Search results for: A. Rynkiewicz

Authors: Mohamed Raouf Benmakrelouf, Wafa Karouche, Joseph Rynkiewicz

Abstract:

In this paper, we propose an alternative method to construct a Bayesian Network (BN). This method relies on a convolutional neural network (CNN classifier), which determinates the edges of the network skeleton. We train a CNN on a normalized empirical probability density distribution (NEPDF) for predicting causal interactions and relationships. We have to find the optimal Bayesian network structure for causal inference. Indeed, we are undertaking a search for pair-wise causality, depending on considered causal assumptions. In order to avoid unreasonable causal structure, we consider a blacklist and a whitelist of causality senses. We tested the method on real data to assess the influence of education on the voting intention for the extreme right-wing party. We show that, with this method, we get a safer causal structure of variables (Bayesian Network) and make to identify a variable that satisfies the backdoor criterion.

Keywords: Bayesian network, structure learning, optimal search, convolutional neural network, causal inference

Procedia PDF Downloads 176

Authors: A. Bajek, J. Skopinska-Wisniewska, A. Rynkiewicz, A. Jundzill, M. Bodnar, A. Marszalek, T. Drewa

Abstract:

Traumatic injury and age-related degenerative diseases associated with cartilage are major health problems worldwide. The articular cartilage is comprised of a relatively small number of cells, which have a relatively slow rate of turnover. Therefore, damaged articular cartilage has a limited capacity for self-repair. New clinical methods have been designed to achieve better repair of injured cartilage. However, there is no treatment that enables full restoration of it. The aim of this study was to evaluate how collagen gel with bone marrow mesenchymal stem cells (MSCs) and collagen gel alone will influence on the hip cartilage repair after injury. Collagen type I was isolated from rats’ tails and cross-linked with N-hydroxysuccinimide in 24-hour process. MSCs were isolated from rats’ bone marrow. The experiments were conducted according to the guidelines for animal experiments of Ethics Committee. Fifteen 8-week-old Wistar rats were used in this study. All animals received hip joint surgery with a total of 30 created cartilage defects. Then, animals were randomly divided into three groups and filled, respectively, with collagen gel (group 1), collagen gel cultured with MSCs (group II) or left untreated as a control (control group). Immunohistochemy and radiological evaluation was carried out 11 weeks post implantation. It has been proved that the surface of the matrix is non-toxic, and its porosity promotes cell adhesion and growth. However, the in vivo regeneration process was poor. We observed the low integration rate of biomaterial. Immunohistochemical evaluation of cartilage after 11 weeks of treatment showed low II and high X collagen expression in two tested groups in comparison to the control one, in which we observed the high II collagen expression. What is more, after radiological analysis, we observed the best regeneration process in control group. The biomaterial construct and mesenchymal stem cells, as well as the use of the biomaterial itself was not sufficient to regenerate the hip cartilage surfaces. These results suggest that the collagen gel based biomaterials, even with MSCs, are not satisfactory in repar of hip cartilage defect. However, additional evaluation is needed to confirm these results.

Keywords: collafen gel, MSCs, cartilage repair, hip cartilage

Procedia PDF Downloads 456

Authors: Mohamed Raouf Benmakrelouf, Joseph Rynkiewicz

Abstract:

Targeted maximum likelihood estimation (TMLE) is well-established method for causal effect estimation with desirable statistical properties. TMLE is a doubly robust maximum likelihood based approach that includes a secondary targeting step that optimizes the target statistical parameter. A causal interpretation of the statistical parameter requires assumptions of the Rubin causal framework. The causal effect of binary variable, E, on outcomes, Y, is defined in terms of comparisons between two potential outcomes as E[YE=1 − YE=0]. Our aim in this paper is to present an adaptation of TMLE methodology to estimate the causal effect of a non-binary categorical variable, providing a large application. We propose coding on the initial data in order to operate a binarization of the interest variable. For each category, we get a transformation of the non-binary interest variable into a binary variable, taking value 1 to indicate the presence of category (or group of categories) for an individual, 0 otherwise. Such a dummy variable makes it possible to have a pair of potential outcomes and oppose a category (or a group of categories) to another category (or a group of categories). Let E be a non-binary interest variable. We propose a complete disjunctive coding of our variable E. We transform the initial variable to obtain a set of binary vectors (dummy variables), E = (Ee : e ∈ {1, ..., |E|}), where each vector (variable), Ee, takes the value of 0 when its category is not present, and the value of 1 when its category is present, which allows to compute a pairwise-TMLE comparing difference in the outcome between one category and all remaining categories. In order to illustrate the application of our strategy, first, we present the implementation of TMLE to estimate the causal effect of non-binary variable on outcome using simulated data. Secondly, we apply our TMLE adaptation to survey data from the French Political Barometer (CEVIPOF), to estimate the causal effect of education level (A five-level variable) on a potential vote in favor of the French extreme right candidate Jean-Marie Le Pen. Counterfactual reasoning requires us to consider some causal questions (additional causal assumptions). Leading to different coding of E, as a set of binary vectors, E = (Ee : e ∈ {2, ..., |E|}), where each vector (variable), Ee, takes the value of 0 when the first category (reference category) is present, and the value of 1 when its category is present, which allows to apply a pairwise-TMLE comparing difference in the outcome between the first level (fixed) and each remaining level. We confirmed that the increase in the level of education decreases the voting rate for the extreme right party.

Keywords: statistical inference, causal inference, super learning, targeted maximum likelihood estimation

Procedia PDF Downloads 103