JAMA network open
-
Machine learning algorithms could identify patients with cancer who are at risk of short-term mortality. However, it is unclear how different machine learning algorithms compare and whether they could prompt clinicians to have timely conversations about treatment and end-of-life preferences. ⋯ In this cohort study, machine learning algorithms based on structured electronic health record data accurately identified patients with cancer at risk of short-term mortality. When the gradient boosting algorithm was applied in real time, clinicians believed that most patients who had been identified as having high risk were appropriate for a timely conversation about treatment and end-of-life preferences.
-
Differences in readmission rates among racial and ethnic minorities have been reported, but data among people with diabetes are lacking despite the high burden of diabetes and its complications in these populations. ⋯ In this study, black patients with diabetes had a significantly higher risk of readmission than members of other racial/ethnic groups. This increased risk was most pronounced among lower-income patients hospitalized in nonprofit, academic, or large hospitals. These findings reinforce the importance of identifying and addressing the many reasons for persistent racial/ethnic differences in health care quality and outcomes.
-
Randomized Controlled Trial
Assessment of Sarcopenia Among Community-Dwelling At-Risk Frail Adults Aged 65 Years and Older Who Received Multidomain Lifestyle Interventions: A Secondary Analysis of a Randomized Clinical Trial.
There is little understanding of the outcomes associated with active lifestyle interventions for sarcopenia among older persons. ⋯ This study suggests that older persons with sarcopenia are responsive to the effects of multidomain lifestyle interventions. Sarcopenia reduction was most pronounced through improved gait speed, and occurred more among those who were male, were younger, or had greater muscle mass.
-
Multicenter Study
Epidemiologic Trends in Clostridioides difficile Infections in a Regional Community Hospital Network.
Clostridioides difficile infection (CDI) remains a leading cause of health care facility-associated infection. A greater understanding of the regional epidemiologic profile of CDI could inform targeted prevention strategies. ⋯ The findings suggest that, despite the modest improvement in health care facility-associated CDI rates, a better understanding of community-acquired CDI incidence is needed for future infection prevention efforts.
-
Comparative Study
Association of Clinical Frailty Scores With Hospital Readmission for Falls After Index Admission for Trauma-Related Injury.
Falls have been associated with morbidity and mortality in elderly patients. Assessment of frailty at hospital admission may help health care professionals evaluate fall risk in patients with trauma-related injury. ⋯ Measurement of frailty at hospital admission may be an effective tool to assess fall risk and discharge disposition among patients with trauma-related injury aged 50 years and older.