Machine Learning Prediction Models for Mortality in Intensive Care Unit Patients with Lactic Acidosis.

dc.contributor.author

Pattharanitima, Pattharawin

dc.contributor.author

Thongprayoon, Charat

dc.contributor.author

Kaewput, Wisit

dc.contributor.author

Qureshi, Fawad

dc.contributor.author

Qureshi, Fahad

dc.contributor.author

Petnak, Tananchai

dc.contributor.author

Srivali, Narat

dc.contributor.author

Gembillo, Guido

dc.contributor.author

O'Corragain, Oisin A

dc.contributor.author

Chesdachai, Supavit

dc.contributor.author

Vallabhajosyula, Saraschandra

dc.contributor.author

Guru, Pramod K

dc.contributor.author

Mao, Michael A

dc.contributor.author

Garovic, Vesna D

dc.contributor.author

Dillon, John J

dc.contributor.author

Cheungpasitporn, Wisit

dc.date.accessioned

2023-10-12T09:11:42Z

dc.date.available

2023-10-12T09:11:42Z

dc.date.issued

2021-10

dc.date.updated

2023-10-12T09:11:39Z

dc.description.abstract

Lactic acidosis is the most common cause of anion gap metabolic acidosis in the intensive care unit (ICU), associated with poor outcomes including mortality. We sought to compare machine learning (ML) approaches versus logistic regression analysis for prediction of mortality in lactic acidosis patients admitted to the ICU. We used the Medical Information Mart for Intensive Care (MIMIC-III) database to identify ICU adult patients with lactic acidosis (serum lactate ≥4 mmol/L). The outcome of interest was hospital mortality. We developed prediction models using four ML approaches consisting of random forest (RF), decision tree (DT), extreme gradient boosting (XGBoost), artificial neural network (ANN), and statistical modeling with forward stepwise logistic regression using the testing dataset. We then assessed model performance using area under the receiver operating characteristic curve (AUROC), accuracy, precision, error rate, Matthews correlation coefficient (MCC), F1 score, and assessed model calibration using the Brier score, in the independent testing dataset. Of 1919 lactic acidosis ICU patients, 1535 and 384 were included in the training and testing dataset, respectively. Hospital mortality was 30%. RF had the highest AUROC at 0.83, followed by logistic regression 0.81, XGBoost 0.81, ANN 0.79, and DT 0.71. In addition, RF also had the highest accuracy (0.79), MCC (0.45), F1 score (0.56), and lowest error rate (21.4%). The RF model was the most well-calibrated. The Brier score for RF, DT, XGBoost, ANN, and multivariable logistic regression was 0.15, 0.19, 0.18, 0.19, and 0.16, respectively. The RF model outperformed multivariable logistic regression model, SOFA score (AUROC 0.74), SAP II score (AUROC 0.77), and Charlson score (AUROC 0.69). The ML prediction model using RF algorithm provided the highest predictive performance for hospital mortality among ICU patient with lactic acidosis.

dc.identifier

jcm10215021

dc.identifier.issn

2077-0383

dc.identifier.issn

2077-0383

dc.identifier.uri

https://hdl.handle.net/10161/29265

dc.language

eng

dc.publisher

MDPI AG

dc.relation.ispartof

Journal of clinical medicine

dc.relation.isversionof

10.3390/jcm10215021

dc.subject

artificial intelligence

dc.subject

critical care

dc.subject

critical care medicine

dc.subject

individualized medicine

dc.subject

intensive care unit

dc.subject

lactate

dc.subject

lactic acid

dc.subject

lactic acidosis

dc.subject

machine learning

dc.subject

mortality

dc.subject

nephrology

dc.subject

personalized medicine

dc.subject

precision medicine

dc.title

Machine Learning Prediction Models for Mortality in Intensive Care Unit Patients with Lactic Acidosis.

dc.type

Journal article

duke.contributor.orcid

Srivali, Narat|0000-0002-6945-329X

pubs.begin-page

5021

pubs.issue

21

pubs.organisational-group

Duke

pubs.organisational-group

School of Medicine

pubs.organisational-group

Clinical Science Departments

pubs.organisational-group

Medicine

pubs.organisational-group

Medicine, Pulmonary, Allergy, and Critical Care Medicine

pubs.publication-status

Published

pubs.volume

10

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Machine Learning Prediction Models for Mortality in Intensive Care Unit Patients with Lactic Acidosis. .pdf
Size:
1.82 MB
Format:
Adobe Portable Document Format