JAMA network open
-
Accurate prediction of outcomes among patients in intensive care units (ICUs) is important for clinical research and monitoring care quality. Most existing prediction models do not take full advantage of the electronic health record, using only the single worst value of laboratory tests and vital signs and largely ignoring information present in free-text notes. Whether capturing more of the available data and applying machine learning and natural language processing (NLP) can improve and automate the prediction of outcomes among patients in the ICU remains unknown. ⋯ Intensive care unit mortality prediction models incorporating measures of clinical trajectory and NLP-derived terms yielded excellent predictive performance and generalized well in this sample of hospitals. The role of these automated algorithms, particularly those using unstructured data from notes and other sources, in clinical research and quality improvement seems to merit additional investigation.
-
Nonpharmacologic methods of reducing the risk of new chronic opioid use among patients with musculoskeletal pain are important given the burden of the opioid epidemic in the United States. ⋯ Early physical therapy appears to be associated with subsequent reductions in longer-term opioid use and lower-intensity opioid use for all of the musculoskeletal pain regions examined.
-
In heart failure (HF), chronic obstructive pulmonary disease (COPD) increases the risk of poor outcomes, but the effect of COPD severity is unknown. This information is important for early intervention tailored to the highest-risk groups. ⋯ In the UK HF community setting, increasing COPD severity was associated with increasing risk of mortality and hospitalization. Prescribed COPD medication intensity and airflow limitation provide the basis for targeting high-risk groups.