Decision tree analysis to predict the risk of intracranial haemorrhage after mild traumatic brain injury in patients taking DOACs

Turcato, Gianni; Zaboli, Arian; Pfeifer, Norbert; Antonio, Miguel; Tenci, Andrea; Giudiceandrea, Alberto; Zannoni, M; Ricci, Giorgio; Bonora, Antonio; Brigo, Francesco

doi:10.1016/j.ajem.2021.08.048

Cited by 15 publications

(15 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it is notable that, although prior studies and metaanalyses demonstrated an association between traumatic ICH and anticoagulation or antiplatelet agents in patients with head trauma, [16][17][18][19] some recent studies did not demonstrate such an association. [20][21][22][23][24] In a retrospective cohort analysis of 2567 patients, Lampart et al did not find a significant relationship between traumatic ICH and any anticoagulant/antiplatelet agents, although combination therapy was associated with an increase in hospital mortality. 25 Similarly, Uccella et al found that patients taking OAT with GCS 15 after blunt head trauma did not have a higher risk for intracranial hemorrhage than the general population.…”

Section: Resultsmentioning

confidence: 99%

“…In the next future, the management of these patients could be based on clinical and trauma-related risk factors rather than anticoagulation therapy alone as proposed in some recent trials. 22,29,30…”

Section: Resultsmentioning

confidence: 99%

“…These data do not support routinely obtaining a repeat CT head after a negative initial CT scan since the risk of complications in asymptomatic anticoagulated head trauma patient is negligible when an initial CT scan is negative. In a recent study by Turcato et al, 22 patients without risk factors for bleeding were free from bad outcomes linked to trauma. However, the decision if and when to schedule the control imaging may be influenced by…”

Section: Should the Head Ct Scan Be Repeated?mentioning

confidence: 91%

“…In a recent trial, Turcato et al 22 proposed to collect these predictors in a "decision tree analyses" in which data mining techniques allow the visualization of relationships between many variables by defining explicit rules for their classification and their influence on the dependent variable. Despite this study having a retrospective observational design requiring to be confirmed in prospective trials, the hypothesis that the introduction of these techniques into clinical practice would reduce the number of CT scans for anticoagulated patients with mTBI is intriguing.…”

Section: Which Are Possible Predictors Of Ich After Mtbi?mentioning

confidence: 99%

See 3 more Smart Citations

The state of the art of the management of anticoagulated patients with mild traumatic brain injury in the Emergency Department

et al. 2022

Self Cite

View full text Add to dashboard Cite

The effects of Oral Anticoagulation Therapy (OAT) in older patients who suffered a mild Traumatic Brain Injury (mTBI) are widely debated but still strong guidelines are lacking and clinical approaches and management are sometimes heterogeneous. Different predictors of adverse outcomes were identified in the literature but their use in the decision-making process is unclear. Moreover, there is no consensus on the appropriate length of stay in the Observation Unit nor on the continuation of OAT, even if the diagnosis of life-threatening delayed post-traumatic Intracranial Hemorrhage is rare. The recurrence of a control CT scan is often needless. This review aims to summarize recent scientific literature focusing on patients with mTBI taking OAT and to identify crucial questions on the topic to suggest a best clinical practice.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Should the Head Ct Scan Be Repeated?mentioning

confidence: 91%

Section: Which Are Possible Predictors Of Ich After Mtbi?mentioning

confidence: 99%

See 2 more Smart Citations

The state of the art of the management of anticoagulated patients with mild traumatic brain injury in the Emergency Department

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Decision tree analyses are an innovative data mining technique that defines explicit rules for the classification of variables and their influence on the dependent variable 9,10,18 . A decision tree divides the sample of observations into different hierarchical levels according to the statistical significance of the variables and, through precise splitting rules, obtains homogeneous subgroups with precise risk estimates 9,10,18 . These analyses produce a hierarchical diagram that can be interpreted easily and that clarifies the relationships between predictors, and between predictors and the outcome of interest 9,10,18 .…”

Section: Methodsmentioning

confidence: 99%

Machine learning validation through decision tree analysis of the Epidemiology‐Based Mortality Score in Status Epilepticus

et al. 2022

Self Cite

View full text Add to dashboard Cite

Objective: This study was undertaken to validate the accuracy of the Epidemiology-Based Mortality Score in Status Epilepticus (EMSE) in predicting the risk of death at 30 days in a large cohort of patients with status epilepticus (SE) using a machine learning system. Methods:We included consecutive patients with SE admitted from 2013 to 2021 at Modena Academic Hospital. A decision tree analysis was performed using the 30-day mortality as a dependent variable and the EMSE predictors as input variables. We evaluated the accuracy of EMSE in predicting 30-day mortality using the area under the receiver operating characteristic curve (AUC ROC), with 95% confidence interval (CI). We performed a subgroup analysis on nonhypoxic SE.Results: A total of 698 patients with SE were included, with a 30-day mortality of 28.9% (202/698). The mean EMSE value in the entire population was 57.1 (SD = 36.3); it was lower in surviving compared to deceased patients (47.1, SD = 31.7 vs. 81.9, SD = 34.8; p < .001). The EMSE was accurate in predicting 30-day mortality, with an AUC ROC of .782 (95% CI = .747-.816). Etiology was the most relevant predictor, followed by age, electroencephalogram (EEG), and EMSE comorbidity group B. The decision tree analysis using EMSE variables correctly predicted the risk of mortality in 77.9% of cases; the prediction was accurate in 85.7% of surviving and in 58.9% of deceased patients within 30 days after SE. In nonhypoxic SE, the most relevant predictor was age, followed by EEG, and EMSE comorbidity group B; the prediction was correct in 78.9% of all cases (89.6% in survivors and 46.1% in nonsurvivors).Significance: This validation study using a machine learning analysis shows that the EMSE is a valuable prognostic tool, and appears particularly accurate and effective in identifying patients with 30-day survival, whereas its performance in predicting 30-day mortality is lower and needs to be further improved.

show abstract

Using distributed root soil moisture data to enhance the performance of rainfall thresholds for landslide warning

Guo

Zhu

et al. 2022

Nat Hazards

View full text Add to dashboard Cite

Decision tree analysis to predict the risk of intracranial haemorrhage after mild traumatic brain injury in patients taking DOACs

Cited by 15 publications

References 19 publications

The state of the art of the management of anticoagulated patients with mild traumatic brain injury in the Emergency Department

The state of the art of the management of anticoagulated patients with mild traumatic brain injury in the Emergency Department

Machine learning validation through decision tree analysis of the Epidemiology‐Based Mortality Score in Status Epilepticus

Using distributed root soil moisture data to enhance the performance of rainfall thresholds for landslide warning

Contact Info

Product

Resources

About