Title : Reinforcing clinical guidelines through mobile phone based applications for health workers in Malawi
| Presenter | Marije Geldoff |
| Abstract | Marije Geldof, former AI student who graduated in 2003, will share her experiences with the work she did for D-tree International in Malawi until November 2014. D-tree International is an American NGO that develops mobile phone applications based on government clinical guidelines for use by health workers, with the aim of improving adherence to the guidelines and in that way quality of care. The presentation will focus on the practicalities of formalizing the government guidelines and the platform Mangologic that was used for this, as well as the reality of implementing the mobile applications in the field. |
Title : Crowdsourcing Ground Truth for Relation Extraction in the Medical Domain
| Presenter | Anca Dumitrache |
| Abstract | I will present the CrowdTruth (http://crowdtruth.org/) approach to performing relation extraction from medical data. CrowdTruth exploits inter-annotator disagreement as a useful signal, allowing us to evaluate data quality, such as ambiguity and vagueness at the sentence level, worker quality, and the quality of the target semantics. I will introduce a workflow for generating gold standard annotations for medical relation extraction through a series of crowdsourcing tasks. Then I will present an evaluation of the crowd data by comparing it with the current gold standard in medical relation extraction. The evaluation is performed by training a relation extraction classifier with both datasets, and comparing the results for F1 measure and accuracy in a cross-validation experiment. |