Early prediction of need for invasive mechanical ventilation in the neonatal intensive care unit using artificial intelligence and electronic health records – A clinical study (2023) Younga Kim

Description

This clinical study details the development of deep learning (DL) prediction models utilizing electronic health records (EHR) to accurately and rapidly detect the need for invasive mechanical ventilation (IMV) in neonates within the NICU. Using 1,394 patient records, the proposed model architecture, featuring bidirectional LSTM layers, demonstrated superior predictive performance (AUROC 0.861) compared to conventional approaches like the newborn early warning score systems (NEWS).