Atrial Fibrillation (AF) data is obtained from a randomized trial to study
the effect of surgical ablation as a treatment option for AF 
among patients with persistent and
long-standing persistent AF who requires mitral valve surgery.
Patients were randomized into two groups: mitral valve
surgery with ablation and mitral valve surgery without ablation.
Patients in the ablation group were further randomized into
two types of procedure: pulmonary vain isolation (PVI)
and biatrial maze procedure.
These patients were followed weekly for a period of 12 months. The
primary outcome of the study is the presence/absence of AF
(binary longitudinal response).
Data includes 228 patients. From 228 patients, 7949 AF measurements
are available with average of 35 measurements per patient.

datasets

Implements Friedman's gradient descent boosting algorithm for modeling longitudinal response using multivariate tree base learners. Longitudinal response could be continuous, binary, nominal or ordinal. A time-covariate interaction effect is modeled using penalized B-splines (P-splines) with estimated adaptive smoothing parameter. Although the package is design for longitudinal data, it can handle cross-sectional data as well. Implementation details are provided in Pande et al. (2017), Mach Learn <DOI:10.1007/s10994-016-5597-1>.

Udaya Kogalur

boostmtree

Boosted Multivariate Trees for Longitudinal Data

AF function

A list containing four elements:<ol>
<li>The 84 patient variables (features).</li>
<li>Time points (time).</li>
<li>Unique patient identifier (id).</li>
<li>Presence or absence of AF (y).</li>
</ol>

AF: Atrial Fibrillation Data

Description

Arguments

Format

References

Examples