In addition, since most of the previous work has focused on solving this task in English, we conducted our experiments on three clinical coding corpora in Spanish. This division allows a fine-grained differentiation within the cluster, which cannot be addressed using a single classifier.
Conquer in spanish code#
Finally, the Ranker calculates the probability of each code considering only the documents in the cluster. Then, we use a Matcher module to assign the probability of documents belonging to each cluster.
Conquer in spanish full#
First, we take full advantage of the hierarchical nature of ontologies to create clusters based on semantic relations. This paper proposes a novel neural network-based architecture for clinical coding.
Since these terminologies are composed of hundreds of codes, this problem can be considered an Extreme Multi-label Classification task. Publisher = "Association for Computational Linguistics",Ībstract = "Clinical coding is the task of transforming medical documents into structured codes following a standard ontology.
Conquer in spanish mods#
Cite (Informal): Divide and Conquer: An Extreme Multi-Label Classification Approach for Coding Diseases and Procedures in Spanish (Barros et al., Louhi 2022) Copy Citation: BibTeX Markdown MODS XML Endnote More options… PDF: Video: = "Divide and Conquer: An Extreme Multi-Label Classification Approach for Coding Diseases and Procedures in panish",īooktitle = "Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI)",Īddress = "Abu Dhabi, United Arab Emirates (Hybrid)", Association for Computational Linguistics. In Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI), pages 138–147, Abu Dhabi, United Arab Emirates (Hybrid). Divide and Conquer: An Extreme Multi-Label Classification Approach for Coding Diseases and Procedures in Spanish. Anthology ID: 2022.louhi-1.16 Volume: Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI) Month: December Year: 2022 Address: Abu Dhabi, United Arab Emirates (Hybrid) Venue: Louhi SIG: Publisher: Association for Computational Linguistics Note: Pages: 138–147 Language: URL: DOI: Bibkey: barros-etal-2022-divide Cite (ACL): Jose Barros, Matias Rojas, Jocelyn Dunstan, and Andres Abeliuk.
Conquer in spanish free#
Automatic coding can profoundly impact healthcare by structuring critical information written in free text in electronic health records. Specifically, we outperformed previous models on two subtasks of the CodiEsp shared task: CodiEsp-D (diseases) and CodiEsp-P (procedures). The experimental results demonstrate the effectiveness of our model, achieving state-of-the-art results on two of the three datasets.
Abstract Clinical coding is the task of transforming medical documents into structured codes following a standard ontology.
0 kommentar(er)
