Machine Learning for Prognosis of Life Expectancy and Diseases
Palak Agarwal1, Navisha Shetty2, Kavita Jhajharia3, Gaurav Aggarwal4, Neha V Sharma5
1Palak Agarwal, Dept. of Information Technology, Manipal University Jaipur, Jaipur, India.
2Navisha Shetty, Dept. of Information Technology, Manipal University Jaipur, Jaipur, India.
3Kavita Jhajharia, Dept. of Information Technology, Manipal University Jaipur, Jaipur, India.
4Gaurav Aggarwal, Dept. of Information Technology, Manipal University Jaipur, Jaipur, India.
5Neha V Sharma, Dept. of Information Technology, Manipal University Jaipur, Jaipur, India.
Manuscript received on 02 July 2019 | Revised Manuscript received on 09 July 2019 | Manuscript published on 30 August 2019 | PP: 1765-1771 | Volume-8 Issue-10, August 2019 | Retrieval Number: J91560881019/2019©BEIESP | DOI: 10.35940/ijitee.J9156.0881019
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Longevity depends on various facets such as economic growth of the country, along with the health innovations of the region. Along with the prophecy of existence, we also figure out how sensitive a particular mainland is to few chronic diseases. These factors have a robust impact on the potential life span of the population. We study the biological and economical aspects of continents and their countries to predict the life expectancy of the population and to perceive the probability of the continent possessing long standing diseases like measles, HIV/AIDS, etc. Our research is conducted on the theory that exhibits the dependency or correlation of life expectancy with the various factors which includes the health factors as well as the economic factors. Two Machine learning algorithms simple linear regression, multiple linear regression are used for predicting the expectancy of life over different continents, whereas, decision tree algorithm, random forest algorithm, and were applied to classify the likelihood of occurrence of the disease. On comparing and contrasting various algorithms, we can infer that, multiple linear regression produces the most accurate results as to what the average life expectancy of the population would be given the current features of the continent like the adult mortality rate, alcohol consumption rate, infant deaths, the GDP of the country, average percentage expenditure of the population on health care and treatments, schooling rate, and other such features. On the other hand, we study five diseases namely, HIV/AIDS, measles, diphtheria, hepatitis B and polio. The experiment concluded that, on majority, random forest produces better results of classification based on the economic factors of the combination of various countries of different continents.
Keywords: Machine Learning, life expectancy, Diseases, life measurement, Regression, Random forest, Decision tree.
Scope of the Article: Machine Design