<div class="section">
<a class="named-anchor" id="S1">
<!--
named anchor
-->
</a>
<h5 class="section-title" id="d4995884e163">Background</h5>
<p id="P1">In an era of “big data,” computationally efficient and privacy-aware solutions
for
large-scale machine learning problems become crucial, especially in the healthcare
domain, where large amounts of data are stored in different locations and owned by
different entities. Past research has been focused on centralized algorithms, which
assume the existence of a central data repository (database) which stores and can
process the data from all participants. Such an architecture, however, can be impractical
when data are not centrally located, it does not scale well to very large datasets,
and introduces single-point of failure risks which could compromise the integrity
and privacy of the data. Given scores of data widely spread across hospitals/individuals,
a decentralized computationally scalable methodology is very much in need.
</p>
</div><div class="section">
<a class="named-anchor" id="S2">
<!--
named anchor
-->
</a>
<h5 class="section-title" id="d4995884e168">Objective</h5>
<p id="P2">We aim at solving a binary supervised classification problem to predict
hospitalizations
for cardiac events using a distributed algorithm. We seek to develop a general decentralized
optimization framework enabling multiple data holders to collaborate and converge
to a common predictive model, without explicitly exchanging raw data.
</p>
</div><div class="section">
<a class="named-anchor" id="S3">
<!--
named anchor
-->
</a>
<h5 class="section-title" id="d4995884e173">Methods</h5>
<p id="P3">We focus on the soft-margin
<i>l</i>
<sub>1</sub>-regularized sparse Support Vector Machine (sSVM) classifier. We develop
an iterative
cluster Primal Dual Splitting (cPDS) algorithm for solving the large-scale sSVM problem
in a decentralized fashion. Such a distributed learning scheme is relevant for multi-institutional
collaborations or peer-to-peer applications, allowing the data holders to collaborate,
while keeping every participant’s data private.
</p>
</div><div class="section">
<a class="named-anchor" id="S4">
<!--
named anchor
-->
</a>
<h5 class="section-title" id="d4995884e184">Results</h5>
<p id="P4">We test cPDS on the problem of predicting hospitalizations due to heart
diseases within
a calendar year based on information in the patients Electronic Health Records prior
to that year. cPDS converges faster than centralized methods at the cost of some communication
between agents. It also converges faster and with less communication overhead compared
to an alternative distributed algorithm. In both cases, it achieves similar prediction
accuracy measured by the Area Under the Receiver Operating Characteristic Curve (AUC)
of the classifier. We extract important features discovered by the algorithm that
are predictive of future hospitalizations, thus providing a way to interpret the classification
results and inform prevention efforts.
</p>
</div>