A Bayesian Approach to Explore Risk Factors for Respiratory Dysfunction in Intensive Care Unit Patient

Norliyana Nor Hisham Shah - Universiti Tenaga Nasional, Kajang, 43000, Malaysia
Normy Norfiza Abdul Razak - Universiti Tenaga Nasional, Kajang, 43000, Malaysia
Asma Abu Samah - Universiti Kebangsaan Malaysia, Bangi, 43600, Malaysia
Nur Athirah Abdul Razak - Universiti Tenaga Nasional, Kajang, 43000, Malaysia
Agileswari Ramasamy - Universiti Tenaga Nasional, Kajang, 43000, Malaysia
Fatanah M. Suhaimi - Universiti Sains Malaysia, Kepala Batas, 11800, Penang, Malaysia
J. Geoffrey Chase - University of Canterbury, Christchurch, 8140, New Zealand


Citation Format:



DOI: http://dx.doi.org/10.30630/joiv.7.3-2.2370

Abstract


Respiratory dysfunction and failure are common in the intensive care unit (ICU); they are often the primary reasons for ICU admission and affect length of stay, mortality, and cost. However, diagnosing respiratory dysfunction requires arterial blood gas values to calculate the partial pressure of arterial oxygen (PaO2) to a fraction of inspired oxygen (FiO2) or P/F ratio. These intermittent blood gas values may be difficult to obtain in some patients or where financial resources are limited. Its varying etiologies and lack of other specific biomarkers make diagnosing difficult without this measurement. Thus, in this study, we investigate commonly available parameters in the ICU for the classification of respiratory dysfunction without arterial blood gas values using a Bayesian network, an unsupervised structural learning method. Clinical data from selected patients in the Medical Information Mart for Intensive Care (MIMIC) III v1.4 database is used to create and validate these models. Bayesian network generated using the taboo order algorithm showed a satisfying performance in the classification of respiratory dysfunction. Results are compared to standard diagnosis with P/F ratio. The predictor variables selected could stratify respiratory dysfunction with 80% accuracy and 94% sensitivity. Hence, without using arterial blood gas values, these parameters could identify respiratory dysfunction in 90% of cases using Bayesian networks.

Keywords


Bayesian network; respiratory failure; intensive care unit; machine learning; classification.

Full Text:

PDF

References


M. Joannidis et al., “Lung–kidney interactions in critically ill patients: consensus report of the Acute Disease Quality Initiative (ADQI) 21 Workgroup,†Intensive Care Medicine, vol. 46, pp. 654 – 672, 2020.

D. H. Livingston and E. A. Deitch, “Multiple organ failure: a common problem in surgical intensive care unit patients,†Annals of Medicine, vol. 27, pp. 13 – 20, 1995.

G. Bellani et al., “Epidemiology, patterns of care, and mortality for patients with acute respiratory distress syndrome in intensive care units in 50 countries’, JAMA, vol. 315, no. 8, pp. 788 – 800, 2016.

G. D. Rubenfeld and M. S. Herridge, “Epidemiology and outcomes of acute lung injury,†Chest, vol. 131, no. 2, pp. 554 – 562, 2007.

J. Villar, J. Blanco, and R. M. Kacmarek, “Current incidence and outcome of the acute respiratory distress syndrome,†Current Opinion in Critical Care, vol. 22, no. 1, pp. 1 – 6, 2016.

C. L. Auriemma et al., “Acute respiratory distress syndrome-attributable mortality in critically ill patients with sepsis,â€. Intensive Care Medicine, vol. 46, no. 6, pp. 1222 – 1231, 2020.

M. A. Matthay et al., “Acute respiratory distress syndrome,â€. Nature reviews Disease primers, vol. 5, no. 1, pp. 1 – 22, 2019.

S. Bolourani et al., “A machine learning prediction model of respiratory failure within 48 hours of patient admission for COVID-19: model development and validation,†Journal of Medical Internet Research, vol. 23, no. (2), e24246. 2021.

Q. Dai et al., “Risk factors for outcomes of acute respiratory distress syndrome patients: a retrospective study,†Journal of Thoracic Disease, vol. 11, no. 3, 673, 2019.

C. Wu et al., “Risk factors associated with acute respiratory distress syndrome and death in patients with coronavirus disease 2019 pneumonia in Wuhan, China,â€. JAMA Internal Medicine, vol. 180, no. 7, pp. 934 – 943, 2020.

R. Houthooft et al., “Predictive modelling of survival and length of stay in critically ill patients using sequential organ failure scores,†Artificial Intelligence in Medicine, vol. 63, no. 3, pp. 191 – 207, 2015.

V. Ranieri et al., “Acute respiratory distress syndrome,†JAMA, vol. 307, no. 23, pp. 2526 – 2533, 2012.

Z. Zhang and H. Ni, “Prediction model for critically ill patients with acute respiratory distress syndrome,†PloS One, vol. 10, no. 3, e0120641, 2015.

S. Le et al., “Supervised machine learning for the early prediction of acute respiratory distress syndrome (ARDS),†Journal of Critical Care, vol. 60, pp. 96 – 102, 2020.

P. Yang et al., “A new method for identifying the acute respiratory distress syndrome disease based on noninvasive physiological parameters,†PloS One, vol. 15, no. 2, e0226962, 2020.

F. K. Ahmad, S. Deris, and N. H. Othman, “Improved Bayesian network structure learning for breast cancer prognosis,†Information Sciences and Computer Engineering, vol. 1, no. 1, 68 – 76, 2010.

Y. Li et al., “Application of group LASSO regression based Bayesian networks in risk factors exploration and disease prediction for acute kidney injury in hospitalized patients with hematologic malignancies,†BMC Nephrology, vol. 21, no. 1, pp. 1 – 11, 2020.

P. Fuster-Parra et al., “Bayesian network modeling: A case study of an epidemiologic system analysis of cardiovascular risk,†Computer Methods and Programs in Biomedicine, vol. 126, pp. 128 – 142, 2016.

K. Mazhar et al., “Bayesian networks identify determinants of outcomes following cardiac surgery in a UK population,†BMC Cardiovascular Disorders, vol. 23, no. 1, 70, 2023.

Z. Yong et al., “Bayesian comorbidity network and cost analysis for asthma,†IEEE Journal of Biomedical and Health Informatics, vol. 26, no. 9, pp. 4714 – 4724, 2022.

M. B. Sesen et al., “Bayesian networks for clinical decision support in lung cancer care,†PloS One, vol. 8, no. 12, e82349, 2013.

C. Jing et al., “Bayesian network based netica for respiratory diseases,†In IOP Conference Series: Materials Science and Engineering, vol. 435, no. 1, p012022, 2018.

N. E. Fenton et al., “Bayesian network model for personalised COVID19 risk assessment and contact tracing,†medRxiv, Preprint posted online January 5, 2021. DOI: 10.1101/2020.07.15.20154286.

E. O. Edye et al., “Applying Bayesian Networks to help Physicians Diagnose Respiratory Diseases in the context of COVID-19 Pandemic,†In 2021 IEEE URUCON, pp. 368 – 371, 2021.

J. H. Yoon, M. R. Pinsky, and G. Clermont, “Artificial intelligence in critical care medicine,†Annual Update in Intensive Care and Emergency Medicine, pp. 353 – 367, 2022.

A. K. I. Wong et al., “Machine learning methods to predict acute respiratory failure and acute respiratory distress syndrome,†Frontiers in Big Data, vol. 3, 579774, 2020.

C. Lam et al., “Multitask learning with recurrent neural networks for acute respiratory distress syndrome prediction using only electronic health record data: model development and validation study,†JMIR Medical Informatics, vol.10, no. 6, e36202, 2022.

A. Allen et al., “Risk assessment of acute respiratory failure requiring advanced respiratory support using machine learning,†Research Square, Preprint posted online June 8, 2022, DOI: 10.21203/rs.3.rs-1668247/v1.

A. E. Johnson et al., “MIMIC-III, a freely accessible critical care database,†Scientific Data, 2016, vol. 3, no. 1, pp. 1 – 9, 2016.

J. -L. Vincent et al., “The SOFA (Sepsis-related Organ Failure Assessment) score to describe organ dysfunction/failure,†Intensive Care Medicine, vol. 22, no. 7, pp. 707 – 701, 1996.

R. Montironi et al., “How to develop and use a Bayesian Belief Network,†Journal of Clinical Pathology, vol. 49, no. 3, pp. 194, 1996.

J. Pearl, “From Bayesian networks to causal networks,†Mathematical models for handling partial knowledge in artificial intelligence, Boston, MA: Springer US, 1995, pp. 157 – 182.

R. Daly, Q. Shen, and S. Aitken, “Learning Bayesian networks: approaches and issues,†The knowledge engineering review, vol. 26, no. 2, pp. 99 – 157, 2011.

K. B. Korb, and A. E. Nicholson, “Bayesian artificial intelligence,†Boca Raton, FL: CRC Press, 2010.

J. Dougherty, R. Kohavi, and M. Sahami, “Supervised and unsupervised discretization of continuous features,†In machine learning proceedings, pp. 94 – 202, 1995.

B. E. N. Anis et al., “A Bayesian network-based approach to improve the effectiveness of maintenance actions in semiconductor industry,†In PHM Society European Conference, vol. 2, no. 1, 2014.

S. Conrady, and L. Jouffe, “Bayesian networks and BayesiaLab: a practical introduction for researchers,†vol. 9, Franklin: Bayesia USA, 2015.

N. Bilan, A. Dastranji, and A. G. Behbahani, “Comparison of the SPO2/FiO2 ratio and the PaO2/FiO2 ratio in patients with acute lung injury or acute respiratory distress syndrome,†Journal of Cardiovascular and Thoracic Research, vol. 7, no. 1, pp. 28 – 31, 2015.

S. Babu et al., “Association between SpO2/FiO2 ratio and PaO2/FiO2 ratio in different modes of oxygen supplementation,†Indian Journal of Critical Care Medicine, vol. 25, no. 9, pp. 1001, 2021.

A. Kumar et al., “Correlation of the SpO2/FiO2 (S/F) ratio and the PaO2/FiO2 (P/F) ratio in patients with COVID-19 pneumonia,†Medicina Intensiva, vol. 46, no. 7, pp. 408, 2022.

S. Ren et al., “Machine learning based algorithms to impute PaO2 from SpO2 values and development of an online calculator,†Scientific Reports, vol. 12, no. 1, pp. 1 – 10, 2022.

D. Zeiberg et al., “Machine learning for patient risk stratification for acute respiratory distress syndrome,†PloS One, vol. 14, no. 3, e0214465, 2019.