phenorm_longit_simpl

'PheNorm' like function adapted to longitudinal data.

Using Electronic Health Record (EHR) is difficult because most of the time the true characteristic of the patient is not available. Instead we can retrieve the International Classification of Disease code related to the disease of interest or we can count the occurrence of the Unified Medical Language System. None of them is the true phenotype which needs chart review to identify. However chart review is time consuming and costly. 'PheVis' is an algorithm which is phenotyping (i.e identify a characteristic) at the visit level in an unsupervised fashion. It can be used for chronic or acute diseases. An example of how to use 'PheVis' is available in the vignette. Basically there are two functions that are to be used: `train_phevis()` which trains the algorithm and `test_phevis()` which get the predicted probabilities. The detailed method is described in preprint by Ferté et al. (2020) <doi:10.1101/2020.06.15.20131458>.

Thomas Ferte

PheVis

Automatic Phenotyping of Electronic Health Record at Visit
Resolution

Boris P. Hejblum

phenorm_longit_simpl function

<dl><dt>df</dt>
<dd>dataframe</dd>
<dt>var_surrogate</dt>
<dd>variables used for building the surrogates</dd>
<dt>surrogates_quali</dt>
<dd>numeric vector of the qualitative surrogate</dd>
<dt>id_rnd</dt>
<dd>ID for random effect</dd>
<dt>rf</dt>
<dd>should pseudo-labellisation with random forest be used (default is FALSE)</dd>
<dt>ntree</dt>
<dd>number of tree for <code>randomforest</code> (default is 100)</dd>
<dt>bool_weight</dt>
<dd>should the sampling probability balance the number of positive and negative extrema.</dd>
<dt>p.noise</dt>
<dd>percentage of noise introduced during the noising step</dd>
<dt>bool_SAFE</dt>
<dd>A boolean. If TRUE, SAFE selection is done, else it is not (default is TRUE)</dd>
<dt>size</dt>
<dd>minimum size of sampling</dd></dl>

Arguments

phenorm_longit_simpl — phenorm_longit_simpl

<dl>

<dt>df</dt>
<dd>dataframe</dd>


<dt>var_surrogate</dt>
<dd>variables used for building the surrogates</dd>


<dt>surrogates_quali</dt>
<dd>numeric vector of the qualitative surrogate</dd>


<dt>id_rnd</dt>
<dd>ID for random effect</dd>


<dt>rf</dt>
<dd>should pseudo-labellisation with random forest be used (default is FALSE)</dd>


<dt>ntree</dt>
<dd>number of tree for <code>randomforest</code> (default is 100)</dd>


<dt>bool_weight</dt>
<dd>should the sampling probability balance the number of positive and negative extrema.</dd>


<dt>p.noise</dt>
<dd>percentage of noise introduced during the noising step</dd>


<dt>bool_SAFE</dt>
<dd>A boolean. If TRUE, SAFE selection is done, else it is not (default is TRUE)</dd>


<dt>size</dt>
<dd>minimum size of sampling</dd>

</dl>

phenorm_longit_simpl: phenorm_longit_simpl

Description

Usage

Value

Arguments