Automated Measurement of Adherence to Traumatic Brain Injury (TBI) Guidelines using Neurological ICU Data

Stell, A., Piper, I. and Moss, L. (2018) Automated Measurement of Adherence to Traumatic Brain Injury (TBI) Guidelines using Neurological ICU Data. In: 11th International Joint Conference on Biomedical Engineering Systems and Technologies, Funchal, Madeira, Portugal, 19-21 Jan 2018, pp. 135-146. ISBN 9789897582813 (doi: 10.5220/0006583801350146)

Abstract

Using a combination of physiological and treatment information from neurological ICU data-sets, adherence to traumatic brain injury (TBI) guidelines on hypotension, intracranial pressure (ICP) and cerebral perfusion pressure (CPP) is calculated automatically. The ICU output is evaluated to capture pressure events and actions taken by clinical staff for patient management, and are then re-expressed as simplified process models. The official TBI guidelines from the Brain Trauma Foundation are similarly evaluated, so the two structures can be compared and a quantifiable distance between the two calculated (the measure of adherence). The methods used include: the compilation of physiological and treatment information into event logs and subsequently process models; the expression of the BTF guidelines in process models within the real-time context of the ICU; a calculation of distance between the two processes using two algorithms (“Direct” and “Weighted”) building on work conducted in th e business process domain. Results are presented across two categories each with clinical utility (minute-by-minute and single patient stays) using a real ICU data-set. Results of two sample patients using a weighted algorithm show a non-adherence level of 6.25% for 42 mins and 56.25% for 708 mins and non-adherence of 18.75% for 17 minutes and 56.25% for 483 minutes. Expressed as two combinatorial metrics (duration/non-adherence (A) and duration * non-adherence (B)), which together indicate the clinical importance of the non-adherence, one has a mean of A=4.63 and B=10014.16 and the other a mean of A=0.43 and B=500.0.

• Item Type: Conference Proceedings
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Stell, Mr Anthony and Piper, Dr Ian and Moss, Dr Laura
• Authors: Stell, A., Piper, I., and Moss, L.
• College/School: College of Medical Veterinary and Life Sciences > School of Medicine, Dentistry & Nursing
• Publisher: SCITEPRESS - Science and Technology Publications
• ISBN: 9789897582813
• Copyright Holders: Copyright © 2018 SCITEPRESS – Science and Technology Publications, Lda.
• First Published: First published in Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies: 135-146
• Publisher Policy: Reproduced in accordance with the copyright policy of the publisher