Entity and relation extraction from clinical case reports of COVID-19: a natural language processing approach

Abstract

Background Extracting relevant information about infectious diseases is an essential task. However, a significant obstacle in supporting public health research is the lack of methods for effectively mining large amounts of health data. Objective This study aims to use natural language processing (NLP) to extract the key information (clinical factors, social determinants of health) from published cases in the literature. Methods The proposed framework integrates a data layer for preparing a data cohort from clinical case reports; an NLP layer to find the clinical and demographic-named entities and relations in the texts; and an evaluation layer for benchmarking performance and analysis. The focus of this study is to extract valuable information from COVID-19 case reports. Results The named entity recognition implementation in the NLP layer achieves a performance gain of about 1–3% compared to benchmark methods. Furthermore, even without extensive data labeling, the relation extraction method outperforms benchmark methods in terms of accuracy (by 1–8% better). A thorough examination reveals the disease’s presence and symptoms prevalence in patients. Conclusions A similar approach can be generalized to other infectious diseases. It is worthwhile to use prior knowledge acquired through transfer learning when researching other infectious diseases.

Improving Clinical Decision Making with a Two-Stage Recommender System: A Case Study on MIMIC-III Dataset

“…Additionally, these systems can help to reduce medical errors and improve patient outcomes. By providing recommendations based on evidence-based medicine and clinical guidelines, clinicians can be more confident in their treatment decisions and provide better care to their patients [36], [37].…”

“…RS [2], [42] have been widely studied and applied in various domains, including ecommerce, social networks, and healthcare. In the medical domain, several studies [21], [37], [43], [44], [44], [45] have investigated the development of clinical decision support systems that assist healthcare professionals in making diagnostic or therapeutic decisions. These systems typically rely on rule-based or ML-based models that analyze patient data and provide recommendations based on clinical guidelines or past patient outcomes.…”

A framework for multi-faceted content analysis of social media chatter regarding non-medical use of prescription medications

“…By building a knowledge graph, it becomes possible to establish relationships and connections between different entities and their networks. This approach can also enrich the NER task [ 22 ] and topic modelling with external knowledge bases, fostering a more adaptable and comprehensive understanding of the data.…”

Exploring COVID-related relationship extraction: Contrasting data sources and analyzing misinformation

“…For the task of COVID-19-related relation detection, the scientific literature has been utilized in [36] to extract biological mechanisms. Furthermore, in [37] , the Transformer-BiLSTM-CRF model has been employed to extract clinical factors and social determinants of health. Additionally, in [38] , the RENET2 model was introduced specifically for extracting gene–disease relations from the scientific literature.…”