Knowledge Discovery in a Community Data Set: Malnutrition among the Elderly

Abstract

ObjectivesThe purpose of this study was to design a prediction model that explains the characteristics of elderly adults at risk of malnutrition.MethodsData were obtained from a large data set, 2008 Korean Elderly Survey, in which the data of 15,146 subjects were entered. With nutritional status a target variable, the input variables included the demographic and socioeconomic status of participants. The data were analyzed by using the SPSS Clementine 12.0 program's feature selection node to select meaningful variables.ResultsAmong the C5.0, C&R Tree, QUEST, and CHAID models, the highest predictability was reported by C&R Tree with the accuracy rate of 77.1%. The presence of more than two comorbidities, living alone status, having severe difficulty in daily activities, and lower perceived economic status were identified as risk factors of malnutrition in elderly.ConclusionsA reliable decision support model was designed to provide accurate information regarding the characteristics of elderly individuals with malnutrition. The findings demonstrated the good feasibility of data mining when used for a large community data set and its value in assisting health professionals and local decision makers to come up with effective strategies for achieving public health goals.

Social and Economic Factors and Malnutrition or the Risk of Malnutrition in the Elderly: A Systematic Review and Meta-Analysis of Observational Studies

“…Of the total 40 included studies, 36 were cross-sectional [13,14,17,18,[20][21][22][23][24][25][26][27][28][29][30][31][32][34][35][36][37][38][39][40][41][42][43][44][45][46][47][48][49][51][52][53] and four were cohort studies [16,19,33,50]. The study population was 60 years old and above, except for two studies that focused only on people aged over either 85 years [26] or 90 years [37].…”

“…All of the studies included people of both genders, except two studies [50,51]-one of them was only focused on men [50] and the other only on women [51]. Of the 40 studies included in the systematic review, according to the Development Human Index from the United Nations Development Program (UNDP) [54], 33 were conducted in regions with a high development human index (Poland [39], Sweden [38,40], China [30,37,53], Turkey [52], Canada [49,50], Italy [14,35], Taiwan [16], Lebanon [17,20,25], Brazil [18], Ireland [19,31], Finland [21], Spain [13,22,26], Norway [23,34], Portugal [24], Korea [27], Iran [28], Sri Lanka [29], New Zealand [48], Mexico [32], Amsterdam [33], Malaysia [36], and Shanghai [51]), five were conducted in regions with a medium development human index (Bangladesh [41,44], India [42], South Africa [43], and Egypt [45]), and two were conducted in regions with a low development human index (Central Africa…”

“…Of the 40 observational studies included in the systematic review, regarding the tools used to assess the nutritional status, 29 studies used the MNA [13,14,[16][17][18]20,21,[23][24][25][26][28][29][30][31][32][34][35][36][37][39][40][41][42][43]45,[51][52][53], one of which also used the Norwegian version of the Nutritional Form For the Elderly (NUFFE-NO) [34]. Of the other studies, five used only the Body Mass Index (BMI) [19,22,33,44,46] and one also used self-reported weight loss [19], four used the Senior in the community: risk evaluation for eating and nutrition (SCREEN II) [38,[48][49][50] and two used the Nutritional Screening Initiative (NSI) [27,47]. Only three studies considered depression as a pathology added to malnutrition [18,28,43].…”

“…Of the total of 40 observational studies included in the systematic review, eight different socioeconomic variables were evaluated: 31 studies evaluated the educational level [13,14,16,18-20, 22,24-30,33,35-37,39,41-49,51-53], 27 the fact of living alone or cohabiting [13,14,19,21,22,[25][26][27][28][29]31,32,[36][37][38][39][40][42][43][44][45][48][49][50][51][52][53], 24 the marital status [13,14,16,19,23,24,26,27,29,30,[33][34][35][36]39,41,42,[44][45][46]48,…”

“…Of the 31 studies that evaluated educational level, 15 established significant relationships with regard to malnutrition or malnutrition risk [14,22,25,27,28,35,39,41,42,[45][46][47]49,52,53], two suggested a significant trend [30,44], and 14 did not present significant differences [13,16,[18][19][20]24,26,29,33,36,37,43,48,51] (Table S2). Of those 15 with signification, 11 studies showed a negative association, that is, the lower the educational level, the higher the malnutrition risk [14,25,28,35,39,41,42,45,46,49,53].…”