Feature selection and oversampling in analysis of clinical data for extubation readiness in extreme preterm infants

We present an approach for the analysis of clinical data from extremely preterm infants, in order to determine if they are ready to be removed from invasive endotracheal mechanical ventilation. The data includes over 100 clinical features, and the subject population is naturally quite small. To address this problem, we use feature selection, specifically mutual information, in order to choose a small subset of informative features. The other challenge we address is class imbalance, as there are many more babies that succeed extubation than those who fail. To handle this problem, we use SMOTE, an algorithm which creates synthetic examples of the minority class.

[1]  P. Davis,et al.  Nasal continuous positive airway pressure immediately after extubation for preventing morbidity in preterm infants , 2003 .

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

[3]  P. Davis,et al.  Nasal continuous positive airways pressure immediately after extubation for preventing morbidity in preterm infants. , 2003, The Cochrane database of systematic reviews.

[4]  Martina Mueller,et al.  Predicting Extubation Outcome in Preterm Newborns: A Comparison of Neural Networks with Clinical Expertise and Statistical Modeling , 2004, Pediatric Research.

[5]  S. Kazzi,et al.  A Cluster-Randomized Trial of Benchmarking and Multimodal Quality Improvement to Improve Rates of Survival Free of Bronchopulmonary Dysplasia for Infants With Birth Weights of Less Than 1250 Grams , 2007, Pediatrics.

[6]  J. Miller,et al.  Pulmonary complications of mechanical ventilation in neonates. , 2008, Clinics in perinatology.

[7]  T. Asano,et al.  ENTROPY , RELATIVE ENTROPY , AND MUTUAL INFORMATION , 2008 .

[8]  G. Sant’Anna,et al.  Implementation of a Respiratory Therapist-Driven Protocol for Neonatal Ventilation: Impact on the Premature Population , 2009, Pediatrics.

[9]  C. Snijders,et al.  Incidents associated with mechanical ventilation and intravascular catheters in neonatal intensive care: exploration of the causes, severity and methods for prevention , 2010, Archives of Disease in Childhood: Fetal and Neonatal Edition.

[10]  Karen A. Brown,et al.  Automated unsupervised respiratory event analysis , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[11]  M. Walsh,et al.  Prediction of bronchopulmonary dysplasia by postnatal age in extremely premature infants. , 2011, American journal of respiratory and critical care medicine.

[12]  G. Sant’Anna,et al.  Weaning infants from mechanical ventilation. , 2012, Clinics in perinatology.

[13]  Doina Precup,et al.  Prediction of extubation readiness in extreme preterm infants based on measures of cardiorespiratory variability , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[14]  Colleen M. Ennett,et al.  Prediction of extubation failure for neonates with respiratory distress syndrome using the MIMIC-II clinical database , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[15]  P. Davis,et al.  Definitions of extubation success in very premature infants: a systematic review , 2013, Archives of Disease in Childhood: Fetal and Neonatal Edition.

[16]  V. Bhandari,et al.  Impact of Early Extubation and Reintubation on the Incidence of Bronchopulmonary Dysplasia in Neonates , 2014, American Journal of Perinatology.