PubMed Health⌕ Search

Biomedical subjects

Ugur Bilge

Publications and source records attributed to Ugur Bilge.

2 recordsLinked to original sources

Agent based simulations in healthcare.

Agent Based Simulations (ABS) is a relatively recent computer paradigm. As opposed to "top down" conventional computer simulations, the ABS approach is a "bottom-up" modelling technique where a medium to high number of independent agents is modelled. These agents' interactions sometimes cause unexpected "emergent" system behaviour. ABS is particularly suitable in the social context such as healthcare where a large number of human agents interact and co-operate for common goals. Today ABS in the social context is often used together with the recently introduced network analysis techniques and network visualization tools for modelling and simulating social agents within organisations. At Akdeniz University we are starting a number of projects for applying ABS technology in healthcare. In this paper we present two of the ongoing projects in this field. Firstly we have developed a prototype simulator for the long term monitoring of Chronic Obstructive Pulmonary Disease (COPD) as a major public health problem. We present the COPD simulator, its agents, parameters and working principles. Secondly we want to apply ABS and the network analysis techniques to visualise and explore informal social networks amongst staff at the Akdeniz University Hospital to assess and evaluate properties of the organisation in terms of its ability to innovate and share knowledge. In our applications, we primarily aim to use ABS in a web-based platform to create a virtual environment for discussion, visualising and running what-if scenarios to test out various options for managing healthcare, as well as sharing information and creating a virtual community.

Computer Simulation↗

An application of a genetic algorithm in conjunction with other data mining methods for estimating outcome after hospitalization in cancer patients.

BACKGROUND: We investigated which factors predicted the risk of in-hospital mortality in a general population of cancer patients with non-terminal disease and whether employing the genetic algorithm technique would be useful in this regard. MATERIAL/METHODS: A total of 201 cancer patients, including all cases of in-hospital mortality over a 2-year period, as well as a control group of subjects discharged during the same period, all having an Eastern Cooperative Oncology Group (ECOG) performance status of of < or =3 at the time of admission, were retrospectively evaluated. Indicators of in-hospital mortality were determined by multivariate logistic regression, recursive partitioning analysis, neural network, and genetic algorithm (GA) techniques. The performance of the different techniques were compared by a number of measures, including receiver operating curve (ROC) analysis. RESULTS: All four analysis methods selected a combination of six explanatory variables to explain the risk of in-hospital mortality: lactate dehydrogenase (LDH), alanine transaminase (ALT), hemoglobin (Hb), white blood cell counts (Wbc), type of cancer, and reason for admission. Compared with the other 3 methods, GA selected the least number of explanatory variables, i.e. LDH and reason for admission, with similar fraction of cases explained (78.6%), and yielded a fitness score of 0.52. CONCLUSIONS: LDH is an important indicator of in-hospital mortality for hospitalized cancer patients not in terminal stage. GA reliably predicted in-hospital mortality and was shown to be as efficient as the other data mining techniques employed in this study. Its use in a clinical setting for prognostication in oncology appears promising.

Adolescent↗