Prospective validation of clinical deterioration predictive models prior to intensive care unit transfer among patients admitted to acute care cardiology wards

https://pubmed.ncbi.nlm.nih.gov/38772399/ An AHRQ-funded study published in Physiological Measurement concluded that a predictive analytics tool called CoMET, developed five years before the COVID-19 pandemic, was very accurate in predicting which patients declined in the hospital during the pandemic. Tested in a randomized controlled trial with more than 10,000 patient visits, the tool accurately predicted significant health declines, primarily due to respiratory issues. The study found that the tool’s predictions remained accurate despite changes in clinical practices over time, including during the pandemic. The analysis underscores the importance of real-world validation for predictive models, researchers concluded.