A Natural Language Processing Pipeline to Study Disparities in Cannabis Use and Documentation Among Children and Young Adults A Survey of 21 Years of Electronic Health Records
Tavabi, N.; Raza, M.; Singh, M.; Golchin, S.; Singh, H.; Hogue, G.; Kiapour, A. M.
Show abstract
The legalizations of medical and recreational cannabis have generated a great deal of interest in studying the health impacts of cannabis products. Despite increases in cannabis use, its documentation during clinical visits is not yet mainstream. This lack of information hampers efforts to study cannabis effects on health outcomes. A clear and in-depth understanding of current trends in cannabis use documentation is necessary to develop proper guidelines to screen and document cannabis use. Here we have developed and used a hierarchical natural language processing pipeline (AUROC=0.94) to evaluate the trends and disparities in cannabis documentation on more than 23 million notes from a large cohort of 370,087 patients seen in a high-volume multi-site pediatric and young adult clinic over a period of 21 years. Our findings show a very low but growing rate of cannabis use documentation (<2%) in electronic health records with significant demographic and socioeconomic disparities in both documentation and use, which requires further attention.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Social media discourse and internet search queries on cannabis as a medicine: A systematic review 96%
- A large Australian longitudinal cohort registry demonstrates sustained safety and efficacy of oral medicinal cannabis for at least two years 96%
- Exploring consumer preferences for cannabis edible products to support public health policy: A discrete choice experiment 94%
Similar papers in this journal
- Using Twitter Data for Cohort Studies of Drug Safety in Pregnancy: A Proof-of-Concept with Beta-Blockers 92%
- Evaluating the Clinical Feasibility of an Artificial Intelligence-Powered Clinical Decision Support System: A Longitudinal Feasibility Study 91%
- Evidence for feasibility of mobile health and social media-based interventions for early psychosis and clinical high risk 90%
Similar papers in this journal
- A Deep Learning Method to Detect Opioid Prescription and Opioid Use Disorder from Electronic Health Records 93%
- Two Data-Driven Approaches to Identifying the Spectrum of Problematic Opioid Use: A Pilot Study within a Chronic Pain Cohort 93%
- Assessment of machine learning algorithms in national data to classify the risk of self-harm among young adults in hospital: a retrospective study 91%
Similar papers in this journal
- Development and Evaluation of Machine Learning Models for the Detection of Emergency Department Patients with Opioid Misuse from Clinical Notes 94%
- Enhancing Research Data Infrastructure to Address the Opioid Epidemic: The Opioid Overdose Network (02-Net) 93%
- Characterization and Racial Stratification of Social Determinants of Health for Individuals with Type 2 Diabetes as Recorded in Electronic Health Records: Implications for Artificial Intelligence Development 92%
Similar papers in this journal
- Changes in Characteristics of Opioid Overdose Death Trends during the COVID-19 Pandemic 92%
- Twitter Discourse on Nicotine as Potential Prophylactic or Therapeutic for COVID-19 92%
- Diagnosis and treatment of opioid-related disorders in a South African private sector medical insurance scheme: a cohort study 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.