Discovering social determinants of health from case reports using natural language processing: algorithmic development and validation

Abstract Background Social determinants of health are non-medical factors that influence health outcomes (SDOH). There is a wealth of SDOH information available in electronic health records, clinical reports, and social media data, usually in free text format. Extracting key information from free text poses a significant challenge and necessitates the use of natural language processing (NLP) techniques to extract key information. Objective The objective of this research is to advance the automatic extraction of SDOH from clinical texts. Setting and data The case reports of COVID-19 patients from the published literature are curated to create a corpus. A portion of the data is annotated by experts to create ground truth labels, and semi-supervised learning method is used for corpus re-annotation. Methods An NLP framework is developed and tested to extract SDOH from the free texts. A two-way evaluation method is used to assess the quantity and quality of the methods. Results The proposed NER implementation achieves an accuracy (F1-score) of 92.98% on our test set and generalizes well on benchmark data. A careful analysis of case examples demonstrates the superiority of the proposed approach in correctly classifying the named entities. Conclusions NLP can be used to extract key information, such as SDOH factors from free texts. A more accurate understanding of SDOH is needed to further improve healthcare outcomes.