Universidade Federal do Ceará
Mestrado e Doutorado em Ciências da Computação

Título: Enhanced Post-Cardiac Arrest Prognostic Assessment: A Multi-Modal Approach Integrating Deep Learning and Clinical EEG Pattern Analysis

Data: 25/11/2024
Horário: 12h00
Local: Sala de Seminários – Bloco 952

Resumo:

According to DATASUS, approximately 13,000 cardiac arrests occurred in Brazil between 2020 and 2023 (ICD-10: I46). The electroencephalogram (EEG) has proven valuable in post-cardiac arrest prognosis, aiding in the assessment of neurological sequelae through the Cerebral Performance Category (CPC) scale, which ranges from full recovery (CPC = 1) to severe impairment or death (CPC = 5), and consequently in the patient’s clinical outcome. This dissertation proposes a multimodal approach that combines deep learning techniques with analysis of clinical EEG patterns to increase the accuracy of prognostic predictions in post-cardiac arrest patients. The proposed methodology employs a dual approach: first, using deep learning architectures for automated feature extraction and pattern recognition of raw EEG signals and, second, incorporating highly malignant EEG patterns, notably those derived from Burst-Suppression patterns, through specialized classification models. This analysis is performed on sequential 12-hour EEG segments, covering the period from 1 to 72 hours after ROSC (return of spontaneous circulation). The hybrid approach allows the capture of complex signal features through machine learning and established clinical markers, potentially offering improved prognostic capabilities across different time windows. By combining the complementary strengths of automated feature extraction and EEG pattern analysis, this research aims to develop a robust prognostic model. Temporal analysis across multiple 12-hour windows provides insights into the evolution of neurological status, while the multimodal approach increases the reliability of the model. The ultimate goal is to provide clinicians with a interpretable tool and a quantitative prognosis to make informed decisions about patient outcomes after cardiac arrest, thereby improving post-resuscitation care and survivors quality of life.

Banca examinadora: