Big Data and Information Analytics: latest papers http://www.aimsciences.org/test_aims/journals/rss.jsp?journalID=27 Latest articles for selected journal http://www.aimsciences.org/test_aims/journals/displayPaper.jsp?paperID=14795 Prediction models for burden of caregivers applying data mining techniques http://www.aimsciences.org/test_aims/journals/displayPaper.jsp?paperID=14795 Introduction: Caregiver stress negatively influences both patients and caregivers. Predictors of caregiver difficulty may provide crucial insights for providers to prioritize those with the highest risk of stress. The purpose of this study was to develop a prediction model of caregiver difficulty by applying data mining techniques to a national behavioral risk factor data set.
    Methods: Behavioral data including 397 variables on 2,264 informal caregivers, who provided any care to a friend or family member during the past month, were extracted from a publicly available national dataset in the U.S (N = 451,075) and analyzed. We applied several classification algorithms (J48, RandomForest, MultilayerPerceptron, AdaboostM1), to iteratively generate prediction models for caregiving difficulty with 10-fold cross validation.
    Results: 44.7% of informal caregivers answered that they faced the greatest difficulties while they took care of patients. Among those who faced the greatest difficulties, the reasons were creating emotional burden (45%). Patient cognitive alteration (e.g. cognitive changes in thinking or remembering during the past year), care hours, and relationship with a caregiver appeared as the main predictors of caregiver stress (classified correctly 63%, difficulty AUC = 65%, no difficulty AUC = 65%).
    Conclusions: Data mining methods were useful to discover new behavioral risk knowledge and to visualize predictors of caregiver stress from a multidimensional behavioral dataset.This study suggests that health professionals target dementia family caregivers who are anticipated to experience patients neuro-cognitive changes, and inform the caregivers about importance of limiting care hours, burn out and delegation of caregiving tasks. ]]>
Sunmoo Yoon, Maria Patrao, Debbie Schauer and Jose Gutierrez Fri, 1 Dec 2017 20:00:00 GMT
http://www.aimsciences.org/test_aims/journals/displayPaper.jsp?paperID=14750 Older adults, frailty, and the social and behavioral determinants of health http://www.aimsciences.org/test_aims/journals/displayPaper.jsp?paperID=14750 Objective: To examine the associations between social and behavioral determinants of health (SBDH) and frailty among older adults using an existing Omaha System dataset collected in the community.
    Design: Secondary exploratory data analysis.
    Setting: An existing dataset of home health records from a Midwestern region, including Omaha System problems, interventions, and Knowledge (K), Behavior (B), and Status (S) outcomes.
    Participants: Older adults (n = 1,618) that were 63.7% female with an average age of 80.1 years (SD = 7.6).
    Methods: This exploratory data analysis study reused an existing Omaha System dataset to reveal hidden patterns in health outcomes of frail vs. non-frail older adults relative to SBDH. Two separate metrics were used to classify SBDH and frailty. An existing summative SBDH index was derived from measures recommended by the Institute of Medicine (IOM). A new frailty index was created based on Omaha System terms mapped to frailty criteria established by Fried and colleagues. Heat maps and line graphs were developed using Microsoft Excel and R. Patterns were discovered and related hypotheses were evaluated using paired samples t-tests and two-way ANOVA tests in R.
    Results: Records (n = 1,618) were divided into SBDH Group 0 with no SBDH Problems (n = 1,397) and SBDH Group 1 with one or more SBDH Problems (n = 221). Overall, there was significant improvement in KBS after home care interventions. SBDH, Frailty, and interactions between SBDH and Frailty were significantly associated with differences in KBS outcomes. Visualizations showed numerous potential patterns for further research.
    Discussion: SBDH Group 1 was largely defined by having the Mental health problem. Being in SBDH Group 1 was negatively associated with KBS outcomes. This aligns with the literature on the impact of mental health on overall health and wellbeing. As frailty scores increased, KBS outcomes decreased, demonstrating a possible continuum of increasing frailty as related co-morbidities accrued. This is a new perspective on frailty that should be further investigated. SBDH group, Frailty, and SBDH-Frailty interaction were all important for understanding outcomes for final K, final S, and difference in K, B, and S. For final B, SBDH group and Frailty were important. Because interaction between SBDH and Frailty was observed for most problems and outcomes, researchers who study Frailty should account for SBDH, especially mental health. SBDH problems were infrequent in the data. This has implications for our ability to understand SBDH in home care. Future research should incorporate data that include SBDH problem assessments.
    Conclusion: This exploratory data analysis study identified relationships between SBDH and frailty for older adults along a continuum of frailty using the Omaha System. Further research is needed to validate the findings and to evaluate the metrics with other datasets and populations. ]]>
Grace Gao, Sasank Maganti and Karen A. Monsen Fri, 1 Dec 2017 20:00:00 GMT
http://www.aimsciences.org/test_aims/journals/displayPaper.jsp?paperID=14773 What can we learn about the Middle East Respiratory Syndrome (MERS) outbreak from tweets? http://www.aimsciences.org/test_aims/journals/displayPaper.jsp?paperID=14773 Sunmoo Yoon, Da Kuang, Peter Broadwell, Haeyoung Lee and Michelle Odlum Fri, 1 Dec 2017 20:00:00 GMT