A machine learning based approach for identifying traumatic brain injury patients for whom a head CT scan can be avoided

Somayeh Molaei; Frederick K. Korley; S. M.Reza Soroushmehr; Hayley Falk; Haris Sair; Kevin Ward; Kayvan Najarian

doi:10.1109/EMBC.2016.7591179

A machine learning based approach for identifying traumatic brain injury patients for whom a head CT scan can be avoided

Somayeh Molaei, Frederick K. Korley, S. M.Reza Soroushmehr, Hayley Falk, Haris Sair, Kevin Ward, Kayvan Najarian

School of Medicine

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

6 Scopus citations

Abstract

Head CT scan is more often used to evaluate patients with suspected traumatic brain injury (TBI). However, the use of head CT scans in evaluating TBI is costly with low value endeavor. In this paper, we propose a new algorithm and a set of features to help clinicians determine which patients evaluated for TBI need a head CT scan using cost sensitive random forest (CSRF) classifier. We show that random forest (RF) and CSRF are useful methods for identifying patients likely to have a positive head CT scan. The proposed algorithm has superior diagnostic accuracy in comparison to the Canadian head CT algorithm, which is currently the most accurate and widely used algorithm for determining which TBI patients need a head CT scan. In the highest sensitivity (i.e. 100%), our method outperforms the Canadian rule in terms of specificity, accuracy and area under ROC curve using cost sensitive classifier. Clinical implementation of this algorithm can help decrease financial costs associated with Emergency Department evaluations for traumatic brain injury, while decreasing patient exposure to avoidable ionizing radiation.

Original language	English (US)
Title of host publication	2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2258-2261
Number of pages	4
ISBN (Electronic)	9781457702204
DOIs	https://doi.org/10.1109/EMBC.2016.7591179
State	Published - Oct 13 2016
Event	38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016 - Orlando, United States Duration: Aug 16 2016 → Aug 20 2016

Publication series

Name	Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Volume	2016-October
ISSN (Print)	1557-170X

Other

Other	38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
Country/Territory	United States
City	Orlando
Period	8/16/16 → 8/20/16

Keywords

Canadian head CT rule
Classification
Head CT scan
Random forest
Traumatic brain injury

ASJC Scopus subject areas

Signal Processing
Biomedical Engineering
Computer Vision and Pattern Recognition
Health Informatics

Access to Document

10.1109/EMBC.2016.7591179

Cite this

Molaei, S., Korley, F. K., Soroushmehr, S. M. R., Falk, H., Sair, H., Ward, K., & Najarian, K. (2016). A machine learning based approach for identifying traumatic brain injury patients for whom a head CT scan can be avoided. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016 (pp. 2258-2261). Article 7591179 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS; Vol. 2016-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2016.7591179

A machine learning based approach for identifying traumatic brain injury patients for whom a head CT scan can be avoided. / Molaei, Somayeh; Korley, Frederick K.; Soroushmehr, S. M.Reza et al.
2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 2258-2261 7591179 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS; Vol. 2016-October).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Molaei, S, Korley, FK, Soroushmehr, SMR, Falk, H, Sair, H, Ward, K & Najarian, K 2016, A machine learning based approach for identifying traumatic brain injury patients for whom a head CT scan can be avoided. in 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016., 7591179, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, vol. 2016-October, Institute of Electrical and Electronics Engineers Inc., pp. 2258-2261, 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016, Orlando, United States, 8/16/16. https://doi.org/10.1109/EMBC.2016.7591179

Molaei S, Korley FK, Soroushmehr SMR, Falk H, Sair H, Ward K et al. A machine learning based approach for identifying traumatic brain injury patients for whom a head CT scan can be avoided. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 2258-2261. 7591179. (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). doi: 10.1109/EMBC.2016.7591179

Molaei, Somayeh ; Korley, Frederick K. ; Soroushmehr, S. M.Reza et al. / A machine learning based approach for identifying traumatic brain injury patients for whom a head CT scan can be avoided. 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 2258-2261 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).

@inproceedings{06c9908f00074764864a575f44c554cf,

title = "A machine learning based approach for identifying traumatic brain injury patients for whom a head CT scan can be avoided",

abstract = "Head CT scan is more often used to evaluate patients with suspected traumatic brain injury (TBI). However, the use of head CT scans in evaluating TBI is costly with low value endeavor. In this paper, we propose a new algorithm and a set of features to help clinicians determine which patients evaluated for TBI need a head CT scan using cost sensitive random forest (CSRF) classifier. We show that random forest (RF) and CSRF are useful methods for identifying patients likely to have a positive head CT scan. The proposed algorithm has superior diagnostic accuracy in comparison to the Canadian head CT algorithm, which is currently the most accurate and widely used algorithm for determining which TBI patients need a head CT scan. In the highest sensitivity (i.e. 100%), our method outperforms the Canadian rule in terms of specificity, accuracy and area under ROC curve using cost sensitive classifier. Clinical implementation of this algorithm can help decrease financial costs associated with Emergency Department evaluations for traumatic brain injury, while decreasing patient exposure to avoidable ionizing radiation.",

keywords = "Canadian head CT rule, Classification, Head CT scan, Random forest, Traumatic brain injury",

author = "Somayeh Molaei and Korley, {Frederick K.} and Soroushmehr, {S. M.Reza} and Hayley Falk and Haris Sair and Kevin Ward and Kayvan Najarian",

year = "2016",

month = oct,

day = "13",

doi = "10.1109/EMBC.2016.7591179",

language = "English (US)",

series = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2258--2261",

booktitle = "2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016",

note = "38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016 ; Conference date: 16-08-2016 Through 20-08-2016",

}

TY - GEN

T1 - A machine learning based approach for identifying traumatic brain injury patients for whom a head CT scan can be avoided

AU - Molaei, Somayeh

AU - Korley, Frederick K.

AU - Soroushmehr, S. M.Reza

AU - Falk, Hayley

AU - Sair, Haris

AU - Ward, Kevin

AU - Najarian, Kayvan

PY - 2016/10/13

Y1 - 2016/10/13

N2 - Head CT scan is more often used to evaluate patients with suspected traumatic brain injury (TBI). However, the use of head CT scans in evaluating TBI is costly with low value endeavor. In this paper, we propose a new algorithm and a set of features to help clinicians determine which patients evaluated for TBI need a head CT scan using cost sensitive random forest (CSRF) classifier. We show that random forest (RF) and CSRF are useful methods for identifying patients likely to have a positive head CT scan. The proposed algorithm has superior diagnostic accuracy in comparison to the Canadian head CT algorithm, which is currently the most accurate and widely used algorithm for determining which TBI patients need a head CT scan. In the highest sensitivity (i.e. 100%), our method outperforms the Canadian rule in terms of specificity, accuracy and area under ROC curve using cost sensitive classifier. Clinical implementation of this algorithm can help decrease financial costs associated with Emergency Department evaluations for traumatic brain injury, while decreasing patient exposure to avoidable ionizing radiation.

AB - Head CT scan is more often used to evaluate patients with suspected traumatic brain injury (TBI). However, the use of head CT scans in evaluating TBI is costly with low value endeavor. In this paper, we propose a new algorithm and a set of features to help clinicians determine which patients evaluated for TBI need a head CT scan using cost sensitive random forest (CSRF) classifier. We show that random forest (RF) and CSRF are useful methods for identifying patients likely to have a positive head CT scan. The proposed algorithm has superior diagnostic accuracy in comparison to the Canadian head CT algorithm, which is currently the most accurate and widely used algorithm for determining which TBI patients need a head CT scan. In the highest sensitivity (i.e. 100%), our method outperforms the Canadian rule in terms of specificity, accuracy and area under ROC curve using cost sensitive classifier. Clinical implementation of this algorithm can help decrease financial costs associated with Emergency Department evaluations for traumatic brain injury, while decreasing patient exposure to avoidable ionizing radiation.

KW - Canadian head CT rule

KW - Classification

KW - Head CT scan

KW - Random forest

KW - Traumatic brain injury

UR - http://www.scopus.com/inward/record.url?scp=85009084329&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009084329&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2016.7591179

DO - 10.1109/EMBC.2016.7591179

M3 - Conference contribution

C2 - 28268778

AN - SCOPUS:85009084329

T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

SP - 2258

EP - 2261

BT - 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016

Y2 - 16 August 2016 through 20 August 2016

ER -

A machine learning based approach for identifying traumatic brain injury patients for whom a head CT scan can be avoided

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this