Crit Care. 2020;24(1):42.

Machine learning algorithm to predict mortality in patients undergoing continuous renal replacement therapy.

, , , , , ,

제1저자 강민우 · 교신저자 한승석

PMID 32028984 PMC7006166 DOI 10.1186/s13054-020-2752-7 IF 11.4 신장내과

소속 (3)

Department of Internal Medicine, Seoul National University College of Medicine, 103 Daehak-ro, Jongno-gu, Seoul, 03080, Korea.
Medical Research Collaborating Center, Seoul National University Hospital, Seoul, Korea.
Department of Internal Medicine, Seoul National University College of Medicine, 103 Daehak-ro, Jongno-gu, Seoul, 03080, Korea. hansway80@gmail.com.

Abstract

BACKGROUND Previous scoring models such as the Acute Physiologic Assessment and Chronic Health Evaluation II (APACHE II) and the Sequential Organ Failure Assessment (SOFA) scoring systems do not adequately predict mortality of patients undergoing continuous renal replacement therapy (CRRT) for severe acute kidney injury. Accordingly, the present study applies machine learning algorithms to improve prediction accuracy for this patient subset.

METHODS We randomly divided a total of 1571 adult patients who started CRRT for acute kidney injury into training (70%, n = 1094) and test (30%, n = 477) sets. The primary output consisted of the probability of mortality during admission to the intensive care unit (ICU) or hospital. We compared the area under the receiver operating characteristic curves (AUCs) of several machine learning algorithms with that of the APACHE II, SOFA, and the new abbreviated mortality scoring system for acute kidney injury with CRRT (MOSAIC model) results.

RESULTS For the ICU mortality, the random forest model showed the highest AUC (0.784 [0.744-0.825]), and the artificial neural network and extreme gradient boost models demonstrated the next best results (0.776 [0.735-0.818]). The AUC of the random forest model was higher than 0.611 (0.583-0.640), 0.677 (0.651-0.703), and 0.722 (0.677-0.767), as achieved by APACHE II, SOFA, and MOSAIC, respectively. The machine learning models also predicted in-hospital mortality better than APACHE II, SOFA, and MOSAIC.

CONCLUSION Machine learning algorithms increase the accuracy of mortality prediction for patients undergoing CRRT for acute kidney injury compared with previous scoring models.

Keywords

Acute kidney injuryContinuous renal replacement therapyIntensive care unitMachine learningMortality

Figures

**Fig. 1** Comparisons of intensive care unit mortality prediction models such as random forest, APACHE II, SOFA, and MOSAIC in the test set. a Receiver operating characteristic curves of random forest, APACHE II, SOFA, and MOSAIC. The bar graph indicates the median value of the AUC in the model. The error bar indicates the range. b Decision curve analysis of random forest, APACHE II, SOFA, and MOSAIC. *P < 0.05. APACHE, Acute Physiology and Chronic Health Evaluation; SOFA, Sequential Organ Failure Assessment; MOSAIC, Mortality Scoring system for AKI with CRRT

**Fig. 2** Calibration belts of a random forest, b APACHE II, c SOFA, and d MOSAIC for ICU mortality prediction in the test set

**Fig. 3** Rank of importance of variables in developing the random forest model for intensive care unit mortality prediction

**Fig. 4** Rank of importance of variables in developing the extreme gradient boost model for intensive care unit mortality prediction

**Fig. 5** Comparisons of in-hospital mortality prediction models such as random forest, APACHE II, SOFA, and MOSAIC in the test set. a Receiver operating characteristic curves of random forest, APACHE II, SOFA, and MOSAIC. The bar graph indicates the median value of the AUC in the model. The error bar indicates the range. b Decision curve analysis of random forest, APACHE II, SOFA, and MOSAIC for in-hospital mortality prediction. *P < 0.05. APACHE, Acute Physiology and Chronic Health Evaluation; SOFA, Sequential Organ Failure Assessment; MOSAIC, Mortality Scoring system for AKI with CRRT

그림 출처: PubMed Central 공개 논문 (PMC7006166)

Conflict of interest statement

The authors declare that they have no competing interests.

그 밖의 정보