Using an adaptive network-based fuzzy inference system for prediction of successful aging: a comparison with common machine learning algorithms

Table 1 The Primary list of features utilized in recognizing SA

Variable type	Variable Group	Variable name
Input	Demographic	Age (years), sex, educational level, marital status
	Socio-Economic	Occupation, income level, family support, insurance situation
	Presence illness	Blood pressure, cerebrovascular accident (CVA), osteopathic, eye disorders, renal disorders, liver disorders, muscle disorders, diabetes, cancer, convalescences, and other diseases
	Functional domain	Ability to perform activities of daily li ving (ADLs), sports activities, exercise time, and type of exercise.
	Sexual health	Sexual health assessment
	Lifestyle domain	Tension management, social and interpersonal relationships, performing disease prevention activities, physical activity, and exercise, assessment of nutritional status, assessment of mal-nutritional status, and general description of lifestyle.
	QoL	Physical health (general health, pain assessment, fatigue, physical dysfunction, physical function), mental and social health (satisfaction, social function, mental dysfunction), total description of the QoL
	Life Satisfaction	Life satisfaction assessment
Output	SA	(SA = 1), (non-SA = 0)

ISSN: 1472-6947