Event-based Pathology Data Prioritisation: A Study using Multi-variate Time Series Classification



Qi, Jing ORCID: 0000-0003-2476-7620, Burnside, Girvan ORCID: 0000-0001-7398-1346, Charnley, Paul and Coenen, Frans ORCID: 0000-0003-1026-6649
(2021) Event-based Pathology Data Prioritisation: A Study using Multi-variate Time Series Classification. In: 13th International Conference on Knowledge Discovery and Information Retrieval, 2021-10-25 - 2021-10-27.

[img] Text
jingQi_IC3K_2021.pdf - Author Accepted Manuscript

Download (268kB) | Preview

Abstract

A particular challenge for any hospital is the large amount of pathology data that doctors are routinely presented with. Pathology result analysis is routine in hospital environments. Some form of machine learning for pathology result prioritisation is therefore desirable. Patients typically have a history of pathology results, and each pathology result may have several dimensions, hence time series analysis for prioritisation suggests itself. However, because of the resource required, labelled prioritisation training data is typically not readily available. Hence traditional supervised learning and/or ranking is not a realistic solution and some alternative solution is required. The idea presented in this paper is to use the outcome event, what happened to a patient, as a proxy for a ground truth prioritisation data set. This idea is explored using two approaches: kNN time series classification and Long Short-Term Memory deep learning.

Item Type: Conference or Workshop Item (Unspecified)
Uncontrolled Keywords: Data Prioritisation, Time Series Classification, kNN, LSTM-RNN
Divisions: Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User: Symplectic Admin
Date Deposited: 12 Oct 2021 10:47
Last Modified: 20 Jan 2023 03:08
DOI: 10.5220/0010643900003064
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3140165