PREDICT-TBI: Comparison of Physician Predictions with the IMPACT Model to Predict 6-Month Functional Outcome in Traumatic Brain Injury

Amzallag, Juliette; Ropers, Jacques; Shotar, Eimad; Mathon, Bertrand; Jacquens, Alice; Degos, Vincent; Bernard, R

doi:10.1007/s12028-023-01718-0

Cited by 4 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, even with such small numbers, the prognostic classification errors of AI are already detectable. Furthermore, our cohort is similar in terms of size and outcomes to other recent cohorts addressing the question of 6-month outcomes in moderate to severe TBI patients (16). Also supporting the external validity of our results, the IMPACT model shows similar prognostic abilities in our population as in other cohorts (17,18).…”

Section: Discussionsupporting

confidence: 87%

Evaluation of ChatGPT in Predicting 6-Month Outcomes After Traumatic Brain Injury

Gakuba,

Le Barbey,

Sar

et al. 2024

Critical Care Medicine

View full text Add to dashboard Cite

Objectives: To evaluate the capacity of ChatGPT, a widely accessible and uniquely popular artificial intelligence-based chatbot, in predicting the 6-month outcome following moderate-to-severe traumatic brain injury (TBI). Design: Single-center observational retrospective study. Setting: Data are from a neuro-ICU from a level 1 trauma center. Patients: All TBI patients admitted to ICU between September 2021 and October 2022 were included in a prospective database. Interventions: None. Measurements and Main Results: Based on anonymized clinical, imaging, and biological information available at the patients’ hospital admission and extracted from the database, clinical vignettes were retrospectively submitted to ChatGPT for prediction of patients’ outcomes. The predictions of two intensivists (one neurointensivist and one non-neurointensivist) both from another level 1 trauma center (Beaujon Hospital), were also collected as was the International Mission on Prognosis and Analysis of Clinical Trials in Traumatic Brain Injury (IMPACT) scoring. Each intensivist, as well as ChatGPT, made their prognostic evaluations independently, without knowledge of the others’ predictions and of the patients’ actual management and outcome. Both the intensivists and ChatGPT were given access to the exact same set of information. The main outcome was a 6-month-functional status dichotomized into favorable (Glasgow Outcome Scale Extended [GOSE] ≥ 5) versus poor (GOSE < 5). Prediction of intracranial hypertension management, pulmonary infectious risk, and removal of life-sustaining therapies was also investigated as secondary outcomes. Eighty consecutive moderate-to-severe TBI patients were included. For the 6-month outcome prognosis, area under the receiver operating characteristic curve (AUC-ROC) for ChatGPT, the neurointensivist, the non-neurointensivist, and IMPACT were, respectively, 0.62 (0.50–0.74), 0.70 (0.59–0.82), 0.71 (0.59–0.82), and 0.81 (0.72–0.91). ChatGPT had the highest sensitivity (100%), but the lowest specificity (26%). For secondary outcomes, ChatGPT’s prognoses were generally less accurate than clinicians’ prognoses, with lower AUC values for most outcomes. Conclusions: This study does not support the use of ChatGPT for prediction of outcomes after TBI.

show abstract

Section: Discussionsupporting

confidence: 87%

Evaluation of ChatGPT in Predicting 6-Month Outcomes After Traumatic Brain Injury

Gakuba,

Le Barbey,

Sar

et al. 2024

Critical Care Medicine

View full text Add to dashboard Cite

show abstract

“…In context, the performance of the IMPACT prognostic model was consistent with prior reports (2, 3), while the performance of critical care physicians was slightly reduced compared with recent studies but still compatible (4). Both humans and predictive models performed within expected ranges, suggesting that the underperformance of ChatGPT cannot be attributed to an unusual patient mix.…”

supporting

confidence: 84%

ChatGPT and Neuroprognostication: A Snow Globe, Not a Crystal Ball*

Azamfirei

2024

Critical Care Medicine

View full text Add to dashboard Cite

“…Traumatic brain injury (TBI) is a significant problem in society that can cause death and long-term disabilities [1,2]. Cycling is a major cause of sports-related TBI both in adults and children, representing nearly 20% of all sports-related brain injuries treated in emergency departments [3,4].…”

Section: Introductionmentioning

confidence: 99%

An Air-Filled Bicycle Helmet for Mitigating Traumatic Brain Injury

Mathon,

Duarte Rocha,

et al. 2023

Bioengineering

Self Cite

View full text Add to dashboard Cite

We created a novel air-filled bicycle helmet. The aims of this study were (i) to assess the head injury mitigation performance of the proposed helmet and (ii) to compare those performance results against the performance results of an expanded polystyrene (EPS) traditional bicycle helmet. Two bicycle helmet types were subjected to impacts in guided vertical drop tests onto a flat anvil: EPS helmets and air-filled helmets (Bumpair). The maximum acceleration value recorded during the test on the Bumpair helmet was 86.76 ± 3.06 g, while the acceleration during the first shock on the traditional helmets reached 207.85 ± 5.55 g (p < 0.001). For the traditional helmets, the acceleration increased steadily over the number of shocks. There was a strong correlation between the number of impacts and the response of the traditional helmet (cor = 0.94; p < 0.001), while the Bumpair helmets showed a less significant dependence over time (cor = 0.36; p = 0.048), meaning previous impacts had a lower consequence. The air-filled helmet significantly reduced the maximal linear acceleration when compared to an EPS traditional helmet, showing improvements in impact energy mitigation, as well as in resistance to repeated impacts. This novel helmet concept could improve head injury mitigation in cyclists.

show abstract

PREDICT-TBI: Comparison of Physician Predictions with the IMPACT Model to Predict 6-Month Functional Outcome in Traumatic Brain Injury

Cited by 4 publications

References 20 publications

Evaluation of ChatGPT in Predicting 6-Month Outcomes After Traumatic Brain Injury

Evaluation of ChatGPT in Predicting 6-Month Outcomes After Traumatic Brain Injury

ChatGPT and Neuroprognostication: A Snow Globe, Not a Crystal Ball*

An Air-Filled Bicycle Helmet for Mitigating Traumatic Brain Injury

Contact Info

Product

Resources

About