Abstract
Tuberculosis (TB) is a major cause of death worldwide. TB research draws heavily on clinical cohorts which can be generated using electronic health records (EHR), but granular information extracted from unstructured EHR data is limited. The St. Michael's Hospital TB database (SMH-TB) was established to address gaps in EHR-derived TB clinical cohorts and provide researchers and clinicians with detailed, granular data related to TB management and treatment. We collected and validated multiple layers of EHR data from the TB outpatient clinic at St. Michael's Hospital, Toronto, Ontario, Canada to generate the SMH-TB database. SMH-TB contains structured data directly from the EHR, and variables generated using natural language processing (NLP) by extracting relevant information from free-text within clinic, radiology, and other notes. NLP performance was assessed using recall, precision and F1 score averaged across variable labels. We present characteristics of the cohort population using binomial proportions and 95% confidence intervals (CI), with and without adjusting for NLP misclassification errors. SMH-TB currently contains retrospective patient data spanning 2011 to 2018, for a total of 3298 patients (N = 3237 with at least 1 associated dictation). Performance of TB diagnosis and medication NLP rulesets surpasses 93% in recall, precision and F1 metrics, indicating good generalizability. We estimated 20% (95% CI: 18.4-21.2%) were diagnosed with active TB and 46% (95% CI: 43.8-47.2%) were diagnosed with latent TB. After adjusting for potential misclassification, the proportion of patients diagnosed with active and latent TB was 18% (95% CI: 16.8-19.7%) and 40% (95% CI: 37.8-41.6%) respectively. SMH-TB is a unique database that includes a breadth of structured data derived from structured and unstructured EHR data by using NLP rulesets. The data are available for a variety of research applications, such as clinical epidemiology, quality improvement and mathematical modeling studies.
Highlights
Tuberculosis (TB) is the top infectious killer worldwide, resulting in 1.6 million deaths in 2017 [1]. 1.7 billion people carry the latent form of the infection, of whom 10% at minimum, will develop the active, infectious form of disease
St. Michael’s Hospital Tuberculosis Database (SMH-TB) is a unique database that includes a breadth of structured data derived from structured and unstructured electronic health records (EHR) data by using natural language processing (NLP) rulesets
The Decision Support Services (DSS) at St Michaels Hospital (SMH) identified encounters which were coded as services provided in the TB outpatient clinic to identify all TB patients
Summary
Tuberculosis (TB) is the top infectious killer worldwide, resulting in 1.6 million deaths in 2017 [1]. 1.7 billion people carry the latent form of the infection, of whom 10% at minimum, will develop the active, infectious form of disease. 1.7 billion people carry the latent form of the infection, of whom 10% at minimum, will develop the active, infectious form of disease. Given the burden of active TB disease is disproportionately carried in low-resource settings, research addressing disease epidemiology, treatment (including clinical trials and programs of delivery), and the use and utility of innovative and point of care diagnostics is often completed in the populations of countries with highest burden of TB. The prevalence of LTBI on the other hand, is considerable even in high-income countries (CDC estimates 13,000,000 people living the USA have LTBI [4]) and research ranging from basic pathogenesis to program development can be conducted on the global population.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
