Predictive Analytics Model Based on Multiclass Classification for Asthma Severity by Using Random Forest Algorithm
- Resource Type
- Conference
- Authors
- Akbar, Wasif; Wu, Wei-Ping; Faheem, Muhammad; Saleem, Sehrish; Javed, Arslan; Saleem, Muhammad Asim
- Source
- 2020 International Conference on Electrical, Communication, and Computer Engineering (ICECCE) Electrical, Communication, and Computer Engineering (ICECCE), 2020 International Conference on. :1-4 Jun, 2020
- Subject
- Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Fields, Waves and Electromagnetics
General Topics for Engineers
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Big Data
Diseases
Forestry
Predictive models
Respiratory system
Data Analytics
Machine Leaning
Disease Prediction
Healthcare
- Language
In modern life, health status prediction has become very crucial. Big data analysis plays a vital role to predict this perfectly. Asthma is a severe chronic disease with severe symptoms. Asthma disease is a chronic disease that leads to death. Researchers have focused on this for better decision making to predict the disease timely use of predictive analysis. This study proposes a Predictive Analytic Model for Asthma prediction using Random Forest (PAM-RF). Data of patients suffering from Asthma has been trained by a random forest approach which predicts to classify the data. Experiments are performed on Hadoop-spark which predicts the future health state of patients. The proposed approach has attained an accuracy of 98.80 percent to predict the asthma disease.