. Very few predictive models have been externally validated in a prospective cohort following the implementation of an artificial intelligence analytic system. This type of real-world validation is critically important due to the risk of data drift, or changes in data definitions or clinical practices over time, that could impact model performance in contemporaneous real-world cohorts.
View Article and Find Full Text PDFBackground: Patients in acute care wards who deteriorate and are emergently transferred to intensive care units (ICUs) have poor outcomes. Early identification of patients who are decompensating might allow for earlier clinical intervention and reduced morbidity and mortality. Advances in bedside continuous predictive analytics monitoring (ie, artificial intelligence [AI]-based risk prediction) have made complex data easily available to health care providers and have provided early warning of potentially catastrophic clinical events.
View Article and Find Full Text PDFTreatment of chronic lymphocytic leukemia (CLL) patients with standard dose infusion of rituximab (RTX), 375 mg/m2, induces clearance of malignant cells from peripheral blood after infusion of 30 mg of RTX. After completion of the full RTX infusion, substantial recrudescence of CLL cells occurs, and these cells have lost > 90% of CD20. To gain insight into mechanism(s) of CD20 loss, we investigated the hypothesis that thrice-weekly low-dose RTX (20 or 60 mg/m2) treatment for CLL over 4 wk would preserve CD20 and enhance leukemic cell clearance.
View Article and Find Full Text PDF