Researcher: Ghanem, Angi Nazih
Name Variants
Ghanem, Angi Nazih
Email Address
Birth Date
2 results
Search Results
Now showing 1 - 2 of 2
Publication Metadata only Evaluating average and heterogeneous treatment effects in light of domain knowledge: impact of behaviors on disease prevalence(Ieee, 2019) N/A; Department of Business Administration; Department of Business Administration; Ghanem, Angi Nazih; Ali, Özden Gür; N/A; Faculty Member; N/A; College of Administrative Sciences and Economics; N/A; 57780Understanding causal treatment effect and its heterogeneity can improve targeting of efforts for prevention and treatment of diseases. A number of methods are emerging to estimate heterogeneous treatment effect from observational data, such as Causal Forest. In this paper, we evaluate the heterogeneous treatment effect estimates in terms of whether they recover the expected direction of the effect based on domain knowledge. We use the individual level health surveys conducted by the Turkish Statistical Institute (TUIK) over the span of eight years with 90K+ observations. We estimate the effect of six behaviors on the probability of two diseases (IHD and Diabetes). We compare two approaches: a) treatment and disease specific Causal Forest models that directly estimate the heterogeneous treatment effect, and b) disease specific Random Forest models of disease probability that are used as simulators to evaluate counterfactual scenarios. We find that, with some exceptions, the signs of Causal Forest heterogeneous treatment effects are aligned with domain knowledge. Causal Forest performed better than the more naive approach of using RF models as simulators which disregards selection bias in treatment assignment.Publication Open Access Estimating the potential impact of behavioral public health interventions nationally while maintaining agreement with global patterns on relative risks(Public Library of Science, 2020) Department of Business Administration; N/A; Department of Business Administration; Ali, Özden Gür; Ghanem, Angi Nazih; Üstün, Tevfik Bedirhan; Faculty Member; Faculty Member; College of Administrative Sciences and Economics; Graduate School of Sciences and Engineering; School of Medicine; 57780; N/A; 261811Objective: this paper introduces a novel method to evaluate the local impact of behavioral scenarios on disease prevalence and burden with representative individual level data while ensuring that the model is in agreement with the qualitative patterns of global relative risk (RR) estimates. The method is used to estimate the impact of behavioral scenarios on the burden of disease due to ischemic heart disease (IHD) and diabetes in the Turkish adult population. Methods: disease specific Hierarchical Bayes (HB) models estimate the individual disease probability as a function of behaviors, demographics, socio-economics and other controls, where constraints are specified based on the global RR estimates. The simulator combines the counterfactual disease probability estimates with disability adjusted life year (DALY)-per-prevalent-case estimates and rolls up to the targeted population level, thus reflecting the local joint distribution of exposures. The Global Burden of Disease (GBD) 2016 study meta-analysis results guide the analysis of the Turkish National Health Surveys (2008 to 2016) that contain more than 90 thousand observations. Findings: the proposed Qualitative Informative HB models do not sacrifice predictive accuracy versus benchmarks (logistic regression and HB models with non-informative and numerical informative priors) while agreeing with the global patterns. In the Turkish adult population, Increasing Physical Activity reduces the DALYs substantially for both IHD by 8.6% (6.4% 11.2%), and Diabetes by 8.1% (5.8% 10.6%), (90% uncertainty intervals). Eliminating Smoking and Second-hand Smoke predominantly decreases the IHD burden 13.1% (10.4% 15.8%) versus Diabetes 2.8% (1.1% 4.6%). Increasing Fruit and Vegetable Consumption, on the other hand, reduces IHD DALYs by 4.1% (2.8% 5.4%) while not improving the Diabetes burden 0.1% (0% 0.1%). Conclusion: while the national RR estimates are in qualitative agreement with the global patterns, the scenario impact estimates are markedly different than the attributable risk estimates from the GBD analysis and allow evaluation of practical scenarios with multiple behaviors.