http://www.biomedcentral.com/bmcmedinformdecismak/ The editor's pick of recent articles published by BMC Medical Informatics and Decision Making 2012-03-29T00:00:00Z Background: This paper explores the meanings given by a diverse range of stakeholders to a decision aid aimed at helping carers of people in early to moderate stages of dementia (PWD) to select community based respite services. Decision aids aim to empower clients to share decision making with health professionals. However, the match between health professionals' perspectives on decision support needs and their clients' perspective is an important and often unstudied aspect of decision aid use. Methods: A secondary analysis was undertaken of qualitative data collected as part of a larger study. The data included twelve interviews with carers of people with dementia, three interviews with expert advisors, and three focus groups with health professionals. A theoretical analysis was conducted, drawing on theories of 'positioning' and professional identity. Results: Health professionals are seen to hold varying attitudes and beliefs about carers' decision support needs, and these appeared to be grounded in the professional identity of each group. These attitudes and beliefs shaped their attitudes towards decision aids, the information they believed should be offered to dementia carers, and the timing of its offering. Some groups understood carers as needing to be protected from realistic information and consequently saw a need to filter information to carer clients. Conclusion: Health professionals' beliefs may cause them to restrict information flows, which can limit carers' ability to make decisions, and limit health services' ability to improve partnering and shared decision making. In an era where information is freely available to those with the resources to access it, we question whether health professionals should filter information. http://www.biomedcentral.com/1472-6947/12/26 Christine Stirling Barbara Lloyd Jenn Scott Jenny Abbey Toby Croft Andrew Robinson BMC Medical Informatics and Decision Making 2012, 12:26 2012-03-29T00:00:00Z 10.1186/1472-6947-12-26 Filtering information to dementia carers Attitudes and beliefs of health professionals, such as the need to protect individuals from realistic information, can cause restricted information flows to carers of dementia patients, which can severely limit shared decision making. /content/figures/1472-6947-12-26-toc.gif BMC Medical Informatics and Decision Making 1472-6947 12 26 2012-03-29T00:00:00Z XML Background: Hospital in-patient falls constitute a prominent problem in terms of costs and consequences. Geriatric institutions are most often affected, and common screening tools cannot predict in-patient falls consistently. Our objectives are to derive comprehensible fall risk classification models from a large data set of geriatric in-patients' assessment data and to evaluate their predictive performance (aim#1), and to identify high-risk subgroups from the data (aim#2). Methods: A data set of n = 5,176 single in-patient episodes covering 1.5 years of admissions to a geriatric hospital were extracted from the hospital's data base and matched with fall incident reports (n = 493). A classification tree model was induced using the C4.5 algorithm as well as a logistic regression model, and their predictive performance was evaluated. Furthermore, high-risk subgroups were identified from extracted classification rules with a support of more than 100 instances. Results: The classification tree model showed an overall classification accuracy of 66%, with a sensitivity of 55.4%, a specificity of 67.1%, positive and negative predictive values of 15% resp. 93.5%. Five high-risk groups were identified, defined by high age, low Barthel index, cognitive impairment, multi-medication and co-morbidity. Conclusions: Our results show that a little more than half of the fallers may be identified correctly by our model, but the positive predictive value is too low to be applicable. Non-fallers, on the other hand, may be sorted out with the model quite well. The high-risk subgroups and the risk factors identified (age, low ADL score, cognitive impairment, institutionalization, polypharmacy and co-morbidity) reflect domain knowledge and may be used to screen certain subgroups of patients with a high risk of falling. Classification models derived from a large data set using data mining methods can compete with current dedicated fall risk screening tools, yet lack diagnostic precision. High-risk subgroups may be identified automatically from existing geriatric assessment data, especially when combined with domain knowledge in a hybrid classification model. Further work is necessary to validate our approach in a controlled prospective setting. http://www.biomedcentral.com/1472-6947/12/19 Michael Marschollek Mehmet Gövercin Stefan Rust Matthias Gietzelt Mareike Schulze Klaus-Hendrik Wolf Elisabeth Steinhagen-Thiessen BMC Medical Informatics and Decision Making 2012, 12:19 2012-03-14T00:00:00Z 10.1186/1472-6947-12-19 Predicting in-patient falls with risk modeling A classification tree model derived from a large data set demonstrates predictive value in identifying individuals at risk for falling and is competitive with current dedicated fall risk screening tools. /content/figures/1472-6947-12-19-toc.gif BMC Medical Informatics and Decision Making 1472-6947 12 19 2012-03-14T00:00:00Z XML