Applying data mining techniques to improve diagnosis in neonatal jaundice

BackgroundHyperbilirubinemia is emerging as an increasingly common problem in newborns due to a decreasing hospital length of stay after birth. Jaundice is the most common disease of the newborn and although being benign in most cases it can lead to severe neurological consequences if poorly evaluated. In different areas of medicine, data mining has contributed to improve the results obtained with other methodologies.Hence, the aim of this study was to improve the diagnosis of neonatal jaundice with the application of data mining techniques.MethodsThis study followed the different phases of the Cross Industry Standard Process for Data Mining model as its methodology.This observational study was performed at the Obstetrics Department of a central hospital (Centro Hospitalar Tâmega e Sousa – EPE), from February to March of 2011. A total of 227 healthy newborn infants with 35 or more weeks of gestation were enrolled in the study. Over 70 variables were collected and analyzed. Also, transcutaneous bilirubin levels were measured from birth to hospital discharge with maximum time intervals of 8 hours between measurements, using a noninvasive bilirubinometer.Different attribute subsets were used to train and test classification models using algorithms included in Weka data mining software, such as decision trees (J48) and neural networks (multilayer perceptron). The accuracy results were compared with the traditional methods for prediction of hyperbilirubinemia.ResultsThe application of different classification algorithms to the collected data allowed predicting subsequent hyperbilirubinemia with high accuracy. In particular, at 24 hours of life of newborns, the accuracy for the prediction of hyperbilirubinemia was 89%. The best results were obtained using the following algorithms: naive Bayes, multilayer perceptron and simple logistic.ConclusionsThe findings of our study sustain that, new approaches, such as data mining, may support medical decision, contributing to improve diagnosis in neonatal jaundice.

[1]  J A Hanley,et al.  Paired receiver operating characteristic curves and the effect of history on radiographic interpretation. CT of the head as a case study. , 1983, Radiology.

[2]  V. Bhutani,et al.  Predictive Ability of a Predischarge Hour-specific Serum Bilirubin for Subsequent Significant Hyperbilirubinemia in Healthy Term and Near-term Newborns , 1999, Pediatrics.

[3]  Ann R Stark,et al.  Early recognition of neonatal hyperbilirubinemia and its emergent management. , 2006, Seminars in fetal & neonatal medicine.

[4]  M. S. Murphy,et al.  Neonatal jaundice: summary of NICE guidance , 2010, BMJ : British Medical Journal.

[5]  Marcia A. Testa,et al.  Management of Hyperbilirubinemia in Newborns: Measuring Performance Using a Benchmarking Model , 2003, Pediatrics.

[6]  A. Goncalves,et al.  Prospective Validation of a Novel Strategy for Assessing Risk of Significant Hyperbilirubinemia , 2011, Pediatrics.

[7]  Shivani Randev,et al.  Predicting neonatal hyperbilirubinemia using first day serum bilirubin levels , 2010, Indian journal of pediatrics.

[8]  Apilak Worachartcheewan,et al.  Identification of metabolic syndrome using decision tree analysis. , 2010, Diabetes research and clinical practice.

[9]  Ehud Zmora,et al.  Yield of recommended blood tests for neonates requiring phototherapy for hyperbilirubinemia. , 2010, The Israel Medical Association journal : IMAJ.

[10]  V. Bhutani,et al.  Universal bilirubin screening for severe neonatal hyperbilirubinemia , 2010, Journal of Perinatology.

[11]  Vinod K. Bhutani,et al.  Predischarge Risk Assessment for Severe Neonatal Hyperbilirubinemia , 2007 .

[12]  M. J. Maisels,et al.  Screening and early postnatal management strategies to prevent hazardous hyperbilirubinemia in newborns of 35 or more weeks of gestation. , 2010, Seminars in fetal & neonatal medicine.

[13]  V. Bhutani,et al.  Combining clinical risk factors with serum bilirubin levels to predict hyperbilirubinemia in newborns. , 2005, The Journal of pediatrics.

[14]  The Lancet.  Detection and treatment of neonatal jaundice , 2010, The Lancet.

[15]  Daniele De Luca.  NICE guidelines on neonatal jaundice: at risk of being too nice. , 2010, Lancet.

[16]  Adélia Jeha Nasser Bernaldo,et al.  Bilirubin dosage in cord blood: could it predict neonatal hyperbilirubinemia? , 2004, Sao Paulo medical journal = Revista paulista de medicina.

[17]  Andreia Malucelli,et al.  Classification of risk micro-areas using data mining. , 2010, Revista de Saúde Pública.

[18]  Hsiang-Yang Chen,et al.  Exploring the risk factors of preterm birth using data mining , 2011, Expert Syst. Appl..

[19]  Andreia Malucelli,et al.  Classificação de microáreas de risco com uso de mineraçãode dados , 2010 .

[20]  Dursun Delen,et al.  Predicting the graft survival for heart-lung transplantation patients: An integrated data mining methodology , 2009, Int. J. Medical Informatics.

[21]  Donal Manning,et al.  Prospective surveillance study of severe hyperbilirubinaemia in the newborn in the UK and Ireland , 2006, Archives of Disease in Childhood Fetal and Neonatal Edition.

[22]  Vinod K. Bhutani,et al.  A Comparison of Alternative Risk-Assessment Strategies for Predicting Significant Neonatal Hyperbilirubinemia in Term and Near-Term Infants , 2008, Pediatrics.

[23]  Dursun Delen,et al.  A machine learning-based approach to prognostic analysis of thoracic transplantations , 2010, Artif. Intell. Medicine.

[24]  Dursun Delen,et al.  Predicting breast cancer survivability: a comparison of three data mining methods , 2005, Artif. Intell. Medicine.

[25]  Subcommittee on Hyperbilirubinemia.  Management of hyperbilirubinemia in the newborn infant 35 or more weeks of gestation. , 2004, Pediatrics.

[26]  Julio Cesar Nievola,et al.  [Data mining and characteristics of infant mortality]. , 2010, Cadernos de saude publica.

[27]  Charles McCulloch,et al.  Risk factors for severe hyperbilirubinemia among infants with borderline bilirubin levels: a nested case-control study. , 2008, The Journal of pediatrics.

[28]  Charlotte A Hobbs,et al.  Trends in Hospitalizations for Neonatal Jaundice and Kernicterus in the United States, 1988–2005 , 2009, Pediatrics.