AGG: An Automated Genogram Generator by Discovering Information in Clinical Texts
Abstract
In Deep Learning, the use of pre-trained language models such as BERT has exploded within NLP for model fine-tuning due to the top performance results. We showcase AGG, an Automated Genogram Generator, capable of extracting relevant family data in clinical texts to generate genograms, which are hierarchical relationship diagrams of a family with special emphasis in the family health. The contributions are: (i) automated real-time genograms generation by family history data discovery in texts through language models fine-tuning; (ii) real-time customization of the visual representation of the genograms; and (iii) web service with user-friendly interactive UI. AGG allows the easy genogram creation to users without expertise and saves time in physicians work.
Cite
Text
García-Santa and Cetina. "AGG: An Automated Genogram Generator by Discovering Information in Clinical Texts." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2022. doi:10.1007/978-3-031-26422-1_38Markdown
[García-Santa and Cetina. "AGG: An Automated Genogram Generator by Discovering Information in Clinical Texts." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2022.](https://mlanthology.org/ecmlpkdd/2022/garciasanta2022ecmlpkdd-agg/) doi:10.1007/978-3-031-26422-1_38BibTeX
@inproceedings{garciasanta2022ecmlpkdd-agg,
title = {{AGG: An Automated Genogram Generator by Discovering Information in Clinical Texts}},
author = {García-Santa, Nuria and Cetina, Kendrick},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2022},
pages = {599-602},
doi = {10.1007/978-3-031-26422-1_38},
url = {https://mlanthology.org/ecmlpkdd/2022/garciasanta2022ecmlpkdd-agg/}
}