A Machine Learning Model for Predicting Intensive Care Unit Admission in Inpatients with COVID-19 Using Clinical Data and Laboratory Biomarkers
<b>Background</b>: Artificial intelligence tools can help improve the clinical management of patients with severe COVID-19. The aim of this study was to validate a machine learning model to predict admission to the Intensive Care Unit (ICU) in individuals with COVID-19. <b>Methods&...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Biomedicines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9059/13/5/1025 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849327393935720448 |
|---|---|
| author | Alfonso Heriberto Hernández-Monsalves Pablo Letelier Camilo Morales Eduardo Rojas Mauricio Alejandro Saez Nicolás Coña Javiera Díaz Andrés San Martín Paola Garcés Jesús Espinal-Enriquez Neftalí Guzmán |
| author_facet | Alfonso Heriberto Hernández-Monsalves Pablo Letelier Camilo Morales Eduardo Rojas Mauricio Alejandro Saez Nicolás Coña Javiera Díaz Andrés San Martín Paola Garcés Jesús Espinal-Enriquez Neftalí Guzmán |
| author_sort | Alfonso Heriberto Hernández-Monsalves |
| collection | DOAJ |
| description | <b>Background</b>: Artificial intelligence tools can help improve the clinical management of patients with severe COVID-19. The aim of this study was to validate a machine learning model to predict admission to the Intensive Care Unit (ICU) in individuals with COVID-19. <b>Methods</b>: A total of 201 hospitalized patients with COVID-19 were included. Sociodemographic and clinical data as well as laboratory biomarker results were obtained from medical records and the clinical laboratory information system. Three machine learning models were generated, trained, and internally validated: logistic regression (LR), random forest (RF), and extreme gradient boosting (XGBoost). The models were evaluated for sensitivity (Sn), specificity (Sp), area under the curve (AUC), precision (P), SHapley Additive exPlanation (SHAP) values, and the clinical utility of predictive models using decision curve analysis (DCA). <b>Results</b>: The predictive model included the following variables: type 2 diabetes mellitus (T2DM), obesity, absolute neutrophil and basophil counts, the neutrophil-to-lymphocyte ratio (NLR), and D-dimer levels on the day of hospital admission. LR showed an Sn of 0.67, Sp of 0.65, AUC of 0.74, and P of 0.66. RF achieved an Sn of 0.87, Sp of 0.83, AUC of 0.96, and P of 0.85. XGBoost demonstrated an Sn of 0.87, Sp of 0.85, AUC of 0.95, and P of 0.86. <b>Conclusions</b>: Among the evaluated models, XGBoost showed robust predictive performance (Sn = 0.87, Sp = 0.85, AUC = 0.95, P = 0.86) and a favorable net clinical benefit in the decision curve analysis, confirming its suitability for predicting ICU admission in COVID-19 and aiding clinical decision-making. |
| format | Article |
| id | doaj-art-7f23010c9d024b84b83bc95c17bbf8ae |
| institution | Kabale University |
| issn | 2227-9059 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomedicines |
| spelling | doaj-art-7f23010c9d024b84b83bc95c17bbf8ae2025-08-20T03:47:53ZengMDPI AGBiomedicines2227-90592025-04-01135102510.3390/biomedicines13051025A Machine Learning Model for Predicting Intensive Care Unit Admission in Inpatients with COVID-19 Using Clinical Data and Laboratory BiomarkersAlfonso Heriberto Hernández-Monsalves0Pablo Letelier1Camilo Morales2Eduardo Rojas3Mauricio Alejandro Saez4Nicolás Coña5Javiera Díaz6Andrés San Martín7Paola Garcés8Jesús Espinal-Enriquez9Neftalí Guzmán10Laboratorio de Investigación en Salud de Precisión, Departamento de Procesos Diagnósticos y Evaluación, Facultad de Ciencias de la Salud, Universidad Católica de Temuco, Temuco 4780000, ChileLaboratorio de Investigación en Salud de Precisión, Departamento de Procesos Diagnósticos y Evaluación, Facultad de Ciencias de la Salud, Universidad Católica de Temuco, Temuco 4780000, ChileDepartamento de Procesos Terapéuticos, Facultad de Ciencias de la Salud, Universidad Católica de Temuco, Temuco 4780000, ChileLaboratorio de Investigación en Salud de Precisión, Departamento de Procesos Diagnósticos y Evaluación, Facultad de Ciencias de la Salud, Universidad Católica de Temuco, Temuco 4780000, ChileLaboratorio de Investigación en Salud de Precisión, Departamento de Procesos Diagnósticos y Evaluación, Facultad de Ciencias de la Salud, Universidad Católica de Temuco, Temuco 4780000, ChileLaboratorio de Investigación en Salud de Precisión, Departamento de Procesos Diagnósticos y Evaluación, Facultad de Ciencias de la Salud, Universidad Católica de Temuco, Temuco 4780000, ChileLaboratorio de Investigación en Salud de Precisión, Departamento de Procesos Diagnósticos y Evaluación, Facultad de Ciencias de la Salud, Universidad Católica de Temuco, Temuco 4780000, ChileLaboratorio Clínico, Hospital Dr. Hernán Henríquez Aravena, Temuco 4780000, ChileCentro Médico AlergoInmuno Araucanía, Temuco 4780000, ChileComputational Genomics Department, National Institute of Genomic Medicine, Mexico City 14610, MexicoLaboratorio de Investigación en Salud de Precisión, Departamento de Procesos Diagnósticos y Evaluación, Facultad de Ciencias de la Salud, Universidad Católica de Temuco, Temuco 4780000, Chile<b>Background</b>: Artificial intelligence tools can help improve the clinical management of patients with severe COVID-19. The aim of this study was to validate a machine learning model to predict admission to the Intensive Care Unit (ICU) in individuals with COVID-19. <b>Methods</b>: A total of 201 hospitalized patients with COVID-19 were included. Sociodemographic and clinical data as well as laboratory biomarker results were obtained from medical records and the clinical laboratory information system. Three machine learning models were generated, trained, and internally validated: logistic regression (LR), random forest (RF), and extreme gradient boosting (XGBoost). The models were evaluated for sensitivity (Sn), specificity (Sp), area under the curve (AUC), precision (P), SHapley Additive exPlanation (SHAP) values, and the clinical utility of predictive models using decision curve analysis (DCA). <b>Results</b>: The predictive model included the following variables: type 2 diabetes mellitus (T2DM), obesity, absolute neutrophil and basophil counts, the neutrophil-to-lymphocyte ratio (NLR), and D-dimer levels on the day of hospital admission. LR showed an Sn of 0.67, Sp of 0.65, AUC of 0.74, and P of 0.66. RF achieved an Sn of 0.87, Sp of 0.83, AUC of 0.96, and P of 0.85. XGBoost demonstrated an Sn of 0.87, Sp of 0.85, AUC of 0.95, and P of 0.86. <b>Conclusions</b>: Among the evaluated models, XGBoost showed robust predictive performance (Sn = 0.87, Sp = 0.85, AUC = 0.95, P = 0.86) and a favorable net clinical benefit in the decision curve analysis, confirming its suitability for predicting ICU admission in COVID-19 and aiding clinical decision-making.https://www.mdpi.com/2227-9059/13/5/1025COVID-19SARS-CoV-2biomarkersmachine learningprecision medicinepersonalized medicine |
| spellingShingle | Alfonso Heriberto Hernández-Monsalves Pablo Letelier Camilo Morales Eduardo Rojas Mauricio Alejandro Saez Nicolás Coña Javiera Díaz Andrés San Martín Paola Garcés Jesús Espinal-Enriquez Neftalí Guzmán A Machine Learning Model for Predicting Intensive Care Unit Admission in Inpatients with COVID-19 Using Clinical Data and Laboratory Biomarkers Biomedicines COVID-19 SARS-CoV-2 biomarkers machine learning precision medicine personalized medicine |
| title | A Machine Learning Model for Predicting Intensive Care Unit Admission in Inpatients with COVID-19 Using Clinical Data and Laboratory Biomarkers |
| title_full | A Machine Learning Model for Predicting Intensive Care Unit Admission in Inpatients with COVID-19 Using Clinical Data and Laboratory Biomarkers |
| title_fullStr | A Machine Learning Model for Predicting Intensive Care Unit Admission in Inpatients with COVID-19 Using Clinical Data and Laboratory Biomarkers |
| title_full_unstemmed | A Machine Learning Model for Predicting Intensive Care Unit Admission in Inpatients with COVID-19 Using Clinical Data and Laboratory Biomarkers |
| title_short | A Machine Learning Model for Predicting Intensive Care Unit Admission in Inpatients with COVID-19 Using Clinical Data and Laboratory Biomarkers |
| title_sort | machine learning model for predicting intensive care unit admission in inpatients with covid 19 using clinical data and laboratory biomarkers |
| topic | COVID-19 SARS-CoV-2 biomarkers machine learning precision medicine personalized medicine |
| url | https://www.mdpi.com/2227-9059/13/5/1025 |
| work_keys_str_mv | AT alfonsoheribertohernandezmonsalves amachinelearningmodelforpredictingintensivecareunitadmissionininpatientswithcovid19usingclinicaldataandlaboratorybiomarkers AT pabloletelier amachinelearningmodelforpredictingintensivecareunitadmissionininpatientswithcovid19usingclinicaldataandlaboratorybiomarkers AT camilomorales amachinelearningmodelforpredictingintensivecareunitadmissionininpatientswithcovid19usingclinicaldataandlaboratorybiomarkers AT eduardorojas amachinelearningmodelforpredictingintensivecareunitadmissionininpatientswithcovid19usingclinicaldataandlaboratorybiomarkers AT mauricioalejandrosaez amachinelearningmodelforpredictingintensivecareunitadmissionininpatientswithcovid19usingclinicaldataandlaboratorybiomarkers AT nicolascona amachinelearningmodelforpredictingintensivecareunitadmissionininpatientswithcovid19usingclinicaldataandlaboratorybiomarkers AT javieradiaz amachinelearningmodelforpredictingintensivecareunitadmissionininpatientswithcovid19usingclinicaldataandlaboratorybiomarkers AT andressanmartin amachinelearningmodelforpredictingintensivecareunitadmissionininpatientswithcovid19usingclinicaldataandlaboratorybiomarkers AT paolagarces amachinelearningmodelforpredictingintensivecareunitadmissionininpatientswithcovid19usingclinicaldataandlaboratorybiomarkers AT jesusespinalenriquez amachinelearningmodelforpredictingintensivecareunitadmissionininpatientswithcovid19usingclinicaldataandlaboratorybiomarkers AT neftaliguzman amachinelearningmodelforpredictingintensivecareunitadmissionininpatientswithcovid19usingclinicaldataandlaboratorybiomarkers AT alfonsoheribertohernandezmonsalves machinelearningmodelforpredictingintensivecareunitadmissionininpatientswithcovid19usingclinicaldataandlaboratorybiomarkers AT pabloletelier machinelearningmodelforpredictingintensivecareunitadmissionininpatientswithcovid19usingclinicaldataandlaboratorybiomarkers AT camilomorales machinelearningmodelforpredictingintensivecareunitadmissionininpatientswithcovid19usingclinicaldataandlaboratorybiomarkers AT eduardorojas machinelearningmodelforpredictingintensivecareunitadmissionininpatientswithcovid19usingclinicaldataandlaboratorybiomarkers AT mauricioalejandrosaez machinelearningmodelforpredictingintensivecareunitadmissionininpatientswithcovid19usingclinicaldataandlaboratorybiomarkers AT nicolascona machinelearningmodelforpredictingintensivecareunitadmissionininpatientswithcovid19usingclinicaldataandlaboratorybiomarkers AT javieradiaz machinelearningmodelforpredictingintensivecareunitadmissionininpatientswithcovid19usingclinicaldataandlaboratorybiomarkers AT andressanmartin machinelearningmodelforpredictingintensivecareunitadmissionininpatientswithcovid19usingclinicaldataandlaboratorybiomarkers AT paolagarces machinelearningmodelforpredictingintensivecareunitadmissionininpatientswithcovid19usingclinicaldataandlaboratorybiomarkers AT jesusespinalenriquez machinelearningmodelforpredictingintensivecareunitadmissionininpatientswithcovid19usingclinicaldataandlaboratorybiomarkers AT neftaliguzman machinelearningmodelforpredictingintensivecareunitadmissionininpatientswithcovid19usingclinicaldataandlaboratorybiomarkers |