Development of a severity of disease score and classification model by machine learning for hospitalized COVID-19 patients.
[EN]Efficient and early triage of hospitalized Covid-19 patients to detect those with higher risk of severe disease is essential for appropriate case management. We trained, validated, and externally tested a machine-learning model to early identify patients who will die or require mechanical ventil...
| Autores: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Tipo de recurso: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2021 |
| País: | España |
| Institución: | Universidad de Salamanca (USAL) |
| Repositorio: | GREDOS. Repositorio Institucional de la Universidad de Salamanca |
| OAI Identifier: | oai:gredos.usal.es:10366/161982 |
| Acceso en línea: | http://hdl.handle.net/10366/161982 |
| Access Level: | acceso abierto |
| Palabra clave: | Machine learning Covid-19 Disease score Hospitalized Artificial intelligence SARS-CoV-2 Area Under Curve Aged Adult Risk Assessment Forecasting Humans Middle Aged Hospitalization Severity of Illness Index Respiration Cohort Studies ROC Curve Retrospective Studies humanos índice de gravedad de la enfermedad anciano mediana edad curva ROC estudios retrospectivos adulto hospitalización evaluación de riesgos estudios de cohortes predicción respiración área bajo la curva |
| id |
ES_3d89bc3d378a89dcfd5fbf79e77bf964 |
|---|---|
| oai_identifier_str |
oai:gredos.usal.es:10366/161982 |
| network_acronym_str |
ES |
| network_name_str |
España |
| repository_id_str |
|
| spelling |
Development of a severity of disease score and classification model by machine learning for hospitalized COVID-19 patients.Marcos Martín, MiguelBelhassen-García, MoncefSánchez-Puente, AntonioSampedro-Gómez, JesúsAzibeiro, RaúlDorado Díaz, Pedro IgnacioMarcano-Millán, EdgarGarcía-Vidal, CarolinaMoreiro Barroso, María TeresaCubino Bóveda, NoeliaPérez-García, María-LuisaRodríguez-Alonso, BeatrizEncinas-Sánchez, DanielPeña-Balbuena, SoniaSobejano-Fuertes, EduardoInés, SandraCarbonell, CristinaLópez Parra, MiriamAndrade-Meira, FernandaLópez-Bernús, AmparoLorenzo, CatalinaCarpio, AdelaPolo-San-Ricardo, DavidSánchez Hernández, Miguel VicenteBorrás Beato, RafaelSagredo-Meneses, VíctorSánchez Fernández, Pedro LuisSoriano, AlexMartín Oterino, José ÁngelMachine learningCovid-19Disease scoreHospitalizedArtificial intelligenceSARS-CoV-2Area Under CurveAgedAdultRisk AssessmentForecastingHumansMiddle AgedHospitalizationSeverity of Illness IndexRespirationCohort StudiesROC CurveRetrospective Studieshumanosíndice de gravedad de la enfermedadancianomediana edadcurva ROCestudios retrospectivosadultohospitalizaciónevaluación de riesgosestudios de cohortespredicciónrespiraciónárea bajo la curva[EN]Efficient and early triage of hospitalized Covid-19 patients to detect those with higher risk of severe disease is essential for appropriate case management. We trained, validated, and externally tested a machine-learning model to early identify patients who will die or require mechanical ventilation during hospitalization from clinical and laboratory features obtained at admission. A development cohort with 918 Covid-19 patients was used for training and internal validation, and 352 patients from another hospital were used for external testing. Performance of the model was evaluated by calculating the area under the receiver-operating-characteristic curve (AUC), sensitivity and specificity. A total of 363 of 918 (39.5%) and 128 of 352 (36.4%) Covid-19 patients from the development and external testing cohort, respectively, required mechanical ventilation or died during hospitalization. In the development cohort, the model obtained an AUC of 0.85 (95% confidence interval [CI], 0.82 to 0.87) for predicting severity of disease progression. Variables ranked according to their contribution to the model were the peripheral blood oxygen saturation (SpO2)/fraction of inspired oxygen (FiO2) ratio, age, estimated glomerular filtration rate, procalcitonin, C-reactive protein, updated Charlson comorbidity index and lymphocytes. In the external testing cohort, the model performed an AUC of 0.83 (95% CI, 0.81 to 0.85). This model is deployed in an open source calculator, in which Covid-19 patients at admission are individually stratified as being at high or non-high risk for severe disease progression. This machine-learning model, applied at hospital admission, predicts risk of severe disease progression in Covid-19 patients.Este trabajo fue financiado parcialmente por Instituto de Salud Carlos III, Ministerio de Ciencia y Tecnología Innovación (Madrid, España) y Fondos FEDER “Una Manera de hacer Europa”, con becas CIBERCV CB16/11/00374 a Pedro-Luis Sanchez y RD16/ 0017/0023 a Miguel Marcos, y por el Instituto de Instituto de Investigación Biomédica de Salamanca (IBSAL) a través de una subvención especial para la investigación de Covid-19.Public Library of Science (PLOS)202520252021info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://hdl.handle.net/10366/161982reponame:GREDOS. Repositorio Institucional de la Universidad de Salamancainstname:Universidad de Salamanca (USAL)InglésCIBERCV CB16/11/00374info:eu-repo/semantics/openAccessoai:gredos.usal.es:10366/1619822026-06-07T06:28:51Z |
| dc.title.none.fl_str_mv |
Development of a severity of disease score and classification model by machine learning for hospitalized COVID-19 patients. |
| title |
Development of a severity of disease score and classification model by machine learning for hospitalized COVID-19 patients. |
| spellingShingle |
Development of a severity of disease score and classification model by machine learning for hospitalized COVID-19 patients. Marcos Martín, Miguel Machine learning Covid-19 Disease score Hospitalized Artificial intelligence SARS-CoV-2 Area Under Curve Aged Adult Risk Assessment Forecasting Humans Middle Aged Hospitalization Severity of Illness Index Respiration Cohort Studies ROC Curve Retrospective Studies humanos índice de gravedad de la enfermedad anciano mediana edad curva ROC estudios retrospectivos adulto hospitalización evaluación de riesgos estudios de cohortes predicción respiración área bajo la curva |
| title_short |
Development of a severity of disease score and classification model by machine learning for hospitalized COVID-19 patients. |
| title_full |
Development of a severity of disease score and classification model by machine learning for hospitalized COVID-19 patients. |
| title_fullStr |
Development of a severity of disease score and classification model by machine learning for hospitalized COVID-19 patients. |
| title_full_unstemmed |
Development of a severity of disease score and classification model by machine learning for hospitalized COVID-19 patients. |
| title_sort |
Development of a severity of disease score and classification model by machine learning for hospitalized COVID-19 patients. |
| dc.creator.none.fl_str_mv |
Marcos Martín, Miguel Belhassen-García, Moncef Sánchez-Puente, Antonio Sampedro-Gómez, Jesús Azibeiro, Raúl Dorado Díaz, Pedro Ignacio Marcano-Millán, Edgar García-Vidal, Carolina Moreiro Barroso, María Teresa Cubino Bóveda, Noelia Pérez-García, María-Luisa Rodríguez-Alonso, Beatriz Encinas-Sánchez, Daniel Peña-Balbuena, Sonia Sobejano-Fuertes, Eduardo Inés, Sandra Carbonell, Cristina López Parra, Miriam Andrade-Meira, Fernanda López-Bernús, Amparo Lorenzo, Catalina Carpio, Adela Polo-San-Ricardo, David Sánchez Hernández, Miguel Vicente Borrás Beato, Rafael Sagredo-Meneses, Víctor Sánchez Fernández, Pedro Luis Soriano, Alex Martín Oterino, José Ángel |
| author |
Marcos Martín, Miguel |
| author_facet |
Marcos Martín, Miguel Belhassen-García, Moncef Sánchez-Puente, Antonio Sampedro-Gómez, Jesús Azibeiro, Raúl Dorado Díaz, Pedro Ignacio Marcano-Millán, Edgar García-Vidal, Carolina Moreiro Barroso, María Teresa Cubino Bóveda, Noelia Pérez-García, María-Luisa Rodríguez-Alonso, Beatriz Encinas-Sánchez, Daniel Peña-Balbuena, Sonia Sobejano-Fuertes, Eduardo Inés, Sandra Carbonell, Cristina López Parra, Miriam Andrade-Meira, Fernanda López-Bernús, Amparo Lorenzo, Catalina Carpio, Adela Polo-San-Ricardo, David Sánchez Hernández, Miguel Vicente Borrás Beato, Rafael Sagredo-Meneses, Víctor Sánchez Fernández, Pedro Luis Soriano, Alex Martín Oterino, José Ángel |
| author_role |
author |
| author2 |
Belhassen-García, Moncef Sánchez-Puente, Antonio Sampedro-Gómez, Jesús Azibeiro, Raúl Dorado Díaz, Pedro Ignacio Marcano-Millán, Edgar García-Vidal, Carolina Moreiro Barroso, María Teresa Cubino Bóveda, Noelia Pérez-García, María-Luisa Rodríguez-Alonso, Beatriz Encinas-Sánchez, Daniel Peña-Balbuena, Sonia Sobejano-Fuertes, Eduardo Inés, Sandra Carbonell, Cristina López Parra, Miriam Andrade-Meira, Fernanda López-Bernús, Amparo Lorenzo, Catalina Carpio, Adela Polo-San-Ricardo, David Sánchez Hernández, Miguel Vicente Borrás Beato, Rafael Sagredo-Meneses, Víctor Sánchez Fernández, Pedro Luis Soriano, Alex Martín Oterino, José Ángel |
| author2_role |
author author author author author author author author author author author author author author author author author author author author author author author author author author author author |
| dc.subject.none.fl_str_mv |
Machine learning Covid-19 Disease score Hospitalized Artificial intelligence SARS-CoV-2 Area Under Curve Aged Adult Risk Assessment Forecasting Humans Middle Aged Hospitalization Severity of Illness Index Respiration Cohort Studies ROC Curve Retrospective Studies humanos índice de gravedad de la enfermedad anciano mediana edad curva ROC estudios retrospectivos adulto hospitalización evaluación de riesgos estudios de cohortes predicción respiración área bajo la curva |
| topic |
Machine learning Covid-19 Disease score Hospitalized Artificial intelligence SARS-CoV-2 Area Under Curve Aged Adult Risk Assessment Forecasting Humans Middle Aged Hospitalization Severity of Illness Index Respiration Cohort Studies ROC Curve Retrospective Studies humanos índice de gravedad de la enfermedad anciano mediana edad curva ROC estudios retrospectivos adulto hospitalización evaluación de riesgos estudios de cohortes predicción respiración área bajo la curva |
| description |
[EN]Efficient and early triage of hospitalized Covid-19 patients to detect those with higher risk of severe disease is essential for appropriate case management. We trained, validated, and externally tested a machine-learning model to early identify patients who will die or require mechanical ventilation during hospitalization from clinical and laboratory features obtained at admission. A development cohort with 918 Covid-19 patients was used for training and internal validation, and 352 patients from another hospital were used for external testing. Performance of the model was evaluated by calculating the area under the receiver-operating-characteristic curve (AUC), sensitivity and specificity. A total of 363 of 918 (39.5%) and 128 of 352 (36.4%) Covid-19 patients from the development and external testing cohort, respectively, required mechanical ventilation or died during hospitalization. In the development cohort, the model obtained an AUC of 0.85 (95% confidence interval [CI], 0.82 to 0.87) for predicting severity of disease progression. Variables ranked according to their contribution to the model were the peripheral blood oxygen saturation (SpO2)/fraction of inspired oxygen (FiO2) ratio, age, estimated glomerular filtration rate, procalcitonin, C-reactive protein, updated Charlson comorbidity index and lymphocytes. In the external testing cohort, the model performed an AUC of 0.83 (95% CI, 0.81 to 0.85). This model is deployed in an open source calculator, in which Covid-19 patients at admission are individually stratified as being at high or non-high risk for severe disease progression. This machine-learning model, applied at hospital admission, predicts risk of severe disease progression in Covid-19 patients. |
| publishDate |
2021 |
| dc.date.none.fl_str_mv |
2021 2025 2025 |
| dc.type.none.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
| format |
article |
| status_str |
publishedVersion |
| dc.identifier.none.fl_str_mv |
http://hdl.handle.net/10366/161982 |
| url |
http://hdl.handle.net/10366/161982 |
| dc.language.none.fl_str_mv |
Inglés |
| language_invalid_str_mv |
Inglés |
| dc.relation.none.fl_str_mv |
CIBERCV CB16/11/00374 |
| dc.rights.none.fl_str_mv |
info:eu-repo/semantics/openAccess |
| eu_rights_str_mv |
openAccess |
| dc.publisher.none.fl_str_mv |
Public Library of Science (PLOS) |
| publisher.none.fl_str_mv |
Public Library of Science (PLOS) |
| dc.source.none.fl_str_mv |
reponame:GREDOS. Repositorio Institucional de la Universidad de Salamanca instname:Universidad de Salamanca (USAL) |
| instname_str |
Universidad de Salamanca (USAL) |
| reponame_str |
GREDOS. Repositorio Institucional de la Universidad de Salamanca |
| collection |
GREDOS. Repositorio Institucional de la Universidad de Salamanca |
| repository.name.fl_str_mv |
|
| repository.mail.fl_str_mv |
|
| _version_ |
1869406453344763904 |
| score |
15,811543 |