![]() ![]() Insomnia has been described as an underdiagnosed and undertreated disease in multiple studies 3, 4, 5 and its prevalence has been estimated between 10% and 40%, depending on the definition of insomnia used 6. In the United States, insomnia is associated with 252.7 million days of lost work per year and an annual cost of $63.2 billion 2. Characterized by difficulty falling asleep, staying asleep, or waking unrefreshed, insomnia has a strong impact on the daily lives of affected individuals. Sleep-related complaints are second only to complaints of pain as a reason to seek medical attention 1. Compared to traditional methods, our study demonstrates that a classification algorithm that incorporates physician notes can more accurately, comprehensively, and quickly identify large cohorts of insomnia patients. In conclusion, an insomnia classification algorithm that incorporates clinical notes is superior to one based solely on billing codes. ![]() When applied to the 314,292-patient population, our algorithm classified 36,810 of the patients with insomnia, of which less than 17% had a billing code for insomnia. Our algorithm had superior performance in identifying insomnia patients compared to billing codes alone (area under the receiver operating characteristic curve = 0.83 vs. ![]() The highest classification performance of our algorithm was achieved when it included a combination of structured variables (billing codes for insomnia, common psychiatric conditions, and joint disorders) and unstructured variables (sleep disorders and psychiatric disorders). Our algorithm combined structured variables (such as International Classification of Diseases 9th Revision codes, prescriptions, laboratory observations) and unstructured variables (such as text mentions of sleep and psychiatric disorders in clinical narrative notes). The patients received care at Massachusetts General Hospital (MGH), Brigham and Women’s Hospital (BWH), or both, between 19. We developed an insomnia classification algorithm by interrogating an electronic medical records (EMR) database of 314,292 patients. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |