@article{10902/29988,
year = {2023},
url = {https://hdl.handle.net/10902/29988},
abstract = {Background and Purpose
Intracranial hemorrhage (ICH) is a common life-threatening condition that must be rapidly diagnosed and treated. However, there is still a lack of consensus regarding treatment, driven to some extent by prognostic uncertainty. While several prediction models for ICH detection have already been published, here we present a deep learning predictive model for ICH prognosis.

Methods
We included patients with ICH (n = 262), and we trained a custom model for the classification of patients into poor prognosis and good prognosis, using a hybrid input consisting of brain CT images and other clinical variables. We compared it with two other models, one trained with images only (I-model) and the other with tabular data only (D-model).

Results
Our hybrid model achieved an area under the receiver operating characteristic curve (AUC) of .924 (95% confidence interval [CI]: .831-.986), and an accuracy of .861 (95% CI: .760-.960). The I- and D-models achieved an AUC of .763 (95% CI: .622-.902) and .746 (95% CI: .598-.876), respectively.

Conclusions
The proposed hybrid model was able to accurately classify patients into good and poor prognosis. To the best of our knowledge, this is the first ICH prognosis prediction deep learning model. We concluded that deep learning can be applied for prognosis prediction in ICH that could have a great impact on clinical decision-making. Further, hybrid inputs could be a promising technique for deep learning in medical imaging.},
organization = {Acknowledgments and disclosures: We would like to acknowledge the coding department for their help in the construction of the database, Mario Pérez Arnedo for his assistance in the development of figures, and Andrew Robson (University of Edinburgh) for reviewing language usage. The authors declare no conflict of interest},
publisher = {Wiley},
publisher = {Journal of Neuroimaging, 2023, 33, 218-226},
title = {A deep learning model for prognosis prediction after intracranial hemorrhage},
author = {Pérez del Barrio, Amaia and Esteve Domínguez, Anna Salut and Menéndez Fernández-Miranda, Pablo and Sanz Bellón, Pablo and Rodríguez González, David and Lloret Iglesias, Lara and Marqués Fraguela, Enrique and González Mandly, Andrés Antonio and Vega, José A.},
}