Clustering is a common task in the field of cheminformatics. A key parameter that needs to be set for nonhierarchical clustering methods, such as k-means, is the number of clusters, k. Traditionally, the value of k is obtained by performing the clustering with different values of k and selecting that value that leads to the optimal clustering. In this study, we describe an approach to selecting k, a priori, based on the R-NN curve algorithm described by Guha et al. (J. Chem. Inf. Model., 2006, 46, 1713-722), which uses a nearest-neighbor technique to characterize the spatial location of compounds in arbitrary descriptor spaces. The algorithm generates a set of curves for the data set which are then analyzed to estimate the natural number of clusters. We then performed k-means clustering with the predicted value of k as well as with similar values to check that the correct number of clusters was obtained. In addition, we compared the predicted value to the number indicated by the average silhouette width as a cluster quality measure. We tested the algorithm on simulated data as well as on two chemical data sets. Our results indicate that the R-NN curve algorithm is able to determine the natural number of clusters and is in general agreement the average silhouette width in identifying the optimal number of clusters. (+info)
A gero-informatics tool to enhance the care of hospitalized older adults with cognitive impairment.
(34/128)
Approximately 50% of hospitalized elders have cognitive impairment (CI) that increases their vulnerability to hospital-acquired complications. Matching geriatric evaluation and recommendations to the true pace of hospital care may improve the care of elders in general, in particular those with CI. Integrating information technology into geriatric services (gero-informatics) might allow reduction of the time to implementation of geriatric recommendations and prevent the initiation of potentially harmful medications and procedures during the critical first 48 hours of hospitalization. This paper reviews our local gero-informatics early experience of developing a computerized decision support system (CDSS) to enhance hospital care for elders with CI by reducing inappropriate use of anticholinergic medications, urinary catheters, and physical restraints. (+info)
Phenobabelomics--mouse phenotype data resources.
(35/128)
Kick-starting health informatics careers--a Canadian approach.
(38/128)
We introduce the Applied Health Informatics Bootcamp. This is an intense, interactive on-site program, augmented by approximately 80 hours of on-line material. The Bootcamp is intended to introduce those with little or no knowledge of Health Informatics (HI) to the nature, key concepts, and applications of this discipline to addressing challenges in the health field. The focus of the program is on Applied Health Informatics (AHI), the discipline addressing the preparation for, and the procurement, deployment, implementation, resourcing, effective usage, and evaluation of informatics solutions in the health system. Although no program of this duration can cover all topics, we target the high profile areas of Health Informatics and point the participants in the direction of broader and deeper explorations. (+info)
Experience versus talent shapes the structure of the Web.
(39/128)