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

Pattharawin Pattharanitima; Charat Thongprayoon; Wisit Kaewput; Fawad Qureshi; Fahad Qureshi; Tananchai Petnak; Narat Srivali; Guido Gembillo; Oisin A O'Corragain; Supavit Chesdachai; Saraschandra Vallabhajosyula; Pramod K Guru; Michael A Mao; Vesna D Garovic; John J Dillon; Wisit Cheungpasitporn

doi:10.3390/jcm10215021

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

J Clin Med. 2021 Oct 28;10(21):5021. doi: 10.3390/jcm10215021.

Authors

Pattharawin Pattharanitima¹, Charat Thongprayoon², Wisit Kaewput³, Fawad Qureshi², Fahad Qureshi⁴, Tananchai Petnak⁵, Narat Srivali⁶, Guido Gembillo⁷, Oisin A O'Corragain⁸, Supavit Chesdachai⁹, Saraschandra Vallabhajosyula¹⁰, Pramod K Guru¹¹, Michael A Mao¹², Vesna D Garovic², John J Dillon², Wisit Cheungpasitporn²

Affiliations

¹ Department of Internal Medicine, Faculty of Medicine, Thammasat University, Pathum Thani 12121, Thailand.
² Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA.
³ Department of Military and Community Medicine, Phramongkutklao College of Medicine, Bangkok 10400, Thailand.
⁴ School of Medicine, University of Missouri-Kansas City, Kansas City, MO 64110, USA.
⁵ Division of Pulmonary and Pulmonary Critical Care Medicine, Faculty of Medicine, Ramathibodi Hospital, Mahidol University, Bangkok 10400, Thailand.
⁶ Division of Pulmonary Medicine, St. Agnes Hospital, Baltimore, MD 21229, USA.
⁷ Unit of Nephrology and Dialysis, Department of Clinical and Experimental Medicine, University of Messina, 98125 Messina, Italy.
⁸ Department of Thoracic Medicine and Surgery, Temple University Hospital, Philadelphia, PA 19140, USA.
⁹ Division of Infectious Disease, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA.
¹⁰ Section of Cardiovascular Medicine, Department of Medicine, Wake Forest University School of Medicine, Winston-Salem, NC 27101, USA.
¹¹ Critical Care Medicine, Mayo Clinic, Jacksonville, FL 32224, USA.
¹² Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Jacksonville, FL 32224, USA.

Abstract

Background: 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.

Methods: 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.

Results: 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).

Conclusion: The ML prediction model using RF algorithm provided the highest predictive performance for hospital mortality among ICU patient with lactic acidosis.

Keywords: artificial intelligence; critical care; critical care medicine; individualized medicine; intensive care unit; lactate; lactic acid; lactic acidosis; machine learning; mortality; nephrology; personalized medicine; precision medicine.