Talk with Ted: an embodied conversational agent for caregivers

Communication is key to the success of any relationship. When it comes to caregivers, having a conversation with a person living with some form of cognitive impairment, such as dementia, can be a struggle. Most people living with dementia experience some form of communication impairment that reduces their ability to express their needs. In this case study, we present the design of an embodied conversation agent (ECA), Ted, designed to educate caregivers about the importance of good communication principles when engaging with people living with dementia. This training tool was trialed and compared to an online training tool, with 23 caregivers divided into two cohorts (12 in the ECA condition, and 11 in the online training tool condition), over a period of 8 weeks using a mixed evaluation approach. Our findings suggest that (a) caregivers developed an emotional connection with the ECA and retained the learning from their interactions with Ted even after 8 weeks had elapsed, (b) caregivers implemented the learnings in their practice, and (c) the changes in care practice were well received by people living with dementia.

Estimating Patient-Level Uncertainty in Seizure Detection Using Group-Specific Out-of-Distribution Detection Technique

Epilepsy is a chronic neurological disorder affecting around 1% of the global population, characterized by recurrent epileptic seizures. Accurate diagnosis and treatment are crucial for reducing mortality rates. Recent advancements in machine learning (ML) algorithms have shown potential in aiding clinicians with seizure detection in electroencephalography (EEG) data. However, these algorithms face significant challenges due to the patient-specific variability in seizure patterns and the limited availability of high-quality EEG data for training, causing erratic predictions. These erratic predictions are harmful, especially for high-stake domains in healthcare, negatively affecting patients. Therefore, ensuring safety in AI is of the utmost importance. In this study, we propose a novel ensemble method for uncertainty quantification to identify patients with low-confidence predictions in ML-based seizure detection algorithms. Our approach aims to mitigate high-risk predictions in previously unseen seizure patients, thereby enhancing the robustness of existing seizure detection algorithms. Additionally, our method can be implemented with most of the deep learning (DL) models. We evaluated the proposed method against established uncertainty detection techniques, demonstrating its effectiveness in identifying patients for whom the model's predictions are less certain. Our proposed method managed to achieve 87%, 89% and 75% in accuracy, specificity and sensitivity, respectively. This study represents a novel attempt to improve the reliability and robustness of DL algorithms in the domain of seizure detection. This study underscores the value of integrating uncertainty quantification into ML algorithms for seizure detection, offering clinicians a practical tool to gauge the applicability of ML models for individual patients.