Keywords:
Computer applications, Management, Lung, Neural networks, CT, RIS, Computer Applications-General, Cost-effectiveness, Statistics, Embolism / Thrombosis, Quality assurance, Economics
Authors:
E. Sjöblom1, C. Lundström1, M. Andersson1, N. Carius2, J. Taghia3; 1Linköping/SE, 2Ljungsbro/SE, 3Uppsala/SE
DOI:
10.1594/ecr2018/C-0108
Aims and objectives
In the management of radiology operations,
it is important to understand the effectiveness of diagnostic pathways.
One source of data to underpin managerial decision-making is the radiology report,
but large-scale mining of such data is a challenge.
The challenge comes from extracting actionable data from the free-text format that most radiology reports consist of [3].
We here study at the problem of quantifying the rate of positive findings in CT pulmonary embolism examinations.
The number of examinations with positive findings versus the total number of examinations is an indicator of the effectiveness of the procedure.
It can be used to answer the question “Are we doing too few or too many CT pulmonary embolism examinations?”.
To address the problem of the free-text format of the reports we use a machine learning approach.
A classifier is trained on a large set of reports from a university hospital.
The classifier and its characteristics is used to create a model for the rate of positive findings in CT pulmonary embolism examinations.