Induction: processes of inference, learning, and discovery
Induction: processes of inference, learning, and discovery
Classifier systems and genetic algorithms
Machine learning: paradigms and methods
Rough Sets: Theoretical Aspects of Reasoning about Data
Rough Sets: Theoretical Aspects of Reasoning about Data
| Hi-index | 0.00 |
Accurately predicting which pregnant women are at risk for giving birth prematurely, or preterm, is a difficult problem in health care. Medical science and research have not offered viable solutions for the prematurity problem. The most persistent limitation for preterm birth risk assessment is our continued lack of understanding about the causes of preterm birth. Data mining and knowledge discovery in database tools are being applied with improved outcomes for predicting birth outcomes in pregnant women. In this project, completed in 1992-1993, three large prenatal databases were acquired. Each database was divided into two halves: 50 percent for training data and 50 percent for testing data. Each data set was then analyzed using statistical and machine learning programs. The best predictive accuracy was accomplished using the system LERS (Learning from Examples using Rough Sets). Manual methods of assessing preterm birth have a positive predictive value of 17 to 38 percent. The data mining methods based on LERS reached a positive predictive value of 59 to 92 percent.