JMIR Publications

ABSTRACT

Background:

Background:

Mortality is a critical variable in healthcare research, but inconsistencies in the availability of death date and cause of death (CoD) information limit the ability to monitor medical product safety and effectiveness.

Objective:

Objective:

To develop scalable approaches using natural language processing (NLP) and large language models (LLM) for the extraction of mortality information from publicly available online data sources, including social media platforms, crowdfunding websites, and online obituaries.

Methods:

Methods. Data were collected from public posts on X (formerly Twitter), GoFundMe campaigns, memorial websites (EverLoved.com and TributeArchive.com), and online obituaries from 2015 to 2022. We developed a natural language processing (NLP) pipeline using transformer-based models to extract key mortality information such as decedent names, dates of birth, and dates of death. We then employed a few-shot learning (FSL) approach with large language models (LLMs) to identify primary and secondary causes of death. Model performance was assessed using precision, recall, F1-score, and accuracy metrics, with human-annotated labels serving as the reference standard for the transformer-based model and a human adjudicator blinded to labeling source for the FSL model reference standard.

Results:

Results:

The best-performing model obtained a micro-averaged F1-score of 0.88 (95% CI, 0.86-0.90) in extracting mortality information. The FSL-LLM approach demonstrated high accuracy in identifying primary CoD across various online sources. For GoFundMe, the FSL-LLM achieved 95.9% accuracy for primary cause identification, compared to 97.9% for human annotators. In obituaries, FSL-LLM accuracy was 96.5% for primary causes, while human accuracy was 99.0%. For memorial websites, FSL-LLM achieved 98.0% accuracy for primary causes, with human accuracy at 99.5%.

Conclusions:

Conclusions:

These findings highlight the potential of leveraging advanced NLP techniques and publicly available data to enhance the timeliness, comprehensiveness, and granularity of mortality surveillance.