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.

Implantable cardioverter-defibrillator placement among patients with left ventricular ejection fraction ≤35 % at least 40 days after acute myocardial infarction.

Background: Implantable cardioverter-defibrillators (ICDs) reduce the risk of sudden cardiac death among patients with persistently reduced (≤35 %) left ventricular ejection fraction (LVEF) at least 40 days following acute myocardial infarction (AMI). Few prior studies have used LVEF measured after the 40-day waiting period to examine primary prevention ICD placement. Methods: We sought to determine factors associated with ICD placement among patients who met LVEF criteria post-MI within a large integrated health care system in the U.S by conducting a retrospective cohort study of Veteran patients hospitalized for AMI from 2004 to 2017 who had documented LVEF ≤35 % from echocardiograms performed between 40 and 455 (90 days +1 year) days post-MI. We used multivariable logistic regression to examine factors associated with ICD placement. Results: Of 12,893 patients with LVEF ≤35 % at least 40 days post-MI, 2176 (16.9 %) received an ICD between 91- and 455-days post-MI. Younger age, fewer comorbidities, revascularization with PCI, and greater use of GDMT were associated with increased odds of receiving an ICD. However, half of patients treated with a beta-blocker, ACE inhibitor or angiotensin receptor blocker, and mineralocorticoid receptor antagonist prior to LVEF assessment did not receive an ICD. Eligible Black patients were less likely (odds ratio 0.80, 95 % confidence interval 0.69-0.92) to receive an ICD than White patients. Conclusion: Many factors affect ICD placement among Veteran patients with a confirmed LVEF ≤35 % at least 40 days post-MI. Greater understanding of factors influencing ICD placement would help clinicians ensure guideline-concordant care.

2018 Update on Pediatric Medical Overuse: A Review.

Importance: Efforts to combat medical overuse have gained traction in recent years, but success has been intermittent and shortcomings have been recognized. A commitment to a strong evidence base is needed to more broadly engage clinicians and reduce overuse. Observations: A structured MEDLINE search and a manual review of tables of contents from selected high-impact journals was performed to identify original research published in 2017 relevant to pediatric overuse. Articles were scored from low to high for 3 categories: quality of methods, magnitude of potential harm, and number of patients potentially harmed. The top-scoring articles presented in this review highlight examples of safe reductions in treatment intensity, including in the setting of cancer, appendicitis, acute respiratory tract infection, and elective anesthesia. This year's articles also provide cautionary examples of rational interventions adopted without a full understanding of potential harms, including pharmacologic migraine therapies, docosahexaenoic acid supplementation for preterm neonates, tight glycemic control for individuals with critically illness, and prophylactic antibiotics for children with vesicoureteral reflux. Conclusions and Relevance: The articles represent high-quality, original research from 2017 that may help mitigate overuse. These works should be fundamental to the maturation of the pediatric overuse field.

2018 Update on Medical Overuse.

Importance: Overuse of medical care is a well-recognized problem in health care, associated with patient harm and costs. We sought to identify and highlight original research articles published in 2017 that are most relevant to understanding medical overuse. Observations: A structured review of English-language articles published in 2017 was performed, coupled with examination of tables of contents of high-impact journals to identify articles related to medical overuse in adult care. Manuscripts were appraised for their quality, clinical relevance, and impact. A total of 1446 articles were identified, 910 of which addressed medical overuse. Of these, 111 articles were deemed to be the most relevant based on originality, methodologic quality, and scope. The 10 most influential articles were selected by author consensus. Findings included that unnecessary electrocardiograms are common (performed in 22% of patients at low risk) and can lead to a cascade of services, lipid monitoring rarely affects care, patients who were overdiagnosed with cancer experienced anxiety and criticism about not seeking treatment, calcium and vitamin D supplementation does not reduce hip fracture (relative risk, 1.09; 95% CI, 0.85-1.39), and pregabalin does not improve symptoms of sciatica but frequently has adverse effects (40% of patients experienced dizziness). Antipsychotic medications increased the severity of delirium in patients receiving hospice care and were associated with an increased risk of death (hazard ratio, 1.7; P = .003), and robotic-assisted radical nephrectomy was without benefits by being slower and more costly than laparoscopic surgery. High-sensitivity troponin testing often yielded false-positive results, as 16% of patients with positive troponin results in a US hospital had a myocardial infarction. One-third of patients who received a diagnosis of asthma had no evidence of asthma. Restructuring the electronic health record was able to reduce unnecessary testing (from 31.3 to 13.9 low-value tests performed per 100 patient visits). Conclusions and Relevance: Many current practices were found to represent overuse, with no benefit and potential harms. Other services were used inappropriately. Reviewing these findings and extrapolating to their patients will enable health care professionals to improve the care they provide.