Epilepsy affects nearly 1% of the global population, of which two thirds can be treated by anti-epileptic drugs and a much lower percentage by surgery. Diagnostic procedures for epilepsy and monitoring are highly specialized and labourintensive. The accuracy of the diagnosis is also complicated by overlapping medical symptoms, varying levels of experience and inter-observer variability among clinical professions. This paper proposes a novel hybrid bilinear deep learning network with an application in the clinical procedures of epilepsy classification diagnosis, where the use of surface electroencephalogram (sEEG) and audiovisual monitoring is standard practice. Hybrid bilinear models based on two types of feature extractors, namely Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), are trained using Short-Time Fourier Transform (STFT) of one-second sEEG. In the proposed hybrid models, CNNs extract spatio-temporal patterns, while RNNs focus on the characteristics of temporal dynamics in relatively longer intervals given the same input data. Second-order features, based on interactions between these spatio-temporal features are further explored by bilinear pooling and used for epilepsy classification. Our proposed methods obtain an F1-score of 97.4% on the Temple University Hospital Seizure Corpus and 97.2% on the EPILEPSIAE dataset, comparing favourably to existing benchmarks for sEEG-based seizure type classification. The open-source implementation of this study is available at https://github.com/NeuroSyd/Epileptic-Seizure-Classification.

This mixed-method feasibility study conducted in New South Wales (NSW), Australia, aimed to explore clinical practices around the identification of patients with refractory epilepsy and referral from primary care to Tertiary Epilepsy Centers. The perceptions of general practitioners, neurologists, and adults living with refractory epilepsy were considered. Methods: Fifty-two data collection events were achieved through 22 semi-structured interviews with six neurologists and 12 adults who currently have, or have had refractory epilepsy, and four family members, 10 clinical observations of patient consultations and 20 surveys with general practitioners. A thematic analysis was conducted on the qualitative data alongside assessment of observational fieldnotes and survey data. Findings: Two main themes emerged: 1) Patient healthcare pathways and care experiences highlighted the complex and deeply contextualized experiences of both patients and healthcare professionals, from first identification of people's seizures, in primary and community care settings, to referral to Tertiary Epilepsy Centers, shedding light on a fragmented, nonstandardized referral process, influenced by both individual and sharedcare practices. 2) Factors impacting referrals and patient pathways indicated that onward referral to a Tertiary Epilepsy Center is affected by the knowledge, or the lack thereof, of healthcare professionals regarding treatment options. Barriers include limited person-centered care, shared decision-making, and refractory epilepsy education for healthcare professionals, which can delay patients' disease identification and can hinder speedy referral pathways and processes, in Australia for up to 17 years. In addition, person-centered communication around care pathways is affected by relationships between clinicians, patients, and family members. Conclusion:This study has identified a noticeable lack of standardized care across epilepsy-related healthcare sectors, which recognizes a need for developing and implementing clearer epilepsy-related guidelines and Continuing Professional Development in the primary and community care settings. This, however, requires greater collaboration and commitment in the primary, community, and tertiary care sectors to address the ongoing misconceptions around professional roles and responsibilities to optimize shared-care practices. Ultimately, prioritizing person-centered care on both patients' and professionals' agendas, in order to improve satisfaction with care experiences of people living with complex epilepsy.

No abstract

No abstract