Random Forest-Based Prediction of Acute Respiratory Distress Syndrome in Patients Undergoing Cardiac Surgery

Authors

  • Wei Wang, MD Department of Respiratory and Critical Care Medicine, the First Medical Centre of Chinese PLA General Hospital, Haidian District, Beijing China
  • Lina Li, MD Department of Respiratory and Critical Care Medicine, the First Medical Centre of Chinese PLA General Hospital, Haidian District, Beijing China
  • Hongjun Gu, MD Department of Respiratory and Critical Care Medicine, the Eighth Medical Centre of Chinese PLA General Hospital, Haidian District, Beijing China
  • Yanqing Chen, MD Department of Haematology, the Second Medical Centre of Chinese PLA General Hospital, Haidian District, Beijing China
  • Yumei Zhen, MD Department of Rehabilitation, Xinkang hospital, Daxing District, Beijing China
  • Zhaorui Dong, MD Department of Cardiovascular Surgery, the First Medical Centre of Chinese PLA General Hospital, Haidian District, Beijing China

DOI:

https://doi.org/10.1532/hsf.5113

Keywords:

cardiac surgery, machine learning, ARDS, predictive model

Abstract

Background: To develop a machine learning-based model for predicting the risk of acute respiratory distress syndrome (ARDS) after cardiac surgery.

Methods: Data were collected from 1011 patients, who underwent cardiac surgery between February 2018 and September 2019. We developed a predictive model on ARDS by using the random forest algorithm of machine learning. The discrimination of the model was then shown by the area under the curve (AUC) of the receiver operating characteristic curve. Internal validation was performed by using a 5-fold cross-validation technique, so as to evaluate and optimize the predictive model. Model visualization was performed to reveal the most influential features during the model output.

Results: Of the 1011 patients included in the study, 53 (5.24%) suffered ARDS episodes during the first postoperative week. This random forest distinguished ARDS patients from non-ARDS patients with an AUC of 0.932 (95% CI=0.896-0.968) in the training set and 0.864 (95% CI=0.718-0.997) in the final test set. The top 10 variables in the random forest were cardiopulmonary bypass time, transfusion red blood cell, age, EuroSCORE II score, albumin, hemoglobin, operation time, serum creatinine, diabetes, and type of surgery.

Conclusion: Our findings suggest that machine learning algorithm is highly effective in predicting ARDS in patients undergoing cardiac surgery. The successful application of the generated random forest may guide clinical decision-making and aid in improving the long-term prognosis of patients.

References

Ball L, Silva PL, Giacobbe DR, Bassetti M, Zubieta-Calleja GR, Rocco P, et al. 2022. Understanding the pathophysiology of typical acute respiratory distress syndrome and severe COVID-19. Expert Rev Respir Med. 16(4):437-446.

Bricher Choque PN, Vieira RP, Ulloa L, Grabulosa C, Irigoyen MC, De Angelis K, et al. 2021. The Cholinergic Drug Pyridostigmine Alleviates Inflammation During LPS-Induced Acute Respiratory Distress Syndrome. Front Pharmacol. 12:624895.

Cheng ZB, Chen H. 2020. Higher incidence of acute respiratory distress syndrome in cardiac surgical patients with elevated serum procalcitonin concentration: a prospective cohort study. Eur J Med Res. 25(1):11.

Dong JF, Xue Q, Chen T, Zhao YY, Fu H, Guo WY, et al. 2021. Machine learning approach to predict acute kidney injury after liver surgery. World J Clin Cases. 9(36):11255-11264.

Hajipour F, Jozani MJ, Moussavi Z. 2020. A comparison of regularized logistic regression and random forest machine learning models for daytime diagnosis of obstructive sleep apnea. Med Biol Eng Comput. 58(10):2517-2529.

Huang L, Song M, Liu Y, Zhang W, Pei Z, Liu N, et al. 2021. Acute Respiratory Distress Syndrome Prediction Score: Derivation and Validation. Am J Crit Care. 30(1):64-71.

Kangelaris KN, Ware LB, Wang CY, Janz DR, Zhuo H, Matthay MA, et al. 2016. Timing of Intubation and Clinical Outcomes in Adults With Acute Respiratory Distress Syndrome. Crit Care Med. 44(1):120-129.

Liang Y, Yeligar SM, Brown LA. 2012. Chronic-alcohol-abuse-induced oxidative stress in the development of acute respiratory distress syndrome. Scientific World Journal. 2012:740308.

Liu J, Sala MA, Kim J. 2021. Dampening the Fire: A Negative Feedback Loop in Acute Respiratory Distress Syndrome. Am J Respir Cell Mol Biol. 64(2):158-160.

Liu Y, Song M, Huang L, Zhu G. 2021. A Nomogram to Predict Acute Respiratory Distress Syndrome After Cardiac Surgery. Heart Surg Forum. 24(3):E445-E450.

Nath B, Chowdhury R, Ni-Meister W, Mahanta C. 2022. Predicting the Distribution of Arsenic in Groundwater by a Geospatial Machine Learning Technique in the Two Most Affected Districts of Assam, India: The Public Health Implications. Geohealth. 6(3):e2021GH000585.

Ramos LA, Blankers M, van Wingen G, de Bruijn T, Pauws SC, Goudriaan AE. 2021. Predicting Success of a Digital Self-Help Intervention for Alcohol and Substance Use With Machine Learning. Front Psychol. 12:734633.

Sanfilippo F, Palumbo GJ, Bignami E, Pavesi M, Ranucci M, Scolletta S, et al. 2022. Acute Respiratory Distress Syndrome in the Perioperative Period of Cardiac Surgery: Predictors, Diagnosis, Prognosis, Management Options, and Future Directions. J Cardiothorac Vasc Anesth. 36(4):1169-1179.

Scott CA, Duryea JD, MacKay H, Baker MS, Laritsky E, Gunasekara CJ, et al. 2020. Identification of cell type-specific methylation signals in bulk whole genome bisulfite sequencing data. Genome Biol. 21(1):156.

Seitz KP, Caldwell ES, Hough CL. 2020. Fluid management in ARDS: an evaluation of current practice and the association between early diuretic use and hospital mortality. J Intensive Care. 8:78.

Stephens RS, Shah AS, Whitman GJ. 2013. Lung injury and acute respiratory distress syndrome after cardiac surgery. Ann Thorac Surg. 95(3):1122-1129.

Su IL, Wu VC, Chou AH, Yang CH, Chu PH, Liu KS, et al. 2019. Risk factor analysis of postoperative acute respiratory distress syndrome after type A aortic dissection repair surgery. Medicine (Baltimore). 98(29):e16303.

Teixeira C, Rosa RG, Maccari JG, Savi A, Rotta FT. 2019. Association between electromyographical findings and intensive care unit mortality among mechanically ventilated acute respiratory distress syndrome patients under profound sedation. Rev Bras Ter Intensiva. 31(4):497-503.

Wong J, Lee SW, Tan HL, Ma YJ, Sultana R, Mok YH, et al. 2020. Lung-Protective Mechanical Ventilation Strategies in Pediatric Acute Respiratory Distress Syndrome. Pediatr Crit Care Med. 21(8):720-728.

Yener N, Üdürgücü M. 2020. Airway Pressure Release Ventilation as a Rescue Therapy in Pediatric Acute Respiratory Distress Syndrome. Indian J Pediatr. 87(11):905-909.

Yuan H, Fan XS, Jin Y, He JX, Gui Y, Song LY, et al. 2019. Development of heart failure risk prediction models based on a multi-marker approach using random forest algorithms. Chin Med J (Engl). 132(7):819-826.

Zhang C, Huang Q, He F. 2022. Correlation of small nucleolar RNA host gene 16 with acute respiratory distress syndrome occurrence and prognosis in sepsis patients. J Clin Lab Anal. 36(7):e24516.

Zhang R, Chen H, Gao Z, Liang M, Qiu H, Yang Y, et al. 2021. The Effect of Loop Diuretics on 28-Day Mortality in Patients With Acute Respiratory Distress Syndrome. Front Med (Lausanne). 8:740675.

Published

2022-12-30

How to Cite

Wang, W. ., Li, L. ., Gu, H., Chen, Y., Zhen, Y., & Dong, Z. (2022). Random Forest-Based Prediction of Acute Respiratory Distress Syndrome in Patients Undergoing Cardiac Surgery. The Heart Surgery Forum, 25(6), E854-E859. https://doi.org/10.1532/hsf.5113

Issue

Section

Article