Name
Abstract | ||
|---|---|---|
Healthcare is a complex process. It is difficult to choose an effective strategy from numerous possible treatment courses. Whether a healthcare strategy is good or bad? The statistic evidence of instances can tell the truth. Recently, many models of machine learning can handle the static data sets well. They usually use classification methods for disease diagnosis, which relates features to diseases. However, few data sets comprise healthcare processes, and few models relate healthcare actions to healthcare results. We propose a Bayesian inference graph for acquiring the experience of experts and the healthcare statistic evidence. We use a set of states to represent the physical condition of a person, and use a set of actions to represent the healthcare methods. Our aim is to build a probabilistic inference graph of each state transition, which shows the probability of a state transition through a certain action. The inference graph, like the experience of human beings, can be enriched. It begins from the prior experience, and then it will increase its knowledge by increasing evidential instances. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1109/ICPPW.2016.65 | 2016 45th International Conference on Parallel Processing Workshops (ICPPW) |
Keywords | Field | DocType |
healthcare,state transition,Dirichlet distribution,statistic evidence,graphical model | Health care,Data set,Bayesian inference,Statistic,Inference,Fiducial inference,Computer science,Artificial intelligence,Graphical model,Dirichlet distribution,Machine learning | Conference |
ISSN | ISBN | Citations |
1530-2016 | 978-1-5090-2826-9 | 1 |
PageRank | References | Authors |
0.35 | 6 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yinglong Dai | 1 | 9 | 2.94 |
| Wenjun Jiang | 2 | 356 | 24.25 |
| Guojun Wang | 3 | 437 | 47.52 |