Diagnostic Surveillance of High-Grade Gliomas: Towards Automated Change Detection Using Radiology Report Classification
Détails
Télécharger: Di Noto_Tommaso_WeaklySuperv_2210.09698v2.pdf (725.16 [Ko])
Etat: Public
Version: de l'auteur⸱e
Licence: CC BY 4.0
Etat: Public
Version: de l'auteur⸱e
Licence: CC BY 4.0
ID Serval
serval:BIB_CD112344008E
Type
Partie de livre
Sous-type
Chapitre: chapitre ou section
Collection
Publications
Institution
Titre
Diagnostic Surveillance of High-Grade Gliomas: Towards Automated Change Detection Using Radiology Report Classification
Titre du livre
Machine Learning and Principles and Practice of Knowledge Discovery in Databases
Editeur
Springer International Publishing
Statut éditorial
Publié
Date de publication
2021
Langue
anglais
Résumé
Natural Language Processing (NLP) on electronic health records (EHRs) can be used to monitor the evolution of pathologies over time to facilitate diagnosis and improve decision-making. In this study, we designed an NLP pipeline to classify Magnetic Resonance Imaging (MRI) radiology reports of patients with high-grade gliomas. Specifically, we aimed to distinguish reports indicating changes in tumors between one examination and the follow-up examination (treatment response/tumor progression versus stability). A total of 164 patients with 361 associated reports were retrieved from routine imaging, and reports were labeled by one radiologist. First, we assessed which embedding is more suitable when working with limited data, in French, from a specific domain. To do so, we compared a classic embedding techniques, TF-IDF, to a neural embedding technique, Doc2Vec, after hyperparameter optimization for both. A random forest classifier was used to classify the reports into stable (unchanged tumor) or unstable (changed tumor). Second, we applied the post-hoc LIME explainability tool to understand the decisions taken by the model. Overall, classification results obtained in repeated 5-fold cross-validation with TF-IDF reached around 89% AUC and were significantly better than those achieved with Doc2Vec (Wilcoxon signed-rank test, P=0.009 ). The explainability toolkit run on TF-IDF revealed some interesting patterns: first, words indicating change such as progression were rightfully frequent for reports classified as unstable; similarly, words indicating no change such as not were frequent for reports classified as stable. Lastly, the toolkit discovered misleading words such as T2 which are clearly not directly relevant for the task. All the code used for this study is made available.
Site de l'éditeur
Création de la notice
18/02/2022 16:27
Dernière modification de la notice
24/07/2024 6:16