Internal and emergency medicine
-
There is limited information on predicting incident cardiovascular outcomes among high- to very high-risk populations such as the elderly (≥ 65 years) in the absence of prior cardiovascular disease and the presence of non-cardiovascular multi-morbidity. We hypothesized that statistical/machine learning modeling can improve risk prediction, thus helping inform care management strategies. We defined a population from the Medicare health plan, a US government-funded program mostly for the elderly and varied levels of non-cardiovascular multi-morbidity. ⋯ Complex models based on machine learning algorithms yielded incrementally better discriminatory power and much improved goodness-of-fitness tests from those based on main effect statistical modeling. This Medicare population represents a highly vulnerable group for incident CVD events. This population would benefit from an integrated approach to their care and management, including attention to their comorbidities and lifestyle factors, as well as medication adherence.
-
Amongst hip fracture admissions, mortality is higher in men than in women. However, sex differences in other care-quality measures have not been well-documented. We aimed to examine sex differences in mortality as well as a wide range of underlying health indicators and clinical outcomes in adults ≥ 60 year of age admitted with hip fractures from their own homes to a single NHS hospital between April-2009 and June-2019. ⋯ Men had a lower risk of a new discharge to residential/nursing care: OR = 0.46 (0.23-0.93). The present study revealed that, in addition to a greater risk of mortality than women, men also had many other adverse health outcomes. These findings, which have not been well-documented, serve to stimulate future targeted preventive strategies and research.