AZAnthony Zagar

Anthony Zagar

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Anthony Zagar has a total of 24 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Evaluating bias control strategies in observational studies using frequentist model averaging

    by Anthony Zagar, Zbigniew Kadziola, Ilya Lipkovich, David Madigan, Doug Faries

    Estimating a treatment effect from observational data requires modeling treatment and outcome subject to uncertainty/misspecification. A previous research has shown that it is not possible to find a uniformly best strategy. In this article we propose a novel Frequentist Model Averaging (FMA) framework encompassing any estimation strategy and accounting for model uncertainty by computing a cross-validated estimate of Mean Squared Prediction Error (MSPE). We present a simulation study with data mimicking an observational database. Model averaging over 15+ strategies was compared with individual strategies as well as the best strategy selected by minimum MSPE. FMA showed robust performance (Bias, Mean Squared Error (MSE), and Confidence Interval (CI) coverage). Other strategies, such as linear regression, did well in simple scenarios but were inferior to the FMA in a scenario with complex confounding.


  • Evaluating different strategies for estimating treatment effects in observational studies

    by Anthony J. Zagar, Zbigniew Kadziola, Ilya Lipkovich, Douglas E. Faries

    Since the introduction of the propensity score (PS), methods for estimating treatment effects with observational data have received growing attention in the literature. Recent research has added substantially to the number of available statistical approaches for controlling confounding in such analyses. However, researchers need guidance to decide on the optimal analytic strategy for any given scenario. To address this gap, we conducted simulations evaluating both well-established methods (regression, PS weighting, stratification, and matching) and more recently proposed approaches (tree-based methods, local control, entropy balancing, genetic matching, prognostic scoring). The simulation scenarios included tree-based and smooth regression models as true data-generation mechanisms. We evaluated an extensive number of analysis strategies combining different treatment choices and outcome models. Key findings include 1) the lack of a single best strategy across all potential scenarios; 2) the importance of appropriately addressing interactions in the treatment choice model and/or outcome model; and 3) a tree-structured treatment choice model and a polynomial outcome model with second-order interactions performed well. One limitation to this initial assessment is the lack of heterogeneous simulation scenarios allowing treatment effects to vary by patient.


  • Open Access

    United States multicenter study of factors predicting the persistence of GH deficiency during the transition period between childhood and adulthood

    by Charmian A Quigley, Anthony J Zagar, Charlie Chunhua Liu, David M Brown, Carol Huseman, Lynne Levitsky, David R Repaske, Eva Tsalikian, John J Chipman

    Many patients with childhood-onset growth hormone (GH) deficiency do not fulfill diagnostic criteria for GH deficiency (GHD) after attainment of adult height and may not require long-term GH treatment. Patients with history of idiopathic GHD (IGHD) pose the greatest management dilemma, as data regarding factors predictive of persistent GHD in this group are lacking.


  • Open Access

    Rationale and design of the multinational observational study assessing insulin use: the MOSAIc study

    by Jennifer M Polinski, Bradley H Curtis, John D Seeger, Niteesh K Choudhry, Anthony Zagar, William H Shrank

    Although consensus guidelines recommend insulin progression among patients with type 2 diabetes (T2DM) who fail to meet glycemic targets over time, many fewer patients are progressed than may benefit. We describe the rationale and design of the MOSAIc (Multinational Observational Study Assessing Insulin use) study, a multinational observational cohort study to identify patient-, physician, and health care environment-based factors associated with insulin progression for patients with T2DM in real-world practice.


  • Open Access

    Rehospitalization following percutaneous coronary intervention for commercially insured patients with acute coronary syndrome: a retrospective analysis

    by Eric S Meadows, Jay P Bae, Anthony Zagar, Tomoko Sugihara, Krishnan Ramaswamy, Rebecca McCracken, Darell Heiselman

    Background: While prior research has provided important information about readmission rates following percutaneous coronary intervention, reports regarding charges and length of stay for readmission beyond 30 days post-discharge for patients in a large cohort are limited. The objective of this study was to characterize the rehospitalization of patients with acute coronary syndrome receiving percutaneous coronary intervention in a U.S. health benefit plan. Methods: This study retrospectively analyzed administrative claims data from a large US managed care plan at index hospitalization, 30-days, and 31-days to 15-months rehospitalization. A valid Diagnosis Related Group code (version 24) associated with a PCI claim (codes 00.66, 36.0X, 929.73, 929.75, 929.78–929.82, 929.84, 929.95/6, and G0290/1) was required to be included in the study. Patients were also required to have an ACS diagnosis on the day of admission or within 30 days prior to the index PCI. ACS diagnoses were classified by the International Statistical Classification of Disease 9 (ICD-9-CM) codes 410.xx or 411.11. Patients with a history of transient ischemic attack or stroke were excluded from the study because of the focus only on ACS-PCI patients. A clopidogrel prescription claim was required within 60 days after hospitalization. Results: Of the 6,687 ACS-PCI patients included in the study, 5,174 (77.4%) were male, 5,587 (83.6%) were <65 years old, 4,821 (72.1%) had hypertension, 5,176 (77.4%) had hyperlipidemia, and 1,777 (26.6%) had diabetes. At index hospitalization drug-eluting stents were the most frequently used: 5,534 (82.8%). Of the 4,384 patients who completed the 15-month follow-up, a total of 1,367 (31.2%) patients were rehospitalized for cardiovascular (CV)-related events, of which 811 (59.3%) were revascularization procedures: 13 (1.0%) for coronary artery bypass graft and 798 (58.4%) for PCI. In general, rehospitalizations associated with revascularization procedures cost more than other CV-related rehospitalizations. Patients rehospitalized for revascularization procedures had the shortest median time from post-index PCI to rehospitalization when compared to the patients who were rehospitalized for other CV-related events. Conclusions: For ACS patients who underwent PCI, revascularization procedures represented a large portion of rehospitalizations. Revascularization procedures appear to be the most frequent, most costly, and earliest cause for rehospitalization after ACS-PCI.