Using Latent Class Analysis to Identify ARDS Sub-phenotypes for Enhanced Machine Learning Predictive Performance

In this work, we utilize Machine Learning for early recognition of patients at high risk of acute respiratory distress syndrome (ARDS), which is critical for successful prevention strategies for this devastating syndrome. The difficulty in early ARDS recognition stems from its complex and heterogenous nature. In this study, we integrate knowledge of the heterogeneity of ARDS patients into predictive model building. Using MIMIC-III data, we first apply latent class analysis (LCA) to identify homogeneous sub-groups in the ARDS population, and then build predictive models on the partitioned data. The results indicate that significantly improved performances of prediction can be obtained for two of the three identified sub-phenotypes of ARDS. Experiments suggests that identifying sub-phenotypes is beneficial for building predictive model for ARDS.

[1]  V. Neuhaus,et al.  Latent Class Analysis , 2010 .

[2]  Tony Wang,et al.  Semantically Enhanced Dynamic Bayesian Network for Detecting Sepsis Mortality Risk in ICU Patients with Infection , 2018, ArXiv.

[3]  Guolong Cai,et al.  A modified acute respiratory distress syndrome prediction score: a multicenter cohort study in China. , 2018, Journal of thoracic disease.

[4]  J Carpenter,et al.  Bootstrap confidence intervals: when, which, what? A practical guide for medical statisticians. , 2000, Statistics in medicine.

[5]  Zhongheng Zhang,et al.  Identification of three classes of acute respiratory distress syndrome using latent class analysis , 2018, PeerJ.

[6]  G. Rubenfeld,et al.  Fifty Years of Research in ARDS., The Epidemiology of Acute Respiratory Distress Syndrome. A 50th Birthday Review , 2017, American journal of respiratory and critical care medicine.

[7]  Jesús Blanco,et al.  Age, PaO2/FIO2, and Plateau Pressure Score: A Proposal for a Simple Outcome Score in Patients With the Acute Respiratory Distress Syndrome* , 2016, Critical care medicine.

[8]  J F Murray,et al.  An expanded definition of the adult respiratory distress syndrome. , 1988, The American review of respiratory disease.

[9]  Adrian E. Raftery,et al.  Model-Based Clustering, Discriminant Analysis, and Density Estimation , 2002 .

[10]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[11]  E. DeLong,et al.  Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. , 1988, Biometrics.

[12]  Benjamin A Goldstein,et al.  Early Acute Lung Injury: Criteria for Identifying Lung Injury Prior to the Need for Positive Pressure Ventilation* , 2013, Critical care medicine.

[13]  M. Balaan,et al.  Acute Respiratory Distress Syndrome , 2016, Critical care nursing quarterly.

[14]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[15]  Thomas Bice,et al.  Cost and Health Care Utilization in ARDS—Different from Other Critical Illness? , 2013, Seminars in Respiratory and Critical Care Medicine.

[16]  Anuj Karpatne,et al.  Predictive Learning in the Presence of Heterogeneity and Limited Training Data , 2014, SDM.

[17]  Peter Szolovits,et al.  MIMIC-III, a freely accessible critical care database , 2016, Scientific Data.

[18]  Ognjen Gajic,et al.  Early identification of patients at risk of acute lung injury: evaluation of lung injury prediction score in a multicenter cohort study. , 2011, American journal of respiratory and critical care medicine.

[19]  Kevin Delucchi,et al.  Subphenotypes in acute respiratory distress syndrome: latent class analysis of data from two randomised controlled trials. , 2014, The Lancet. Respiratory medicine.

[20]  M. Matthay,et al.  Is there still a role for the lung injury score in the era of the Berlin definition ARDS? , 2014, Annals of Intensive Care.

[21]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[22]  Kevin L. Delucchi,et al.  Latent class analysis of ARDS subphenotypes: a secondary analysis of the statins for acutely injured lungs from sepsis (SAILS) study , 2018, Intensive Care Medicine.

[23]  J F Nunn,et al.  Adult respiratory distress syndrome—how many cases in the UK? , 1988, Anaesthesia.

[24]  Anders Larsson,et al.  Epidemiology, Patterns of Care, and Mortality for Patients With Acute Respiratory Distress Syndrome in Intensive Care Units in 50 Countries. , 2016, JAMA.

[25]  Richard A. Johnson,et al.  A new family of power transformations to improve normality or symmetry , 2000 .