Adaptation of autoencoder for sparsity reduction from clinical notes representation learning

Le, Thanh Dung, Noumeir, Rita, Rambaud, Jerome, Sans, Guillaume et Jouvet, Philippe. 2023. « Adaptation of autoencoder for sparsity reduction from clinical notes representation learning ». IEEE Journal of Translational Engineering in Health and Medicine, vol. 11. pp. 469-478.
Compte des citations dans Scopus : 2.

Prévisualisation

PDF Noumeir-R-2023-26278.pdf - Version publiée Licence d'utilisation : Creative Commons CC BY. Télécharger (698kB) | Prévisualisation

Résumé

When dealing with clinical text classification on a small dataset recent studies have confirmed that a well-tuned multilayer perceptron outperforms other generative classifiers, including deep learning ones. To increase the performance of the neural network classifier, feature selection for the learning representation can effectively be used. However, most feature selection methods only estimate the degree of linear dependency between variables and select the best features based on univariate statistical tests. Furthermore, the sparsity of the feature space involved in the learning representation is ignored. Goal: Our aim is therefore to access an alternative approach to tackle the sparsity by compressing the clinical representation feature space, where limited French clinical notes can also be dealt with effectively. Methods: This study proposed an autoencoder learning algorithm to take advantage of sparsity reduction in clinical note representation. The motivation was to determine how to compress sparse, high- dimensional data by reducing the dimension of the clinical note representation feature space. The classification performance of the classifiers was then evaluated in the trained and compressed feature space. Results: The proposed approach provided overall performance gains of up to 3% for each evaluation. Finally, the classifier achieved a 92% accuracy, 91% recall, 91% precision, and 91% f1-score in detecting the patient’s condition. Furthermore, the compression working mechanism and the autoencoder prediction process were demonstrated by applying the theoretic information bottleneck framework.

Type de document:	Article publié dans une revue, révisé par les pairs
Professeur:	Professeur Noumeir, Rita
Affiliation:	Génie électrique
Date de dépôt:	13 mars 2023 15:15
Dernière modification:	30 août 2023 17:57
URI:	https://espace2.etsmtl.ca/id/eprint/26278

Actions (Authentification requise)

Dernière vérification avant le dépôt