Final Dataset for Neural Network Models included in Project RF-2016-02364081 Final Report. Short Title: "A generalized prediction framework of preterm birth"
Description
Scaled input dataset for training the Long Short-Term Memory (LSTM) recurrent neural networks for prediction of gestational age at birth developed and included in the RF-2016-02364081 project titled "A generalized prediction framework of preterm birth: The combination of maternal risk factors, fetal and newborn functional and structural brain connectivity for predicting neurodevelopmental outcome".
Files
Steps to reproduce
The Final Dataset for Neural Network Models included in Project RF-2016-02364081 Final Report is transformed for input in LSTM models defined, fit and evaluated employing Keras and Tensorflow in a Python environment with other libraries for data analysis and visualization. Short description of related papers linked to the RF-2016-02364081 Dataset and cited below: - https://doi.org/10.1186/s12884-021-03654-3 refers to the published manuscript titled "A hierarchical procedure to select intrauterine and extrauterine factors for methodological validation of preterm birth risk estimation" (Della Rosa et a., 2021) including thereoretical assumptions for maternal characteristics included in LSTM models - https://doi.org/10.1093/texcom/tgaa008 refers to the published manuscript titled " Subcortico-Cortical Functional Connectivity in the Fetal Brain: A Cognitive Development Blueprint." (Canini et al., 2020), including thereoretical assumptions for fetal characteristics included in LSTM models - https://doi.org/10.1016/j.bandc.2020.105669 refers to the published manuscript titled " The effects of the functional interplay between the Default Mode and Executive Control Resting State Networks on cognitive outcome in preterm born infants at 6 months of age." (Della Rosa et al., 2021), including thereoretical assumptions for neonatal characteristics included in LSTM models - https://doi.org/10.1007/s12021-022-09592-5 refers to the published manuscript titled " RS-FetMRI: a MATLAB-SPM Based Tool for Pre-processing Fetal Resting-State fMRI Data" (Pecco et al., 2021), including the the theoretical background and validation of the RS-FetMRI open-source package developed for fetal brain resting-state functional imaging preprocessing before computation of fetal functional connectivity variables in input to LSTM models. - https://github.com/NicoloPecco/RS-FetMRI refers to the GitHub repository for RS-FetMRI open-source package code. Please also cite the above-mentioned manuscripts for any reference to the Final Dataset for Neural Network Models included in Project RF-2016-02364081 Final Report. Short Title: "A generalized prediction framework of preterm birth"
Institutions
Categories
Funding
Ministero della Salute
RF-2016-02364081