arXiv subjects

Douglas Teodoro

Publications and source records attributed to Douglas Teodoro.

23 records · Page 2Linked to original sources

arXiv2021

Classification of hierarchical text using geometric deep learning: the case of clinical trials corpus

We consider the hierarchical representation of documents as graphs and use geometric deep learning to classify them into different categories. While graph neural networks can efficiently handle the variable structure of hierarchical documents using the permutation invariant message passing operations, we show that we can gain extra performance improvements using our proposed selective graph pooling operation that arises from the fact that some parts of the hierarchy are invariable across different documents. We applied our model to classify clinical trial (CT) protocols into completed and terminated categories. We use bag-of-words based, as well as pre-trained transformer-based embeddings to featurize the graph nodes, achieving f1-scores around 0.85 on a publicly available large scale CT registry of around 360K protocols. We further demonstrate how the selective pooling can add insights into the CT termination status prediction. We make the source code and dataset splits accessible.

cs.CL↗

arXiv2020

Named entity recognition in chemical patents using ensemble of contextual language models

Chemical patent documents describe a broad range of applications holding key reaction and compound information, such as chemical structure, reaction formulas, and molecular properties. These informational entities should be first identified in text passages to be utilized in downstream tasks. Text mining provides means to extract relevant information from chemical patents through information extraction techniques. As part of the Information Extraction task of the Cheminformatics Elsevier Melbourne University challenge, in this work we study the effectiveness of contextualized language models to extract reaction information in chemical patents. We assess transformer architectures trained on a generic and specialised corpora to propose a new ensemble model. Our best model, based on a majority ensemble approach, achieves an exact F1-score of 92.30% and a relaxed F1-score of 96.24%. The results show that ensemble of contextualized language models can provide an effective method to extract information from chemical patents.

cs.CL↗

arXiv2017

Design of an Integrated Analytics Platform for Healthcare Assessment Centered on the Episode of Care

Assessing care quality and performance is essential to improve healthcare processes and population health management. However, due to bad system design and lack of access to required data, this assessment is often delayed or not done at all. The goal of our research is to investigate an advanced analytics platform that enables healthcare quality and performance assessment. We used a user-centered design approach to identify the system requirements and have the concept of episode of care as the building block of information for a key performance indicator analytics system. We implemented architecture and interface prototypes, and performed a usability test with hospital users with managerial roles. The results show that by using user-centered design we created an analytical platform that provides a holistic and integrated view of the clinical, financial and operational aspects of the institution. Our encouraging results warrant further studies to understand other aspects of usability.

cs.CY↗

arXiv2017

Archetypes for Representing Data about the Brazilian Public Hospital Information System and Outpatient High Complexity Procedures System

The Brazilian Ministry of Health has selected the openEHR model as a standard for electronic health record systems. This paper presents a set of archetypes to represent the main data from the Brazilian Public Hospital Information System and the High Complexity Procedures Module of the Brazilian public Outpatient Health Information System. The archetypes from the public openEHR Clinical Knowledge Manager (CKM), were examined in order to select archetypes that could be used to represent the data of the above mentioned systems. For several concepts, it was necessary to specialize the CKM archetypes, or design new ones. A total of 22 archetypes were used: 8 new, 5 specialized and 9 reused from CKM. This set of archetypes can be used not only for information exchange, but also for generating a big anonymized dataset for testing openEHR-based systems.

cs.CY↗

arXiv2017

Improving average ranking precision in user searches for biomedical research datasets

Availability of research datasets is keystone for health and life science study reproducibility and scientific progress. Due to the heterogeneity and complexity of these data, a main challenge to be overcome by research data management systems is to provide users with the best answers for their search queries. In the context of the 2016 bioCADDIE Dataset Retrieval Challenge, we investigate a novel ranking pipeline to improve the search of datasets used in biomedical experiments. Our system comprises a query expansion model based on word embeddings, a similarity measure algorithm that takes into consideration the relevance of the query terms, and a dataset categorisation method that boosts the rank of datasets matching query constraints. The system was evaluated using a corpus with 800k datasets and 21 annotated user queries. Our system provides competitive results when compared to the other challenge participants. In the official run, it achieved the highest infAP among the participants, being +22.3% higher than the median infAP of the participant's best submissions. Overall, it is ranked at top 2 if an aggregated metric using the best official measures per participant is considered. The query expansion method showed positive impact on the system's performance increasing our baseline up to +5.0% and +3.4% for the infAP and infNDCG metrics, respectively. Our similarity measure algorithm seems to be robust, in particular compared to Divergence From Randomness framework, having smaller performance variations under different training conditions. Finally, the result categorization did not have significant impact on the system's performance. We believe that our solution could be used to enhance biomedical dataset management systems. In particular, the use of data driven query expansion methods could be an alternative to the complexity of biomedical terminologies.

cs.IR↗