Assessing Opioid Use Patient Representations and Subtypes

摘要

Precision medicine, diagnosis, treatment, and prevention that accounts for natural human variability, can be beneficial for complex populations. The opioid user population is heterogeneous, characterized by many disorders, medications, and procedures. Using Electronic Health Record data, we create a patient representation, finding similarities between structured data, and then cluster the patients into patient subtypes. These subtypes can then be used for subsequent analysis.