Page 22 - AIH-1-4

Artificial Intelligence in Health

ORIGINAL RESEARCH ARTICLE
Health-care app detection using optimized

clustering

Ciza Thomas * and Rendhir R. Prasad 2
1
1 School of Computer Science and Technology, Karunya Institute of Technology and Sciences,
Coimbatore, Tamil Nadu, India
2 Department of Information Technology, Government College of Engineering, Trivandrum, Kerala, India

Abstract

Medical health-care apps have become ubiquitous in today’s world, enhancing
health-care quality at affordable costs. The continuous development of new apps
underscores their high acceptance and popularity. Machine learning techniques offer
effective app identification owing to their high prediction accuracy, particularly with
a training dataset of known apps. Although machine learning techniques provide
high detection accuracy for known apps, they exhibit abysmal accuracy in detecting
unknown and novel apps. This research proposes a novel approach to optimizing
the K-means clustering algorithm for detecting zero-day apps. The proposed
technique integrates a perceptron feed-forward neural network to determine the
coordinates of the centroids of the clusters in K-means clustering. Experimental
evaluations demonstrate the efficacy of the proposed approach in enhancing the
performance of K-means clustering, providing improved detection for both known
and unknown medical health-care apps. A total of 30 health-care apps was utilized
in this evaluation. This research enhances the detection accuracy of medical health-
care apps, particularly zero-day apps. The intercluster similarity of the benign class
*Corresponding author:
Ciza Thomas improved to 0.99, and that of the malicious class improved to 0.91, highlighting the
(cizathomas@karunya.edu) improved classification of the apps. The major contribution of this work is achieving
an intercluster similarity of 0.89 for detecting novel apps.
Citation: Thomas C, Prasad RR.
Health-care app detection using
optimized clustering. Artif Intell
Health. 2024;1(4):16-29. Keywords: Medical apps; Health-care apps; Machine learning; Artificial neural network;
doi: 10.36922/aih.2585 K-means clustering; Euclidean distance measure; Within-class similarity
Received: December 30, 2023
Accepted: June 13, 2024
Published Online: August 16, 2024 1. Introduction
Copyright: © 2024 Author(s). Medical health-care apps have become ubiquitous in today’s world, playing a pivotal
This is an Open-Access article role in enhancing health-care quality at an affordable cost. Health-care apps are software
distributed under the terms of the
Creative Commons Attribution programs designed for mobile devices, including laptops, tablets, and smartphones,
License, permitting distribution, which often integrate with wearable devices. The functionalities of health-care apps are
and reproduction in any medium,
provided the original work is diverse, ranging from displaying vital information to assisting patients in monitoring
properly cited. their health. The constant influx of new apps, driven by high acceptance and popularity,
Publisher’s Note: AccScience is evident, including contributions from startups. However, the rapid development has
Publishing remains neutral with raised concerns about inadequate security measures, potentially compromising privacy,
regard to jurisdictional claims in
published maps and institutional authenticity, and data integrity for both patients and medical professionals. Addressing
affiliations. these security concerns is crucial to ensuring the safety and confidentiality of health-

Volume 1 Issue 4 (2024) 16 doi: 10.36922/aih.2585