Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Hamza Tazi Bouardi's Website
About me
Page not in menu
This is a page not in th emain menu
Posts
portfolio
An Anchoring Approach to Medical Information Extraction using Clinical BERT Embeddings (May 2020)
Performing Named Entity Recognition on the i2b2 2010 dataset using clinicalBERT and an anchoring approach, warm-starting clinicalBERT embeddings with noisy-labeled MIMIC III notes using UMLS terms.
EVaRegression: A novel approach to Stable Regression (Dec. 2019)
A way of performing stable regression based on a new risk measure, the Entropic Value at Risk (EVaR), instead of the Conditional Value at Risk (CVaR) used in (Bertsimas and Paskov, 2019).
Stable Support Vector Machines and Logistic Regression (Dec. 2019)
An extension of Stable Regression from (Bertsimas and Paskov, 2019) to SVMs and Logistic Regression, allowing coefficients to be up to 200% more stable (in terms of standard deviation). Implemented in Python and Julia.
publications
Forecasting COVID-19 and Analyzing the Effect of Government Interventions
Published in Operations Research (major revision), 2020
Paper describing and analyzing the performance and predictions of the DELPHI (Differential Equations Lead to Predictions of Hospitalizations and Infections) epidemiological model for COVID-19. This paper also analyzes the effect of government interventions, as it is a central part of the model and its extensions.
Recommended citation: M. Li, H. Tazi Bouardi et al. (2020), Forecasting COVID-19 and Analyzing the Effect of Government Interventions, Operations Research (major revision). https://www.medrxiv.org/content/10.1101/2020.06.23.20138693v1.full.pdf
From Predictions to Prescriptions: A Data-Driven Response to COVID-19
Published in Health Care Management Science (currently under review), 2020
Paper gathering the whole CovidAnalytics.io research effort, with applications of Operations Research and Management Science spanning personalized medicine, optimal resource allocation, and epidemiological modeling.
Recommended citation: D. Bertsimas et al. (2020), From Predictions to Prescriptions: A Data-Driven Response to COVID-19, Health Care Management Science (under review). https://www.medrxiv.org/content/10.1101/2020.06.26.20141127v1.full.pdf
Trauma Outcome Predictor
Published in ArXiV (under review), 2020
Paper leveraging Optimal Classification Trees (D. Bertsimas and J. Dunn, 2017) and K-NN Optimal Imputation (D. Bertsimas, C. Pawlowski and Y.D. Zhuo, 2018) methods on a dataset with EHR information and 1.2M+ rows in Julia and Python to predict mortality and morbidity for trauma patients with 0.93 and 0.77 AUROC (C-Statistic).
Recommended citation: D. Bertsimas et al. (2020), Trauma Outcome Predictor, 34th Eastern Association for the Surgery of Trauma Annual Scientific Assembly. http://academicpages.github.io/files/paper3.pdf
Optimizing Vaccine Allocation to Combat the COVID-19 Pandemic
Published in ArXiV, 2020
Paper describing a coordinate descent algorithm that iterates between optimizing vaccine allocations (e.g. based on the population’s risk classes) and simulating the dynamics of the pandemic (using an extension of the DELPHI epidemiological model) in order to reduce the number of deaths given a certain allocated budget.
Recommended citation: D. Bertsimas et al. (2020), Optimizing Vaccine Allocation to Combat the COVID-19 Pandemic, under review. http://academicpages.github.io/files/paper3.pdf