Retrospective Analysis of Prognostic Factors of Severe Traumatic Brain Injury in a University Hospital in Turkey

Özyurt, Erhan; Göksu, Erkan; Cengiz, Melike; Yılmaz, Murat; Ramazanoğlu, Atilla

doi:10.5137/1019-5149.jtn.9181-13.0

Cited by 7 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various efforts have been made to predict the prognosis of TBI patients, exploring factors such as Glasgow Coma Scale (GCS), age, pupillary reactivity, injury severity, and clinical condition (e.g., hypoxia, respiratory distress, and hypotension) in numerous studies. The evaluation of brain injury extent and classification using CT scans is also closely linked to mortality [ 5 , 6 , 7 , 8 ].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Algorithm Predicts Mortality Risk in Intensive Care Unit for Patients with Traumatic Brain Injury

Tu,

Tau,

Chen

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Background: Numerous mortality prediction tools are currently available to assist patients with moderate to severe traumatic brain injury (TBI). However, an algorithm that utilizes various machine learning methods and employs diverse combinations of features to identify the most suitable predicting outcomes of brain injury patients in the intensive care unit (ICU) has not yet been well-established. Method: Between January 2016 and December 2021, we retrospectively collected data from the electronic medical records of Chi Mei Medical Center, comprising 2260 TBI patients admitted to the ICU. A total of 42 features were incorporated into the analysis using four different machine learning models, which were then segmented into various feature combinations. The predictive performance was assessed using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve and validated using the Delong test. Result: The AUC for each model under different feature combinations ranged from 0.877 (logistic regression with 14 features) to 0.921 (random forest with 22 features). The Delong test indicated that the predictive performance of the machine learning models is better than that of traditional tools such as APACHE II and SOFA scores. Conclusion: Our machine learning training demonstrated that the predictive accuracy of the LightGBM is better than that of APACHE II and SOFA scores. These features are readily available on the first day of patient admission to the ICU. By integrating this model into the clinical platform, we can offer clinicians an immediate prognosis for the patient, thereby establishing a bridge for educating and communicating with family members.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine Learning Algorithm Predicts Mortality Risk in Intensive Care Unit for Patients with Traumatic Brain Injury

Tu,

Tau,

Chen

et al. 2023

Diagnostics

View full text Add to dashboard Cite

show abstract

Current Status and Outcomes of Critical Traumatic Brain Injury (GCS = 3–5) in a Developing Country: A Retrospective, Registry‐Based Study

et al. 2022

View full text Add to dashboard Cite

Background Patients sustaining critical TBI [initial Glasgow Coma Scale (GCS) B 5] generally have poor outcomes. Little is known about the frequency, mortality rate, and functional outcomes of such patients in Iran. Methods In this retrospective, registry-based cohort study, the demographic and clinicoradiological findings of TBI patients were queried from March 21, 2017, to March 21, 2020. We included TBI patients with initial GCS of 3-5. The functional outcome was assessed using the Glasgow Outcome Score-extended 6 (GOSE-6) months after the hospital discharge. Patients were classified as having unfavorable (GOSE-6 B 4) and favorable (GOSE-6 [ 4) outcomes. Gathered data were compared between groups. Multivariable logistic regression analysis was done to find factors affecting the outcome. Results Four hundred ninety-seven patients (mean age = 37.59 ± 17.89) were enrolled, and 69.2% had unfavorable outcomes. Elderly patients (age C 65 years) were highly overrepresented among the unfavorable group. 48.9% had bilateral fixed dilated pupils (BDFP), who mostly attained unfavorable outcomes. The overall in-hospital mortality rate was 50.3%. The in-hospital mortality rate was appalling among elderly patients with BFDP and GCS 3( 90%) and GCS 4(100%). Age C 65 years [odds ratio (OR) 3.45, 95% confidence interval (CI) 1.19-10.04], and BFDP (OR 4.48,) increase the odds of unfavorable outcomes according to the regression analysis. ConclusionThe survival rate and favorable outcomes of critical TBI patients are generally poor. However, we believe that the neurotrauma surgeons should discuss with patients' proxies and explain the clinical conditions and possible outcomes.

show abstract

Clinical study on acute craniocerebral injury treated with mild hypothermia auxiliary therapy

Zhang

Dou

et al. 2016

Journal of Acute Disease

View full text Add to dashboard Cite

Retrospective Analysis of Prognostic Factors of Severe Traumatic Brain Injury in a University Hospital in Turkey

Abstract: AIm: To examine the use of prognostic factors such as age, Glasgow Coma Scale (GCS) score, pupil reactivity and computerized tomography (CT) findings for predicting the prognosis of severe traumatic brain injury (TBI) patients in Turkey.

Cited by 7 publications

References 17 publications

Machine Learning Algorithm Predicts Mortality Risk in Intensive Care Unit for Patients with Traumatic Brain Injury

Machine Learning Algorithm Predicts Mortality Risk in Intensive Care Unit for Patients with Traumatic Brain Injury

Current Status and Outcomes of Critical Traumatic Brain Injury (GCS = 3–5) in a Developing Country: A Retrospective, Registry‐Based Study

Clinical study on acute craniocerebral injury treated with mild hypothermia auxiliary therapy

Contact Info

Product

Resources

About