JAMA network open
-
Hospital readmissions are associated with patient harm and expense. Ways to prevent hospital readmissions have focused on identifying patients at greatest risk using prediction scores. ⋯ Among 3 hospitals in different settings, an automated machine learning score better predicted readmissions than commonly used readmission scores. More efficiently targeting patients at higher risk of readmission may be the first step toward potentially preventing readmissions.
-
Inadequate treatment of opioid use disorder (OUD) in pregnant women increases the risk of life-threatening consequences on maternal and fetal outcomes. Untreated OUD during pregnancy is associated with higher rates of adverse outcomes among newborns. ⋯ These results appeared to show significant variations in the patterns of OUD diagnosis and receipt of medication-assisted treatment among pregnant women, suggesting the need to further explore the source of these variations.