Back

The International Classification of Diseases, 10th Edition, Clinical Modification (ICD-10-CM) Code I16.0 Accurately Identifies Patients with Hypertensive Urgency

Kaiser, J.; Liao, V.; Kamel, H.; Ng, C.; Lappin, R. I.; Liberman, A. L.

2023-02-07 neurology
10.1101/2023.02.05.23285422 medRxiv
Show abstract

ObjectiveHypertensive urgency, defined as acutely elevated BP without target organ damage, is associated with an increased risk of adverse cardiovascular events and accounts for a substantial proportion of national emergency department (ED) visits. To advance research in this space, we sought to validate the new ICD-10-CM diagnostic code for hypertensive urgency within a single healthcare system. MethodsWe performed a retrospective chart-review study of ED encounters at Weill Cornell Medicine from 2016 - 2021. We randomly selected 25 encounters with the ICD-10-CM code I16.0 as the primary discharge diagnosis and 25 encounters with primary ICD-10-CM discharge diagnosis codes for benign headache disorders. A single board-certified vascular neurologist reviewed all 50 encounters while blinded to the assigned ICD-10-CM codes to identify cases of hypertensive urgency. We calculated the sensitivity, specificity, and positive predictive values of the ICD-10-CM code I16.0 with 95% confidence intervals (CI). ResultsOut of 50 randomly selected ED encounters, 24 were adjudicated as hypertensive urgency. All encounters adjudicated as hypertensive urgency had been assigned the ICD-10-CM discharge diagnosis code of I16.0. All 25 of the encounters adjudicated as headache were assigned an ICD-10-CM discharge diagnosis code for a benign headache disorder. The ICD-10-CM code for hypertensive urgency, I16.0, was thus found to have a sensitivity of 100% (95% CI: 86-100%), specificity of 96% (95% CI: 80-100%), and positive predictive value of 96% (95% CI: 78-99%). ConclusionWe found that the new ICD-10-CM code for hypertensive urgency, I16.0, can reliably identify patients with this condition.

Matching journals

The top 12 journals account for 50% of the predicted probability mass.

50% of probability mass above

"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.