Open Access

ARTICLE

AI Powered Asthma Prediction Towards Treatment Formulation: An Android App Approach

Saydul Akbar Murad¹, Apurba Adhikary², Abu Jafar Md Muzahid¹, Md. Murad Hossain Sarker³, Md. Ashikur Rahman Khan², Md. Bipul Hossain², Anupam Kumar Bairagi^4,*, Mehedi Masud⁵, Md. Kowsher⁶

1 Faculty of Computing, Universiti Malaysia Pahang, 26600, Pekan, Pahang, Malaysia
2 Department of Information and Communication Engineering, Noakhali Science and Technology University (NSTU), Noakhali, Bangladesh
3 Department of Information and Communication Technology, Comilla University (CoU), Comilla, Bangladesh
4 Computer Science and Engineering Discipline, Khulna University, Khulna, 9208, Bangladesh
5 Department of Computer Science, College of Computers and Information Technology, Taif University, Taif, 21944, Saudi Arabia
6 Department of Computer Science, Stevens Institute of Technology, Hoboken, NJ 07030, USA

* Corresponding Author: Anupam Kumar Bairagi. Email:

Intelligent Automation & Soft Computing 2022, 34(1), 87-103. https://doi.org/10.32604/iasc.2022.024777

Received 30 October 2021; Accepted 17 December 2021; Issue published 15 April 2022

Abstract

Asthma is a disease which attacks the lungs and that affects people of all ages. Asthma prediction is crucial since many individuals already have asthma and increasing asthma patients is continuous. Machine learning (ML) has been demonstrated to help individuals make judgments and predictions based on vast amounts of data. Because Android applications are widely available, it will be highly beneficial to individuals if they can receive therapy through a simple app. In this study, the machine learning approach is utilized to determine whether or not a person is affected by asthma. Besides, an android application is being created to give therapy based on machine learning predictions. To collect data, we enlisted the help of 4,500 people. We collect information on 23 asthma-related characteristics. We utilized eight robust machine learning algorithms to analyze this dataset. We found that the Decision tree classifier had the best performance, out of the eight algorithms, with an accuracy of 87%. TensorFlow is utilized to integrate machine learning with an Android application. We accomplished asthma therapy using an Android application developed in Java and running on the Android Studio platform.

---

Keywords

---