PISASCORE

PISASCORE Prediction Tool

PISASCORE is a predictor, based on machine learning technologies, to estimate the survival of very preterm infants based on perinatal data.

We have released a easy-to-use webservice tool to compute PISASCORE on single samples and on sample batches.

PISASCORE Model Training

The code used to train the machine learning based predictor is maintained in the Github of my student Marco Podda.

Citation

If you find this code useful, please remember to cite:

Podda Marco, Bacciu Davide, Micheli Alessio, Bellu Roberto, Placidi Giulia, Gagliardi Luigi : A machine learning approach to estimating preterm infants survival: development of the Preterm Infants Survival Assessment (PISA) predictor. In: Nature Scientific Reports, 8 , 2018.

BibTeX (Download)

@article{naturescirep2018,
title = {A machine learning approach to estimating preterm infants survival: development of the Preterm Infants Survival Assessment (PISA) predictor},
author = {Podda Marco and Bacciu Davide and Micheli Alessio and Bellu Roberto and Placidi Giulia and Gagliardi Luigi },
url = {https://doi.org/10.1038/s41598-018-31920-6},
doi = {10.1038/s41598-018-31920-6},
year  = {2018},
date = {2018-09-13},
journal = {Nature Scientific Reports},
volume = {8},
abstract = {Estimation of mortality risk of very preterm neonates is carried out in clinical and research settings. We aimed at elaborating a prediction tool using machine learning methods. We developed models on a cohort of 23747 neonates <30 weeks gestational age, or <1501 g birth weight, enrolled in the Italian Neonatal Network in 2008–2014 (development set), using 12 easily collected perinatal variables. We used a cohort from 2015–2016 (N = 5810) as a test set. Among several machine learning methods we chose artificial Neural Networks (NN). The resulting predictor was compared with logistic regression models. In the test cohort, NN had a slightly better discrimination than logistic regression (P < 0.002). The differences were greater in subgroups of neonates (at various gestational age or birth weight intervals, singletons). Using a cutoff of death probability of 0.5, logistic regression misclassified 67/5810 neonates (1.2 percent) more than NN. In conclusion our study – the largest published so far – shows that even in this very simplified scenario, using only limited information available up to 5 minutes after birth, a NN approach had a small but significant advantage over current approaches. The software implementing the predictor is made freely available to the community.},
keywords = {bioinformatics, biomedical data, neural networks, support vector machine},
pubstate = {published},
tppubtype = {article}
}