Machine learning using the extreme gradient boosting (XGBoost) algorithm predicts 5-day delta of SOFA score at ICU admission in COVID-19 patients

Montomoli, Jonathan; Romeo, Luca; Moccia, Sara; Bernardini, Michele; Migliorelli, Lucia; Berardini, Daniele; Donati, Abele; Carsetti, Andrea; Bocci, Maria Grazia; Fumeaux, Thierry; Guerci, Philippe; Schüpbach, Reto; İnce, Can; Frontoni, Emanuele; Hilty, Matthias P.; Alfaro-Farias, Mario; Vizmanos-Lamotte, Gerardo; Tschoellitsch, Thomas; Meier, Jens; Aguirre-Bermeo, Hernán; Apolo, Janina; Martínez, Alberto; Jurkolow, Geoffrey; Delahaye, Gauthier; Novy, Emmanuel; Losser, Marie-Reine; Wengenmayer, Tobias; Rilinger, Jonathan; Staudacher, Dawid L.; David, Sascha; Welte, Tobias; Stahl, Klaus; Pavlos, Agios; Aslanidis, Theodoros; Korsós, Anita; Babik, Barna; Nikandish, Reza; Rezoagli, Emanuele; Giacomini, Matteo; Nova, Alice; Fogagnolo, Alberto; Spadaro, Savino; Ceriani, Roberto L.; Murrone, Martina; Wu, Maddalena Alessandra; Cogliati, Chiara; Colombo, Riccardo; Catena, E; Turrini, Fabrizio; Simonini, Maria Sole; Fabbri, Silvia; Potalivo, Antonella; Facondini, Francesca; Gangitano, Gianfilippo; Perin, Tiziana; Antonelli, Massimo; Gommers, Diederik; Rodríguez-García, Raquel; Gámez-Zapata, Jorge; Taboada-Fraga, Xiana; Castro, Pedro; Téllez, Adrián; Lander-Azcona, Arantxa; Escós-Orta, Jesús; Martín-Delgado, María Cruz; Algaba-Calderon, Angela; Franch-Llasat, Diego; Roche-Campo, Ferrán; Lozano-Gómez, Herminia; Zalba-Etayo, Begoña; Michot, Marc; Klarer, Alexander; Ensner, Rolf; Schøtt, Peter; Urech, Severin; Zellweger, Núria; Merki, Lukas; Lambert, Adriana; Laube, Marcus; Jeitziner, Marie M.; Jenni-Moser, Béatrice; Wiegand, Jan; Yuen, Bernd; Lienhardt-Nobbe, Barbara; Westphalen, Andrea; Salomon, Petra; Drvaric, Iris; Hillgaertner, Frank; Sieber, Marianne; Dullenkopf, Alexander; Petersen, Lina; Chau, Ivan; Ksouri, Hatem; Sridharan, Govind; Cereghetti, Sara; Boroli, Filippo; Pugin, Jérôme; Grazioli, Serge; Rimensberger, Peter C.; Bürkle, Christian; Marrel, Julien; Brenni, Mirko; Fleisch, Isabelle; Lavanchy, Jerome; Perez, Marie-Hélène; Ramelet, Anne‐Sylvie; Weber, Anja Baltussen; Gerecke, Peter; Christ, Andreas; Ceruti, Samuele; Glotta, Andrea; Marquardt, Katharina; Shaikh, Karim; Hübner, Tobias; Neff, Thomas; Redecker, Hermann; Moret-Bochatay, Mallory; Bentrup, FriederikeMeyer zu; Studhalter, Michael; Stephan, Michael; Brem, Jan; Gehring, Nadine; Selz, Daniela; Naon, Didier; Kleger, Gian‐Reto; Pietsch, Urs; Filipovic, Miodrag; Ristic, Anette; Sepulcri, Michael; Heise, Antje; Laurent, Marilene Franchitti; Laurent, Jean-Christophe; García, Pedro David Wendel; Schuepbach, Reto A.; Heuberger, Dorothea M.; Bühler, Philipp; Brugger, Silvio D.; Fodor, Patricia; Locher, Pascal; Camen, Giovanni; Gaspert, Tomislav; Jović, Marija; Haberthuer, Christoph; Lussman, Roger F.; Çolak, Elif

doi:10.1016/j.jointm.2021.09.002

Cited by 35 publications

(17 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… AlJame et al. (2021) used RF and XGBoost for screening COVID-19 from other patients while Montomoli et al. (2021) has used it to predict change in the SOFA score in a five day span for ICU admitted COVID-19 patients.…”

Section: Discussionmentioning

confidence: 99%

A Comparison of XGBoost, Random Forest, and Nomograph for the Prediction of Disease Severity in Patients With COVID-19 Pneumonia: Implications of Cytokine and Immune Cell Profile

Hong

Zhou

Jin

et al. 2022

Front. Cell. Infect. Microbiol.

View full text Add to dashboard Cite

Background and AimsThe aim of this study was to apply machine learning models and a nomogram to differentiate critically ill from non-critically ill COVID-19 pneumonia patients.MethodsClinical symptoms and signs, laboratory parameters, cytokine profile, and immune cellular data of 63 COVID-19 pneumonia patients were retrospectively reviewed. Outcomes were followed up until Mar 12, 2020. A logistic regression function (LR model), Random Forest, and XGBoost models were developed. The performance of these models was measured by area under receiver operating characteristic curve (AUC) analysis.ResultsUnivariate analysis revealed that there was a difference between critically and non-critically ill patients with respect to levels of interleukin-6, interleukin-10, T cells, CD4+ T, and CD8+ T cells. Interleukin-10 with an AUC of 0.86 was most useful predictor of critically ill patients with COVID-19 pneumonia. Ten variables (respiratory rate, neutrophil counts, aspartate transaminase, albumin, serum procalcitonin, D-dimer and B-type natriuretic peptide, CD4+ T cells, interleukin-6 and interleukin-10) were used as candidate predictors for LR model, Random Forest (RF) and XGBoost model application. The coefficients from LR model were utilized to build a nomogram. RF and XGBoost methods suggested that Interleukin-10 and interleukin-6 were the most important variables for severity of illness prediction. The mean AUC for LR, RF, and XGBoost model were 0.91, 0.89, and 0.93 respectively (in two-fold cross-validation). Individualized prediction by XGBoost model was explained by local interpretable model-agnostic explanations (LIME) plot.ConclusionsXGBoost exhibited the highest discriminatory performance for prediction of critically ill patients with COVID-19 pneumonia. It is inferred that the nomogram and visualized interpretation with LIME plot could be useful in the clinical setting. Additionally, interleukin-10 could serve as a useful predictor of critically ill patients with COVID-19 pneumonia.

show abstract

Section: Discussionmentioning

confidence: 99%

A Comparison of XGBoost, Random Forest, and Nomograph for the Prediction of Disease Severity in Patients With COVID-19 Pneumonia: Implications of Cytokine and Immune Cell Profile

Hong

Zhou

Jin

et al. 2022

Front. Cell. Infect. Microbiol.

View full text Add to dashboard Cite

show abstract

“…This will allow us to evaluate the model in light of external factors, like possible viral variants, the diffusion of viable alternatives in patient care and therapy strategies, or the effects of vaccines on the disease progression and diffusion. Furthermore, an additional line of further research could regard the combination of our methods with models predicting the worsening of health status over time [ 26 ] so as to provide clinicians with more information about patients’ health status and better risk stratification indications.…”

Section: Discussionmentioning

confidence: 99%

A robust and parsimonious machine learning method to predict ICU admission of COVID-19 patients

Famiglini

Campagner

Carobene

et al. 2022

Med Biol Eng Comput

View full text Add to dashboard Cite

In this article, we discuss the development of prognostic machine learning (ML) models for COVID-19 progression, by focusing on the task of predicting ICU admission within (any of) the next 5 days. On the basis of 6,625 complete blood count (CBC) tests from 1,004 patients, of which 18% were admitted to intensive care unit (ICU), we created four ML models, by adopting a robust development procedure which was designed to minimize risks of bias and over-fitting, according to reference guidelines. The best model, a support vector machine, had an AUC of .85, a Brier score of .14, and a standardized net benefit of .69: these scores indicate that the model performed well over a variety of prediction criteria. We also conducted an interpretability study to back up our findings, showing that the data on which the developed model is based is consistent with the current medical literature. This also demonstrates that CBC data and ML methods can be used to predict COVID-19 patients’ ICU admission at a relatively low cost: in particular, since CBC data can be quickly obtained by means of routine blood exams, our models could be used in resource-constrained settings and provide health practitioners with rapid and reliable indications. Graphical abstract

show abstract

“…For example, based on the intensive care unit (ICU), the work of Cheng, Fu-Yuan et al [ 48 ] exploits ML to create a risk prioritization tool that predicts the ICU transfer within 24 hours. Another interesting work done by Montomoli et al [ 49 ] exploits Extreme Gradient Boosting (XGBoost) algorithm to predict the increase or decrease in patients’ Sequential Organ Failure Assessment (SOFA) score on day 5 after ICU admission.…”

Section: Discussionmentioning

confidence: 99%

Neural-Symbolic Ensemble Learning for early-stage prediction of critical state of Covid-19 patients

Fadja

Fraccaroli

Bizzarri

et al. 2022

Med Biol Eng Comput

View full text Add to dashboard Cite

Recently, Artificial Intelligence (AI) and Machine Learning (ML) have been successfully applied to many domains of interest including medical diagnosis. Due to the availability of a large quantity of data, it is possible to build reliable AI systems that assist humans in making decisions. The recent Covid-19 pandemic quickly spread over the world causing serious health problems and severe economic and social damage. Computer scientists are actively working together with doctors on different ML models to diagnose Covid-19 patients using Computed Tomography (CT) scans and clinical data. In this work, we propose a neural-symbolic system that predicts if a Covid-19 patient arriving at the hospital will end in a critical condition. The proposed system relies on Deep 3D Convolutional Neural Networks (3D-CNNs) for analyzing lung CT scans of Covid-19 patients, Decision Trees (DTs) for predicting if a Covid-19 patient will eventually pass away by analyzing its clinical data, and a neural system that integrates the previous ones using Hierarchical Probabilistic Logic Programs (HPLPs). Predicting if a Covid-19 patient will end in a critical condition is useful for managing the limited number of intensive care at the hospital. Moreover, knowing early that a Covid-19 patient could end in serious conditions allows doctors to gain early knowledge on patients and provide special treatment to those predicted to finish in critical conditions. The proposed system, entitled Neural HPLP, obtains good performance in terms of area under the receiver operating characteristic and precision curves with values of about 0.96 for both metrics. Therefore, with Neural HPLP, it is possible not only to efficiently predict if Covid-19 patients will end in severe conditions but also possible to provide an explanation of the prediction. This makes Neural HPLP explainable, interpretable, and reliable.

show abstract

Machine learning using the extreme gradient boosting (XGBoost) algorithm predicts 5-day delta of SOFA score at ICU admission in COVID-19 patients

Cited by 35 publications

References 19 publications

A Comparison of XGBoost, Random Forest, and Nomograph for the Prediction of Disease Severity in Patients With COVID-19 Pneumonia: Implications of Cytokine and Immune Cell Profile

A Comparison of XGBoost, Random Forest, and Nomograph for the Prediction of Disease Severity in Patients With COVID-19 Pneumonia: Implications of Cytokine and Immune Cell Profile

A robust and parsimonious machine learning method to predict ICU admission of COVID-19 patients

Neural-Symbolic Ensemble Learning for early-stage prediction of critical state of Covid-19 patients

Contact Info

Product

Resources

About