Year: 2021
Type: article
Abstract: Life expectancy at older ages has seen an increment in the past 100 years and factors influencing longevity are since being studied. Public health sectors (PHS) across the globe are trying hard to understand longevity trends to improve living conditions and provide necessary medical facilities; but there is no single tool that can help the overall cause of recording and/or measuring and/or predicting human longevity. The objectives of this study are to help PHS understand longevity-influencing factors and to offer a framework to record and predict longevity trends in any population around the globe. This study has gathered fifteen longevity-influencing factors from literature between 2000 and 2020; with a special focus on APOE genotype; and based on them, has developed a framework GenF, including a rule base dataset of 73,728 rules, to predict longevity. Furthermore, the study has also used GenF to perform feature selection on the rule base and generate another rule base for customized longevity predictions. Models, using four different machine learning classifiers, are then trained on both rule bases to predict longevity.
Source: Informatics in Medicine Unlocked
Authors: Sadia Khalid, Uzair Rasheed, Usman Qamar
Institution: National University of Sciences and Technology
Language: English
Subfield: Health Information Management
Field: Health Professions
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $1,500
OpenAlex ID: W3203046246
