Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Aug 1;22(1):203.
doi: 10.1186/s12911-022-01953-z.

An interpretable neural network for outcome prediction in traumatic brain injury

Cristian Minoccheri  1 , Craig A Williamson  2   3 , Mark Hemmila  3   4 , Kevin Ward  3   5 , Erica B Stein  6 , Jonathan Gryak  7   3   8 , Kayvan Najarian  7   3   8   5   9
Affiliations

An interpretable neural network for outcome prediction in traumatic brain injury

Cristian Minoccheri et al. BMC Med Inform Decis Mak. .

Abstract

Background: Traumatic Brain Injury (TBI) is a common condition with potentially severe long-term complications, the prediction of which remains challenging. Machine learning (ML) methods have been used previously to help physicians predict long-term outcomes of TBI so that appropriate treatment plans can be adopted. However, many ML techniques are "black box": it is difficult for humans to understand the decisions made by the model, with post-hoc explanations only identifying isolated relevant factors rather than combinations of factors. Moreover, such models often rely on many variables, some of which might not be available at the time of hospitalization.

Methods: In this study, we apply an interpretable neural network model based on tropical geometry to predict unfavorable outcomes at six months from hospitalization in TBI patients, based on information available at the time of admission.

Results: The proposed method is compared to established machine learning methods-XGBoost, Random Forest, and SVM-achieving comparable performance in terms of area under the receiver operating characteristic curve (AUC)-0.799 for the proposed method vs. 0.810 for the best black box model. Moreover, the proposed method allows for the extraction of simple, human-understandable rules that explain the model's predictions and can be used as general guidelines by clinicians to inform treatment decisions.

Conclusions: The classification results for the proposed model are comparable with those of traditional ML methods. However, our model is interpretable, and it allows the extraction of intelligible rules. These rules can be used to determine relevant factors in assessing TBI outcomes and can be used in situations when not all necessary factors are known to inform the full model's decision.

Keywords: Clinical decision support systems; Interpretable machine learning; Neural networks; Outcome prediction; Traumatic brain injury.

PubMed Disclaimer

Conflict of interest statement

Jonathan Gryak and Kayvan Najarian are named inventors on a patent application related to the tropical geometry-based fuzzy neural network used in this work. All other authors declare no conflict of interest.

Figures

Fig. 1
Fig. 1
A schematic of the tropical geometry-based neural network introduced in [27]
Fig. 2
Fig. 2
Membership functions for the concepts of low, medium, and high of the variable “third ventricle compression—rad.”, extracted from the model trained on SHAP features with ℓ0-sparsity
Fig. 3
Fig. 3
Rules extracted from MRMR features without a sparsity term
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Abujaber A, et al. Prediction of in-hospital mortality in patients with post traumatic brain injury using National Trauma Registry and Machine Learning Approach. Scand J Trauma Resusc Emerg Med. 2020;28:44. doi: 10.1186/s13049-020-00738-5. - DOI - PMC - PubMed
    1. Amorim RL, et al. Prediction of early TBI mortality using a machine learning approach in a LMIC population. Front Neurol. 2020;10:1366. doi: 10.3389/fneur.2019.01366. - DOI - PMC - PubMed
    1. Bangirana P, Giordani B, Kobusingye O, et al. Patterns of traumatic brain injury and six-month neuropsychological outcomes in Uganda. BMC Neurol. 2019;19:18. doi: 10.1186/s12883-019-1246-1. - DOI - PMC - PubMed
    1. Becker K, et al. Withdrawal of support in intracerebral hemorrhage may lead to self-fulfilling prophecies. Neurology. 2001;56:766–772. doi: 10.1212/WNL.56.6.766. - DOI - PubMed
    1. Farzaneh N, Williamson CA, Gryak J, Najarian K. A hierarchical expert-guided machine learning framework for clinical decision support systems: an application to traumatic brain injury prognostication. npj Digit. Med. 2021;4:78. - PMC - PubMed

Publication types