Anticoagulants; Increased, Asthma, Atrial Fibrillation Rapid, Chronic Kidney Diseases, Chronic Obstructive Pulmonary Disease, Gout Flare, Heart Failure, Hypertensive Urgency, Infection
Conditions
Brief summary
This is a retrospective study drawing on data from the Brigham and Women's Hospital Home Hospital Program's Database. Sociodemographic and clinical data from a training cohort were used to train a machine learning algorithm to predict blood potassium throughout a patient's admission. This algorithm was then validated in a validation cohort.
Interventions
Apply a machine learning algorithm to estimate a patient's potassium.
Sponsors
Study design
Eligibility
Inclusion criteria
Was a subject in the Brigham and Women's Home Hospital study and has a completed record in the study's database.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Serum potassium concentration | From date of admission to date of discharge, through study completion on average 7 days. | Serum potassium, measured in millimol per liter |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Hyperkalemia | From date of admission to date of discharge, through study completion on average 7 days. | Serum potassium greater than 5.1 millimol per liter |
| Hypokalemia | From date of admission to date of discharge, through study completion on average 7 days. | Serum potassium less than 3.4 millimol per liter |
| Normokalemia | From date of admission to date of discharge, through study completion on average 7 days. | Serum potassium between 3.4 and 5.1 millimol per liter |
| Serum potassium less than versus greater than or equal to 4 millimol per liter | From date of admission to date of discharge, through study completion on average 7 days. | Serum potassium falling either less than versus greater than or equal to 4 millimol per liter |
Countries
United States
Contacts
Associate Physician