Comparison of the prediction of extremely low birth weight neonatal mortality by regression analysis and by neural networks

Early Human Development

Volumn 65, Issue 2, 2001, Pages 123-137

  Ambalavanan, Namasivayam ^a   Carlo, Waldemar A ^a  

^a University of Alabama at Birmingham   (United States)

Author keywords

Logistic models; Neural networks (Computer); Predictive value of tests; ROC curve

Indexed keywords

ACCURACY; APGAR SCORE; AREA UNDER THE CURVE; ARTIFICIAL NEURAL NETWORK; BIRTH WEIGHT; CONFERENCE PAPER; CONTROLLED STUDY; DATA BASE; DEMOGRAPHY; FEMALE; GESTATIONAL AGE; HEALTH CENTER; HUMAN; INTERMETHOD COMPARISON; MAJOR CLINICAL STUDY; MALE; NEWBORN; NEWBORN MORTALITY; PREDICTION; RECEIVER OPERATING CHARACTERISTIC; REGRESSION ANALYSIS; STATISTICAL MODEL; VERY LOW BIRTH WEIGHT;

AREA UNDER CURVE; BIRTH WEIGHT; FEMALE; GESTATIONAL AGE; HUMANS; INFANT MORTALITY; INFANT, NEWBORN; INFANT, PREMATURE, DISEASES; INFANT, VERY LOW BIRTH WEIGHT; MALE; NEURAL NETWORKS (COMPUTER); PREDICTIVE VALUE OF TESTS; REGRESSION ANALYSIS; ROC CURVE; SURVIVAL RATE;

EID: 0034788535     PISSN: 03783782     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0378-3782(01)00228-6     Document Type: Conference Paper

References (48)

1. Outcomes of extremely low birth weight infants
2. The limit of viability-neonatal outcome of infants born at 22 to 25 weeks' gestation
3. Perinatal outcomes of a large cohort of extremely low gestational age infants (twenty-three to twenty-eight completed weeks of gestation)
4. Multivariate risks among extremely premature infants
5. Changes in survival patterns of very low-birth-weight infants from 1980 to 1993
6. Score for neonatal acute physiology: A physiologic severity index for neonatal intensive care
7. Birthweight and illness severity: Independent predictors of neonatal severity
8. The CRIB (clinical risk index for babies) score: A tool for assessing initial neonatal risk and comparing performance of neonatal intensive care units
9. The use of CRIB (clinical risk index for babies) score in auditing the performance of one neonatal intensive care unit
10. The Swedish national prospective study on extremely low birthweight (ELBW) infants. Incidence, mortality, morbidity and survival in relation to level of care
11. Delivery room resuscitation decisions for extremely premature infants
12. How aggressive should delivery room cardiopulmonary resuscitation be for extremely low birth weight infants?
13. Viability, morbidity, and resource use among newborns of 501- to 800-g birth weight. National Institute of Child Health and Human Development Neonatal Research Network
14. Estimation of outcome and restriction of interventions in neonates
15. Introduction to neural networks
16. Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes
17. Prediction of outcome in critically ill patients using artificial neural network synthesized by genetic algorithm
18. Artificial neural network for predicting intracranial hemorrhage in preterm neonates
19. Artificial neural network for risk assessment in preterm neonates
20. Comparison of mortality risk: A score for very low birthweight infants
21. Birthweight-specific mortality for extremely low birth weight infants vanishes by four days of age: Epidemiology and ethics in the neonatal care unit
22. Relation between perinatal factors and outcome of very low birth weight infants
23. Antenatal steroid administration is associated with an improved chance of improved survival in preterm infants
24. The relationship of maternal complications to outcomes in very low birthweight infants in an era of changing neonatal care
25. The risk of neonatal death and respiratory distress syndrome in relation to birth weight of preterm infants
26. The relationship of Apgar scores, gestational age, and birthweight to survival of low-birthweight infants
27. Obstetric determinants of neonatal survival: Influence of willingness to perform cesarean delivery on survival of extremely low-birth-weight infants
28. Adolescent pregnancy: Understanding the impact of age and race on outcomes
29. Clinical chorioamnionitis and the prognosis for very low birth weight infants
30. Neonatal outcome after preterm delivery for preeclampsia
31. Abruptio placentae: Risk factors and perinatal outcome
32. Survival prospects of extremely preterm infants: A 10-year experience in a single perinatal center
33. The Northwestern University Multihospital Twin Study: II. Mortality of first versus second twins
34. The meaning and use of the area under a receiver operating characteristic curve
35. Comparing the areas under two or more correlated receiver operating characteristic curves: A non-parametric approach
36. Score for neonatal acute physiology: Validation in three Kaiser Permanente neonatal intensive care units
37. CRIB and SNAP: Assessing the risk of death for preterm neonates
38. Modeling mortality in the intensive care unit: Comparing the performance of a back-propagation, associative-learning neural network with multivariate logistic regression
39. Prediction and cross-validation of neural networks versus logistic regression: Using hepatic disorders as an example
40. Predicting mortality after coronary artery bypass surgery: What do artificial neural networks learn?
41. Analysis of the clinical variables driving decision in an artificial neural network trained to identify the presence of myocardial infarction
42. Prediction of hemorrhagic blood loss with a genetic algorithm neural network
43. Neural network studies: 2. Variable selection
44. Multivariable prognostic models: Issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors
45. Prognostic modelling with logistic regression analysis: A comparison of selection and estimation methods in small data sets
46. Classification of normal and abnormal electrogastrograms using multilayer feedforward neural networks
47. New Ballard Score, expanded to include extremely premature infants
48. Design construction and evaluation of systems to predict risk in obstetrics