"Decision tree analysis for assessing the risk of post-traumatic haemorrhage after mild traumatic brain injury in patients on oral anticoagulant therapy".
Anticoagulation
Decision tree
Emergency department
Machine learning
Mild traumatic brain injury
Minor head injury
Minor head trauma
Oral anticoagulants
Risk factors
Trauma
Journal
BMC emergency medicine
ISSN: 1471-227X
Titre abrégé: BMC Emerg Med
Pays: England
ID NLM: 100968543
Informations de publication
Date de publication:
24 03 2022
24 03 2022
Historique:
received:
04
11
2021
accepted:
14
03
2022
entrez:
25
3
2022
pubmed:
26
3
2022
medline:
3
5
2022
Statut:
epublish
Résumé
The presence of oral anticoagulant therapy (OAT) alone, regardless of patient condition, is an indication for CT imaging in patients with mild traumatic brain injury (MTBI). Currently, no specific clinical decision rules are available for OAT patients. The aim of the study was to identify which clinical risk factors easily identifiable at first ED evaluation may be associated with an increased risk of post-traumatic intracranial haemorrhage (ICH) in OAT patients who suffered an MTBI. Three thousand fifty-four patients in OAT with MTBI from four Italian centers were retrospectively considered. A decision tree analysis using the classification and regression tree (CART) method was conducted to evaluate both the pre- and post-traumatic clinical risk factors most associated with the presence of post-traumatic ICH after MTBI and their possible role in determining the patient's risk. The decision tree analysis used all clinical risk factors identified at the first ED evaluation as input predictor variables. ICH following MTBI was present in 9.5% of patients (290/3054). The CART model created a decision tree using 5 risk factors, post-traumatic amnesia, post-traumatic transitory loss of consciousness, greater trauma dynamic, GCS less than 15, evidence of trauma above the clavicles, capable of stratifying patients into different increasing levels of ICH risk (from 2.5 to 61.4%). The absence of concussion and neurological alteration at admission appears to significantly reduce the possible presence of ICH. The machine-learning-based CART model identified distinct prognostic groups of patients with distinct outcomes according to on clinical risk factors. Decision trees can be useful as guidance in patient selection and risk stratification of patients in OAT with MTBI.
Sections du résumé
BACKGROUND
The presence of oral anticoagulant therapy (OAT) alone, regardless of patient condition, is an indication for CT imaging in patients with mild traumatic brain injury (MTBI). Currently, no specific clinical decision rules are available for OAT patients. The aim of the study was to identify which clinical risk factors easily identifiable at first ED evaluation may be associated with an increased risk of post-traumatic intracranial haemorrhage (ICH) in OAT patients who suffered an MTBI.
METHODS
Three thousand fifty-four patients in OAT with MTBI from four Italian centers were retrospectively considered. A decision tree analysis using the classification and regression tree (CART) method was conducted to evaluate both the pre- and post-traumatic clinical risk factors most associated with the presence of post-traumatic ICH after MTBI and their possible role in determining the patient's risk. The decision tree analysis used all clinical risk factors identified at the first ED evaluation as input predictor variables.
RESULTS
ICH following MTBI was present in 9.5% of patients (290/3054). The CART model created a decision tree using 5 risk factors, post-traumatic amnesia, post-traumatic transitory loss of consciousness, greater trauma dynamic, GCS less than 15, evidence of trauma above the clavicles, capable of stratifying patients into different increasing levels of ICH risk (from 2.5 to 61.4%). The absence of concussion and neurological alteration at admission appears to significantly reduce the possible presence of ICH.
CONCLUSIONS
The machine-learning-based CART model identified distinct prognostic groups of patients with distinct outcomes according to on clinical risk factors. Decision trees can be useful as guidance in patient selection and risk stratification of patients in OAT with MTBI.
Identifiants
pubmed: 35331163
doi: 10.1186/s12873-022-00610-y
pii: 10.1186/s12873-022-00610-y
pmc: PMC8944105
doi:
Substances chimiques
Anticoagulants
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
47Informations de copyright
© 2022. The Author(s).
Références
Trauma Surg Acute Care Open. 2020 Apr 19;5(1):e000453
pubmed: 32377569
JAMA. 2005 Sep 28;294(12):1511-8
pubmed: 16189364
Surgery. 2019 Dec;166(6):983-990
pubmed: 31326191
J Trauma Acute Care Surg. 2012 Jul;73(1):126-30
pubmed: 22710784
Intern Emerg Med. 2018 Oct;13(7):1077-1087
pubmed: 29520701
Brain Inj. 2020 May 11;34(6):834-839
pubmed: 32286890
Ann Emerg Med. 2019 Jan;73(1):66-75
pubmed: 30236417
Adv Emerg Nurs J. 2017 Oct/Dec;39(4):300-308
pubmed: 29095182
Emerg Med J. 2020 Nov;37(11):666-673
pubmed: 32900858
Crit Care. 2019 Feb 22;23(1):62
pubmed: 30795779
Am J Emerg Med. 2021 May;43:180-185
pubmed: 32122712
J Head Trauma Rehabil. 2020 Sep/Oct;35(5):E441-E449
pubmed: 32472829
Am J Emerg Med. 2021 Dec;50:388-393
pubmed: 34478944
J Trauma Acute Care Surg. 2020 Jan;88(1):186-194
pubmed: 31688828
J Neurotrauma. 2001 Jul;18(7):657-64
pubmed: 11497092
Jt Comm J Qual Patient Saf. 2012 Nov;38(11):483-9
pubmed: 23173394
Am J Emerg Med. 2019 Sep;37(9):1677-1680
pubmed: 30573225
Eur J Neurol. 2012 Feb;19(2):191-8
pubmed: 22260187
Am J Emerg Med. 2017 Sep;35(9):1317-1319
pubmed: 28400068
J Emerg Med. 2019 Dec;57(6):817-824
pubmed: 31648805
Thromb Res. 2019 Feb;174:113-120
pubmed: 30593997
Intern Emerg Med. 2021 Jun;16(4):1061-1070
pubmed: 33386604
Haemophilia. 2015 Nov;21(6):715-22
pubmed: 26248714
World Neurosurg. 2016 Sep;93:100-3
pubmed: 27245564
JAMA. 2015 Dec 22-29;314(24):2672-81
pubmed: 26717031