Prediction of periventricular leukomalacia. Part II: Selection of hemodynamic features using computational intelligence.
ABSTRACT The objective of Part II is to analyze the dataset of extracted hemodynamic features (Case 3 of Part I) through computational intelligence (CI) techniques for identification of potential prognostic factors for periventricular leukomalacia (PVL) occurrence in neonates with congenital heart disease.
The extracted features (Case 3 dataset of Part I) were used as inputs to CI based classifiers, namely, multi-layer perceptron (MLP) and probabilistic neural network (PNN) in combination with genetic algorithms (GA) for selection of the most suitable features predicting the occurrence of PVL. The selected features were next used as inputs to a decision tree (DT) algorithm for generating easily interpretable rules of PVL prediction.
Prediction performance for two CI based classifiers, MLP and PNN coupled with GA are presented for different number of selected features. The best prediction performances were achieved with 6 and 7 selected features. The prediction success was 100% in training and the best ranges of sensitivity (SN), specificity (SP) and accuracy (AC) in test were 60-73%, 74-84% and 71-74%, respectively. The identified features when used with the DT algorithm gave best SN, SP and AC in the ranges of 87-90% in training and 80-87%, 74-79% and 79-82% in test. Among the variables selected in CI, systolic and diastolic blood pressures, and pCO(2) figured prominently similar to Part I. Decision tree based rules for prediction of PVL occurrence were obtained using the CI selected features.
The proposed approach combines the generalization capability of CI based feature selection approach and generation of easily interpretable classification rules of the decision tree. The combination of CI techniques with DT gave substantially better test prediction performance than using CI and DT separately.
Artificial Intelligence in Medicine 12/2004; 32(3):151-5. · 1.35 Impact Factor
Article: Comparison between neural networks and multiple logistic regression to predict acute coronary syndrome in the emergency room.[show abstract] [hide abstract]
ABSTRACT: Patients with suspicion of acute coronary syndrome (ACS) are difficult to diagnose and they represent a very heterogeneous group. Some require immediate treatment while others, with only minor disorders, may be sent home. Detecting ACS patients using a machine learning approach would be advantageous in many situations. Artificial neural network (ANN) ensembles and logistic regression models were trained on data from 634 patients presenting an emergency department with chest pain. Only data immediately available at patient presentation were used, including electrocardiogram (ECG) data. The models were analyzed using receiver operating characteristics (ROC) curve analysis, calibration assessments, inter- and intra-method variations. Effective odds ratios for the ANN ensembles were compared with the odds ratios obtained from the logistic model. The ANN ensemble approach together with ECG data preprocessed using principal component analysis resulted in an area under the ROC curve of 80%. At the sensitivity of 95% the specificity was 41%, corresponding to a negative predictive value of 97%, given the ACS prevalence of 21%. Adding clinical data available at presentation did not improve the ANN ensemble performance. Using the area under the ROC curve and model calibration as measures of performance we found an advantage using the ANN ensemble models compared to the logistic regression models. Clinically, a prediction model of the present type, combined with the judgment of trained emergency department personnel, could be useful for the early discharge of chest pain patients in populations with a low prevalence of ACS.Artificial Intelligence in Medicine 12/2006; 38(3):305-18. · 1.35 Impact Factor
Article: Cumulative index of exposure to hypocarbia and hyperoxia as risk factors for periventricular leukomalacia in low birth weight infants.[show abstract] [hide abstract]
ABSTRACT: Hypocarbia and hyperoxia are risk factors for periventricular leukomalacia in low birth weight infants. The association of a cumulative index of exposure to hypocarbia and hyperoxia and periventricular leukomalacia has not been evaluated. Our goal was to examine the relationship between cumulative index of exposure to hypocarbia and hyperoxia and periventricular leukomalacia during the first 7 days of life in low birth weight infants. Blood gas results were recorded in 6-hour intervals among low birth weight infants in a prospective data registry. Cumulative index of exposure to hypocarbia was calculated as the difference between arterial carbon dioxide level and 35 mmHg multiplied by the time interval in hours for each 6-hour block in a 24-hour day for the first 7 days of life. Cumulative index of exposure to hyperoxia was calculated in the same manner for arterial oxygen level >80 mm Hg. The relationship between exposure to hypocarbia, hyperoxia, and periventricular leukomalacia was examined in 778 infants with blood gas and cranial sonography data. Twenty-one infants had periventricular leukomalacia. Hypocarbia occurred in 489 infants and hyperoxia in 502 infants. Infants with periventricular leukomalacia were more likely to have a lower gestational age and to require delivery room resuscitation than those without periventricular leukomalacia. More infants in the highest quartile of exposure to hypocarbia had periventricular leukomalacia compared to those with no hypocarbia. Risk of periventricular leukomalacia was increased in infants with the highest quartile of exposure to hypocarbia after adjusting for maternal and neonatal variables, none to be associated with periventricular leukomalacia. Cumulative index exposure to hyperoxia was not related to periventricular leukomalacia. Cumulative exposure to hypocarbia and not hyperoxia was independently related to risk of periventricular leukomalacia in low birth weight infants.PEDIATRICS 10/2006; 118(4):1654-9. · 4.47 Impact Factor