Data Prioritisation in the Absence of a Ground Truth

7^th April 2021, 11:30
Jing Qi

Abstract

Pathology results play a critical role in medical decision making. A particular challenge is the large number of pathology results that doctors are presented with on a daily basis. Some form of pathology result prioritisation is therefore a necessity. However, there is no readily available training data that would support a traditional supervised learning approach. Thus, to address the problem of data prioritisation in the absence of ground truth data, we proposed two solutions with the first one considering prioritisation by Anomaly Detection (using DBSAN) and the second using Ground Truth Proxy (KNN and RNN). Experimental results show that both mechanisms were able to identify priority records.

Biography

Jing Qi is a second-year PhD student in the Department of Computer Science at the University of Liverpool. Her work mainly focuses on machine learning. She is especially interested in research related to the use of the tools and techniques of machine learning to process sequential (time series) data in the context of a range of application domains.