Application of Data Science in Analysis of Different Usage of Mobile Health Applications
Saheed Yusuf, Tareq Al Jaber* and Majid Bahmanzadeh
School of Computer Science, University of Hull, United Kingdom
*Corresponding Author: Tareq Al Jaber, School of Computer Science, University
of Hull, United Kingdom.
March 14, 2023; Published: April 06, 2023
The health sector is one of the most important sectors in any society which also greatly influences economic growth. The adoption of technology in the health sector has contributed a lot of improvements and thus help automate some of the processes, saving time and manpower. Technological advancement in the health sector has led to the evolution of Mobile Health (mHealth) applications to ease some of the medical processes like diagnosis, education, treatment, monitoring etc. This study aims to focus on the usability of the mHealth applications based on the datasets scraped on the popular mobile application stores which are the App store (iOS) and Play store (Android) and what influences the usage of the mHealth applications. The datasets for this study were gathered through web scraping. Data cleaning, feature engineering, data visualization, data analysis and modelling were carried out on these datasets using Python programming language and its libraries. The result of this study shows that mHealth applications that are free to download have higher performance and usability than paid applications. Likewise, applications that provide in-app purchases tend to have higher performance and usability than applications that do not provide in-app purchases. Also, predictive models were trained for predicting the performance of the mHealth application and the XGBoost classifier had the best performance based on accuracy and f1-score. To increase the usability of mHealth applications, it is recommended to promote in-app purchases in mHealth applications rather than asking users to pay to download without having a feel of the service(s) rendered by the applications.
Keywords: HMHealth Applications; Data Science; Performance Evaluation; Feature Engineering; Data Analysis
- Habtemariam MK and Semegn ST. “Setting health sector priorities: a brief overview of Ethiopia’s experience”. Cost Effectiveness and Resource Allocation1 (2016): 1-3.
- Nolan P. “Measuring productivity in the health sector”. Policy Quarterly Special issue: Assessing and Enhancing New Zealand's Productivity 14.3 (2018).
- Mathews SC., et al. “Digital health: a path to validation”. NPJ Digital Medicine1 (2019): 1-9.
- Park Y. “Emerging new era of mHealth technologies”. Healthcare Informatics Research4 (2016): 253-254.
- Wang C and Qi H. “Influencing Factors of Acceptance and Use Behavior of Mobile Health Application Users: Systematic Review”. Healthcare (Basel)3 (2021): 357.
- Steinhubl SR., et al. “The emerging field of mHealth”. Science Translational Medicine283 (2015): rv3.
- Zhou L., et al. “The mHealth App Usability Questionnaire (MAUQ): development and validation study”. JMIR Mhealth Uhealth 4 (2019): e11500.
- Zhao Bo. “Web Scraping”. (2017): 1-3.
- Gheorghe M., et al. “Modern techniques of web scraping for data scientists”. International Journal of User-System Interaction1 (2018): 63-75.
- Awangga RM., et al. “Implementation of web scraping on Github task monitoring system”. TELKOMNIKA (Telecommunication Computing Electronics and Control) 17.1 (2019): 275-281.
- Kamiran F and Calders T. “Data preprocessing techniques for classification without discrimination”. Knowledge and Information Systems1 (2012): 1-33.
- Nargesian F., et al. “Learning Feature Engineering for Classification”. In (2017): 2529–2535.
- Hunter JD. “Matplotlib: A 2D graphics environment”. Computing in Science Engineering3 (2007): 90-95.
- Kodinariya TM and Makwana PR. “Review on determining number of Cluster in K-Means Clustering”. International Journal6 (2013): 90-95.
- Waskom ML. “Seaborn: statistical data visualization” 6.60 (2021): 3021.
- Rahaman M., et al. “Machine learning to predict the martensite start temperature in steels”. Metallurgical and Materials Transactions A 5 (2019): 2081-2091.
- M A H Shaikh and K Barbé. "Initial Estimation of Wiener-Hammerstein System with Random Forest". 2019 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), Auckland, New Zealand (2019): 1-6.
- Pedregosa F., et al. “Scikit-learn: Machine learning in Python”. The Journal of Machine Learning Research 12 (2011): 2825-2830.
- Zhang Harry. “The Optimality of Naive Bayes”. Proceedings of the Seventeenth International Florida Artificial Intelligence Research Society Conference, FLAIRS (2004): 2.
- Susan L. “Building a Logistic Regression in Python, Step by Step” (2017).
- Li W., et al. “Gene expression value prediction based on XGBoost algorithm”. Frontiers in Genetics 10 (2019): 1077.