Artificial neural network for risk assessment in preterm neonates.

AIM: To predict the individual neonatal mortality risk of preterm infants using an artificial neural network "trained" on admission data. METHODS: A total of 890 preterm neonates (< 32 weeks gestational age and/or < 1500 g birthweight) were enrolled in our retrospective study. The neural network trained on infants born between 1990 and 1993. The predictive value was tested on infants born in the successive three years. RESULTS: The artificial neural network performed significantly better than a logistic regression model (area under the receiver operator curve 0.95 vs 0.92). Survival was associated with high morbidity if the predicted mortality risk was greater than 0.50. There were no preterm infants with a predicted mortality risk of greater than 0.80. The mortality risks of two non-survivors with birthweights > 2000 g and severe congenital disease had largely been underestimated. CONCLUSION: An artificial neural network trained on admission data can accurately predict the mortality risk for most preterm infants. However, the significant number of prediction failures renders it unsuitable for individual treatment decisions.

Artificial neural network for predicting intracranial haemorrhage in preterm neonates.

Intraventricular haemorrhage (IVH) incidence is used to assess peri-/neonatal therapy, and to make intra- and inter-hospital quality assessments. Unbiased assessment is complicated by the amount of confounding factors. Is an artificial neural network (ANN) able to early and accurately forecast the occurrence of severe IVH in an individual patient? Is it superior to classic multiple logistic regression? We conducted an observational study on pre-existing routine data. Admission data were available from 890 preterm neonates (gestational age < 32 weeks, birthweight < 1500 g). Patients were randomly assigned to either a training, or a validation set (50%/50%). Using the training set data an ANN was trained. A second predictive model was developed by stepwise multiple logistic regression analysis. Using the validation set input data both models delivered estimates of the probability for severe IVH to occur in each individual patient. Receiver operating characteristic (ROC) curves were used to compare prognostic performance. The optimal ANN processed 13 input variables, whereas stepwise logistic regression analysis only identified five independent predictor variables. The area under the ROC curve was 0.935 for the ANN and 0.884 for the logistic regression model (p = 0.001). Adjusted for 95%, 90%, 85%, 80% and 75% specificity, the sensitivity of the ANN was significantly superior to that of the logistic regression model. Due to its ability to give an accurate prognosis based solely on admission data, a trained ANN qualifies as a tool for local quality control.

Diagnosis, therapy, and outcome of ventricular septal defects in the 1st year of life: a two-dimensional colour-Doppler echocardiography study.

Between January 1987 and July 1989 a ventricular septal defect (VSD) as a single cardiac lesion was detected in 269 small infants aged less than 1 year. The diagnosis was achieved by two-dimensional echocardiography and Doppler colour flow mapping using subcostal, parasternal, apical, and suprasternal views. VSDs were divided into perimembraneous, muscular, malalignment, and subpulmonary defects. Septal defects in complex lesions and atrioventricular defects were excluded. In group 1 (174 infants up to 4 weeks of age, mean 10 days) 125 muscular (71.8%), 35 (20.1%) perimembraneous, 12 (6.9%) malalignment, and 2 (1.1%) subpulmonary defects were diagnosed. One baby had a combined perimembraneous and muscular defect. In another baby a malalignment defect was associated with an av-canal. In group 2 (95 infants aged 4 weeks to 1 year, mean 4.0 months), 57 (60%) muscular, 32 (33.6%) perimembraneous and 6 (6.3%) malalignment defects were found. Within the maximum observation period of 13 months, spontaneous closure occurred in 72 (42.6%) of 169 infants who had a sufficient follow up. Sixty-four had a muscular (88.9%) and 8 (11.1%) a perimembraneous defect. Surgical intervention was required in 11 patients: five perimembraneous defects were closed, one was palliated. Five infants with a malalignment defect were palliated. The malalignment defect frequently needed surgical intervention even in newborns; it never closed spontaneously. About 10% of patients with perimembraneous septal defect required surgery. Spontaneous closure rarely occurred in early infancy. Muscular VSDs were most frequent but virtually never required therapy. Spontaneous closure rate was about 50% during the 1st year of life.