LIG-Doctor: efficient patient trajectory prediction using Bidirectional Minimal Gated-Recurrent Networks - Archive ouverte HAL Access content directly
Journal Articles Information sciences, Information Sciences Year : 2021

LIG-Doctor: efficient patient trajectory prediction using Bidirectional Minimal Gated-Recurrent Networks

Abstract

The interest for patient trajectory prediction, a sort of computer-aided medicine, has steadily increased with the pace of artificial intelligence innovation. Notwithstanding, the design of effective systems able to predict clinical outcomes based on the history of a patient is far from trivial. Works so far are based on neural architectures with low performance, especially when using low-cardinality datasets; alternatively, complex inference approaches are hard to reproduce and/or extrapolate as they are designed for very specific circumstances. We introduce LIG-Doctor, an artificial neural network architecture based on two Minimal Gated Recurrent Unit networks functioning in a bidirectional parallel manner, benefiting from temporal events both forward and backward. In comparison to state-of-the-art works, consistent improvements were achieved in prognosis prediction, as assessed with metrics Recall@k, Precision@k, F1-score, and AUC-ROC. Besides the detailed delineation of our architecture, a sequence of experiments is reported with insights that progressively guided design decisions to inspire future works on similar problems. Our results shall contribute to the improvement of computer-aided medicine and, more generally, to processes related to the design of neural network architectures.
Fichier principal
Vignette du fichier
LigDoc-FinalDraft.pdf (769.54 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03018704 , version 1 (23-11-2020)

Identifiers

Cite

Jose F Rodrigues-Jr, Marco A Gutierrez, Gabriel Spadon, Bruno Brandoli, Sihem Amer-Yahia. LIG-Doctor: efficient patient trajectory prediction using Bidirectional Minimal Gated-Recurrent Networks. Information sciences, Information Sciences, 2021, ⟨10.1016/j.ins.2020.09.024⟩. ⟨hal-03018704⟩
63 View
290 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More