an increase in vaccination coverage. Given the high fatality rate of severe COVID-19, disease severity prediction models must incorporate these temporal variations. In this light, the present study seeks to develop a model to predict COVID-19 mortality in hospitalized patients. The Extreme Gradient Boost model was used to predict COVID-19 mortality upon hospital admission, and the results were correlated with laboratory test results, vaccination status, comorbidities, and clinical signs and symptoms at the time of admission. Clinical data from electronic medical records, vaccination databases, and severe acute respiratory syndrome (SARS) reports were used. The XGBoost model performed best, with an area under the curve (AUC) of 96.4% at epidemiological week 53 of 2020. The most significant variables for the model were body temperature, blood pressure, respiratory rate, heart rate, urea, magnesium, sodium, and C reactive protein levels. Our study identified key clinical and laboratory variables for predicting COVID-19 mortality. |
| Audience | Academic |
| Author | Evsukoff, Alexandre Prado, Jose Carlos Andrade Medronho, Roberto de |
| Author_xml | – sequence: 1 fullname: Prado, Jose Carlos – sequence: 2 fullname: Evsukoff, Alexandre – sequence: 3 fullname: Andrade Medronho, Roberto de |
| BookMark | eNp1Ut1OFDEUHhJMBPQdSrzyYnbbaTs_CTe4LLgRAxfq7eZse2YtmWnJtEOAt9EbH4QXszO7ChhJk_6c8_216X6ya53FJDlkdMJkRadMMJ6WLOMZzSSnxYSVjMW92E32_vZeJ_veX1GaFVxkeztHJ3cWWqMI3kDTQzDOElcTILOLb4uTlFVEI4Tv5LpDbdTYbp3GhvTe2DWZ34YOWyRnHWiDNpAPzvkwdC63hBsknwfCdJzdRiiWXRQmEE0NPPyCeDL24WcMAkO9dV1Acu26xxi9B6vdy4bT-XgBNSQctH780eq3iUfDzTU2oGjTY_Tx_xgF05j70WzLe9HzTfKqhsbj2-16kHw9nX-ZfUzPL84Ws-PzdM0oo6mSlS5LJXJRUC1XJROUoazKmmcSmChlIYEXRbWSWuaC0nyVI8VCMagkV5zxg-TdRncNDS6NrV3oQLXGq-VxKXMmZE5pRE3-g4pDY3yL-FVqE-vPCO-fESIm4G1YQ-_98tPl4in2N3WfxBw |
| ContentType | Journal Article |
| Copyright | COPYRIGHT 2025 Associacao Brasileira de Pos-Graduacao em Saude Coletiva - ABRASCO |
| Copyright_xml | – notice: COPYRIGHT 2025 Associacao Brasileira de Pos-Graduacao em Saude Coletiva - ABRASCO |
| DBID | KPI INF |
| DOI | 10.1590/1413-81232025307.18112024 |
| DatabaseName | Gale In Context: Global Issues Gale OneFile: Informe Academico |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Public Health |
| ExternalDocumentID | A856145600 |
| GeographicLocations | Brasil América Latina |
| GeographicLocations_xml | – name: América Latina – name: Brasil |
| GroupedDBID | 2WC 53G 5GY 5VS 7RV 7X7 88E 8C1 8FE 8FG 8FI 8FJ 8G5 ABDHV ABJCF ABUWG ABXHO ACHQT ACIWK ADBBV AFFHD AFKRA AHMBA ALMA_UNASSIGNED_HOLDINGS APOWU AZQEC BAIFH BAWUL BBTPI BCNDV BENPR BGLVJ BKEYQ BPHCQ BVXVI CCPQU C~G DIK DU5 DWQXO E3Z EBD EBS ECGQY EJD EMOBN F5P FYUFA GNUQQ GUQSH HCIFZ HMCUK IAO INF INH INR ITC J34 KPI KQ8 L6V M1P M2O M7S NAPCQ OK1 OVT PHGZM PHGZT PIMPY PJZUB PPXIY PQGLB PQQKQ PROAC PSQYO PTHSS PV9 RDY RNS RSC RSL RZL SCD SV3 UKHRP XSB |
| ID | FETCH-LOGICAL-g1010-c59d88c46470d5b81401e598f325a148575a3779b5d564006b6e0e7c1a953c313 |
| ISSN | 1413-8123 |
| IngestDate | Sat Nov 29 13:46:39 EST 2025 Tue Nov 04 18:09:44 EST 2025 Thu Nov 13 15:53:37 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 7 |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-g1010-c59d88c46470d5b81401e598f325a148575a3779b5d564006b6e0e7c1a953c313 |
| PageCount | 15 |
| ParticipantIDs | gale_infotracmisc_A856145600 gale_infotracacademiconefile_A856145600 gale_incontextgauss_KPI_A856145600 |
| PublicationCentury | 2000 |
| PublicationDate | 20250701 |
| PublicationDateYYYYMMDD | 2025-07-01 |
| PublicationDate_xml | – month: 07 year: 2025 text: 20250701 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Ciência & saude coletiva |
| PublicationYear | 2025 |
| Publisher | Associacao Brasileira de Pos-Graduacao em Saude Coletiva - ABRASCO |
| Publisher_xml | – name: Associacao Brasileira de Pos-Graduacao em Saude Coletiva - ABRASCO |
| SSID | ssj0027342 |
| Score | 2.36882 |
| Snippet | The COVID-19 pandemic has evolved dynamically with the emergence of new variants and an increase in vaccination coverage. Given the high fatality rate of... |
| SourceID | gale |
| SourceType | Aggregation Database |
| StartPage | 1 |
| Title | Dynamic evaluation of a COVID-19 death prediction model using Extreme Gradient Boosting Predictive Model/Modelo preditivo de avaliaçao dinâmica de morte por COVID-19 usando Extreme Gradient Boosting/Evaluacion dinámica de un modelo de prediccion de muertes por COVID-19 utilizando modelo Extreme Gradient Boosting |
| Volume | 30 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVPQU databaseName: Engineering Database issn: 1413-8123 databaseCode: M7S dateStart: 19980101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: http://search.proquest.com omitProxy: false ssIdentifier: ssj0027342 providerName: ProQuest – providerCode: PRVPQU databaseName: Health & Medical Collection issn: 1413-8123 databaseCode: 7X7 dateStart: 19980101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://search.proquest.com/healthcomplete omitProxy: false ssIdentifier: ssj0027342 providerName: ProQuest – providerCode: PRVPQU databaseName: Nursing & Allied Health Database issn: 1413-8123 databaseCode: 7RV dateStart: 19980101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://search.proquest.com/nahs omitProxy: false ssIdentifier: ssj0027342 providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central issn: 1413-8123 databaseCode: BENPR dateStart: 19980101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.proquest.com/central omitProxy: false ssIdentifier: ssj0027342 providerName: ProQuest – providerCode: PRVPQU databaseName: Public Health Database (ProQuest) issn: 1413-8123 databaseCode: 8C1 dateStart: 19980101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://search.proquest.com/publichealth omitProxy: false ssIdentifier: ssj0027342 providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database issn: 1413-8123 databaseCode: PIMPY dateStart: 19980101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: http://search.proquest.com/publiccontent omitProxy: false ssIdentifier: ssj0027342 providerName: ProQuest – providerCode: PRVPQU databaseName: Research Library issn: 1413-8123 databaseCode: M2O dateStart: 19980101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://search.proquest.com/pqrl omitProxy: false ssIdentifier: ssj0027342 providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwEDZtQQgJIZ6iUJBBSByiaDfvROKy3ZaHoO2Klqq3ynlsiWhjlGxW_Ttw4S9w7x9jZuw8FnWlcuCSzcbJfHY8XzxxxjOMvXKjzHMSOzSFb0emGwrXFNk0M0USJGngx8KjLAqHn4Ld3fDoKJqsrP5u1sLMT4OiCM_Po-__tavhGHQ2Lp39h-5uhcIB2IdOhy10O2yv1PFbKsd8L463WgM53jv8sGVakZGi1YfBAdJc5QmnbDhGTbMG2-cznDE03pXkCzbDxRAVuUZP9AWYrQgvgBrSr1SioECCaEPMceaEvr8HAo7kBe3bGJYAy8_Qu9cAq7-rEDoGpXI5NCBtU2MSrG0j0Wok1roFBK-apU4EsDorcWJ5EW6Woy8bQurrliL3TfdxTrAjjE9ChKlEnaKvP4Yvn7ej2wRkyObbCvrTnMrea0tVf5M6DqZaWdT5HqNrqQCBO1layuKr7Pzepcrh3s7O2F7ryav5pDiWwP3eLEUFD_q8pFszkZWJjaqpLDsz9qnOY11nwzRGm59H--O93tgE9oYJ9pjTH7z0Ry1F0qA3ElmXjo9eNKQIC1oS1tjBKcYQzO6hWsy-GJP84-SymOSjEAPIorG8yq7bgRehM-WOvddNdTiUtqoFusleaPjBUnBtFPXMu4O77I5-L-Mjxad7bCUr7rPbalKbq7V6D6690dziHbe4nHLBG93ixC3ecYuThnHiFtdqxhs1442a8Y5bnDg1UMziLbNAMFfMuvgl4F9eXPxE_cfjxCgOKt5VQzFqOeCg4xPJ-tHIqnWNCbDjEsEoLv0F1HKpuW4p5kP25e32wfi9qdOvmCcWusgkXpSGYeL6bjBMvRhD41kZdPXUsT1huZjaV2C40thLPR9MAT_2s2EWJJaI4PHvWM4jtlbIInvMeOrZcZhM46GdgTUcBCK2vNR3w3iYTi3HidfZS-z6YwxIU6DH24moq-oYlO-4U7V19lqfNJWzEnijFxABBMawWzhzY-FMGDGTXvGTq6A9Zbc6Pm-wtVlZZ8_YjWQ-y6vyOWn7HzadO48 |
| linkProvider | ProQuest |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Dynamic+evaluation+of+a+COVID-19+death+prediction+model+using+Extreme+Gradient+Boosting+Predictive+Model%2FModelo+preditivo+de+avalia%C3%A7ao+din%C3%A2mica+de+morte+por+COVID-19+usando+Extreme+Gradient+Boosting%2FEvaluacion+din%C3%A1mica+de+un+modelo+de+prediccion+de+muertes+por+COVID-19+utilizando+modelo+Extreme+Gradient+Boosting&rft.jtitle=Ci%C3%AAncia+%26+saude+coletiva&rft.au=Prado%2C+Jose+Carlos&rft.au=Evsukoff%2C+Alexandre&rft.au=Andrade+Medronho%2C+Roberto+de&rft.date=2025-07-01&rft.pub=Associacao+Brasileira+de+Pos-Graduacao+em+Saude+Coletiva+-+ABRASCO&rft.issn=1413-8123&rft.volume=30&rft.issue=7&rft.spage=1&rft_id=info:doi/10.1590%2F1413-81232025307.18112024&rft.externalDBID=KPI&rft.externalDocID=A856145600 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1413-8123&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1413-8123&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1413-8123&client=summon |