Files
2020-01-30 16:24:26 +01:00

36 lines
2.1 KiB
Plaintext

<%@ Control Language="C#" AutoEventWireup="true" CodeBehind="mod_about.ascx.cs" Inherits="WebLCP.WUC.mod_about" %>
<div class="card">
<div class="card-header bg-dark text-light">
<div class="row">
<div class="col-9">
<h2>PROJECT DESCRIPTION</h2>
</div>
<div class="col-3 text-right p-0">
<img src="../Images/brain.png" class="img-fluid" width="128" />
</div>
</div>
</div>
<div class="card-body">
<p>The project aims at detecting the presence of any cut-offs in AD biomarkers distribution that allows to classify subject/patients in terms of prognostic evaluation. In particular, the main target is to provide a free, user-friendly on-line interface of an ad-hoc developed algorithm that evaluates the effects of genetic/demographic AD-related factors (APOE, age and sex) on the detected biomarker cut-offs. The idea is to allow people non-familiar with the R package to use this powerful instrument for improving the disease understanding and to create a platform for collaboration of different centers and researchers.</p>
<p>
This on-line software is an open and user-friendly tool for:
</p>
<ol>
<li>extracting any data-driven cut-off of quantitative biomarker (i.e. continuous variable) and
</li>
<li>evaluating the effect of APOE, age and sex on cut-offs estimation (Marizzoni, Ferrari, et al. 2019; <a href="https://doi.org/10.1016/j.neurobiolaging.2019.12.019" target="_blank">https://doi.org/10.1016/j.neurobiolaging.2019.12.019</a>).
</li>
</ol>
<p>
The cut-off extraction is based on finite Gaussian mixture model approach that allows to produce a probabilistic clustering/classification of the data into any subgroups (defined by the components of the mixture distribution) of the overall population. The effect of APOE, age and sex on cut-offs values was estimated by applying an extension of finite mixture model applied to a generalized linear model (more details are reported
<asp:HyperLink runat="server" NavigateUrl="~/MethodSpecs">here.</asp:HyperLink>)
</p>
</div>
</div>