IGTProjection-class

IGTProjection

IGTProjection,IGTProjection-class

Class <code>IGTProjection</code> object contains the estimated Information Geometric Temporal plot projection
of a <code>DataTemporalMap</code> object.

Functions to delineate temporal dataset shifts in Electronic Health
Records through the projection and visualization of dissimilarities
among data temporal batches. This is done through the estimation of
data statistical distributions over time and their projection in
non-parametric statistical manifolds, uncovering the patterns of the
data latent temporal variability. 'EHRtemporalVariability' is
particularly suitable for multi-modal data and categorical variables
with a high number of values, common features of biomedical data where
traditional statistical process control or time-series methods may not
be appropriate. 'EHRtemporalVariability' allows you to explore and
identify dataset shifts through visual analytics formats such as
Data Temporal heatmaps and Information Geometric Temporal (IGT) plots.
An additional 'EHRtemporalVariability' Shiny app can be used to load
and explore the package results and even to allow the use of these
functions to those users non-experienced in R coding. (Sáez et al. 2020)
<doi:10.1093/gigascience/giaa079>.

Carlos S<c3><a1>ez

EHRtemporalVariability

Delineating Temporal Dataset Shifts in Electronic Health Records

Carlos Sáez

Alba Gutiérrez-Sacristán

Isaac Kohane

Juan M García-Gómez

Paul Avillach

Biomedical Data Science Lab, Universitat Politècnica de València (Spain) 

Department of Biomedical Informatics, Harvard Medical School 

IGTProjection-class function

<dl>
<dt><code>dataTemporalMap</code></dt>
<dd>the <code>DataTemporalMap</code> object from which the projection was estimated</dd></dl>
<dt><code>projection</code></dt>
<dd>d-by-c <code>matrix</code> of the IGT projection for d temporal batches in c dimensions calculated from the <code>estimateIGTProjection</code> function</dd>
<dt><code>embeddingType</code></dt>
<dd>embedding function used for the IGT projection calculation in the <code>estimateIGTProjection</code> function</dd>
<dt><code>stress</code></dt>
<dd>stress achieved in the lower-dimensional embedding, depending on the embedding type (e.g., classicalmds will return 1-GOF as returned by stats::cmdscale function, and nonmetricmds will return final stress in percent, as returned by the MASS::isoMDS function)</dd>

Slots

Class IGTProjection — IGTProjection-class

<dl>
<dt><code>dataTemporalMap</code></dt>
<dd>the <code>DataTemporalMap</code> object from which the projection was estimated</dd>


<dt><code>projection</code></dt>
<dd>d-by-c <code>matrix</code> of the IGT projection for d temporal batches in c dimensions calculated from the <code>estimateIGTProjection</code> function</dd>


<dt><code>embeddingType</code></dt>
<dd>embedding function used for the IGT projection calculation in the <code>estimateIGTProjection</code> function</dd>


<dt><code>stress</code></dt>
<dd>stress achieved in the lower-dimensional embedding, depending on the embedding type (e.g., classicalmds will return 1-GOF as returned by stats::cmdscale function, and nonmetricmds will return final stress in percent, as returned by the MASS::isoMDS function)</dd>


</dl>

Class IGTProjection

IGTProjection-class: Class IGTProjection

Description

Arguments

Value

Slots

Details