Identifying treatment heterogeneity in atrial fibrillation using a novel causal machine learning method.

BACKGROUND: Lifelong oral anticoagulation is recommended in patients with atrial fibrillation (AF) to prevent stroke. Over the last decade, multiple new oral anticoagulants (OACs) have expanded the number of treatment options for these patients. While population-level effectiveness of OACs has been compared, it is unclear if there is variability in benefit and risk across patient subgroups. METHODS: We analyzed claims and medical data for 34,569 patients who initiated a nonvitamin K antagonist oral anticoagulant (non-vitamin K antagonist oral anticoagulant (NOAC); apixaban, dabigatran, and rivaroxaban) or warfarin for nonvalvular AF between 08/01/2010 and 11/29/2017 from the OptumLabs Data Warehouse. A machine learning (ML) method was applied to match different OAC groups on several baseline variables including, age, sex, race, renal function, and CHA2DS2 -VASC score. A causal ML method was then used to discover patient subgroups characterizing the head-to-head treatment effects of the OACs on a primary composite outcome of ischemic stroke, intracranial hemorrhage, and all-cause mortality. RESULTS: The mean age, number of females and white race in the entire cohort of 34,569 patients were 71.2 (SD, 10.7) years, 14,916 (43.1%), and 25,051 (72.5%) respectively. During a mean follow-up of 8.3 (SD, 9.0) months, 2,110 (6.1%) of patients experienced the composite outcome, of whom 1,675 (4.8%) died. The causal ML method identified 5 subgroups with variables favoring apixaban over dabigatran; 2 subgroups favoring apixaban over rivaroxaban; 1 subgroup favoring dabigatran over rivaroxaban; and 1 subgroup favoring rivaroxaban over dabigatran in terms of risk reduction of the primary endpoint. No subgroup favored warfarin and most dabigatran vs warfarin users favored neither drug. The variables that most influenced favoring one subgroup over another included Age, history of ischemic stroke, thromboembolism, estimated glomerular filtration rate, Race, and myocardial infarction. CONCLUSIONS: Among patients with AF treated with a NOAC or warfarin, a causal ML method identified patient subgroups with differences in outcomes associated with OAC use. The findings suggest that the effects of OACs are heterogeneous across subgroups of AF patients, which could help personalize the choice of OAC. Future prospective studies are needed to better understand the clinical impact of the subgroups with respect to OAC selection.

Candidate metrics for evaluating the impact of prescriber education on the safe use of extended-release/long-acting (ER/LA) opioid analgesics.

OBJECTIVE: The objective of this study was to develop metrics to assess opioid prescribing behavior as part of the evaluation of the Extended-Release/Long-Acting (ER/LA) Opioid Analgesic Risk Evaluation and Mitigation Strategies (REMS). DESIGN: Candidate metrics were selected using published guidelines, examined using sensitivity analyses, and applied to cross-sectional rolling cohorts of Medicare patients prescribed with extended-release oxycodone (ERO) between July 2, 2006 and July 1, 2011. Potential metrics included prescribing opioid-tolerant-only ER/LA opioid analgesics to non-opioid-tolerant patients, prescribing early fills to patients, and ordering drug screens. RESULTS: Proposed definitions for opioid tolerance were seven continuous days of opioid usage of at least 30 mg oxycodone equivalents, within the 7 days (primary) or 30 days (secondary) prior to first opioid-tolerant-only ERO prescription. Forty-four percent of opioid-tolerant-only ERO episodes met the primary opioid tolerance definition; 56% met the secondary definition. Fills were deemed "early" if a prescription was filled before 70% (primary) or 50% (secondary) of the prior prescription's days' supply was to be consumed. Five percent (primary) and 2% (secondary) of episodes had more than or equal to two early fills during treatment. At least one drug screen was billed in 14% of episodes. Stratified analyses indicated that older patients were less likely to be opioid tolerant at the time of the first opioid-tolerant-only ERO prescription. CONCLUSIONS: Investigators propose three metrics to monitor changes in prescribing behaviors for opioid analgesics that might be used to evaluate the ER/LA Opioid Analgesics REMS. Low frequencies of patients, particularly those >85 years, were likely to be opioid tolerant prior to receiving prescriptions for opioid-tolerant-only ERO.